Work at least 6 challenging, interesting problems from Chapter 6. If you don't choose challenging problems, then you're not going to be prepared for Thursday's test!
*** The Gator cheerleaders came out to practice with the band tonight and, when they were done, went into the gym and cheered for the freshman basketball team. Go Gators***
And they just mentioned both Venn diagrams and Simpson's Paradox on Numb3rs!
HW due Monday, December 8: Problems 7.55 and 7.58. The test will be on Thursday.
HW due Wednesday, December 3 - 7.32, .37, .38, and .39
HW for Monday- Problems 7.1-7.3 from the text CHAPTER SEVEN!
Please be safe. I will not be at CiCi's on Sunday, November 23. Also, please note that the email system is going to be down until we get back to school in December.
Have a happy Thanksgiving.
Tuesday, December 09, 2008
Monday, November 17, 2008
Chapter 5 - Generating and collecting data
Here's a website with some summary information about experimental design.
HW due Wednesday, 11/19/08: Problems 2006-5 and 2004-2 from the AP exams. Do the work on a separate piece of paper. No credit will be given for work done on the handout. If you missed class on Tuesday, swing by before school to get a copy or go to the AP website to retrieve a copy, but be prepared for class! Your test is on Thursday.
HW due Tuesday, 11/18/08: Problems 5.46-5.49. Your test on Chapter 5 is Thursday.
HW due Monday, 11/17/08: Problem 5, part c from the 2005 exam. The original question is found at www.collegeboard.com/apstudents.
A survey will be conducted to examine the educational level of adult heads of households in the United States. Each respondent in the survey will be placed into one of the following two categories:
(c) Since education is largely the responsibility of each state, the agency wants to be sure that estimates are available for each state as well as for the nation. Identify a sampling method that will achieve this additional goal and briefly describe a way to select the survey sample using this method.
Your answer must be written and complete and reflect your best reasoning.
Your test on this chapter is Thursday.
HW due Friday: 5.9, 5.10, 5.13, 5.14. Know how each of these types of bias occurs and what its implications are: response, non-response, voluntary response, wording, undercoverage. Also, how does convenience sampling lead to bias?
Know also how to conduct surveys using each of these methods:
Stratified random sample: Create layers of homogeneous groups and randomly sample from each.
Systematic random sample: Select every nth person for the survey.
Cluster sampling: Survey a smaller heterogeneous group that has characteristics similar to the entire population.
Simple random sampling of size n: (the ideal) use random methods that ensure that every person has the same likelihood of selection AND that every possible group of n people has the same likelihood of selection.
Your HW due Wednesday 11/12 is 5.1-5.5 (after reading the first four pages of the chapter).
Here are the questions that will be on the long form and the short form of the census in 2010. The actual date of the census will be April 1, 2010.
HW due Wednesday, 11/19/08: Problems 2006-5 and 2004-2 from the AP exams. Do the work on a separate piece of paper. No credit will be given for work done on the handout. If you missed class on Tuesday, swing by before school to get a copy or go to the AP website to retrieve a copy, but be prepared for class! Your test is on Thursday.
HW due Tuesday, 11/18/08: Problems 5.46-5.49. Your test on Chapter 5 is Thursday.
HW due Monday, 11/17/08: Problem 5, part c from the 2005 exam. The original question is found at www.collegeboard.com/apstudents.
A survey will be conducted to examine the educational level of adult heads of households in the United States. Each respondent in the survey will be placed into one of the following two categories:
- Does not have a high school diploma
- Has a high school diploma
(c) Since education is largely the responsibility of each state, the agency wants to be sure that estimates are available for each state as well as for the nation. Identify a sampling method that will achieve this additional goal and briefly describe a way to select the survey sample using this method.
Your answer must be written and complete and reflect your best reasoning.
Your test on this chapter is Thursday.
HW due Friday: 5.9, 5.10, 5.13, 5.14. Know how each of these types of bias occurs and what its implications are: response, non-response, voluntary response, wording, undercoverage. Also, how does convenience sampling lead to bias?
Know also how to conduct surveys using each of these methods:
Stratified random sample: Create layers of homogeneous groups and randomly sample from each.
Systematic random sample: Select every nth person for the survey.
Cluster sampling: Survey a smaller heterogeneous group that has characteristics similar to the entire population.
Simple random sampling of size n: (the ideal) use random methods that ensure that every person has the same likelihood of selection AND that every possible group of n people has the same likelihood of selection.
Your HW due Wednesday 11/12 is 5.1-5.5 (after reading the first four pages of the chapter).
Here are the questions that will be on the long form and the short form of the census in 2010. The actual date of the census will be April 1, 2010.
Thursday, November 06, 2008
Chapter 4 Examining Nonlinear Relationships
Due Friday 11/7/08: Problems 4.41-48 in the book. YOu'll need to read the section that precedes these questions. The test is on Monday. Don't wait until the last minute to work problems. [Check out the Barron's sudy guide, sections 4 and 5 for more problems.]
UPDATE: The Chapter 4 test has been postponed to Monday, November 10, but you still need to work problems!
HW due Wed 11/5/08: You should have worked at least 5 problems from the first section of the chapter plus problems 4.23 and 4.26. It would be helpful for you to work more problems, since your test is Thursday.
HW due Friday: Bongiorno! Problem 4.12, the pizza problem. Sorry for the delay. The CCSD filters wouldn't let me post from school. si I had to wait until I got home.
HW due Thursday: problem 4.5 plus at least one of 4.6, 4.8, and 4.10. Finish your worksheet from today.
HW due Wednesday: Write out comprehensive notes for Chapter 4.
The test will be the Thursday after the election day.
UPDATE: The Chapter 4 test has been postponed to Monday, November 10, but you still need to work problems!
HW due Wed 11/5/08: You should have worked at least 5 problems from the first section of the chapter plus problems 4.23 and 4.26. It would be helpful for you to work more problems, since your test is Thursday.
HW due Friday: Bongiorno! Problem 4.12, the pizza problem. Sorry for the delay. The CCSD filters wouldn't let me post from school. si I had to wait until I got home.
HW due Thursday: problem 4.5 plus at least one of 4.6, 4.8, and 4.10. Finish your worksheet from today.
HW due Wednesday: Write out comprehensive notes for Chapter 4.
The test will be the Thursday after the election day.
Tuesday, October 21, 2008
Chapter 3 Examining Relationships
This chapter introduces methods of describing, evaluating, and predicting a relationship between two variables. We are extending our look into Chapter 15 as well.
The test is Monday over Chapter 3 and Chapter 15. Most of the emphasis is on Chapter 3. How could you prove that you know the material?
Due FRIDAY, 10/24: Create detailed written instructions for finding r, the LSRL, residuals, s, and SEof b, performing the hypothesis test for a slope, and for finding the confidence interval for a slope.
15.6 and 15.8 from the text.
Due Wednesday, 10/22: Find 4 examples of regression output using a computer program in the text. For each one, construct null and alternate hypotheses for inferences about the slope of the LSRL, perform the calculations related to your hypotheses, and write out the conclusion in the context of the problem. We are ignoring for now the assumptions/conditions portion of the required steps in inference. All of this must be written on paper-not on your calculator or stored in your heads.
Due Tuesday, 10/14: Translate the definitions from Chapter 15 into language you understand more easily.
Due Monday 10/13: Problems .33, .34, .38, .39, .43, .44, .45. Problems 3.29-3.32 were due Thursday, 10/9.
Due 10/6: Become experts. It's up to you, now. Become able to calculate r, b, a, and the residuals in tables quickly and efficiently. Y'all need to practice so you are fluent!
It boils down to becoming experts in the same thing we've done on the calculator, Fathom, and Excel for 3 days. You could ue a data set from an example in the book and rework it until it is second nature.
Due 10/3: Work 2 challenging problems from the first section that you haven't already worked to PROVE that you are an expert on correlation.
10/1: Looked at data and linear relationships using Fathom. Become an expert on the first section of chapter 3 (3.1).
HW due Wednesday, 10/1: 3.13, .17, .19, .20, .23, .24, .28
Homework for 9/29: familiarize yourself with the correlation and regression applet on the textbook website.
http://bcs.whfreeman.com/tps3e/
HW due 9/26: Problems 3.5 and 3.6 from the text. Problem 3.5 involves one of my favorite relationships: manatee deaths cause powerboat registrations.
HW due 9/25: Be prepared to generate a linear model to solve the copier repair problem and defend your choice of variables.
HW due 9/24: Create an annotated outline of the chapter (include vocabulary and formulas and where you found them). This should take about 2 pages.
The test is Monday over Chapter 3 and Chapter 15. Most of the emphasis is on Chapter 3. How could you prove that you know the material?
Due FRIDAY, 10/24: Create detailed written instructions for finding r, the LSRL, residuals, s, and SEof b, performing the hypothesis test for a slope, and for finding the confidence interval for a slope.
15.6 and 15.8 from the text.
Due Wednesday, 10/22: Find 4 examples of regression output using a computer program in the text. For each one, construct null and alternate hypotheses for inferences about the slope of the LSRL, perform the calculations related to your hypotheses, and write out the conclusion in the context of the problem. We are ignoring for now the assumptions/conditions portion of the required steps in inference. All of this must be written on paper-not on your calculator or stored in your heads.
