Self-Assessment Module 10




Introduction Instructions Resources Assessment 1. Algebraic Notation and Operations 2. Descriptive Statistics 3. Tabular Displays of Data 4. Graphical Displays of Data 5. Research Topics, Theory, Constructs, Questions, and Hypothesis 6. Research Designs 7. Measurement 8. Sampling 9. Probability 10. Basics of Inferential Statistics 11. One-Group Inferential Statistics 12. Two-Group Inferential Statistics 13. Critiquing Education and Social Science Research Answer Key		Module 10: Basics of Inferential Statistics This section assesses conceptual understanding of inferential statistics. Inferential statistics are used widely in education and social science research and evaluation. Question 1: What is the main purpose of inferential statistics? A. To make inferences about a sample from a population B. To make inferences about a population from a sample C. To help one understand the field of statistics D. To confuse graduate students E. None of the above Question 2: What are random sampling errors? A. Mistakes researchers sometimes make when drawing a random sample B. Differences between samples and the population from which they are drawn that occur by chance during random sampling C. Differences between populations that can happen by chance up to the .05 level D. When the null hypothesis is wrong E. None of the above Question 3: A researcher takes a census of the entire population of presidents of two-year colleges in the mid-Atlantic region and finds those in public institution have average salaries of $2,100 dollars more than those in private institutions, but the difference proves not to be statistically significant. What should be inferred from this data about possible salary differences? A. There is no difference in the average salaries of the two groups B. We cannot be sure whether there is a difference in the average salaries of the two groups C. The public institution presidents have average salaries $2,100 greater than private institution presidents D. Not enough information is provided to make an inference E. None of the above Question 4: What is a null hypothesis? A. The hypothesis that is being tested B. Any other hypothesis not being tested C. A hypothesis that is statistically significant D. A hypothesis that is not statistically significant E. None of the above Question 5: In hypothesis testing, what is a Type I error? A. Rejection of the null hypothesis when it is true B. Failure to reject the null hypothesis when it is false C. Presuming the distribution is normal when it isn't D. Presuming the distribution is not normal when it is E. None of the above Question 6: In hypothesis testing, what is a Type II error? A. Rejection of the null hypothesis when it is true B. Failure to reject the null hypothesis when it is false C. Presuming the distribution is normal when it isn't D. Presuming the distribution is not normal when it is E. None of the above Question 7: In hypothesis testing, what is alpha error? A. The maximum Type I error to be tolerated when hypothesis testing B. The minimum Type I error to be encountered when hypothesis testing C. The maximum Type II error to be tolerated when hypothesis testing D. The minimum Type II error to be encountered when hypothesis testing E. None of the above Question 8: What are the most common alpha levels used in social science hypothesis testing? A. 95 and 99 B. 01 and 05 C. .95 and .99 D. .01 and .05 E. None of the above Question 9: In hypothesis testing, when should you use a one-tail test? A. When the population is normally distributed B. When the population is skewed C. When the alternative to the null hypothesis is directional D. When the alternative to the null hypothesis is non-directional E. None of the above Question 10: In hypothesis testing, when should you use a two-tail test? A. When the population is normally distributed B. When the population is skewed C. When the alternative to the null hypothesis is directional D. When the alternative to the null hypothesis is non-directional E. None of the above Question 11: In hypothesis testing, what is power? A. The probability of accepting the null hypothesis when it is true B. The probability of rejecting the null hypothesis when it is false C. The size of the sample relative to the size of the population D. The size of the standard deviation relative to the mean difference E. None of the above Question 12: Parametric statistical tests of hypotheses involving two or more groups should be used when what general conditions are met? A. When you know the parameters of the population and the sample. B. When you do not know the parameters of the population and the sample C. When the independent variable is an interval or ratio measure, the population distribution is approximately normal or the sample size exceeds 25, and there is homogeneity of variance. D. When the dependent variable is an interval or ratio measure, the population distribution is approximately normal or the sample size exceeds 25, and there is homogeneity of variance. E. None of the above Question 13: Non-parametric statistical tests should be used when what conditions are met? A. When you know the parameters of the population and the sample. B. When you do not know the parameters of the population and the sample C. When the independent variable does not meet the conditions for parametric tests D. When the dependent variable does not meet the conditions for parametric tests E. None of the above Question 14: What is the main advantage and disadvantage of parametric tests in comparison to non-parametric tests? A. Parametric tests are more powerful but the data must comply with more assumptions B. Parametric tests are more powerful but are subject to more potential bias C. Non-parametric tests are more powerful but the data must comply with more assumptions D. Non-parametric tests are more powerful but are subject to more potential bias E. None of the above Question 15: In hypothesis testing, what are the critical values? A. The values of a population parameter that are specified in the null hypothesis B. The values of z, t, Chi Square, etc. beyond which you conclude the null hypothesis is rejected at a given level of significance C. The computed z, t, Chi Square, etc. value which is compared against the tabular values for these statistics. D. The alpha and beta levels used in significance testing. E. None of the above Question 16: If a null hypothesis is found to be statistically significant at the .1 level, what does that mean? A. It means that you should reject the null hypothesis with only a 0.1 chance of being wrong B. It means that you should reject the null hypothesis with not more than a 0.1 chance of being wrong C. It means that you should accept the null hypothesis with only a 0.1 chance of being wrong D. It means that you should accept the null hypothesis with not more than a 0.1 chance of being wrong E. None of the above Question 17: A normal distribution of values is characterized by: A. The frequency distribution is constant (is rectangular) and ranges from 0 to 1 B. The frequency distribution is constant (is rectangular) and ranges from 0 to 100 C. The frequency distribution is bell shaped with 95% of the values within plus and minus 1.96 standard deviations of the mean D. The frequency distribution is cumulative with 95% of the values within plus and minus 1.96 standard deviations of the mean E. None of the above Question 18: A negatively skewed distribution is characterized by: A. A longer and flatter tail to the right side B. A longer and flatter tail to the left side C. Where there are more negative values than positive ones D. Where there are less negative values than positive ones E. None of the above Question 19: If the variance of a set of six scores is 25, what is the standard deviation? A. Less than 25 B. The same (i.e., 25) C. More than 25 D. It depends on information that is not provided E. None of the above Question 20: If 9 is added to each score in a normal distribution with a mean of 25 and a standard deviation of 12, the new standard deviation will be: A. 3 B. 16 C. 18 D. 21 E. None of the above Question 21: If a set of measures has a mean of 20 and a variance of 16. How many standard deviations is 14 from the mean? A. 3/8 B. 3/4 C. 1.5 D. 1.7 E. None of the above Question 22: Julie scores 65 on a history test with a mean of score of 50 and a standard deviation of 10, and scores 65 on science test with a mean of 40 and a standard deviation of 20. On which test did Julie do better relative to the other students? A. On the history test B. On the science test C. Equally well on both D. Insufficient information is provided for judging E. None of the above Question 23: In inferential statistics, what is a confidence interval? A. It is the same as statistical significance B. It is the inverse of statistical significance C. It is a lower and upper estimate (at a given level of significance ) of a sample value D. It is a lower and upper estimate (at a given level of significance) of a population value E. None of the above Question 24: If a sample has a mean of 36 and a standard error of the mean of 4, approximately what is the 95 percent confidence interval? A. About 34 - 38 B. About 32 - 40 C. About 28 - 44 D. About 24 - 48 E. None of the above