# 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 drop variable use NULL: let(mtcars, am = NULL) %>% head()
##
## Attaching package: 'maditr'
## The following object is masked from 'package:base':
##
## sort_by
##
## Use 'expss_output_viewer()' to display tables in the RStudio Viewer.
## To return to the console output, use 'expss_output_default()'.
# import our data for the lab
# for the homework, you will import the mydata.csv that we created in the Data Prep Lab
d2 <- read.csv(file="Data/mydata.csv", header = T)
table(d2$gender) #the table command shows us what the levels of this variable are, and how many participants are in each level
##
## f m nb
## 1546 530 31
table(d2$age)
##
## 1 between 18 and 25 2 between 26 and 35 3 between 36 and 45 4 over 45
## 1940 113 37 17
hist(d2$moa_independence) #the hist command creates a histogram of the variable
hist(d2$swb)
hist(d2$support)
hist(d2$stress)
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, one variable (moa_independence) was outside of the accepted range. For this analysis, we will use it anyway, but outside of this class this is bad practice.
describe(d2) #we use this to univariate normality ... skew and kurtosis, (-2/+2)
## vars n mean sd median trimmed mad min max range skew
## gender* 1 2107 1.28 0.48 1.00 1.21 0.00 1.0 3.0 2.0 1.36
## age* 2 2107 1.11 0.43 1.00 1.00 0.00 1.0 4.0 3.0 4.42
## moa_independence 3 2107 3.54 0.47 3.67 3.61 0.49 1.0 4.0 3.0 -1.49
## swb 4 2107 4.43 1.33 4.50 4.49 1.48 1.0 7.0 6.0 -0.36
## support 5 2107 5.53 1.13 5.75 5.66 0.99 0.0 7.0 7.0 -1.10
## stress 6 2107 3.07 0.60 3.10 3.07 0.59 1.3 4.6 3.3 -0.01
## kurtosis se
## gender* 0.74 0.01
## age* 21.17 0.01
## moa_independence 2.75 0.01
## swb -0.49 0.03
## support 1.35 0.02
## stress -0.16 0.01
cross_cases(d2, gender, age) # update variable2 and variable3 with your categorical variable names
|  age | ||||
|---|---|---|---|---|
| Â 1 between 18 and 25Â | Â 2 between 26 and 35Â | Â 3 between 36 and 45Â | Â 4 over 45Â | |
|  gender | ||||
|    f | 1439 | 68 | 27 | 12 |
|    m | 471 | 45 | 9 | 5 |
|    nb | 30 | 1 | ||
|    #Total cases | 1940 | 113 | 37 | 17 |
plot(d2$moa_independence, d2$swb,
main="Scatterplot of MOA_Independence and SWB",
xlab = "MOA_Independence",
ylab = "SWB")
plot(d2$support, d2$stress,
main="Scatterplot of Support and Stress",
xlab = "Support",
ylab = "Stress")
# boxplots use ONE CATEGORICAL and ONE CONTINUOUS variable
# make sure that you enter them in the right order!!!
# categorical variable goes BEFORE the tilde ~
# continuous variable goes AFTER the tilde
boxplot(data=d2, swb~age,
main="Boxplot of Age and Satisfaction with Life Scale (SWB)",
xlab = "Age",
ylab = "SWB")
boxplot(data=d2, stress~gender,
main="Boxplot of Gender and Stress",
xlab = "Gender",
ylab = "Stress")