Due Tuesday, 10/14: Translate the definitions from Chapter 15 into language you understand more easily.
Due Monday 10/13: Problems .33, .34, .38, .39, .43, .44, .45. Problems 3.29-3.32 were due Thursday, 10/9.
Due 10/6: Become experts. It's up to you, now. Become able to calculate r, b, a, and the residuals in tables quickly and efficiently. Y'all need to practice so you are fluent!
It boils down to becoming experts in the same thing we've done on the calculator, Fathom, and Excel for 3 days. You could ue a data set from an example in the book and rework it until it is second nature.
Due 10/3: Work 2 challenging problems from the first section that you haven't already worked to PROVE that you are an expert on correlation.
10/1: Looked at data and linear relationships using Fathom. Become an expert on the first section of chapter 3 (3.1).
HW due Wednesday, 10/1: 3.13, .17, .19, .20, .23, .24, .28
Homework for 9/29: familiarize yourself with the correlation and regression applet on the textbook website.
http://bcs.whfreeman.com/tps3e/
HW due 9/26: Problems 3.5 and 3.6 from the text. Problem 3.5 involves one of my favorite relationships: manatee deaths cause powerboat registrations.
HW due 9/25: Be prepared to generate a linear model to solve the copier repair problem and defend your choice of variables.
HW due 9/24: Create an annotated outline of the chapter (include vocabulary and formulas and where you found them). This should take about 2 pages.
Thursday, September 18, 2008
Chapter 2 - Describing Location
The Chapter 1 tests have been graded and returned to students.
The test on Chapter 2 is Monday. Bring your calculator. C U at CiCi's if you're up for it! (Behind the Starbuck's on Hwy 92) Have you tried the online quiz?
HW due Friday, Sept 19 (International Talk Like a Pirate Day!!) Work at least seven challenging problems from Chapter 2 that we haven't assigned yet. The more you challenge yourself, the better prepared you'll be for the test on Monday.
HW due Wednesday: Problems 2.51 through 2.54. Chapter 2 test will be on Monday.
HW due Tuesday, Sept 16th: 2.46, 2.47, & 2.50.
HW due Monday, Sept. 15th: 2.43 and 2.44.
Come by before school to put CtlgHelp on TI-83 plus and TI-84 calculators.
HW due Sept 12th: problems 2.37, 2.38 AFTER you've read pages 148-154
HW due Sept 11th: problems 2.29, .30, .32, and .34.
HW due Sept 10th: problems 2.23-2.26 from the text
Health alert: http://www.reuters.com/article/newsOne/idUSSYD5846120080815
HW due Sept 9th: Problems 2.5-2.8 from the text.
HW due Sept 8th: Problems 2.10 and 2.13 from the text PLUS find the median, Q1, and Q3 of the triangular distribution defined by the segment connecting (0, 1) to (2, 0) or whatever triangle distribution (with the fat side on the left!!!) we assigned in your class.
Be safe.
The test on Chapter 2 is Monday. Bring your calculator. C U at CiCi's if you're up for it! (Behind the Starbuck's on Hwy 92) Have you tried the online quiz?
HW due Friday, Sept 19 (International Talk Like a Pirate Day!!) Work at least seven challenging problems from Chapter 2 that we haven't assigned yet. The more you challenge yourself, the better prepared you'll be for the test on Monday.
HW due Wednesday: Problems 2.51 through 2.54. Chapter 2 test will be on Monday.
HW due Tuesday, Sept 16th: 2.46, 2.47, & 2.50.
HW due Monday, Sept. 15th: 2.43 and 2.44.
Come by before school to put CtlgHelp on TI-83 plus and TI-84 calculators.
HW due Sept 12th: problems 2.37, 2.38 AFTER you've read pages 148-154
HW due Sept 11th: problems 2.29, .30, .32, and .34.
HW due Sept 10th: problems 2.23-2.26 from the text
Health alert: http://www.reuters.com/article/newsOne/idUSSYD5846120080815
HW due Sept 9th: Problems 2.5-2.8 from the text.
HW due Sept 8th: Problems 2.10 and 2.13 from the text PLUS find the median, Q1, and Q3 of the triangular distribution defined by the segment connecting (0, 1) to (2, 0) or whatever triangle distribution (with the fat side on the left!!!) we assigned in your class.
Be safe.
Tuesday, September 02, 2008
Chapter 1 - Exploratory data analysis
We are learning how to create graphical representations of data and to interpret different graphs.
MESSAGE TO AP STUDENTS: It is impossible for you to make up the discussions and interactions that you miss when you are absent from class. Therefore, it is your responsibility to keep up with the homework so you are not behind when you return to class. This means that you need to get the assignments from the blog or another student. Email me if you need more information--but don't show up empty-handed after an absence! You'll only get further behind.
HW for 9/2: Take notes on timeplots and ogives from the text. You will be expected to construct these graphs tomorrow in class. You would benefit from looking through the chapter summary to see if there is anything you don't understand/can't do. The test is THURSDAY!
HW for 8/29: Using the data collected in class, recreate the box and whisker plot, the stemplot, and the histogram representing the data. Look in your book for directions for the following: Back to back stemplots, back to back histograms, and parallel boxplots. Separate your data into boy data and girl data and create each of those graphs to compare the boy data to the girl data.
ALSO, consider the effect of outliers on the mean, median, standard deviation, and interquartile range of the data. Which of these measurements will be affected tremendously by outliers?
Be safe.
HW for 8/27: Bring in a graph that excites you. It must be a histogram, boxplot, stemplot, or other graph that you can write about BUT NOT A BARGRAPH. The graph can be from the newspaper, a magazine (with permission from the owner to cut it out!) or printed from the Internet.
HW for 8/26: Using the data from problem 1.11 in the text, create a split stem-and-leaf graph of the ages of the Presidents at inauguration. Write a few sentences describing what you have created and compare/contrast the results with the histogram that you created in class to represent the same data.
MESSAGE TO AP STUDENTS: It is impossible for you to make up the discussions and interactions that you miss when you are absent from class. Therefore, it is your responsibility to keep up with the homework so you are not behind when you return to class. This means that you need to get the assignments from the blog or another student. Email me if you need more information--but don't show up empty-handed after an absence! You'll only get further behind.
HW for 9/2: Take notes on timeplots and ogives from the text. You will be expected to construct these graphs tomorrow in class. You would benefit from looking through the chapter summary to see if there is anything you don't understand/can't do. The test is THURSDAY!
HW for 8/29: Using the data collected in class, recreate the box and whisker plot, the stemplot, and the histogram representing the data. Look in your book for directions for the following: Back to back stemplots, back to back histograms, and parallel boxplots. Separate your data into boy data and girl data and create each of those graphs to compare the boy data to the girl data.
ALSO, consider the effect of outliers on the mean, median, standard deviation, and interquartile range of the data. Which of these measurements will be affected tremendously by outliers?
Be safe.
HW for 8/27: Bring in a graph that excites you. It must be a histogram, boxplot, stemplot, or other graph that you can write about BUT NOT A BARGRAPH. The graph can be from the newspaper, a magazine (with permission from the owner to cut it out!) or printed from the Internet.
HW for 8/26: Using the data from problem 1.11 in the text, create a split stem-and-leaf graph of the ages of the Presidents at inauguration. Write a few sentences describing what you have created and compare/contrast the results with the histogram that you created in class to represent the same data.
Thursday, August 21, 2008
New Year. New Faces.
Look for your homework below. Accel Math is in red and AP Stat is in blue.
Here's a treat for those who made it this far. Watch for the back flip and the dismount.
Calculator news! Check out these deals:
http://forums.slickdeals.net/showthread.php?t=874733
Welcome to the first posting of the new school year. Until the school website is updated with the new course, both AP Statistics and Accelerated Math I will share this blog. Both groups should change the batteries in their calculators.
Accelerated Math I- No HW for Monday 8/11. We generated some data today and began to analyze the class results. We'll continue to analyze the results tomorrow and look at data that are not discrete. Our primary topics for these few days center on functions and independent and dependent variables.
The Accelerated Math assignment for Tuesday night 8/12 is to complete the worksheet handed out in class (Fiona #1). For Thursday 8/14 night, students should complete problems 2 & 3 from Fiona worksheet #2.
Over the weekend, (8/15) make sure that you have finished problem #3 from the Fiona worksheet (using the results from problem 1!!!). Be careful. There are multiple parts to each section. Describe your method and the meaning.
HW for 8/18: Complete the yellow sheet: Problem #5. Be sure to answer all the questions asked.
HW for 8/19: Do as many of these as you need to become proficient--
Make up two ordered pairs of numbers. Calculate the slope of the line through those points. Calculate the y-intercept of the same line. Write the equation of the line through those points.
Hints: You can use the slope formula m = (y2 - y1)/(x2 - x1) to calculate the slope and the slope-intercept or point-slope formula to determine the y-intercept.
Calculator recommendations: The ideal calculators for Accel. Math I, Accel Math 2, and all higher math courses (including AP STAT) are the TI-83 and TI-84 families of calculators. The silver editions are preferrred, because they have more memory and more spaces for useful programmed applications. The TI-nspire calculator also has these capabilities and more. For an extra $30 or so you get something akin to a hand-held computer.
