Compare and contrast the bootstrap and randomization test procedures we have discussed.

## Directions

There are 4 questions. The first two questions are discussion type questions. These require no data analysis, but do require insights into the material that has been covered. The final two questions are data analysis type questions which require you to build, analyze, and interpret data in order to communicate relevant findings.

You should only show results in this document that relevant to your discussions. Remember you can use eval=FALSE, and other R markdown arguments to present your code. Since I have the .rmd I can see all code that was not presented in the word document.

## Problem 1 (20 points)

Compare and contrast the bootstrap and randomization test procedures we have discussed.In this discussion you should describe the purpose of each method (why would you use them), the procedure they follow, and then how they differ. Finally give a few sentences on each that would explain to a novice what these methods do and why we should trust their results.

## Problem 2 (20 Points)

Compare and contrast the model selection procedures we’ve discussed in this course.Specifically focus your discussion on R-squared, ANOVA, AIC, BIC, K-Fold Cross Validation, and Random Splitting. You should further focus on when are these methods able to be used and when are they not. Finally discuss your preference for a technique and give reasons why.

## Problem 3 (30 Points)

In the `Credit` data in the `ISLR` package it contains 400 customers and information on their credit history. For full information of the data look at the `help` file. A company has approached us to build a model to better understand factors that influence the `Balance` variable, which is average credit card balance in USD. Using the information in your model:

* Discuss the influential variables

* Discuss why you chose the variables you choose to put in the model.

* Explain any concerns about use of certain variables in the model?

* Discuss how your model was created and any insights you can provide the customer based on the results.

*HINT: Adding Gender and/or Ethnicity could be controversial or illegal in some uses of this model, you should discuss your decision on these variables and how it effects the organizations ability to use your model for prediction or inference.*

“`{r}

library(ISLR)

head(Credit)

“`

## Problem 4 (30 Points)

Using the `Wool` data in the `alr4` package:

* Produce a scatterplot matrix of all variables in the dataset

* Fit the full main effects model using `Cycles` as the response and **all** other variables as predictors

* Interpret the Tukey HSD intervals and test with regard to load.

* Explain what changes you would make to the model to help it better predict `Cycles`

“`{r}

library(alr4)

head(Wool)

“`

Requirements:

Collepals.com Plagiarism Free Papers

Are you looking for custom essay writing service or even dissertation writing services? Just request for our write my paper service, and we'll match you with the best essay writer in your subject! With an exceptional team of professional academic experts in a wide range of subjects, we can guarantee you an unrivaled quality of custom-written papers.

Get ZERO PLAGIARISM, HUMAN WRITTEN ESSAYS

Why Hire Collepals.com writers to do your paper?

Quality- We are experienced and have access to ample research materials.

We write plagiarism Free Content

Confidential- We never share or sell your personal information to third parties.

Support-Chat with us today! We are always waiting to answer all your questions.