Question

A random group of desktop computer sales was selected from an electronic discount chain to analyze the size of

monitor purchased with the computer.   The data is as follows:

Monitor type

15" CRT

15" flat panel

17" CRT

17" flat panel

19" CRT

Number of sales

18

23

11

9

4

At the .05 level of significance, is there evidence to reject the hypothesis that the number of monitors is

equally distributed between the five types?

Answer 1

here null hypothesis:Ho: number of monitors is equally distributed between the five types

alternate hypotheiss:Ha:  number of monitors is not equally distributed between the five types

degree of freedom =categories-1=5-1=4

for 4 degree of freedom and 0.05 level ; rejection region >=9.488

applying chi square goodness of fit test:

		observed	Expected		Chi square
category	Probability(p)	Oi	Ei=total*p		R2i=(Oi-Ei)2/Ei
15' CRT	0.200	18.000	13.000		1.923
15' flat panel	0.200	23.000	13.000		7.692
17' CRT	0.200	11.000	13.000		0.308
17' flat panel	0.200	9.000	13.000		1.231
19' CRT	0.200	4.000	13.000		6.231
total	1.000	65	65		17.385

as test statistic 17.385 is in rejection region; we reject null hypothesis

\we have sufficient evidence at 0.05 level to reject the hypothesis that the number of monitors is

equally distributed between the five types,.