The TI-86 and TI-89 do not have the same sets of functions that the 83-84-nspire calculators do, and are not as useful in these courses.
AP Stat- We began to interpret an interesting graph. We'll continue to analyze the given graph and to generate some additional data tomorrow. HW for Monday 8/11: Describe in detail how to tie a shoelace. Tues 8/12: write up the directions for entering data (ordered pairs) into your calculator, graphing a scatterplot, and generating the best fit line. You will need to know how to perform these actions for the labs on Wednesday. For Thursday 8/14: Compute the number of days until the beginning of the next millenium showing all work. Explain your calculations and assumptions as you go.
AP Stat students - HW due Monday Aug. 18: Select 4 negative and 4 positive numbers with decimal parts between -6 and 6. (For example, -1.96 and 1.645). We will call those z-scores. Knowing that the mean (mu) of IQ scores according to a particular test is 100 and the standard deviation (sigma) is 15, compute the IQ scores that correspond to the eight z-values you chose. Check your work using the formula z = (x - mu)/sigma. . . also known as difference on the top and the error on the bottom.
Calculator recommendations are embedded in the Accel Math I information above.
Be safe.
HW for 8/18: Find the estimated IQ scores of 8 celebrities. Convert the IQ scores to z-scores. Of course, show the celebrity's name, his/her IQ score, and the z-score for that measurement.
HW for 8/19: (1) REWRITE the example that we used today in class, cleaning it up and adding explanations to the example. You should have both the old version and the new version in your notes. (2) Select a set of numerical data with at least 10 values. Using the notes as a guide, calculate the mean and sample standard deviation of your set of data by creating columns as shown. Create a histogram of your data.
Here's a treat for those who made it this far. Watch for the back flip and the dismount.
Calculator news! Check out these deals:
http://forums.slickdeals.net/showthread.php?t=874733
Welcome to the first posting of the new school year. Until the school website is updated with the new course, both AP Statistics and Accelerated Math I will share this blog. Both groups should change the batteries in their calculators.
Accelerated Math I- No HW for Monday 8/11. We generated some data today and began to analyze the class results. We'll continue to analyze the results tomorrow and look at data that are not discrete. Our primary topics for these few days center on functions and independent and dependent variables.
The Accelerated Math assignment for Tuesday night 8/12 is to complete the worksheet handed out in class (Fiona #1). For Thursday 8/14 night, students should complete problems 2 & 3 from Fiona worksheet #2.
Over the weekend, (8/15) make sure that you have finished problem #3 from the Fiona worksheet (using the results from problem 1!!!). Be careful. There are multiple parts to each section. Describe your method and the meaning.
HW for 8/18: Complete the yellow sheet: Problem #5. Be sure to answer all the questions asked.
HW for 8/19: Do as many of these as you need to become proficient--
Make up two ordered pairs of numbers. Calculate the slope of the line through those points. Calculate the y-intercept of the same line. Write the equation of the line through those points.
Hints: You can use the slope formula m = (y2 - y1)/(x2 - x1) to calculate the slope and the slope-intercept or point-slope formula to determine the y-intercept.
For 8/20:Finish the salmon (orange) worksheet you picked up in class. Answers should be on your own paper. The quiz results were mostly good. Most common error: graphing a line instead of dots when the domain only contains discrete points. We have to pay attention to these details.
For 8/21: Graph y = x-squared, y = 2 x-squared, and y = x-squared + 2 on the same graph we started in class. Use colored pencil if you can to differentiate among the graphs.
Calculator recommendations: The ideal calculators for Accel. Math I, Accel Math 2, and all higher math courses (including AP STAT) are the TI-83 and TI-84 families of calculators. The silver editions are preferrred, because they have more memory and more spaces for useful programmed applications. The TI-nspire calculator also has these capabilities and more. For an extra $30 or so you get something akin to a hand-held computer.
The TI-86 and TI-89 do not have the same sets of functions that the 83-84-nspire calculators do, and are not as useful in these courses.
AP Stat- We began to interpret an interesting graph. We'll continue to analyze the given graph and to generate some additional data tomorrow. HW for Monday 8/11: Describe in detail how to tie a shoelace. Tues 8/12: write up the directions for entering data (ordered pairs) into your calculator, graphing a scatterplot, and generating the best fit line. You will need to know how to perform these actions for the labs on Wednesday. For Thursday 8/14: Compute the number of days until the beginning of the next millenium showing all work. Explain your calculations and assumptions as you go.
AP Stat students - HW due Monday Aug. 18: Select 4 negative and 4 positive numbers with decimal parts between -6 and 6. (For example, -1.96 and 1.645). We will call those z-scores. Knowing that the mean (mu) of IQ scores according to a particular test is 100 and the standard deviation (sigma) is 15, compute the IQ scores that correspond to the eight z-values you chose. Check your work using the formula z = (x - mu)/sigma. . . also known as difference on the top and the error on the bottom.
Calculator recommendations are embedded in the Accel Math I information above.
Be safe.
HW for 8/18: Find the estimated IQ scores of 8 celebrities. Convert the IQ scores to z-scores. Of course, show the celebrity's name, his/her IQ score, and the z-score for that measurement.
HW for 8/19: (1) REWRITE the example that we used today in class, cleaning it up and adding explanations to the example. You should have both the old version and the new version in your notes. (2) Select a set of numerical data with at least 10 values. Using the notes as a guide, calculate the mean and sample standard deviation of your set of data by creating columns as shown. Create a histogram of your data.
HW for 8/20: find all the combinations of five integers [0,5], with minimum average, with maximum average, with minimum standard deviation, and with maximum standard deviation. First assume that numbers can be repeated, then do the problem again with no repeated numbers.
HW for 8/21: Find a site online with the rules for logarithms and re-learn them to be prepared for the mental exercises of Friday.
Click here for a cool site for histograms.
Click here for a decent site that shows how to calculate standard deviations.
Friday, June 20, 2008
Back from the AP reading
The grading of the exams went smoothly, with the entire set of 110,000 exams graded by the close of business on Wednesday night. Although students from other schools seemed to think that the problems were hard, the teachers and professors who graded the tests were not complaining about a lot of low scores. I guess that's a good sign!
The chief reader (Christine Franklin, from UGA) evaluates the distribution and sets the cut points for the different final scores based on how students performed on the repeated questions from previous years. That done, the scores have to be approved by the AP psychometric gurus and processed for release to students. In other words, your scores should be available on time.
My role at the reading was a little different this year. In past years I've been assigned to a grading group of 12 people headed by two table leaders, then trained to grade two problems from the regular exam according to the rubric. For seven full days the people in each group grade those two problems. For instance, a reader may grade question #5 (the moose problem) and the table leader checks the scoring. Since there are six problems on the test and this year over 500 readers, there are a lot of people grading the same problem. Once a problem has been graded, that test booklet is bundled up and passed to a group that grades another question, and the process continues until all of the problems have been graded. If a reader has a question, she asks her grading partner, then her table leader. If the problem is not yet resolved, the question goes to the question leaders.
This time Ms. Franklin put me in a grading group with a bunch of REALLY experienced readers (famous and incredibly important people in statistics, like one of the authors of a popular textbook) who graded the make-up exam. We also graded two questions each (plus one from the regular exam), but we were the only ones to grade those problems. When we had questions, the people who wrote the rubric were right at our tables to answer and help us resolve any issues. Since none of you took the make-up exam this year, I never had to worry about accidentally grading one of my own students' tests, but every time readers commented on how great an answer was I told them that it must have been one of MY students. :) The trick with grading the make-up exam is that we can never divulge the contents of the exam to anyone, but that shouldn't be a problem because I have already forgotten it all!
You may be wondering (as I did) how I qualified for that special grading group. I think that they chose the very best former table leaders and other important people they could find, then filled in the rest with some experienced people from Georgia. Clarification: some of the important people were also from Georgia, so the line between the superstars and the poser (me) was blurred. Oh yeah, and they said that we we were selected because we were fast graders. I thought you'd enjoy that.
A few students, usually those who are stumped by a problem, write notes to the graders asking for mercy or generosity in grading. I'm sure they're joking, but they might be surprised to know how wonderful, helpful, and patient the graders really are. About half of the graders are college instructors who give up a week of their summers or coveted summer courses to validate this process for our students. The high school teachers are the ones who have attended or led workshops and conferences in statistics. Some of them haven't even ended their school years yet and have to pay their school districts back for the substitutes they needed. These people write the creative lessons published in books and shared online. They write the the textbooks and the study guides. They do it for students. They spend all day grading exams, then come back after dinner to hear a guest speaker talk about mathematical modeling or to share best practices. They are on constant lookout for ways to help their students understand statistics better.
This goes for the English Lit, French, and APUSH graders who were there at the same time, too.
I am honored and humbled to be invited to participate in this process with these amazing people.
Video time: http://www.youtube.com/watch?v=zTPhZcxnBSE&feature=related
http://www.youtube.com/watch?v=Ac3CtHYo5rY&feature=related
http://www.youtube.com/watch?v=IKkBBVxI5qU&feature=related
The chief reader (Christine Franklin, from UGA) evaluates the distribution and sets the cut points for the different final scores based on how students performed on the repeated questions from previous years. That done, the scores have to be approved by the AP psychometric gurus and processed for release to students. In other words, your scores should be available on time.
