knitr::opts_chunk$set(fig.width = 8, fig.height = 3)
Note: The type
argument in generate()
is automatically filled based on the entries for specify()
and
hypothesize()
. It can be removed throughout the examples that follow. It is left in to reiterate the type of generation process being performed.
library(nycflights13) library(dplyr) library(stringr) library(infer) set.seed(2017) fli_small <- flights %>% sample_n(size = 500) %>% mutate(half_year = case_when( between(month, 1, 6) ~ "h1", between(month, 7, 12) ~ "h2" )) %>% mutate(day_hour = case_when( between(hour, 1, 12) ~ "morning", between(hour, 13, 24) ~ "not morning" )) %>% select(arr_delay, dep_delay, half_year, day_hour, origin, carrier)
arr_delay
, dep_delay
half_year
("h1"
, "h2"
), day_hour
("morning"
, "not morning"
)origin
("EWR"
, "JFK"
, "LGA"
)carrier
The recommended approach is to use specify() %>% calculate()
:
obs_t <- fli_small %>% specify(arr_delay ~ half_year) %>% calculate(stat = "t", order = c("h1", "h2"))
The observed $t$ statistic is r obs_t
.
Or using t_test
in infer
obs_t <- fli_small %>% t_test(formula = arr_delay ~ half_year, alternative = "two_sided", order = c("h1", "h2")) %>% dplyr::pull(statistic)
The observed $t$ statistic is r obs_t
.
Or using another shortcut function in infer
:
obs_t <- fli_small %>% t_stat(formula = arr_delay ~ half_year, order = c("h1", "h2"))
The observed $t$ statistic is r obs_t
.
t_null_perm <- fli_small %>% # alt: response = arr_delay, explanatory = half_year specify(arr_delay ~ half_year) %>% hypothesize(null = "independence") %>% generate(reps = 1000, type = "permute") %>% calculate(stat = "t", order = c("h1", "h2")) visualize(t_null_perm) + shade_p_value(obs_stat = obs_t, direction = "two_sided")
t_null_perm %>% get_p_value(obs_stat = obs_t, direction = "two_sided")
t_null_theor <- fli_small %>% # alt: response = arr_delay, explanatory = half_year specify(arr_delay ~ half_year) %>% hypothesize(null = "independence") %>% # generate() ## Not used for theoretical calculate(stat = "t", order = c("h1", "h2")) visualize(t_null_theor, method = "theoretical") + shade_p_value(obs_stat = obs_t, direction = "two_sided")
visualize(t_null_perm, method = "both") + shade_p_value(obs_stat = obs_t, direction = "two_sided")
fli_small %>% t_test(formula = arr_delay ~ half_year, alternative = "two_sided", order = c("h1", "h2")) %>% dplyr::pull(p_value)
Add the following code to your website.
For more information on customizing the embed code, read Embedding Snippets.