Generating & calculating
The infer pipeline for hypothesis testing requires four steps to calculate the null distribution: specify, hypothesize, generate, and calculate.
Let's continue the pipeline you began in the previous coding exercise. We'll get a set of differences in proportions that are distributed as though the null hypothesis, that the proportion of late shipments is the same across freight cost groups, is true.
late_shipments
is available; dplyr
, infer
, and ggplot2
are loaded.
This exercise is part of the course
Hypothesis Testing in R
Hands-on interactive exercise
Have a go at this exercise by completing this sample code.
# Extend the pipeline to generate 2000 permutations
generated <- late_shipments %>%
specify(
late ~ freight_cost_group,
success = "Yes"
) %>%
hypothesize(null = "independence") %>%
___
# See the result
generated