My role at the reading was a little different this year. In past years I've been assigned to a grading group of 12 people headed by two table leaders, then trained to grade two problems from the regular exam according to the rubric. For seven full days the people in each group grade those two problems. For instance, a reader may grade question #5 (the moose problem) and the table leader checks the scoring. Since there are six problems on the test and this year over 500 readers, there are a lot of people grading the same problem. Once a problem has been graded, that test booklet is bundled up and passed to a group that grades another question, and the process continues until all of the problems have been graded. If a reader has a question, she asks her grading partner, then her table leader. If the problem is not yet resolved, the question goes to the question leaders.
This time Ms. Franklin put me in a grading group with a bunch of REALLY experienced readers (famous and incredibly important people in statistics, like one of the authors of a popular textbook) who graded the make-up exam. We also graded two questions each (plus one from the regular exam), but we were the only ones to grade those problems. When we had questions, the people who wrote the rubric were right at our tables to answer and help us resolve any issues. Since none of you took the make-up exam this year, I never had to worry about accidentally grading one of my own students' tests, but every time readers commented on how great an answer was I told them that it must have been one of MY students. :) The trick with grading the make-up exam is that we can never divulge the contents of the exam to anyone, but that shouldn't be a problem because I have already forgotten it all!
You may be wondering (as I did) how I qualified for that special grading group. I think that they chose the very best former table leaders and other important people they could find, then filled in the rest with some experienced people from Georgia. Clarification: some of the important people were also from Georgia, so the line between the superstars and the poser (me) was blurred. Oh yeah, and they said that we we were selected because we were fast graders. I thought you'd enjoy that.
A few students, usually those who are stumped by a problem, write notes to the graders asking for mercy or generosity in grading. I'm sure they're joking, but they might be surprised to know how wonderful, helpful, and patient the graders really are. About half of the graders are college instructors who give up a week of their summers or coveted summer courses to validate this process for our students. The high school teachers are the ones who have attended or led workshops and conferences in statistics. Some of them haven't even ended their school years yet and have to pay their school districts back for the substitutes they needed. These people write the creative lessons published in books and shared online. They write the the textbooks and the study guides. They do it for students. They spend all day grading exams, then come back after dinner to hear a guest speaker talk about mathematical modeling or to share best practices. They are on constant lookout for ways to help their students understand statistics better.
This goes for the English Lit, French, and APUSH graders who were there at the same time, too.
I am honored and humbled to be invited to participate in this process with these amazing people.
Video time: http://www.youtube.com/watch?v=zTPhZcxnBSE&feature=related
http://www.youtube.com/watch?v=Ac3CtHYo5rY&feature=related
http://www.youtube.com/watch?v=IKkBBVxI5qU&feature=related
Monday, May 19, 2008
Final exam preparation
(1) All classes have received their take-home portion of the final exam. The problem must be worked out completely, correctly answering the questions posed , on a separate sheet of paper. For underclassmen, the graph may be drawn on the question sheet itself. This is an individual assignment. You are not to collaborate on this problem. The problem is due on the day of your final.
(2) The in-class part of your final will consist of 21 problems from the practice multiple choice tests. The content relates to second semester topics.
Show me your best work!
(2) The in-class part of your final will consist of 21 problems from the practice multiple choice tests. The content relates to second semester topics.
Show me your best work!
Sunday, May 04, 2008
The practice tests
For Tuesday: Dress in layers because the gym is CCOOOOOOOOOOOOLLLLLLDDDD!
Replace your batteries if it has been a while since they were changed. Remember to run CtlgHelp (an APP) and Diagnostics ON (use catalog to find this).
Bring your student ID, pencils, and a pen.
Come to the outside classroom a little BEFORE THE END OF third period. You need to eat before you test. I'm bringing food.
Estudiantes del AP Espanol: We will save food for you. Come out to the outdoor classroom after the other exam.
DO NOT BRING study guides, textbooks, cell phones, i-pods, etc.
Post any questions to me by 9:00 for best shot at getting an answer.
GO TROJANS.
It's about 5:40 PM and I'm finally home. Please call if you have an urgent need to meet at CiCi's. 7/ 354 . 1791 (number is broken into pieces to discourage phishers).
I WILL NOT be at CiCi's at 2:00. You folks can still go and be an amazing, productive group, though. Be smart.
I will touch base again when I re-enter the cyper-world.
There will be ONE MORE multiple choice test on Thursday. The format is the same as the previous tests. This grade will replace the lowest of the multiple choice test grades. Be prepared.
The practice tests have been graded, the grades posted, and the adjustments are complete. There are three grades representing the original test score or a measure of improvement as follows:
If the original score on test 2 > test 1, then the original test 2 score is inserted as test 1's score as well.
If the score on test 3> test 2, then test 3's score is inserted as test 2's score as well.
No, if test 3 > test 2> test 1 you DON'T get test 3 posted three times.
Congratulations to those who scored over 100% on test 3. The highest score was 33 correct with 2 wrong for a raw score of 32.5 and a posted score of 162.5. That score also replaced the student's lower test #2 score.
OK. Have you ever had something in your eye and you just couldn't bring yourself to cry to wash it out? This would do the trick:
http://youtube.com/watch?v=WIxtxwiqK-s
I warned you.
Find some time this weekend to do the practice exam in the packet handed out on Thursday, but your next assessment is MULTIPLE CHOICE. Practice with a study guide. Find the topics that you don't remember. Brush up. Take a deep breath. See you Sunday for pineapple pizza?
- - - - -
Today's multiple choice test scores are posted to I-Parent. The next test will be Thursday.
The third opportunity for the practice free response test is Wednesday afternoon.
Video alert: The movie Wargames (released 25 years ago!!) is on amc right now. The best part is toward the end of the movie, when the computer gets smart.
Replace your batteries if it has been a while since they were changed. Remember to run CtlgHelp (an APP) and Diagnostics ON (use catalog to find this).
Bring your student ID, pencils, and a pen.
Come to the outside classroom a little BEFORE THE END OF third period. You need to eat before you test. I'm bringing food.
Estudiantes del AP Espanol: We will save food for you. Come out to the outdoor classroom after the other exam.
DO NOT BRING study guides, textbooks, cell phones, i-pods, etc.
Post any questions to me by 9:00 for best shot at getting an answer.
GO TROJANS.
It's about 5:40 PM and I'm finally home. Please call if you have an urgent need to meet at CiCi's. 7/ 354 . 1791 (number is broken into pieces to discourage phishers).
I WILL NOT be at CiCi's at 2:00. You folks can still go and be an amazing, productive group, though. Be smart.
I will touch base again when I re-enter the cyper-world.
There will be ONE MORE multiple choice test on Thursday. The format is the same as the previous tests. This grade will replace the lowest of the multiple choice test grades. Be prepared.
The practice tests have been graded, the grades posted, and the adjustments are complete. There are three grades representing the original test score or a measure of improvement as follows:
If the original score on test 2 > test 1, then the original test 2 score is inserted as test 1's score as well.
If the score on test 3> test 2, then test 3's score is inserted as test 2's score as well.
No, if test 3 > test 2> test 1 you DON'T get test 3 posted three times.
Congratulations to those who scored over 100% on test 3. The highest score was 33 correct with 2 wrong for a raw score of 32.5 and a posted score of 162.5. That score also replaced the student's lower test #2 score.
OK. Have you ever had something in your eye and you just couldn't bring yourself to cry to wash it out? This would do the trick:
http://youtube.com/watch?v=WIxtxwiqK-s
I warned you.
Find some time this weekend to do the practice exam in the packet handed out on Thursday, but your next assessment is MULTIPLE CHOICE. Practice with a study guide. Find the topics that you don't remember. Brush up. Take a deep breath. See you Sunday for pineapple pizza?
- - - - -
Today's multiple choice test scores are posted to I-Parent. The next test will be Thursday.
The third opportunity for the practice free response test is Wednesday afternoon.
Video alert: The movie Wargames (released 25 years ago!!) is on amc right now. The best part is toward the end of the movie, when the computer gets smart.
Tuesday, April 15, 2008
Chapter 14 - The final frontier
Inferences for regression
HW for Monday: Entire free response test from 2004. Take 90 minutes under test conditions.
HW for Friday: Problem 6 from 2007 AP exam.
HW due Thursday: Problems 14.11 and 14.18 PLUS the chapter summary.
HW due Wednesday: Problem 2 from the 2006 exam. Language is critical. If you do not know what the question asks, look at Example 14.5 in the text. Respond IN CONTEXT. There will be no partial credit for this problem.
DO NOT FORGET that your one-page summary of the selected chapter is due Thursday.
This chapter explains how to use the slope of a LSRL calculated from a sample and the std dev of the slopes
Why are there only n-2 degrees of freedom?
Why do we make such a big deal about s sub-b1 being the std dev of the slopes?
HW for Tuesday: problems 14.1 and 14.2 from the text.
Chapter summary due Thursday.
HW for Monday: Entire free response test from 2004. Take 90 minutes under test conditions.
