• Clone your assignment repo in RStudio Cloud (ae-08-first-models-pp-TEAMNAME)
• In your R Markdown file, load the data the way we have been doing it in the course slides, paying attention to which character strings will be labelled as NAs upon reading the data.
• See here for the full data dictionary.

1. Fit the following models, and for each interpret the slope and the intercept.

• Model 1: Predict price of paintings from a numerical variable.
• Model 2: Predict log price of paintings from the same numerical variable.
• Model 3: Predict log price of paintings from the a categorical variable.
• Model 4: Predict log price of paintings from two variables: the numerical and the categorical variables you used above categorical variable.

Note: Model 4 requires the use of multiple regression. Suppose your data frame is called df, your response variable is y, and your explanatory variables are x1 and x2. You can fit this model with

lm(y ~ x1+ x2, data = df)

and use functions like tidy(), glance(), augment() on the model object. For interpretations of coefficients, refer to your reading from Chapter 8 of OpenIntro Statistics.

2. Report and interpret the \(R^2\) values of the models you built above.

3. Using Model 4, calculate the price of a new painting. You’ll need to come up with new hypothetical values for the attributes of this new painting for the explanatory variables you used in your model. Make sure you’re not extrapolating, and show how you checked this in your answer.

4. Describe why transformations of variables might complicate model interpretations more so than predictions made on a model.