Karin

R Markdown

This is an R Markdown document. Markdown is a simple formatting syntax for authoring HTML, PDF, and MS Word documents. For more details on using R Markdown see http://rmarkdown.rstudio.com.

When you click the Knit button a document will be generated that includes both content as well as the output of any embedded R code chunks within the document. You can embed an R code chunk like this:

Including Plots

You can also embed plots, for example:

# Nalaganje potrebnih paketov
library(dplyr)

## Warning: package 'dplyr' was built under R version 4.2.3

## 
## Attaching package: 'dplyr'

## The following objects are masked from 'package:stats':
## 
##     filter, lag

## The following objects are masked from 'package:base':
## 
##     intersect, setdiff, setequal, union

library(tidyr)

## Warning: package 'tidyr' was built under R version 4.2.3

library(broom)
library(purrr)

## Warning: package 'purrr' was built under R version 4.2.3

# Preberite podatke
podatki <- read.table("C:/Users/Benjamin/Downloads/podatki.csv", header=TRUE, sep=";", dec=",")
colnames(podatki) <- c("vzorec", "vrednost")

# Izpis prvih nekaj vrstic in strukture podatkov
print(head(podatki))

##   vzorec  vrednost
## 1    CON 0.5834238
## 2    CON 0.3476931
## 3    CON 0.5821974
## 4    CON 0.3792870
## 5    CON 0.4416285
## 6    CON 0.2896861

print(str(podatki))

## 'data.frame':    180 obs. of  2 variables:
##  $ vzorec  : chr  "CON" "CON" "CON" "CON" ...
##  $ vrednost: num  0.583 0.348 0.582 0.379 0.442 ...
## NULL

shapiro_results_podatki <- podatki %>%
  group_by(vzorec) %>%
  summarise(
    shapiro_test = list(shapiro.test(vrednost)),
    .groups = 'drop'
  ) %>%
  mutate(
    shapiro_test_tidy = map(shapiro_test, tidy),
    p.value = map_dbl(shapiro_test_tidy, "p.value")
  )

wilcox_result_podatki <- wilcox.test(vrednost ~ vzorec, data = podatki, paired = FALSE)
print(wilcox_result_podatki)

## 
##  Wilcoxon rank sum test with continuity correction
## 
## data:  vrednost by vzorec
## W = 1187, p-value = 4.538e-05
## alternative hypothesis: true location shift is not equal to 0

# Izračun velikosti učinka za podatki
# Izračunamo velikost učinka ročno
# Velikost učinka za Wilcoxonov test je približno enaka U-statistiki / (n1 * n2)
# Kjer sta n1 in n2 velikosti skupin
n1_podatki <- sum(podatki$vzorec == unique(podatki$vzorec)[1])
n2_podatki <- sum(podatki$vzorec == unique(podatki$vzorec)[2])
U_podatki <- wilcox_result_podatki$statistic
effect_size_podatki <- U_podatki / (n1_podatki * n2_podatki)

print(effect_size_podatki)

##         W 
## 0.2637778

# Preberite dodatne podatke
podatki2 <- read.table("C:/Users/Benjamin/Downloads/podatki2.csv", header=TRUE, sep=";", dec=",")

# Preverjanje Shapiro-Wilk testa
shapiro_results <- podatki2 %>%
  group_by(vzorec) %>%
  summarise(
    shapiro_test = list(shapiro.test(vrednost)),
    .groups = 'drop'
  ) %>%
  mutate(
    shapiro_test_tidy = map(shapiro_test, tidy),
    p.value = map_dbl(shapiro_test_tidy, "p.value")
  )

print(shapiro_results)

## # A tibble: 2 × 4
##   vzorec shapiro_test shapiro_test_tidy p.value
##   <chr>  <list>       <list>              <dbl>
## 1 LUM A  <htest>      <tibble [1 × 3]>    0.452
## 2 TNRD   <htest>      <tibble [1 × 3]>    0.677

# Izvedba Wilcoxon testa
wilcox_result <- wilcox.test(vrednost ~ vzorec, data = podatki2, paired = FALSE)

## Warning in wilcox.test.default(x = DATA[[1L]], y = DATA[[2L]], ...): cannot
## compute exact p-value with ties

print(wilcox_result)

## 
##  Wilcoxon rank sum test with continuity correction
## 
## data:  vrednost by vzorec
## W = 183, p-value = 0.3784
## alternative hypothesis: true location shift is not equal to 0

# Izračun velikosti učinka
# Izračunamo velikost učinka ročno
# Velikost učinka za Wilcoxonov test je približno enaka U-statistiki / (n1 * n2)
# Kjer sta n1 in n2 velikosti skupin
n1 <- sum(podatki2$vzorec == unique(podatki2$vzorec)[1])
n2 <- sum(podatki2$vzorec == unique(podatki2$vzorec)[2])
U <- wilcox_result$statistic
effect_size <- U / (n1 * n2)

print(effect_size)

##         W 
## 0.5980392

Note that the echo = FALSE parameter was added to the code chunk to prevent printing of the R code that generated the plot.