A study was conducted to investigate the effectiveness of a work site health pro

Question

A study was conducted to investigate the effectiveness of a work site health promotion program in reducing the prevalence of cigarette smoking. Thirty-two work sites were randomly assigned either to implement the health program or to make no changes for a period of two years. The promotion program consisted of health education classes combined with a payroll-based incentive system. The data collected during the study are saved in the data set program (Table B.15). For each work site, smoking prevalence at the start of the study is saved under the variable name baseline, and smoking prevalence at the end of the two year period under the name followup. The variable group contains the value 1 for work sites that implemented the health program and 2 for the sites that did not. a) For the work sites that implemented the health promotion program, test (Wilcoxon Signed-Rank Test) the null hypothesis that the median difference in smoking prevalence over the two year period is equal to 0. b) Test the same null hypothesis for the sites that did not make any changes. c) Evaluate the null hypothesis that the median difference in smoking prevalence over the two year period for work sites that implemented the program is equal to the median difference for sits that did not (Mann Whitney U test) d) Do you believe that the health promotion program was effective in reducing the prevalence of smoking? Explain.

Data set program; variable group, baseline, and followup

2 16.50 18.02

2 29.60 29.68

2 24.80 19.27

2 31.11 27.35

2 26.65 23.70

2 16.66 17.73

2 28.06 25.74

2 9.85 12.44

2 20.37 15.64

2 26.66 28.76

2 28.13 27.35

2 26.85 26.39

2 25.71 25.15

2 24.09 24.16

2 23.25 25.13

2 21.87 18.64

1 28.61 24.34

1 27.56 27.71

1 32.21 22.15

1 25.22 21.33

1 26.44 23.76

1 28.93 28.93

1 22.26 16.39

1 29.55 26.15

1 22.67 19.70

1 25.78 19.54

1 15.41 13.49

1 28.03 28.47

1 23.90 21.52

1 15.82 13.99

1 19.09 16.84

1 24.51 23.02

Explanation / Answer

Copy the data into .csv file and read it into R. Then execute the following commands.

> data1=read.csv(file.choose(),header=T)
>attach(data1)

a)> x=Baseline[Group==1]

> y=Followup[Group==1]

> wilcox.test(x,y,paired=T)

        Wilcoxon signed rank test with continuity correction

data: x and y

V = 117, p-value = 0.001332

alternative hypothesis: true location shift is not equal to 0

Since p-value is very small, we reject the null hypothesis and conclude that the median difference in smoking prevalence over the two year period for the work sites implementing the promotion program is significantly different from 0.

b)> x=Baseline[Group==2]

> y=Followup[Group==2]

> wilcox.test(x,y,paired=T)

        Wilcoxon signed rank test

data: x and y

V = 92, p-value = 0.2312

alternative hypothesis: true location shift is not equal to 0

Since p-value > 0.05, we accept the null hypothesis and conclude that the median difference in smoking prevalence over the two year period for the work sites not implementing the promotion program is not significantly different from 0.

c)> diff1=x-y #Group1

> diff2=x-y #Group2

> wilcox.test(diff1,diff2,paired=F)

        Wilcoxon rank sum test

data: diff1 and diff2

W = 180, p-value = 0.05134

alternative hypothesis: true location shift is not equal to 0

d) Since p-value > 0.05, we accept the null hypothesis and conclude that the median difference in smoking prevalence over the two year period for work sites that implemented the program is not significantly different from the median difference for sites that did not hence implying that the health program was not of much use.

Related Questions

Navigate

• Browse (All)
• Browse A
• Subjects

Integrity-first tutoring: explanations and feedback only — we do not complete graded work. Learn more.