HW for Friday: Problem 6 from 2007 AP exam.
HW due Thursday: Problems 14.11 and 14.18 PLUS the chapter summary.
HW due Wednesday: Problem 2 from the 2006 exam. Language is critical. If you do not know what the question asks, look at Example 14.5 in the text. Respond IN CONTEXT. There will be no partial credit for this problem.
DO NOT FORGET that your one-page summary of the selected chapter is due Thursday.
This chapter explains how to use the slope of a LSRL calculated from a sample and the std dev of the slopes
- to create a confidence interval for capturing the slope of the true equation through ALL the data and
- to make decisions about a hypothesized linear relationship.
Why are there only n-2 degrees of freedom?
Why do we make such a big deal about s sub-b1 being the std dev of the slopes?
HW for Tuesday: problems 14.1 and 14.2 from the text.
Chapter summary due Thursday.
Wednesday, April 02, 2008
Chapter 13 Inferences using Chi-square
Your Chapter 12 tests are available Thursday morning for pick up in room 313. I have posted an answer key outside room 313 for comparison.
What can you do to prepare for Thursday's test? Have you taken the online quiz? Select the link to the right>>>>>>
Have you used a study guide? You have now learned almost everything from the syllabus for the exam, so get to work!
Have you read the chapter in the text? Y, M, and M explained these concepts differently. If you didn't "get it" the way I explained it, you might like their version.
Did you google lesson chi-square test or something like it? Sometimes you can find nifty applets that make the concepts clear.
See you on Thursday.
HW due Wednesday, April 2: Complete 5 problems from the chapter review (NOT 28 or 29) in preparation for Thursday's test.
HW due Tuesday, April 1: Read pages 717 through 724. Do problems 13.14 and 13.16.
HW due Monday, March 31: Problems 28 and 29 (which requires simulation). Leave yourself enough time to do problem 29 or go to CiCi's.
HW due Friday: Problems 13.9, 13.10, 13.12.
HW due Thursday: Write up your answer to the free response problem handed out in class AND work problems 13.1 and 13.3.
We will study three different types of test that use chi-square methods in this chapter:
goodness of fit: compares one sample distribution to an expected distribution to see if it matches the expected counts closely or not (for example, comparing a sample of M&Ms by color to the % the company says it produces).
test of independence: determines whether there is evidence that a relationship exists between at least two categorical characteristics within a population based on the counts of observations in one sample (for example, analyzing applications to law school to see if undergraduate major and admission rate have a relationship).
test of homogeneity: compares counts within the distributions of two or more comparable samples to see if there is a significant difference inthe mixes (for example, comparing color distribution of a sample of milk chocolate M&Ms to the distribution of a sample of peanut M&Ms to see if there is a difference).
Each of the methods uses the formula sum [(O-E)^2/E]. This is the formula that Dr. Chuck Tate had written on his "grill" in the Statz 4 Life video.
Our plan is to do lots of labs and practice writing free response answers for the next few days. Our test is Thursday of next week.
For more information, scroll down to the Chapter 13 information from 2006 and 2007 on this blog.
Our probability lab is a week from Friday. We need parent volunteers to help with the activities. Please ask your parents to email me if they want to be part of this fun experience. They'll have a blast.
What can you do to prepare for Thursday's test? Have you taken the online quiz? Select the link to the right>>>>>>
Have you used a study guide? You have now learned almost everything from the syllabus for the exam, so get to work!
Have you read the chapter in the text? Y, M, and M explained these concepts differently. If you didn't "get it" the way I explained it, you might like their version.
Did you google lesson chi-square test or something like it? Sometimes you can find nifty applets that make the concepts clear.
See you on Thursday.
HW due Wednesday, April 2: Complete 5 problems from the chapter review (NOT 28 or 29) in preparation for Thursday's test.
HW due Tuesday, April 1: Read pages 717 through 724. Do problems 13.14 and 13.16.
HW due Monday, March 31: Problems 28 and 29 (which requires simulation). Leave yourself enough time to do problem 29 or go to CiCi's.
HW due Friday: Problems 13.9, 13.10, 13.12.
HW due Thursday: Write up your answer to the free response problem handed out in class AND work problems 13.1 and 13.3.
We will study three different types of test that use chi-square methods in this chapter:
goodness of fit: compares one sample distribution to an expected distribution to see if it matches the expected counts closely or not (for example, comparing a sample of M&Ms by color to the % the company says it produces).
test of independence: determines whether there is evidence that a relationship exists between at least two categorical characteristics within a population based on the counts of observations in one sample (for example, analyzing applications to law school to see if undergraduate major and admission rate have a relationship).
test of homogeneity: compares counts within the distributions of two or more comparable samples to see if there is a significant difference inthe mixes (for example, comparing color distribution of a sample of milk chocolate M&Ms to the distribution of a sample of peanut M&Ms to see if there is a difference).
Each of the methods uses the formula sum [(O-E)^2/E]. This is the formula that Dr. Chuck Tate had written on his "grill" in the Statz 4 Life video.
Our plan is to do lots of labs and practice writing free response answers for the next few days. Our test is Thursday of next week.
For more information, scroll down to the Chapter 13 information from 2006 and 2007 on this blog.
Our probability lab is a week from Friday. We need parent volunteers to help with the activities. Please ask your parents to email me if they want to be part of this fun experience. They'll have a blast.
Saturday, March 22, 2008
Chapter 12 Inference for proportions (Yeah!)
HW for Monday: In preparation for Tuesday's test, the MINIMUM assignment is to work four problems (your choice) from the Chapter Review. This means that at least four problems have to be completed correctly. For instance, if problem 28 had been in the review section, your answer would include a complete hypothesis test or confidence interval--not just your opinion.
HW for Friday: 12.25, .26, and .28.
March Madness: post your NCAA men's basketball brackets at CBSSportsline with the Linnerstats bracket. The password for the bracket is just what you'd expect, gogators. If you are a bracket rookie, this means that you predict the winners of the 63 games in the NCAA basketball championship tournament. The software at CBSSportsline makes it really easy. You have to work fast. . . the brackets close soon.
HW for Thursday: Write up the inferences (hypothesis test and confidence interval) you generated today using the fluffy pom poms. Make your answers complete and correct. First period, please be prepared to meet me in our temporary location after our brief homeroom first thing Thursday.
HW due Wednesday: Complete write-up (PHANTOMS) of the Skittles hypothesis you generated in class. (Run a 1-proportion z-test on a large-enough sample of Skittles. The size of the sample depends on what you consider a "success.")
HW due Tuesday, March 18th: 12.13, 12.15, 12.16, 12.17. Please note: The answers in the back of the book for problem 13 used 0.33 as the value for 1/3. Obviously, this is not going to give you the "correct" answer. Please use 1/3 instead of their estimate and realize that your answers will be a little different from theirs, but yours will be correct! You can check your answers using the STAT TEST 1-PROP Z TEST on the calculator. The observation based on your results will not change just because you used a slightly different input.
The test on Chapter 12 will be next Tuesday, the 25th.
We're finally back where we began, with inferences for proportions. You should complete your compare/contrast study guide (that you created from scratch) where you compare the formulas, language, and assumptions of each of the three chapters. The headings are z-procedures for means, t-procedures for means, and z-procedures for proportions. Know how to justify each of the formulas for standard deviations in the two-proportion inferences algebraically.
HW: Using the combined data from two sleeves of mini M&Ms (as you will find in the holiday section of the grocery store), test the null hypothesis P = 1/6, where p represents the true proportion of brown M&Ms (the best ones!). Perform the complete test, using PHANTOMS as a guide. For those who were absent, we're talking about the little tiny plastic sleeves of M&Ms that come in a blue bag (about 17 to the bag). There are around 50 M&Ms in each sleeve unless you get short-changed.
HW for Friday: 12.25, .26, and .28.
March Madness: post your NCAA men's basketball brackets at CBSSportsline with the Linnerstats bracket. The password for the bracket is just what you'd expect, gogators. If you are a bracket rookie, this means that you predict the winners of the 63 games in the NCAA basketball championship tournament. The software at CBSSportsline makes it really easy. You have to work fast. . . the brackets close soon.
HW for Thursday: Write up the inferences (hypothesis test and confidence interval) you generated today using the fluffy pom poms. Make your answers complete and correct. First period, please be prepared to meet me in our temporary location after our brief homeroom first thing Thursday.
HW due Wednesday: Complete write-up (PHANTOMS) of the Skittles hypothesis you generated in class. (Run a 1-proportion z-test on a large-enough sample of Skittles. The size of the sample depends on what you consider a "success.")
HW due Tuesday, March 18th: 12.13, 12.15, 12.16, 12.17. Please note: The answers in the back of the book for problem 13 used 0.33 as the value for 1/3. Obviously, this is not going to give you the "correct" answer. Please use 1/3 instead of their estimate and realize that your answers will be a little different from theirs, but yours will be correct! You can check your answers using the STAT TEST 1-PROP Z TEST on the calculator. The observation based on your results will not change just because you used a slightly different input.
The test on Chapter 12 will be next Tuesday, the 25th.
