---
title: "Regression"
author: "Tera Letzring"
date: "October 2017"
output: html_document
---

```{r setup, include=FALSE}

knitr::opts_chunk$set(echo = TRUE)
library(QuantPsyc)
```

```{r read in data}

#set the working directory (wd) to the folder that contains the script file, and read in the data
x <- getwd()
setwd(x)

mydata = read.table("USairpollution.csv", header=T, sep=",")  
attach(mydata)
head(mydata)
```

```{r regression models}

#basic linear model with output
Model1 <- lm(SO2~manu, data=mydata)
summary(Model1)

#to exclude cases with missing data
Model2 <- lm(SO2~manu, data=mydata, na.action=na.exclude)
summary(Model2)

#to get standardized coefficients, use a function from the QuantPsyc package
lm.beta(Model1)

```

```{r confidence intervals}

#uses function in the QuantPsyc package
confint(Model1)
```

```{r check assumptions}

#plots to check for adherence to assumptions
plot(Model1)

#histogram to check for normality of the distribution of residuals with a normal curve (run all lines at the same time)
sresid <- studres(Model1)
hist(sresid, freq=FALSE,
   main="Distribution of Studentized Residuals")
xfit<-seq(min(sresid),max(sresid),length=40)
yfit<-dnorm(xfit)
lines(xfit, yfit) 
```