Your main goal is to model the relationship between various variables in the dataset and price of paintings. For this application exercise you are asked to stick to models with one explanatory variable.

- Model fitting:
- Try at least 5 different models, that is at least 5 different explanatory variables.
- Make sure some are categorical and some are numerical.
**Extra credit:**For the adventorous… Re-level at least one of your variables, e.g. combine a few levels into one, or turn a numerical variable into a categorical variable. When doing this, do not overwrite the original variable, but instead create a new variable.*Hint:*`plyr`

package:`revalue()`

or`mapvalues()`

or`car`

package:`recode()`

might be useful, but there are other ways of accomplishing this too.

- Interpretations:
- Interpret the slope and the intercept of each model.
- Interpret the \(R^2\) of each model.

- Synthesis: At the end write one synthesis paragraph comparing your models and determine which model does the best job in explaining the variability in prices of paintings. Your interpretations should be in context of the data, which means you need to understand the context of your data. Thankfully your data expert will be available to answer questions on Piazza! (But don’t leave them till the last minute.)

Codebook: https://stat.duke.edu/courses/Fall15/sta112.01/data/paris_paintings.html

Go to the Resources on Sakai and download

`paris_paintings.csv`

Upload this file to RStudio Server

Load using the following (make sure data file is in the correct working directory):

```
pp <- read.csv("paris_paintings.csv", stringsAsFactors = FALSE) %>%
tbl_df()
```

Your submission should be an R Markdown file in your team App Ex repo, in a folder called `AppEx_03`

.

Tuesday, Sep 22, beg of class

merge conflics on GitHub – you’re working in the same repo now!

Issues will arise, and that’s fine! Commit and push often, and ask questions when stuck.