Lab 13

# Installing required packages
if (!require("dplyr"))
  install.packages("dplyr")

## Loading required package: dplyr

## 
## Attaching package: 'dplyr'

## The following objects are masked from 'package:stats':
## 
##     filter, lag

## The following objects are masked from 'package:base':
## 
##     intersect, setdiff, setequal, union

if (!require("tidyverse"))
  install.packages("tidyverse")

## Loading required package: tidyverse

## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ forcats   1.0.0     ✔ readr     2.1.5
## ✔ ggplot2   3.4.4     ✔ stringr   1.5.1
## ✔ lubridate 1.9.3     ✔ tibble    3.2.1
## ✔ purrr     1.0.2     ✔ tidyr     1.3.1
## ── 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(dplyr)
library(ggplot2)

mydata <- read.csv("https://raw.githubusercontent.com/drkblake/Data/main/Educ_Income_2022.csv")

# Specify the DV and IV
mydata$DV <- mydata$PctCollege #Edit YOURDVNAME
mydata$IV <- mydata$FamIncome #Edit YOURIVNAME
# Look at the DV and IV
ggplot(mydata, aes(x = DV)) + geom_histogram(color = "black", fill = "#1f78b4")

## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.

## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.
# Creating and summarizing an initial regression model called myreg, and checking for bivariate outliers.
options(scipen = 999)
myreg <- lm(DV ~ IV,
            data = mydata)
plot(mydata$IV, mydata$DV)
abline(lm(mydata$DV ~ mydata$IV))

# Creating and summarizing an initial regression model called myreg, and checking for bivariate outliers.
options(scipen = 999)
myreg <- lm(DV ~ IV,
            data = mydata)
plot(mydata$IV, mydata$DV)
abline(lm(mydata$DV ~ mydata$IV))

# Real or random?
summary(myreg)

## 
## Call:
## lm(formula = DV ~ IV, data = mydata)
## 
## Residuals:
##     Min      1Q  Median      3Q     Max 
## -9.0510 -3.1047 -0.3815  3.1929 15.9863 
## 
## Coefficients:
##                 Estimate   Std. Error t value             Pr(>|t|)    
## (Intercept) -17.59952875   2.52111063  -6.981       0.000000000428 ***
## IV            0.00052124   0.00003511  14.846 < 0.0000000000000002 ***
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Residual standard error: 4.672 on 93 degrees of freedom
## Multiple R-squared:  0.7032, Adjusted R-squared:  0.7001 
## F-statistic: 220.4 on 1 and 93 DF,  p-value: < 0.00000000000000022

# What if I see outliers?

# Check leverage values
leverage <- as.data.frame(hatvalues(myreg))
view(leverage)

# Delete an oulier by specifying its row number
mydata <- mydata[-c(931), ]