Raeann Cruz PAD 6833 Homework 4

library(tidyverse)

## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ dplyr     1.2.1     ✔ readr     2.2.0
## ✔ forcats   1.0.1     ✔ stringr   1.6.0
## ✔ ggplot2   4.0.3     ✔ tibble    3.3.1
## ✔ lubridate 1.9.5     ✔ tidyr     1.3.2
## ✔ purrr     1.2.2     
## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag()    masks stats::lag()
## ℹ Use the conflicted package (<http://conflicted.r-lib.org/>) to force all conflicts to become errors

library(readxl)
library(pastecs)

## 
## Attaching package: 'pastecs'
## 
## The following objects are masked from 'package:dplyr':
## 
##     first, last
## 
## The following object is masked from 'package:tidyr':
## 
##     extract

load("NSDUH_2023.Rdata")

pastecs::stat.desc(data$`BNGDRMDAYS`)

##                         x
## nbr.val      5.670500e+04
## nbr.null     0.000000e+00
## nbr.na       0.000000e+00
## min          1.000000e+00
## max          5.000000e+00
## range        4.000000e+00
## sum          2.428770e+05
## median       5.000000e+00
## mean         4.283167e+00
## SE.mean      5.994653e-03
## CI.mean.0.95 1.174955e-02
## var          2.037743e+00
## std.dev      1.427495e+00
## coef.var     3.332803e-01

BNGDRMDAYS measures the frequency of binge alcohol use during the past 30 days.

data<- data %>% drop_na(`BNGDRMDAYS`)

data<- data %>% filter(BNGDRMDAYS>0)
head(data$BNGDRMDAYS)

## [1] 3 2 5 5 5 5

hist(data$BNGDRMDAYS)

data<-data%>%mutate(LOG_CFS=log(BNGDRMDAYS))%>%
select(BNGDRMDAYS,LOG_CFS)

head(data)

## # A tibble: 6 × 2
##   BNGDRMDAYS LOG_CFS
##        <dbl>   <dbl>
## 1          3   1.10 
## 2          2   0.693
## 3          5   1.61 
## 4          5   1.61 
## 5          5   1.61 
## 6          5   1.61

hist(data$LOG_CFS)