Question

Use R Studio to answer the following

1. Four medical clinics (A, B, C, D) conducted a clinical trial for a cancer drug.  Their patient pools were sampled to examine their age distributions. The results are summarized below. Test the hypothesis that clinic and patient age are independent. Use a = 0.05.

(HINT: first make a data frame with four columns and three rows. See the example in the notes with the three shifts and four grades of lumber.)

	Medical Clinic
Patient Age	A	B	C	D
0-18	35	28	37	42
19-30	20	22	34	26
>30	12	8	10	6

Answer 1

R Code

Creation of data matrix
data=matrix(c(35,28,37,42,20,22,34,26,12,8,10,6), nrow = 3, ncol = 4,byrow=TRUE,dimnames = list(c("0-18","19-30",">30"), c("A","B","C","D")))
# Chi square test
chisq <- chisq.test(data)
# p value
chisq$p.value

Now p value is 0.5095548 which is greater than 0.05 (level of significance)
So we do not reject H0 and conclude that clinic and patient age are independent.