We're finally back where we began, with inferences for proportions. You should complete your compare/contrast study guide (that you created from scratch) where you compare the formulas, language, and assumptions of each of the three chapters. The headings are z-procedures for means, t-procedures for means, and z-procedures for proportions. Know how to justify each of the formulas for standard deviations in the two-proportion inferences algebraically.
HW: Using the combined data from two sleeves of mini M&Ms (as you will find in the holiday section of the grocery store), test the null hypothesis P = 1/6, where p represents the true proportion of brown M&Ms (the best ones!). Perform the complete test, using PHANTOMS as a guide. For those who were absent, we're talking about the little tiny plastic sleeves of M&Ms that come in a blue bag (about 17 to the bag). There are around 50 M&Ms in each sleeve unless you get short-changed.
Monday, March 10, 2008
Chapter 11 Statistical Inference Part II (t-procedures)
HW for Wednesday, March 12: Find 10 problems from chapter 11 that have not been assigned yet and complete them. If you find problems that you cannot do, mark those, but they do not count toward your ten. YOUR TEST IS THURSDAY.
HW due Tuesday, March 11: 11.31 and 11.32. Keep the data from today's class in your calculator so we can finish the process tomorrow. Remember, the test is Thursday.
HW due Thursday, March 6: 11.10, 11.15. 11.17
HW due Friday, March 7 (Coach Rinehimer's birthday!!!): 11.16. 11.19, 11.20, 11.27, 11.30 (These are all related!) Good job with the pasta and grip labs today. My hypotheses were that there were 104 pieces of pasta on average in a cup and that the difference between right and left hand squeeze strengths was 7 pounds on average. Your job was to (1) collect data, (2) perform a hypothesis test using your results, and (3) construct a confidence interval for the average or averge difference. EACH of you is responsible for knowing how to do all the steps of these investigations.
HW due Monday, March 10: 11.26, 11.28
Your test on Chapter 11 will be Thursday, March 13th.
Happy Centennial!!!
W.S. Gosset's paper (remember, the brewer who developed the t-distribution?)was published in Biometrika 100 years ago THIS MONTH!
A link to the paper (of course he did not publish online. . .).
HW due Tuesday, March 11: 11.31 and 11.32. Keep the data from today's class in your calculator so we can finish the process tomorrow. Remember, the test is Thursday.
HW due Thursday, March 6: 11.10, 11.15. 11.17
HW due Friday, March 7 (Coach Rinehimer's birthday!!!): 11.16. 11.19, 11.20, 11.27, 11.30 (These are all related!) Good job with the pasta and grip labs today. My hypotheses were that there were 104 pieces of pasta on average in a cup and that the difference between right and left hand squeeze strengths was 7 pounds on average. Your job was to (1) collect data, (2) perform a hypothesis test using your results, and (3) construct a confidence interval for the average or averge difference. EACH of you is responsible for knowing how to do all the steps of these investigations.
HW due Monday, March 10: 11.26, 11.28
Your test on Chapter 11 will be Thursday, March 13th.
Happy Centennial!!!
W.S. Gosset's paper (remember, the brewer who developed the t-distribution?)was published in Biometrika 100 years ago THIS MONTH!
A link to the paper (of course he did not publish online. . .).
Saturday, February 23, 2008
Chapter 10 Statistical Inference Part 1
HW due Thursday: Problems 10.67 and 10.68 PLUS create a study guide for Chapter 10. YOUR TEST will be Tuesday, March 4. This is a short day, so you will have to think fast! HW due Monday: 10.70, 10.71, 10.78, 10.81, 10.82, 10.86. In addition to reviewing, we will be taking an ASMA test and starting Chapter 11 Thursday, Friday, and Monday.
HW due Wednesday: Problems 39, 40, and 43 done completely. Answers from the calculator are not sufficient.
HW due Tuesday, Feb 26: Problems 27, 28, 33, and 34 covering hypothesis testing. You may need to refer to the PHANTOMS side of the worksheet. If you have difficulty writing hypotheses, do problems 30, 31, and 32 as well.
RE: Hypotheses writing
The hypotheses always include PARAMETERS, not statistics. Use mu and p, not x-bar and p-hat. The null hypothesis always has an "equal to" nature rather than a greater than or less than.
HW due Monday, Feb 25: Problems from Chapter 10 (5, 12, 13, 14, 15). You will need to read the subsection, example, and info box before problem 13 to do the last few problems.
The AP registration deadline is upon us! Go to the Lassiter homepage and register for your exams. Bring a check to Ms Gasaway tomorrow.
HW for Friday, Feb 22: Do problems from Chapter 10: 10.6, 10.7, and 10.8 using your choice of SCAD or PHANTOMS and PANIC. The answers should be complete!
HW due Thursday, Feb 21: RE-DO problems 12.6-12.9 using the PHANTOMS or PANIC guides handed out in class. For those who miss Thursday's class due to a field trip, bring all homework on the day you return to demonstrate that you are current in the class or I will assign a more comprehensive set of problems upon your return to catch you up.
For Friday, Feb 22: continue to create confidence intervals, this time using x-bar and sigma of x. Do problems from Chapter 10: 10.6, 10.7, and 10.8. What assumptions or conditions do you need to check? If you guessed (1) SRS and independent observations, (2) population distribution is approximately normally distributed (or your sample is large enough for the central limit theorem to apply), and (3) the sample is less than one-tenth of the population size, then your brain is a finely-tuned instrument.
As you recall from Friday, the formula for the confidence interval for one proportion is p-hat +/- z* times SQRT(p-hat*(1-p-hat)/n)).
The source of the handout in today's class is
http://www.district196.org/evhs/People/baileyrcweb/APS%20Files/APS%20Main.htm
Please strike through the references to "retaining" the null hypothesis as well as the graph of a normal distribution on the confidence interval page. These are not appropriate for AP Statistics.
HW due Wednesday, Feb 20: 12.8 and 12.9 with complete solutions.
HW due Friday: Journal entry using problem 3 from the 2006 AP exam PLUS problems 12.6 and 12.7 from the text.
Alpha = the probability of rejecting the null hypothesis when the null hypothesis is true. It is the probability of a Type 1 error. This is the area associated with the rejection region.
HW due Thursday: Finish the 4-page worksheet about Distracted Drivers. Work on your journal entry (due Friday in a composition notebook).
HW due Tuesday: Problems 12.4 and 12.5. You'll have to read the information on the two pages preceding these questions. Come to class prepared to (1) explain how likely/unlikely your sample of pom-poms was from today's activity. That means that you have to calculate the z-value for your observation and compute the probability in the tail. ALSO, (2) be ready to explain how to simulate the distracted driver scenario using cards.
HW due Monday: Page 7 of 2006 Form B, problem 3 (golf balls) AND figure out a way to simulate the situation for problem 5 on page 9 of 2007 (the cell phone distraction problem).
JOURNAL ENTRY: The complete, perfect write-up of problem 3 from 2006 (page 8) will be due on Friday. The problem should be the first part of the entry, your fabulous answer should follow. This is the first problem to be entered in your composition notebook.
Has anyone tried this website? http://stattrek.com/AP-Statistics-1/AP-Statistics-Intro.aspx?Tutorial=ap
I wondered if it was helpful. Please let me know.
HW due Wednesday: Problems 39, 40, and 43 done completely. Answers from the calculator are not sufficient.
HW due Tuesday, Feb 26: Problems 27, 28, 33, and 34 covering hypothesis testing. You may need to refer to the PHANTOMS side of the worksheet. If you have difficulty writing hypotheses, do problems 30, 31, and 32 as well.
RE: Hypotheses writing
The hypotheses always include PARAMETERS, not statistics. Use mu and p, not x-bar and p-hat. The null hypothesis always has an "equal to" nature rather than a greater than or less than.
HW due Monday, Feb 25: Problems from Chapter 10 (5, 12, 13, 14, 15). You will need to read the subsection, example, and info box before problem 13 to do the last few problems.
The AP registration deadline is upon us! Go to the Lassiter homepage and register for your exams. Bring a check to Ms Gasaway tomorrow.
HW for Friday, Feb 22: Do problems from Chapter 10: 10.6, 10.7, and 10.8 using your choice of SCAD or PHANTOMS and PANIC. The answers should be complete!
HW due Thursday, Feb 21: RE-DO problems 12.6-12.9 using the PHANTOMS or PANIC guides handed out in class. For those who miss Thursday's class due to a field trip, bring all homework on the day you return to demonstrate that you are current in the class or I will assign a more comprehensive set of problems upon your return to catch you up.
For Friday, Feb 22: continue to create confidence intervals, this time using x-bar and sigma of x. Do problems from Chapter 10: 10.6, 10.7, and 10.8. What assumptions or conditions do you need to check? If you guessed (1) SRS and independent observations, (2) population distribution is approximately normally distributed (or your sample is large enough for the central limit theorem to apply), and (3) the sample is less than one-tenth of the population size, then your brain is a finely-tuned instrument.
As you recall from Friday, the formula for the confidence interval for one proportion is p-hat +/- z* times SQRT(p-hat*(1-p-hat)/n)).
The source of the handout in today's class is
http://www.district196.org/evhs/People/baileyrcweb/APS%20Files/APS%20Main.htm
Please strike through the references to "retaining" the null hypothesis as well as the graph of a normal distribution on the confidence interval page. These are not appropriate for AP Statistics.
