In charlotte-ngs/asmss2022: Applied Statistical Methods in Animal Science - Spring Semester 2022

Use a sample of the dataset pedigreemm::milk to do model selection

n_nr_rec_p3 <- 20
set.seed(7212)
vec_sample_idx <- sample(nrow(pedigreemm::milk), n_nr_rec_p3)
vec_sample_idx

Get the records

tbl_milk_p03 <- tibble::as_tibble(pedigreemm::milk[vec_sample_idx,])
tbl_milk_p03

Select only the columns lact and dim and the response fat.

library(dplyr)
tbl_milk_p03 <- tbl_milk_p03 %>% select(id, lact, dim, fat)
tbl_milk_p03

Add a random column and call it hei

n_mean_hei <- 149
n_sd_hei <- 2.12
vec_hei <- rnorm(n_nr_rec_p3, mean = n_mean_hei, sd = n_sd_hei)
tbl_milk_p03$hei <- as.integer(vec_hei)
tbl_milk_p03

Model selection

lm_milk_full <- lm(fat ~ lact + dim + hei, data = tbl_milk_p03)
summary(lm_milk_full)

olsrr::ols_step_best_subset(lm_milk_full)

summary(aov(fat ~ lact + dim + hei, data = tbl_milk_p03))

Save Data to File

s_exam_data_p03 <- file.path(here::here(), "docs", "data", "asm_exam_p03.csv")
if (!file.exists(s_exam_data_p03))
  readr::write_csv(tbl_milk_p03, s_exam_data_p03)

charlotte-ngs/asmss2022 documentation built on June 7, 2022, 1:33 p.m.