Search⌘ K
Home
Courses
Data-Centric Statistical Inference Using R and Tidyverse

Comparing with the Original Workflow

Explore how to create bootstrap distributions and construct confidence intervals using the infer package in R. Learn to apply functions like generate, calculate, and visualize to replicate and improve original workflows. Understand how to summarize bootstrap resamples and compare methods for confidence interval construction.

We'll cover the following...

Note that the steps of the infer workflow so far produce the same results as the original workflow using the rep_sample_n() function we saw earlier.

In other words, the following two code snippets produce similar results:

R
# infer workflow:
pennies_sample %>% specify(response = year) %>% 
generate(reps = 1000 , type = "bootstrap")
# Original workflow:
pennies_sample %>%
rep_sample_n(size = 50, replace = TRUE,reps = 1000)

The pipeline used for exploring the calculate() function as shown in the below figure:

Using the calculate() function for summary statistics
Using the calculate() function for summary statistics

After we generate() many replicates of bootstrap resampling with replacement, we next want to summarize each of the 1,000 resamples of size 50 to a single sample statistic value. As seen in the diagram, the calculate() function does this. ...