HW due Wednesday, Feb 20: 12.8 and 12.9 with complete solutions.
HW due Friday: Journal entry using problem 3 from the 2006 AP exam PLUS problems 12.6 and 12.7 from the text.
Alpha = the probability of rejecting the null hypothesis when the null hypothesis is true. It is the probability of a Type 1 error. This is the area associated with the rejection region.
HW due Thursday: Finish the 4-page worksheet about Distracted Drivers. Work on your journal entry (due Friday in a composition notebook).
HW due Tuesday: Problems 12.4 and 12.5. You'll have to read the information on the two pages preceding these questions. Come to class prepared to (1) explain how likely/unlikely your sample of pom-poms was from today's activity. That means that you have to calculate the z-value for your observation and compute the probability in the tail. ALSO, (2) be ready to explain how to simulate the distracted driver scenario using cards.
HW due Monday: Page 7 of 2006 Form B, problem 3 (golf balls) AND figure out a way to simulate the situation for problem 5 on page 9 of 2007 (the cell phone distraction problem).
JOURNAL ENTRY: The complete, perfect write-up of problem 3 from 2006 (page 8) will be due on Friday. The problem should be the first part of the entry, your fabulous answer should follow. This is the first problem to be entered in your composition notebook.
Has anyone tried this website? http://stattrek.com/AP-Statistics-1/AP-Statistics-Intro.aspx?Tutorial=ap
I wondered if it was helpful. Please let me know.
Monday, February 04, 2008
Chapter 9 Sampling Distributions
Welcome to the beginning of inferential statistics! Your test is Thursday February 7.
Elaborate response to a question about mu and x-bar is in the comments section below. Don't miss it.
Work all the problems on the latest problem worksheet for homework Tuesday.
Mean of sampling distribution = mean of population regardless of shape of distribution
Std dev of sampling distribution = std dev of population divided by sqrt (n) regardless of shape of distribution as long as sample does not exceed 1/10th population.
Central Limit Theorem
Case 0: Underlying distribution is normal à sampling distribution is AUTOMATICALLY normal. The Central Limit Theorem DOES NOT APPLY. It isn't needed.
Case 1: If the sample is tiny (less than or equal to 10), then the population distribution must be nearly normal for the Central Limit Theorem to kick in.
Case 2: If the sample is moderate (up to about 35), then the population needs to be mound shaped without outliers for the Central Limit Theorem to kick in.
Case 3: If the sample is large, then the Central Limit Theorem kicks in.
****Write the implications of the Central Limit Theorem in your own words.
Thus, the answer to the questions at the end of problems .27 and .28 from Friday are that we DID NOT need the underlying distribution to be normal for us to use the formulas for the mean and the std dev of the sampling distribution (mu x = mu x-bar and std dev x-bar = std dev x / sqrt n, as shown in the text). Knowing that the distribution of x is Normal or knowing that the CLT applies is essential to working the sampling distribution problems using Normal methods.
HW: Problems 17 through 19 on the w/s from last week AND problems 8.34-8.36 on the w/s we handed out in class today.
Here's an applet that will help to show what happens to the distribution of the sample means as the sample size increases and as the distribution of the population is more or less normal. Set the radio buttons to show only the sample means and sample 100 at a time.
http://wise.cgu.edu/sdmmod/sdm_applet.asp
As you saw in the histograms today, the larger the sample size, the narrower the distribution of sample means. In fact, the standard deviation of the distribution of sample means shrinks proportionally to 1/( square root of the sample size)[the std dev of the sampling means = sigma of x times 1/sqrt n]. You'll see this in your READING of section 9.3 and practice it in your HOMEWORK for the weekend: 9.26 through 9.29.
For those who need to refresh their understanding of histograms, do problems 1.4 and 1.41 by hand.
Don't forget about CiCi's on Sunday if you are available.
What is the probability. . . ?http://www.time.com/time/health/article/0,8599,1707541,00.html?cnn=yes
Due Friday: Work problems 12-16 on the handout. Be an expert on these proportion problems and normal approximation for the binomial before you come to class. Friday we start sampling distributions for sample means.
Due Thursday: Problems 8-11 on the handout.
Due Wednesday: Problems 9.17 and 9.18, worked and explained completely, OR problems 9.19 and 9.20, which are more routine but must be completed.
What happens when the sample size increases??? If your variable of interest is the sample proportion, the distribution of sample proportions (p-hats) will become "tighter," that is that it will have less variability as the sample size increases.
Now, if you're talking about the values of X in a binomial distribution, as the number of trials increases, the variability of the number of successes also increases. Arrrrrggggh! Sometimes the standard deviation increases, sometimes it decreases.
One of the important ideas that you were supposed to catch was that the population size does not affect the variability of the sampling distribution. You "see" this when you look at the formulas--there is no mention of the population size in the formula for the standard deviation.
So, what is the point? For those binomial distributions where the expected number of successes and the expected number of failures are both at least ten, the sampling distribution of the Xs or the p-hats may be modeled (approximately) by the normal curve. Thus, you can calculate z-values for the values of interest, X or p-hat, and use the standard normal table or normalcdf to calculate probabilities. Cool.
This is part of the foundation for the polling estimates that you see so often during these election years.
Here's a new section for the blog called Because You Asked. One of the gurus of AP Statistics wrote an article that explains the 10% rule. You can find it through College Board at the following link.
http://apcentral.collegeboard.com/apc/members/courses/teachers_corner/39161.html
Due Tuesday: Problems 9.14 and 9.15 PLUS you must read the pages between these problems. Get your journal ready for the first entry.
Due Monday: All of the work previously assigned and a complete, correct draft of the answers to the "depth of the refracting layer" problem we worked in class on Thursday and Friday.
HW due Friday: Read through page 467 CAREFULLY. Work problems 9.1-9.4, 9.6, 9.8, 9.9, and 9.12. Do problem 9.7 if you get the chance (otherwise, it will be due later).
Parameters are measures of populations.
Statistics are measures of samples.
Examples of parameters: the mean of a population (mu, AKA mu sub x), the population proportion (p), the population standard deviation (sigma).
Examples of statistics: the sample mean (x-bar), the sample proportion (p-hat), and the sample standard deviation (s sub x).
The mean of all the sample means of a distribution (the sampling distribution) is the same as the mean of the distribution. This means that mu sub x-bar equals mu sub x.
The variability of the sample means (the variance of the sampling distribution)decreases as the sample size increases.
As long as the population is REALLY large compared to the sample, the size of the population does not affect the variability of the sample means.
HW for Thursday: Complete the blue sheet AND do problems 9.1-9.4 and 9.8.
Questions to ponder: What does the histogram of your penny-ages look like?
Does the histogram from a small sample have the same shape as a large sample's histogram?
What do you think that the average age of the pennies is?
How far out are outliers?
What are the important characteristics that you need to include when describing a probability histogram (either frequency diagram or relative frequency diagram)?
Elaborate response to a question about mu and x-bar is in the comments section below. Don't miss it.
Work all the problems on the latest problem worksheet for homework Tuesday.
Mean of sampling distribution = mean of population regardless of shape of distribution
Std dev of sampling distribution = std dev of population divided by sqrt (n) regardless of shape of distribution as long as sample does not exceed 1/10th population.
Central Limit Theorem
Case 0: Underlying distribution is normal à sampling distribution is AUTOMATICALLY normal. The Central Limit Theorem DOES NOT APPLY. It isn't needed.
Case 1: If the sample is tiny (less than or equal to 10), then the population distribution must be nearly normal for the Central Limit Theorem to kick in.
Case 2: If the sample is moderate (up to about 35), then the population needs to be mound shaped without outliers for the Central Limit Theorem to kick in.
Case 3: If the sample is large, then the Central Limit Theorem kicks in.
****Write the implications of the Central Limit Theorem in your own words.
Thus, the answer to the questions at the end of problems .27 and .28 from Friday are that we DID NOT need the underlying distribution to be normal for us to use the formulas for the mean and the std dev of the sampling distribution (mu x = mu x-bar and std dev x-bar = std dev x / sqrt n, as shown in the text). Knowing that the distribution of x is Normal or knowing that the CLT applies is essential to working the sampling distribution problems using Normal methods.
HW: Problems 17 through 19 on the w/s from last week AND problems 8.34-8.36 on the w/s we handed out in class today.
Here's an applet that will help to show what happens to the distribution of the sample means as the sample size increases and as the distribution of the population is more or less normal. Set the radio buttons to show only the sample means and sample 100 at a time.
http://wise.cgu.edu/sdmmod/sdm_applet.asp
As you saw in the histograms today, the larger the sample size, the narrower the distribution of sample means. In fact, the standard deviation of the distribution of sample means shrinks proportionally to 1/( square root of the sample size)[the std dev of the sampling means = sigma of x times 1/sqrt n]. You'll see this in your READING of section 9.3 and practice it in your HOMEWORK for the weekend: 9.26 through 9.29.
For those who need to refresh their understanding of histograms, do problems 1.4 and 1.41 by hand.
Don't forget about CiCi's on Sunday if you are available.
