Instructions for Class on March 20, 2017

03202017.txt

## RUN ALL THIS SYNTAX BEFORE WE START
## This will install and load all the packages you need for class today. 

ipak <- function(pkg){
    new.pkg <- pkg[!(pkg %in% installed.packages()[, "Package"])]
    if (length(new.pkg)) 
        install.packages(new.pkg, dependencies = TRUE)
    sapply(pkg, require, character.only = TRUE)
}

packages <- c("ggplot2", "dplyr", "car", "Rmisc")
ipak(packages)

## STOP AND WAIT FOR ME

salary <- data.frame("name" =c("Bill Gates", "Warren Buffett", "Donald Trump", "Bob", "Steve", "Lisa", "Karen", "David Glassman", "Ben", "Piper", "Hope"), 
                  money = c(10000000,12000000,2000000, 42000,35000,54000,27500,400000,33000, 75000, 87000))
                  
## Let's learn about dplyr's arrange command
## How do we put things in a descending order? 

## How about some filter practice. Create a smaller dataset of just people who aren't rich. 

## Let's learn a little about mean, median, and standard deviation. 

## Let's say that you wanted to find out what the average salary was for women vs. men.
salary$gender <- c("M", "M", "M", "F", "F", "M", "M", "F", "F", "M", "M", "F", "F")

## Here's a dataset of heights and weights
pop <- read.csv(url("https://goo.gl/PPrmeY"))

## Let's do some work on their means, medians, and standard deviations. 



## NOW LOAD IN A NEW DATASET 
cces <- read.csv(url("https://goo.gl/Ukt2xt"))
## Here's the codebook
https://dataverse.harvard.edu/file.xhtml?fileId=3004424&version=1.2

## Tell me which gender has, on average, a higher level of education
## Now, tell me which gender, on average, has a higher household income