Lukyanova_HiSqr.R

# Классические методы статистики: критерий хи-квадрат

q=qchisq(p = 0.95, df = 1)
q

## [1] 3.841459

########### Задача о вкусовых предпочтениях соков ###############

observed_juice <- c(32, 28, 16, 14, 10)
res <- chisq.test(observed_juice, p = c(1/5, 1/5, 1/5, 1/5, 1/5))
res

## 
##  Chi-squared test for given probabilities
## 
## data:  observed_juice
## X-squared = 18, df = 4, p-value = 0.001234

q=qchisq(p = 0.95, df = 4)
q

## [1] 9.487729

############## Мыши  #####################

mice = matrix( c(13, 44, 25, 29), 2,2)
mice

##      [,1] [,2]
## [1,]   13   25
## [2,]   44   29

chisq.test(mice)

## 
##  Pearson's Chi-squared test with Yates' continuity correction
## 
## data:  mice
## X-squared = 5.7923, df = 1, p-value = 0.0161

chisq.test(mice, correct=FALSE)

## 
##  Pearson's Chi-squared test
## 
## data:  mice
## X-squared = 6.7955, df = 1, p-value = 0.009139

############### Три популяции наземных моллюсков  ################
light <- c(12, 40, 45)
dark <- c(87, 34, 75)
very.dark <- c(3, 8, 2)
color.data <- matrix(c(light, dark, very.dark), nrow = 3,dimnames = list(c("Pop1", "Pop2", "Pop3"), c("Light", "Dark", "Very dark")))
color.data

##      Light Dark Very dark
## Pop1    12   87         3
## Pop2    40   34         8
## Pop3    45   75         2

chisq.test(color.data)

## Warning in chisq.test(color.data): Chi-squared approximation may be incorrect

## 
##  Pearson's Chi-squared test
## 
## data:  color.data
## X-squared = 43.434, df = 4, p-value = 8.411e-09