Question

For the question below, state what your null and alternative hypotheses are and select the appropriate test. Assess assumptions and do whatever needs to be done depending on your results (ie, doing a transformation of data or selecting a non-parametric if data violate assumptions). If you decide to run a Kruskal-Wallis test, you can assume the data satisfy those assumptions. Recall that it is generally considered ok to violate one assumption, especially if sample size is not too small. Perform the test and report the p value with the biological interpretation of your data. Finally, make a plot of the data that DOES NOT have a title, but does have proper x and y axis labels (can do it in excel or SPSS).

2)

You find 24 people diagnosed with depression. You randomly assign them to three groups: control, 20 minutes per day of jogging, 60 minutes per day jogging. After a pre-determined time period, you ask them to rank their depression level from 1 to 10, with 1 being very depressed and 10 being not depressed. You collect the following data:

Control	Jog 20	Jog 60
2.3	2.2	5.9
2.6	2.7	6.6
5.1	3.9	3.8
4.9	2.9	4.9
5.8	4.6	5.6
3.7	4.8	6
2.9	4.9	5.6
4.4	6.5	6.2

Answer 1

For the question below, state what your null and alternative hypotheses are and select the appropriate test. Assess assumptions and do whatever needs to be done depending on your results (ie, doing a transformation of data or selecting a non-parametric if data violate assumptions). If you decide to run a Kruskal-Wallis test, you can assume the data satisfy those assumptions. Recall that it is generally considered ok to violate one assumption, especially if sample size is not too small. Perform the test and report the p value with the biological interpretation of your data. Finally, make a plot of the data that DOES NOT have a title, but does have proper x and y axis labels (can do it in excel or SPSS).

2)

You find 24 people diagnosed with depression. You randomly assign them to three groups: control, 20 minutes per day of jogging, 60 minutes per day jogging. After a pre-determined time period, you ask them to rank their depression level from 1 to 10, with 1 being very depressed and 10 being not depressed. You collect the following data:

Since data are in Ranks ( ordinal level of measurement), Kruskal-Wallis test is used to compare the three groups.

Null hypothesis: The three groups are from identical populations.

Alternative hypothesis: At least one of the groups comes from a different population than the others.

Spss output

Kruskal-Wallis Test

Ranks
	Group	N	Mean Rank
Depression level	Control	8	9.56
	Jog 20	8	9.94
	Jog 60	8	18.00
	Total	24

Test Statisticsa,b
	Depression level
Kruskal-Wallis H	7.290
df	2
Asymp. Sig.	.026
a. Kruskal Wallis Test
b. Grouping Variable: Group

Calculated Kruskal-Wallis test value =7.29, P=0.026 which is < 0.05 level of significance. Ho is rejected. We conclude that depression level of the three groups are different.