Modeling Categorical Data

{{Student Name}}

2023-07-17

Instructions

Using R Studio

I am giving you some examples of rendered Tables and Figures section.

Your goal is to:

• Make a rmd file that knits to an HTML answer with the same style (make it as similar as possible).
• Use dataset from this link: https://www.kaggle.com/datasets/thedevastator/higher-education-predictors-of-student-retention?select=dataset.csv.
• Explore data.
• Define your main 5 variables in the VarN style as example shown in the Tables and Figures section.
• Answer the questions in the Analysis section by selecting the correct [] and filling out the ______ from your own data
• Repeat the modeling process 2 more times. Evaluate the 3 models in the last section of the Analysis section. You can use as many new variables as your dataset has for the new models.
• Hard coding the Analysis section is allowed.
• Match the presented tables and/or figures in the Tables and Figures
• Do not hard code the Tables and Figures section.

Please match the Analysis and Tables and Figures sections as close as you can.

Please submit both the rmd and your knitted HTML to the link on Canvas.

You can use any dataset, extra points for novelty.

Select the variables you will use and replace the Var1, Var2, etc. placeholders below. Your variables can be continuous or discrete, a mix is recommended.

Remove the Instructions section from your final Knit.

Analysis (Fact)

1. Var1 [is]/[is not] a significant predictor of Var2 ( = ______, p = ______).
2. Males show an [increase]/[decrease] in the Odds of the subject's symptoms by ______ %.
3. When looking at Var1, Var2, Var3, Var4 and the interaction of Var3 and Var4 at the same time, the below terms are significant (delete terms that are not significant).
   • Var1 ( = ______, p = ______)
   • Var2 ( = ______, p = ______)
   • Var3 ( = ______, p = ______)
   • Var3:Var4 ( = ______, p = ______)
4. Evaluate other 2 models (different formula/specification). Evaluate the 3 models comparatively.

Tables and Figures as Examples:

In this example: Var1 = Sex Var2 = Improved Var3 = Height Var4 = Weight