Question

From the list given to you for each of the following hypothesis testing situations, indicate the test you would use and explain the reason  

1. Pearsons Product-Moment Correlation Coefficient (Test #13)  

2. Spearman Rank Correlation (Test# 14)

3. Simple Linear Regression (Test# 15)  

4. ANOVA (Test # 16)

5. Kruskal-Wallis (Test # 17)

----

1. A researcher wants to know what the relationship is between how fifteen people do in a debate tournament (first place to fifteenth place), and how they do in a drama meet (also ordered from first to last)

2. You want to predict how many push-ups students will be able to do after participating in a fitness program from the number of push-ups they could do before the program starts.

3. You want to compare the mean numbers of push-ups done by 40 children who have attended one of three different fitness camps in order to see which fitness program is better.

4. A researcher wants to test the effects of 4 treatments on Poplar tree weights. The claim at the 5% significance level is that all four of the treatments produce the same median weight for poplar trees grown from seedlings. The hypotheses are:

Ho: M1 = M2 = M3 = M4

Ha: At least two medians differ from each other

Answer 1

1. A researcher wants to know what the relationship is between how fifteen people do in a debate tournament (first place to fifteenth place), and how they do in a drama meet (also ordered from first to last

Spearman Rank Correlation is a nonparametric measure of rank correlation (statistical dependence between the rankings of two variables).

Spearman's coefficient is appropriate for both continuous and discrete ordinal variables

2. You want to predict how many push-ups students will be able to do after participating in a fitness program from the number of push-ups they could do before the program starts.

since we want to predict

regression will be used

3. You want to compare the mean numbers of push-ups done by 40 children who have attended one of three different fitness camps in order to see which fitness program is better.

Anova is a technique that can be used to compare means of two or more samples

4. A researcher wants to test the effects of 4 treatments on Poplar tree weights. The claim at the 5% significance level is that all four of the treatments produce the same median weight for poplar trees grown from seedlings. The hypotheses are:

Ho: M1 = M2 = M3 = M4

Ha: At least two medians differ from each other

This is Kruskal-Wallis

It is non-paramteric test equilvalent of ANOVA

t is used for comparing two or more independent samples of equal or different sample sizes.

the null hypothesis is that the medians of all groups are equal, and the alternative hypothesis is that at least one population median of one group is different from the population median of at least one other group.