Skip to content
Permalink
main
Switch branches/tags

Name already in use

A tag already exists with the provided branch name. Many Git commands accept both tag and branch names, so creating this branch may cause unexpected behavior. Are you sure you want to create this branch?
Go to file
 
 
Cannot retrieve contributors at this time
---
title: "Lab 1 Part 2"
---
Exercise 1: Fitting a distribution beyond histograms
```{r}
EPI_data <- read.csv('2010EPI_data.csv')
colnames(EPI_data) <- EPI_data[1,]
EPI_data <- EPI_data[-c(1),]
attach(EPI_data)
fix(EPI_data)
EPI_data$EPI <- as.numeric(EPI_data$EPI)
```
```{r}
#cumulative density function
plot(ecdf(EPI_data$EPI), do.points=FALSE, verticals=TRUE)
```
```{r}
#creating a Q-Q plot
par(pty='s')
qqnorm(EPI_data$EPI)
qqline(EPI_data$EPI)
```
```{r}
#Q-Q plot against generated distribution (rotating through different x's)
x <- seq(30,95,1)
#x <-seq(30,95,2)
#x <-seq(30,96,2)
qqplot(qt(ppoints(250), df = 5), x, xlab = "Q-Q plot for t dsn")
qqline(x)
```
Repeating Exercise 1 with 'DALY' values
```{r}
EPI_data$DALY <- as.numeric(EPI_data$DALY)
plot(ecdf(EPI_data$DALY),do.points=FALSE,verticals = TRUE)
plot(ecdf(EPI_data$DALY),do.points=TRUE,verticals = TRUE)
par(pty='m')
qqnorm(EPI_data$DALY)
qqline(EPI_data$DALY)
#x <- seq(30,95,1)
x <-seq(30,95,2)
#x <-seq(30,96,2)
qqplot(qt(ppoints(250),df=5),x, xlab = "Q-Q plot")
qqline(x)
```
Repeating Exercise 1 with 'AIR_E' values
```{r}
EPI_data$AIR_E <- as.numeric(EPI_data$AIR_E)
plot(ecdf(EPI_data$AIR_E),do.points=FALSE,verticals = TRUE)
plot(ecdf(EPI_data$AIR_E),do.points=TRUE,verticals = TRUE)
par(pty='s')
qqnorm(EPI_data$AIR_E)
qqline(EPI_data$AIR_E)
#x <- seq(30,95,1)
#x <-seq(30,95,2)
x <-seq(30,96,2)
qqplot(qt(ppoints(250),df=5),x, xlab = "Q-Q plot")
qqline(x)
```
Comparing Distributions
```{r}
boxplot(EPI_data$EPI, EPI_data$DALY)
boxplot(EPI_data$EPI, EPI_data$AIR_E)
boxplot(EPI_data$AIR_E, EPI_data$DALY)
```
Inter-Comparing the Data
```{r}
#setting all to numeric
EPI_data$ENVHEALTH <- as.numeric(EPI_data$ENVHEALTH)
EPI_data$ECOSYSTEM <- as.numeric(EPI_data$ECOSYSTEM)
EPI_data$AIR_H <- as.numeric(EPI_data$AIR_H)
EPI_data$WATER_H <- as.numeric(EPI_data$WATER_H)
EPI_data$WATER_E <- as.numeric(EPI_data$WATER_E)
EPI_data$BIODIVERSITY <- as.numeric(EPI_data$BIODIVERSITY)
```
```{r}
#ecdf plots
plot(ecdf(EPI_data$ENVHEALTH),do.points=FALSE,verticals = TRUE)
plot(ecdf(EPI_data$ENVHEALTH),do.points=TRUE,verticals = TRUE)
plot(ecdf(EPI_data$ECOSYSTEM),do.points=FALSE,verticals = TRUE)
plot(ecdf(EPI_data$ECOSYSTEM),do.points=TRUE,verticals = TRUE)
plot(ecdf(EPI_data$AIR_H),do.points=FALSE,verticals = TRUE)
plot(ecdf(EPI_data$AIR_H),do.points=TRUE,verticals = TRUE)
plot(ecdf(EPI_data$WATER_H),do.points=FALSE,verticals = TRUE)
plot(ecdf(EPI_data$WATER_H),do.points=TRUE,verticals = TRUE)
plot(ecdf(EPI_data$WATER_E),do.points=FALSE,verticals = TRUE)
plot(ecdf(EPI_data$WATER_E),do.points=TRUE,verticals = TRUE)
plot(ecdf(EPI_data$BIODIVERSITY),do.points=FALSE,verticals = TRUE)
plot(ecdf(EPI_data$BIODIVERSITY),do.points=TRUE,verticals = TRUE)
```