
library(testthat)

source("user_code.R")
test_that("perform_t_test returns correct structure and types", {
  result <- perform_t_test(c(1, 2, 3), c(4, 5, 6))
  expect_true(is.list(result), info = "Result should be a list.")
  expect_true("p_value" %in% names(result), info = "List should contain 'p_value'.")
  expect_true("significant" %in% names(result), info = "List should contain 'significant'.")
  expect_true(is.numeric(result$p_value), info = "'p_value' should be numeric.")
  expect_true(is.logical(result$significant), info = "'significant' should be logical.")
})

test_that("perform_chi_squared_test returns correct structure and types", {
  result <- perform_chi_squared_test(c(10, 20, 30), c(12, 18, 30))
  expect_true(is.list(result), info = "Result should be a list.")
  expect_true("p_value" %in% names(result), info = "List should contain 'p_value'.")
  expect_true("significant" %in% names(result), info = "List should contain 'significant'.")
  expect_true(is.numeric(result$p_value), info = "'p_value' should be numeric.")
  expect_true(is.logical(result$significant), info = "'significant' should be logical.")
})

test_that("t-test detects significant difference when means differ", {
  group1 <- c(2, 2, 2, 2, 2)
  group2 <- c(10, 10, 10, 10, 10)
  result <- perform_t_test(group1, group2)
  expect_true(result$significant, info = "Should be significant when means are far apart.")
})

test_that("t-test detects non-significance when means are similar", {
  group1 <- c(5, 5, 5, 5, 5)
  group2 <- c(5.1, 5, 5, 5, 5)
  result <- perform_t_test(group1, group2)
  expect_false(result$significant, info = "Should not be significant when means are very close.")
})

test_that("chi-squared test detects significance for large frequency differences", {
  observed <- c(100, 10, 10)
  expected <- c(40, 40, 40)
  result <- perform_chi_squared_test(observed, expected)
  expect_true(result$significant, info = "Should be significant for large differences in frequencies.")
})

test_that("chi-squared test detects non-significance for similar frequencies", {
  observed <- c(10, 20, 30)
  expected <- c(10, 20, 30)
  result <- perform_chi_squared_test(observed, expected)
  expect_false(result$significant, info = "Should not be significant when observed and expected are equal.")
})

test_main.R

En praktisk introduktion til R-programmering tilpasset biologer og bioinformatikere. Lær at analysere, visualisere og fortolke biologiske data ved hjælp af R med virkelighedsnære eksempler fra genomik, økologi og eksperimentel biologi.

Lær det grundlæggende i R-programmering med fokus på biologiske data, herunder variabler, datatyper og grundlæggende datamanipulation.

Dyk ned i statistiske metoder til analyse af biologiske data, herunder beskrivende statistik, hypoteseprøvning og fortolkning af resultater.

Behersk kunsten at visualisere biologiske data ved hjælp af R, fra grundlæggende diagrammer til mere avancerede visualiseringer relevante for eksperimenter.

Lær at arbejde med genomiske data og udvikle reproducerbare arbejdsgange til videnskabelig forskning i R.

Challenge: Hypoteseafprøvning med Biologiske Data

Løsning