# if you haven't run this code before, you'll need to download the below packages first
# instructions on how to do this are included in the video
# but as a reminder, you use the packages tab to the right
library(psych) # for the describe() command
library(expss) # for the cross_cases() command
## Loading required package: maditr
##
## To get total summary skip 'by' argument: take_all(mtcars, mean)
# import our data for the lab
# for the homework, you will import the mydata.csv that we created in Data Prep Lab
d2 <- read.csv(file = "Data/mydata.csv" , header = T)
table(d2$age) #the table command shows us what the levels of this variable are, and how many participants are in each level
##
## 1 under 18 2 between 18 and 25 3 between 26 and 35 4 between 36 and 45
## 645 56 6 90
## 5 over 45
## 190
table(d2$mhealth)
##
## anxiety disorder bipolar
## 100 4
## depression eating disorders
## 25 19
## none or NA obsessive compulsive disorder
## 782 17
## other ptsd
## 24 16
hist(d2$covid_pos) #the hist command creates a histogram of the variable
hist(d2$support)
hist(d2$pas_covid)
We analyzed the skew and kurtosis of our continuous variables and all were within the accepted range (-2/+2).
We analyzed the skew and kurtosis of our … and most were within the accepted range (-2/+2). However, some variables (list them in parentheses) were outside of the accepted range. For this analysis, we will use them anyway, but outside of this class this is bad practice.
describe(d2) #we use this to check univariate normality ... skew and kurtosis, (-2/+2)
## vars n mean sd median trimmed mad min max range skew kurtosis
## age* 1 987 2.11 1.66 1.00 1.89 0.00 1 5 4 0.96 -0.94
## mhealth* 2 987 4.63 1.38 5.00 4.89 0.00 1 8 7 -1.52 2.77
## covid_pos 3 987 1.84 3.27 0.00 1.08 0.00 0 15 15 1.76 2.13
## support 4 987 3.59 0.95 3.67 3.64 0.99 1 5 4 -0.42 -0.61
## gender* 5 987 1.37 0.79 1.00 1.20 0.00 1 4 3 1.77 1.45
## pas_covid 6 987 3.23 0.68 3.22 3.25 0.66 1 5 4 -0.22 0.11
## se
## age* 0.05
## mhealth* 0.04
## covid_pos 0.10
## support 0.03
## gender* 0.03
## pas_covid 0.02
cross_cases(d2,mhealth,covid_pos) #update variable2 and variable3 with your categorical variable names
|  covid_pos | ||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Â 0Â | Â 1Â | Â 2Â | Â 3Â | Â 4Â | Â 5Â | Â 6Â | Â 7Â | Â 8Â | Â 9Â | Â 10Â | Â 11Â | Â 12Â | Â 13Â | Â 14Â | Â 15Â | |
|  mhealth | ||||||||||||||||
|    anxiety disorder | 59 | 4 | 4 | 5 | 7 | 4 | 3 | 5 | 3 | 3 | 1 | 1 | 1 | |||
|    bipolar | 1 | 1 | 1 | 1 | ||||||||||||
|    depression | 18 | 1 | 1 | 1 | 1 | 1 | 1 | 1 | ||||||||
|    eating disorders | 7 | 1 | 2 | 4 | 3 | 1 | 1 | |||||||||
| Â Â Â none or NAÂ | 564 | 19 | 15 | 27 | 26 | 27 | 20 | 21 | 11 | 17 | 13 | 7 | 11 | 1 | 2 | 1 |
|    obsessive compulsive disorder | 4 | 2 | 1 | 2 | 1 | 1 | 2 | 1 | 1 | 1 | 1 | |||||
|    other | 11 | 1 | 3 | 1 | 3 | 2 | 3 | |||||||||
|    ptsd | 9 | 1 | 1 | 1 | 1 | 1 | 2 | |||||||||
|    #Total cases | 673 | 28 | 28 | 35 | 37 | 35 | 28 | 31 | 21 | 26 | 15 | 9 | 13 | 3 | 3 | 2 |
plot(d2$pas_covid, d2$support,
main="Scatterplot of pas_covid and support",
xlab = "pas_covid",
ylab = "support")
plot(d2$covid_pos, d2$support,
main="Scatterplot of covid_pos and support",
xlab = "covid_pos",
ylab = "support")
#boxplots use ONE CATEGORICAL and ONE CONTINUOUS variable
#make sure that you enter them in the right order !
# categorical variables goes BEfORE the tilde
# continuous variable goes AFTER the tilde
boxplot(data=d2, support~mhealth,
main="Boxplot of mhealth and support",
xlab = "mhealth",
ylab = "support")
boxplot(data=d2, pas_covid~gender,
main="Boxplot of gender and pas_covid",
xlab = "gender",
ylab = "pas_covid")