naomispence

data.aov1 <- aov(gss123$paeduc ~ gss123$race, data=gss123)
summary(data.aov1)
by(gss123$race, gss123$paeduc, mean, na.rm=T)
TukeyHSD(data.aov1)

naomispence

##CHANGE VARNAME TO YOUR VARIABLE NAME; CHANGE TITLES AND X-AXIS LABELS
frequency(addhealthW5$VARNAME, title= "Frequency Distribution of YOUR VARIABLE DESCRIPTION")
#INTERPRET THE RESULT OF THE LINE ABOVE
frequency(addhealthW5$VARNAME, cumulative.percent=TRUE, title="YOUR VARIABLE DESCRIPTION")
#INTERPRET THE RESULT OF THE LINE ABOVE

ggplot(data=subset(addhealthW5, !is.na(VARNAME)), aes(x = VARNAME)) + 
  geom_bar(color="blue", fill="yellow", aes(y = ((..count..)/sum(..count..)))) + 
  scale_y_continuous(labels = scales::percent) + 
  ggtitle("Bar Graph of of YOUR VARIABLE DESCRIPTION, Wave 5 Add Health") + 

naomispence

# be sure you have the line below where you load libraries and options to load the dataset from the server.
data("addhealthW5")

#if you need to recode any of your variable values, you should do it before you label your dummy codes
addhealthW5$H5HR2[addhealthW5$H5HR2 == 6] <- 5
#the line right above this note changes the old dummy code 6 to a dummy code of 5, which combines the two groups.

#if you need to code out missing data (R calls it NA), you would use the example shown in the line below.
addhealthW5$VARNAME[addhealthW5$VARNAME == 97] <- NA
#in the line above, the number inside the ] needs to be the dummy code for missing data on your variable.

naomispence

library(ggplot2)
library(dplyr)
library(lsr)
library(descr)
library(Hmisc)
library('lehmansociology')
options(scipen = 999)
data(wave5addhealth)

wave5addhealth<-wave5addhealth[wave5addhealth$H5TO6<97,]

naomispence

library(ggplot2)
library(dplyr)
library(lsr)
library(descr)
library(Hmisc)
library('lehmansociology')
options(scipen = 999)
data(wave5addhealth)

naomispence

#Lab Report 5: Making and Comparing Confidence Intervals
library(ggplot2)
library(dplyr)
library(lsr)
library(descr)
library(Hmisc)
library('lehmansociology')
data(gss123)
options(scipen = 999)

naomispence

##Comparing CIs and distributions

#Load the libraries and data first
library(ggplot2)
library(dplyr)
library(lsr)
library(descr)
library(Hmisc)
library('lehmansociology')
data(gss123)

naomispence

#START BY LOADING LIBRARIES AND OPTIONS
library(aws.s3)
library(ggplot2)
library(dplyr)
library(lsr)
library(descr)
library(Hmisc)
library('lehmansociology')
options(scipen = 999)

naomispence

#Lab: Scatterplots and Regression

#Load the libraries and data first
library(ggplot2)
library(dplyr)
library(lsr)
library(descr)
library(Hmisc)
library('lehmansociology')
data(gss123)

naomispence

#Lab: Scatterplots and Regression

#Load the libraries and data first
library(ggplot2)
library(dplyr)
library(lsr)
library(descr)
library(Hmisc)
library('lehmansociology')