This is completed in R

The data comes from the [Centers for Disease Control](www.cdc.gov) - BRFSS_2021 data

.csv with data:

https://drive.google.com/file/d/1ClGAAudIiIPMY4UMIENKEtyLIRMB54cY/view?usp=drive_link

codebook:

https://drive.google.com/file/d/1P1Wy4LcEqdf6DBlqbiWnf39fcywme129/view?usp=drive_link

The only allowable packages are `tidyverse`, `caret`, `Hmisc`, `lsr`, `olsrr`, `psych`, `lm.beta`.

• Load libraries using thesuppressPackageStartupMessages() function
• e.g.suppressPackageStartupMessages(library(tidyverse))

For the final section, you will choose four variables to explore in ways we have not. With those variables, complete the following.

make it clear, though, the distinction between each question/problem with comments and spacing.)

• Q10: Address the values of each of the variables (use the codebook for this and include your answer as comments). For instance, is "none" equal to a value other than 0? Are there extra decimals implied? Are there other values that should be excluded based on the responses they represent? Update the dataset you will use for the remainder of the problems to account for these values. GENHLTH, CHECKUP1, and FRUIT2 variables can not be used.
• Q11: Remove any outliers for each applicable variable. Make sure you are updating the dataset from Q10 and using this dataset for the remainder of the problems. Briefly explain why you chose the method you used. Make sure to comment it out.
• Q12: Complete exploratory analyses (for each variable) doing appropriate visualizations with ggplot2.
• Q13: Run basic descriptive statistics. Be sure to address each variable.
• Q14: Finally, run at least 2 different, appropriate regressions predicting one of those variables. These regressions should use different predictor(s). Identify the best model.

answers must be clearly identifiable.