Comparing t-distribution with normal distribution

This short set of notes will show some differences in the t-distribution with varying degrees of freedom with a normal distribution. This

df <- c(2, 10, 15, 20, 30, 50, 100, 1000)

t_dist <- do.call('rbind', lapply(seq_along(df), function(xx) data.frame(value = seq(-5, 5, .01), density = dt(seq(-5, 5, .01), df = df[xx]), df = df[xx], normal = FALSE)))

z_dist <- data.frame(value = seq(-5, 5, .01), density = dnorm(seq(-5, 5, .01)), normal = TRUE, df = 0)

dist <- rbind(t_dist, z_dist)

head(dist)

##   value     density df normal
## 1 -5.00 0.007127781  2  FALSE
## 2 -4.99 0.007167524  2  FALSE
## 3 -4.98 0.007207557  2  FALSE
## 4 -4.97 0.007247883  2  FALSE
## 5 -4.96 0.007288503  2  FALSE
## 6 -4.95 0.007329422  2  FALSE

library(tidyverse)

## ── Attaching packages ─────────────────────────────────────── tidyverse 1.3.2 ──
## ✔ ggplot2 3.3.6      ✔ purrr   0.3.4 
## ✔ tibble  3.1.8      ✔ dplyr   1.0.10
## ✔ tidyr   1.2.1      ✔ stringr 1.4.1 
## ✔ readr   2.1.2      ✔ forcats 0.5.2 
## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag()    masks stats::lag()

library(ggformula)

## Loading required package: ggstance
## 
## Attaching package: 'ggstance'
## 
## The following objects are masked from 'package:ggplot2':
## 
##     geom_errorbarh, GeomErrorbarh
## 
## Loading required package: scales
## 
## Attaching package: 'scales'
## 
## The following object is masked from 'package:purrr':
## 
##     discard
## 
## The following object is masked from 'package:readr':
## 
##     col_factor
## 
## Loading required package: ggridges
## 
## New to ggformula?  Try the tutorials: 
## 	learnr::run_tutorial("introduction", package = "ggformula")
## 	learnr::run_tutorial("refining", package = "ggformula")

library(patchwork)

theme_set(theme_bw(base_size = 18))

dist %>%
filter(df %in% c(0, 2)) %>%
gf_point(density ~ value, color = ~ normal, size = 1) %>%
  gf_refine(theme(legend.position = 'none')) /
dist %>%
filter(df %in% c(0, 10)) %>%
gf_point(density ~ value, color = ~ normal, size = 1) %>%
  gf_refine(theme(legend.position = 'none')) / 
  dist %>%
filter(df %in% c(0, 100)) %>%
gf_point(density ~ value, color = ~ normal, size = 1) %>%
  gf_refine(theme(legend.position = 'none'))