Question

T F 1. A p-value of .008 in hypothesis testing means there is only a .8% chance we could get such sample statistics from the population if the null hypothesis is as stated. Such an event is considered unlikely and we would reject the null hypothesis.

T F 2. As a general rule in hypothesis testing, it is always safer to set up your alternate hypothesis with a greater-than or less-than orientation.

_____3. If the level of significance is .02 then the chance of making a Type I error is:

A. zero B.98% C.2/100 D.19/20 E. cannot be calculated

T F 4. When doing two population proportion hypothesis tests, we get our “normalcy” for the z-distribution by keeping the sample sizes from each population greater than or equal to 50.

T F 5.If making a Type II error is much more serious than making a Type I error, you would select a .01 rather than a .10 alpha risk.

T F 6. When comparing 3 or more population means using ANOVA, we can make the test more robust regarding assumptions by keeping the sample sizes the same in each population.

T F 7. It is always more difficult to reject the null hypothesis using the t distribution compared to the z distribution given the same level of significance (alpha risk) and sample size.

T F 8. Dependent sample hypothesis tests have a smaller source of variation than independent sample hypotheses tests.

T F 9. We could use the z or t distribution to compare more than two populations, but the resulting buildup of Type I error would be an issue.

T F 10. The “computer effect” described in one of our daily stats lessons refers to the large amount of useful stats output that can be produced by anyone with statistics software.

T F 11. We assume normalcy when using the t-distribution for hypothesis testing.

______12. The “before and after” t-test is appropriate to use when:

A. Four samples are compared at once.

B. Any two samples are compared

C. Independent samples are compared.

D. Dependent samples are compared.

E. None of the above is correct.

T F 13. One advantage of using the p-value method of hypothesis testing is that it allows you to see how close your reject/fail to reject decision was.

T F 14. In addition to hypothesis testing, the F-distribution can be used in a test comparing two population variances

T F 15. As you reduce your chances of making a Type I error you increase your chances of making a Type II error.

T F 16. The p-values used in hypothesis testing for the most part must be calculated by hand using the P-value formula.

T F 17. When doing a one population proportion hypothesis tests we must do a normalcy check in Step 3 before we can use the z-distribution.

T F 18. A good hypothesis testing strategy is to select a level of significance in Step 2 that minimizes the chances of making the most costly error.

T F 19. A “robust” statistics technique is one that gives good decision-making help even if we don’t meet all required assumptions exactly.

T F 20. A Type I error occurs when you fail to reject the null hypothesis when it should have been rejected.

T F 21. In Step 3 of the hypothesis testing procedure the test statistic is powered by population values.

T F 22. As the degrees of freedom change, the shape of the F-distribution curve changes shape, but it always remains positive, starting at 0 and moving off to the right.

T F 23. In hypothesis testing, when we fail to reject the null hypothesis we are saying the difference between the sample statistic and the population parameter is not statistically significant.

T F 24. An important equation when using the F-distribution to do hypothesis tests comparing 3 populations is: SStotal = SST + SSE.

T F 25. When writing up a hypothesis testing conclusion in Step 6 it is OK to say either “we fail to reject the null” or “we accept the null hypothesis”.

Answer 1

As per the guidelines I am suggested to answer only four sub-parts at a time, please ask rest of the questions separately. I will be happy to help.

1) True

As we know that the smaller is the p value, the stronger is the evidence to reject the null hypothesis, and accept the alternative hypothesis is the test.

2) True

As the null hypothesis is always kept with a symbol of equal to in it.

3) Answer - C) 2/100

As alpha is the level of significance which is the probability of accepting a type 1 error.

4) False

Instead of more than 50, we generally use the rule of more than 30 sample data.

Please upvote if this helps. Thanks.