Lecture 14
Duke University
STA 199 - Summer 2023
2023-10-12
– Clone ae-13
– hw-4 due Friday
– Project Proposal
– Find a data set!
– The data sets should meet the following criteria:
– At least 300 observations (or approved by me)
– At least 6 unique columns that are useful and not simply identifiers (or approved by me)
– Data must be real
How is the line of best fit fit?
– What is correlation?
– What is the coefficient of determination?
– What is there relationship?
The amount of variability in our response y that is explained by x
– Statistic that measures how “spread out” data are from the center of the data
– Practice modeling in R
– Write out equations
– Define terms
– Interpret coefficient
– Categorical explanatory variable
“we expect, on average”
predicting the mean for all possible values at the given explanatory value
We assume that our prediction comes from a normal distribution