Study Questiions of Quiz #2

Variables, Univariate Statistics & Statistical Inference

1. What are the (four) major types of measures/behaviors involved in statistical analyses? What procedures can influence which of these we have in a given data collection? How can the data analyst know which type(s) are involved in a particular study?

2. What do we mean when we say our data analyses are "inferential"? How do we know whether our "inferences" are correct?

3. What are the population and sample characteristics that increase and decrease the accuracy of our inferences about the population mean? How should we use this information when designing our data collections?

4. What is an "SEM"? Describe how this can be estimated from a single sample and why this estimation process is reasonable.

5. Describe the different purposes and approaches to getting a stratified sample. How can stratified sampling lead to a poor representation of the population parameters?

Statistical Hypothesis Testing & Univariate Tests

6. Describe the process of NHST and tell the possible outcomes. (Be sure to tell what this acronym means.)

7. Discriminate among the various types of statistical decision errors and tell the likely reasons for each. How can we be certain whether or not we have committed one of these errors with a particular analysis?

8. Describe the univariate significance tests applied to quantitative & qualitative data, including the H0:, usual RH:, and the two different ways these test are often applied.

ANOVA

9. Describe the three bivariate significance test we will be using in this class and how to decide which one to use.

10. State the generic H0: for each of the three types of significance tests. Tell the parts that are common to the H0:s of all three tests and what part of each is specific to that particular test.

11. What are the possible RH: and outcomes for an ANOVA analysis? (Be sure to cover all the possible decision errors.)

12. When can the results of an ANOVA be used to test each of the major types of research hypotheses? (attributive, associative & causal)

13. Compare and contrast the uses of the between groups and within‑groups ANOVA models (kinds of data, null hypotheses, possible values).

Pearson's r & X²

14. What are the possible RH: and outcomes for a Pearson's correlation analysis? (Be sure to cover all the possible decision errors.)

15. When can the results of a Pearson's correlation analysis be used to test each of the major types of research hypotheses? (attributive, associative & causal)

16. What are the possible RH: and outcomes for a Pearson's X² analysis? (Be sure to cover all the possible decision errors.)

17. When can the results of a Pearson's X² analysis be used to test each of the major types of research hypotheses? (attributive, associative & causal)

Details of Bivariate Tests

18. Compare and contrasts the "interesting pairs" of the four bivariate data analysis models we are working with.

19. Tell the components of a complete null hypothesis and how its expression differs when using each of the following: Pearson's correlation, Chi‑square, Between Groups ANOVA and Within‑groups ANOVA.

20. Tell the symbolic H0:, range of possible values, basis for H0: rejection and how one describes the "direction" or "pattern" of a non‑H0: outcome for each of the following: Pearson's correlation, Chi‑square, Between Groups ANOVA and Within‑groups ANOVA.

21. Respond to and describe the statement, "Rejecting the null hypothesis guarantees support for the research hypothesis."

NHST Controversy, Confidence Intervals, Effect Size & Power Analysis

22. What are the "three positions" in the NHST controversy? Which do you prefer & why?

23. What are confidence intervals and what three types did we explore? What does a CI tell that is redundant with NHST? What additional information is provided by Cis?

24. Describe effect size estimates, tell how they are related to significance tests, the information they provide that is not provided by significance tests.

25. What is meant by "statistical power" and what is the advantage if our research has lots of it? Describe how power analyses are conducted and how they can inform out statistical decisions.

26. Tell the possible outcomes of a statistical decision and how we determine the probability of each.

Transformations and Data Screening

27. Tell the common types of transformations applied to quantitative data. Distinguish between "linear" and "nonlinear" transformations applied to quantitative variables, in terms of the operations and their results. What is the most common use of each?

28. Describe the effects of each type of linear transformation upon the mean and standard deviation of a set of quantitative data. Describe each of the following common transformations and describe why each is linear or nonlinear:

1) Z-scores 2) T-scores 3) change scores 4) y' values

29. What is the purpose of a sample? What are outliers and what difficulties do they cause? Tell the two most common ways of identifying outliers, which is currently preferred, why? What is the critical step in this process that helps ensure the absence of "sleaze"?

30. Describe how to apply outlier analysis to prepare data for bivariate analyses.