What is the probability. . . ?http://www.time.com/time/health/article/0,8599,1707541,00.html?cnn=yes
Due Friday: Work problems 12-16 on the handout. Be an expert on these proportion problems and normal approximation for the binomial before you come to class. Friday we start sampling distributions for sample means.
Due Thursday: Problems 8-11 on the handout.
Due Wednesday: Problems 9.17 and 9.18, worked and explained completely, OR problems 9.19 and 9.20, which are more routine but must be completed.
What happens when the sample size increases??? If your variable of interest is the sample proportion, the distribution of sample proportions (p-hats) will become "tighter," that is that it will have less variability as the sample size increases.
Now, if you're talking about the values of X in a binomial distribution, as the number of trials increases, the variability of the number of successes also increases. Arrrrrggggh! Sometimes the standard deviation increases, sometimes it decreases.
One of the important ideas that you were supposed to catch was that the population size does not affect the variability of the sampling distribution. You "see" this when you look at the formulas--there is no mention of the population size in the formula for the standard deviation.
So, what is the point? For those binomial distributions where the expected number of successes and the expected number of failures are both at least ten, the sampling distribution of the Xs or the p-hats may be modeled (approximately) by the normal curve. Thus, you can calculate z-values for the values of interest, X or p-hat, and use the standard normal table or normalcdf to calculate probabilities. Cool.
This is part of the foundation for the polling estimates that you see so often during these election years.
Here's a new section for the blog called Because You Asked. One of the gurus of AP Statistics wrote an article that explains the 10% rule. You can find it through College Board at the following link.
http://apcentral.collegeboard.com/apc/members/courses/teachers_corner/39161.html
Due Tuesday: Problems 9.14 and 9.15 PLUS you must read the pages between these problems. Get your journal ready for the first entry.
Due Monday: All of the work previously assigned and a complete, correct draft of the answers to the "depth of the refracting layer" problem we worked in class on Thursday and Friday.
HW due Friday: Read through page 467 CAREFULLY. Work problems 9.1-9.4, 9.6, 9.8, 9.9, and 9.12. Do problem 9.7 if you get the chance (otherwise, it will be due later).
Parameters are measures of populations.
Statistics are measures of samples.
Examples of parameters: the mean of a population (mu, AKA mu sub x), the population proportion (p), the population standard deviation (sigma).
Examples of statistics: the sample mean (x-bar), the sample proportion (p-hat), and the sample standard deviation (s sub x).
The mean of all the sample means of a distribution (the sampling distribution) is the same as the mean of the distribution. This means that mu sub x-bar equals mu sub x.
The variability of the sample means (the variance of the sampling distribution)decreases as the sample size increases.
As long as the population is REALLY large compared to the sample, the size of the population does not affect the variability of the sample means.
HW for Thursday: Complete the blue sheet AND do problems 9.1-9.4 and 9.8.
Questions to ponder: What does the histogram of your penny-ages look like?
Does the histogram from a small sample have the same shape as a large sample's histogram?
What do you think that the average age of the pennies is?
How far out are outliers?
What are the important characteristics that you need to include when describing a probability histogram (either frequency diagram or relative frequency diagram)?
Wednesday, January 16, 2008
Chapter 8 Some special probability distributions
TEST Tuesday 1/22/08
HW due 1/18: 8.41, 8.42
HW due 1/17: 8.37, 8.38, 8.39
HW due 1/16: 8.27, 8.28, 8.30, 8.31
HW due 1/15: 8.24, 8.25
With apologies to our Harvard buddies, here is a summary of binomial distribution facts and methods:
http://www.stat.yale.edu/Courses/1997-98/101/binom.htm
HW due 1/14: 8.19, .20, .22, .23
You guys rocked today! Your questions and explanations were top notch. HW 1/10 Answer problem #11 fromt he worksheet in the blue book using all three of the methods: formula, binomial pdf, and binomial cdf. Show all work and include explanations that you can rely upon to remind you of these methods later in the semester. Be neat and write legibly. Use appropriate language.
HW 1/9 Answer the questions from the 12 days worksheet that have a binomial setting.
HW 1/8 Write up a study guide for the Binomial Probability section of Chapter 8 AND answer questions 8.1-8.4. Bring the "12 days" worksheet back so we can discuss it.
Check out the arbitrary (not random) stuff in the next blog!
HW due 1/18: 8.41, 8.42
HW due 1/17: 8.37, 8.38, 8.39
HW due 1/16: 8.27, 8.28, 8.30, 8.31
HW due 1/15: 8.24, 8.25
With apologies to our Harvard buddies, here is a summary of binomial distribution facts and methods:
http://www.stat.yale.edu/Courses/1997-98/101/binom.htm
HW due 1/14: 8.19, .20, .22, .23
You guys rocked today! Your questions and explanations were top notch. HW 1/10 Answer problem #11 fromt he worksheet in the blue book using all three of the methods: formula, binomial pdf, and binomial cdf. Show all work and include explanations that you can rely upon to remind you of these methods later in the semester. Be neat and write legibly. Use appropriate language.
HW 1/9 Answer the questions from the 12 days worksheet that have a binomial setting.
HW 1/8 Write up a study guide for the Binomial Probability section of Chapter 8 AND answer questions 8.1-8.4. Bring the "12 days" worksheet back so we can discuss it.
Check out the arbitrary (not random) stuff in the next blog!
Sunday, January 06, 2008
First semester final exam and other neat stuff to read
A timely article about polling: http://www.cnn.com/2008/POLITICS/01/02/projection.explainer/index.html?iref=newssearch
Article on the effect of improved organizational skills on boys' achievement in school:
http://www.iht.com/articles/2008/01/01/america/01boys.php
Have you seen the Norwegian engineering recruitment videos yet? Scroll down and let me know what you think.
For info on influential points and outliers, google statistics influential points. Some students posted pretty good (but terribly distracting) powerpoints.
The SAT results for Georgia broken down in all kinds of interesting ways:
http://www.collegeboard.com/prod_downloads/about/news_info/cbsenior/yr2007/GA_07.pdf
These data prompt discussion about causation, such as whether choosing a technical major makes your math score higher. What do you think?
On the lack of publicity for Nobel Prize Winners:
http://pharmtech.findpharma.com/pharmtech/From+the+Editor/What-Good-is-Winning-a-Prize-if-No-One-Cares/ArticleStandard/Article/detail/469658
So you want to be a casino mogul? How about starting with one of these jobs?
http://www.state.nj.us/oag/ge/2000news/slotlab.htm
Shortages of engineers (Click on the READ online button, then click on the lower right corner of the pages to advance through the newsletter)
http://thefloridaengineer.eng.ufl.edu/themagazine/fe0801/index.php
Two videos from Norway:
There's one bad word in this one written in the subtitles. Please excuse this word--the rest of the video promotes engineering for young people. (And you know how those crazy Norwegians are.)
http://www.youtube.com/watch?v=gXZZknJWtGg&feature=related
http://www.youtube.com/watch?v=JFoMmJAAHjg&feature=related
Water use statistics for Cobb: http://www.ajc.com/metro/content/metro/cobb/stories/2007/12/19/cobb_water_1220.html
Interesting webpage about one of our community members and how his company provides service in disaster relief:
http://cateringcajun.net/_wsn/page7.html
Chance, conditional probability, and MARS!
http://www.cnn.com/2007/TECH/space/12/21/mars.asteroid.ap/index.html
Article on the effect of improved organizational skills on boys' achievement in school:
http://www.iht.com/articles/2008/01/01/america/01boys.php
Have you seen the Norwegian engineering recruitment videos yet? Scroll down and let me know what you think.
For info on influential points and outliers, google statistics influential points. Some students posted pretty good (but terribly distracting) powerpoints.
The SAT results for Georgia broken down in all kinds of interesting ways:
http://www.collegeboard.com/prod_downloads/about/news_info/cbsenior/yr2007/GA_07.pdf
These data prompt discussion about causation, such as whether choosing a technical major makes your math score higher. What do you think?
On the lack of publicity for Nobel Prize Winners:
http://pharmtech.findpharma.com/pharmtech/From+the+Editor/What-Good-is-Winning-a-Prize-if-No-One-Cares/ArticleStandard/Article/detail/469658
So you want to be a casino mogul? How about starting with one of these jobs?
http://www.state.nj.us/oag/ge/2000news/slotlab.htm
Shortages of engineers (Click on the READ online button, then click on the lower right corner of the pages to advance through the newsletter)
http://thefloridaengineer.eng.ufl.edu/themagazine/fe0801/index.php
Two videos from Norway:
There's one bad word in this one written in the subtitles. Please excuse this word--the rest of the video promotes engineering for young people. (And you know how those crazy Norwegians are.)
http://www.youtube.com/watch?v=gXZZknJWtGg&feature=related
http://www.youtube.com/watch?v=JFoMmJAAHjg&feature=related
Water use statistics for Cobb: http://www.ajc.com/metro/content/metro/cobb/stories/2007/12/19/cobb_water_1220.html
Interesting webpage about one of our community members and how his company provides service in disaster relief:
http://cateringcajun.net/_wsn/page7.html
Chance, conditional probability, and MARS!
http://www.cnn.com/2007/TECH/space/12/21/mars.asteroid.ap/index.html
Subscribe to:
Posts (Atom)
Posts
