517,866 views
24 votes
24 votes
Use the Wilcoxon matched-pairs signed rank test to determine whether there is a significant difference between the related populations represented by the data below. Assume a 5% level of significance and (differences = before - after).

Before After
5.6 6.4
1.3 1.5
4.7 4.6
3.8 4.3
2.4 2.1
5.5 6.0
5.1 5.2
4.6 4.5
3.7 4.5

a. What is the value of T= 36.5 is wrong
b. What is the value of T= 8.5 is wrong
c. What is the test statistic, T= 5 is wrong

User Rob L
by
2.8k points

1 Answer

23 votes
23 votes

Answer:

We fail to reject the null and conclude thattherw is no difference in population means.

Explanation:

Before After

5.6 6.4

1.3 1.5

4.7 4.6

3.8 4.3

2.4 2.1

5.5 6.0

5.1 5.2

4.6 4.5

3.7 4.5

H0 : There is no difference in population

H1 : There population are not all equal

Difference, d = (Before - After)

d = -0.8, -0.2, 0.1, -0.5, 0.3, -0.5, -0.1, 0.1, -0.8

The test statistic :

T = dbar / (Sd/√n)

dbar = Σx / n = - 2.4 / 9 = 0.2666

Standard deviation of difference Sd; [√Σ(d - dbar)² / n-1]

Sd = 0.403 (using calculator)

Hence,

T = dbar / (Sd/√n)

-0.266 / (0.403/√9)

-0.266 / 0.1343333

= - 1.980

The Pvalue ;

df = n - 1 ; 9 - 1 = 8

Pvalue(-1.980, 8) = 0.083

α = 0.05

Since Pvalue > α; We fail to reject the null and conclude thattherw is no difference in population means.

User Ewout Kleinsmann
by
2.7k points