Question

Mark each of the following as true or false and justify your response.

1. If you fail to reject the null hypothesis, then the research hypothesis is false.

2. Independent variables may be linearly related.

3. A slope of 1.2 indicates that the independent variable changes 12 units for every 10 unit change in the dependent variable.

4. If a variable is normally distributed with a mean of 50 and a variance of 9, then approximately 68% of scores are between 41 and 59.

5. A paired t-test can only be used for experimental study designs.

6. Relative Risk (RR) may be calculated for retrospective and prospective studies.

7. Randomization helps to eliminate confounding.

8. For a normally distributed random variable, P(a<X<b) <.5 if a>0 and b>0.

9. The mean for a variable will be less than the median if the variable has a unimodal distribution.

10. The p-value for a two-tailed test will always be greater than the p-value for one-tailed test.

11. An experimental study should always be conducted whenever possible.

12. Sample statistics for variables in a data set should only be calculated for a case-control study.

13. Results from studies should always be generalized to the entire population regardless of the sample.

14. Stratified analysis may reveal differences between groups.

15. Confidence intervals should only be used when trying to estimate means and proportions.

Answer 1

Solution:

1. Generally research hypothesis is alternative hypothesis, hence if we reject the null hypothesis research hypothesis is true. So answer is False

2. For linear correlation,one dependent and one independent variable is required so they cannot be independent. So answer is False

3. A slope of 1.2 indicates that the dependent variable changes 1.2 units for every 1 unit change in the independent variable. So answer is False

4.

Answer is False

5.

A paired t- test can only be used for experimental study designs - False

6.

Relative risk is calculated for prospective studies so

Answer is False