Question

Wilfley and colleagues (2008) tested whether the antiobesity drug sibutramine would be an effective treatment for people with binge eating disorder. They measured the frequency of binge eating every 2 weeks for 24 weeks during treatment. The following table lists a portion of the data similar to results reported by the authors for the frequency of binge eating over the first 8 weeks of the drug treatment.

Frequency of Binge Eating
Baseline	Week 2	Week 4	Week 6	Week 8
4	1	0	0	1
6	4	2	0	0
3	0	1	1	0
1	1	0	1	1
2	2	1	1	1
5	1	2	2	2

(a) Complete the F-table. (Round your answers to two decimal places.)

Source of Variation	SS	df	MS	Fobt
Between groups
Between persons
Within groups (error)
Total

Make a decision to retain or reject the null hypothesis. (Assume experimentwise alpha equal to 0.05.)

Retain the null hypothesis.Reject the null hypothesis.    

(b) Use the Bonferroni procedure to make the post hoc test. In which week do we first see significant differences compared to baseline?

Week 2 is the first week where significant differences from baseline are evident.Week 4 is the first week where significant differences from baseline are evident.    Week 6 is the first week where significant differences from baseline are evident.Week 8 is the first week where significant differences from baseline are evident.None of the weeks are significantly different from the baseline.

Answer 1

a)

ANOVA
Source of Variation	SS	df	MS	F	P-value	F crit
Between groups	5.708333	5	1.141667	1.272446	0.32621	2.901295
Between Persons	1.791667	3	0.597222	0.665635	0.586033	3.287382
Error	13.45833	15	0.897222
Total	20.95833	23

at alph = 0.05 we failed to reject H_0 of between group and between persons means effects

pvalu not less than 0.05

b) based on part a) there is no significant effect of groups or persons

Bonferroni Procedure (Bonferonni Correction)
This multiple-comparison post-hoc correction is used when you are performing many independent or dependent statistical tests at the same time. The problem with running many simultaneous tests is that the probability of a significant result increases with each test run. This post-hoc test sets the significance cut off at ?/n. For example, if you are running 20 simultaneous tests at ?=0.05, the correction would be 0.0025. More detail. The Bonferroni does suffer from a loss of power. This is due to several reasons, including the fact that Type II error rates are high for each test. In other words, it overcorrects for Type I errors.(source;http://www.statisticshowto.com/post-hoc/)

Note: I used Excel to analyse two way anova without replication.