Inference with and without outlier (t-test)
Not only can one point change the estimated regression line, but it can also change the inferential analysis.
The datasets with and without the outlier are provided as hypdata_outlier
and hypdata_no_outlier
respectively.
This exercise is part of the course
Inference for Linear Regression in R
Exercise instructions
- Run a linear regression of
response
vs.explanatory
onhypdata_outlier
, and extract the coefficient-level information. - Do the same for
hypdata_no_outlier
. - Look at the output. How do the coefficients and p-values differ?
Hands-on interactive exercise
Have a go at this exercise by completing this sample code.
# Model response vs. explanatory on hypdata_outlier and tidy it
___
# Do the same on hypdata_no_outlier
___