Test 2 Review

(See caution at the end of the document.)

Test Reviews:

These Test Reviews are not intended to replace doing the classwork and doing the homework These are not lists of objectives for the chapters nor are they complete lists of the topics. The textbook and homework provide those. These Test Reviews focus on topics and problems that students in previous semesters have been somewhat more likely to make mistakes on than the rest of the material.

It is pointless to even read these questions until you have read the chapters and done the homework. After that, you might want to write out answers to the questions (maybe conferring with other students in your class) and then bring the questions and your answers to the instructor or a tutor so that they can help you with any misunderstandings you have.

Test 2:

Read the chapter summaries and use them and your homework as guidelines for what to put on your page of notes. Also, be sure that you understand all the material from the first test, particularly any problem on that test for which you missed any part. Then look over the following comments about things that students sometimes miss on tests to make sure you understand these.

  1. Chapters 4 and 5 go together pretty well. Be prepared to take a set of data and compute everything we learned to compute in these chapters and interpret all of it. Sometimes students forget to study the interpretation of the slope coefficient and the intercept.
  2. Understand the meaning of r-squared.
  3. Be able to determine which variable should be the response variable.  Understand why you get a different regression line if you choose the other variable as the response variable.
  4. Be able to make a residual plot of the residuals versus the explanatory variable.
  5. Be able to determine whether a point is influential in regression. 
  6. Be able to determine whether a point is influential in correlation.
  7. Understand and use the cautions about correlation and regression.
  8. Computations: You must be able to use your calculator to compute means. If you are not able to use your usual technology on the test, you won't be required to compute the standard deviations on the test. Recall that we don't compute r, the correlation coefficient except with Minitab. I'll give you that when you need if for a problem on the test. Be sure that you can compute the regression coefficients from the means, standard deviations, and r.
  9. Distinguish between quantitative and categorical data and know which techniques are appropriate to analyze which types of data.
  10. Determine from the statement of the problem which variable should be the response variable and know what that means for scatterplots and the regression equation.
  11. Compute conditional distributions and marginal distributions and to graph these.
  12. Answer various questions about two-way tables.
  13. Take the data in a three-way table and produce a two-way table of the type requested from it.
  14. Answer questions involving Simpson's Paradox.
  15. Be sure that you can distinguish between the population and the sample. Is the sample the ones you selected, or the ones you actually observed? (I.e., do "nonrespondents" count as part of the sample, according to the definitions here?)
  16. Is a stratified random sample the same as a simple random sample?
  17. Draw a diagram of your experimental design, like the diagrams (called outlines) of completely randomized designs and of block designs. Use the "jargon" of experimental design correctly, such as factors, treatments, etc.
  18. Identify and discuss the main principles of experimental design.
  19. For a given question, describe a good sampling design or a good experimental design, as appropriate.
  20. Identify problems with, and answer questions about, a given sampling design or experimental design.

 

Discussion in class always supersedes any information on the Web about what is covered on what test. I make no guarantee that the Web version will be updated as things change, although I do attempt to do so. However, it is very unlikely that very much will change at any one time, so it is completely reasonable to do much of your studying from this even if you are not sure what was said in class. If you missed any class, you should get someone's notes and read through them before you consider that you have fully prepared for the test.

This was last updated on October 9, 2007 . Mary Parker, mparker@austincc.edu