setwd("C:/Users/ANGE/Documents")data_sex = matrix(c(12, 9, 17, 2), 2, 2,
dimnames = list(c("Female", "Male"),
c("GenXpert_Oui","GenXpert_Non")))
data_sex## GenXpert_Oui GenXpert_Non
## Female 12 17
## Male 9 2
chisq.test(data_sex)##
## Pearson's Chi-squared test with Yates' continuity correction
##
## data: data_sex
## X-squared = 3.7338, df = 1, p-value = 0.05332
fisher.test(data_sex)##
## Fisher's Exact Test for Count Data
##
## data: data_sex
## p-value = 0.03406
## alternative hypothesis: true odds ratio is not equal to 1
## 95 percent confidence interval:
## 0.01472235 0.99752173
## sample estimates:
## odds ratio
## 0.1642988
data_race = matrix(c(6, 1, 19, 1, 2 ,11), 3, 2,
dimnames = list(c("Azawak", "Borgou", "White Fulani"),
c("GenXpert_Oui","GenXpert_Non")))
data_race## GenXpert_Oui GenXpert_Non
## Azawak 6 1
## Borgou 1 2
## White Fulani 19 11
fisher.test(data_race)##
## Fisher's Exact Test for Count Data
##
## data: data_race
## p-value = 0.2658
## alternative hypothesis: two.sided
data_age = matrix(c(3, 6, 8, 9, 1 , 6, 3, 4), 4, 2,
dimnames = list(c("Three years old", "Four years old", "Five years old", "Six years old"),
c("GenXpert_Oui","GenXpert_Non")))
data_age## GenXpert_Oui GenXpert_Non
## Three years old 3 1
## Four years old 6 6
## Five years old 8 3
## Six years old 9 4
fisher.test(data_age)##
## Fisher's Exact Test for Count Data
##
## data: data_age
## p-value = 0.6812
## alternative hypothesis: two.sided
p value > = 0.05, association could not be established
In case of significant association, odds ratio are diplayed as well as confidence interval
Good luck bro...