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_rnotebook()' to display tables inside R Notebooks.
## To return to the console output, use 'expss_output_default()'.
# import data for the lab
# For HW import mydata.csv
d2 <- read.csv(file="data/mydata.csv", header = T)
table(d2$trans) #shows level of variable and how many participants
##
## no Prefer not to say yes
## 941 37 31
table(d2$age)
##
## 1 under 18 2 between 18 and 25 3 between 26 and 35 4 between 36 and 45
## 673 54 6 87
## 5 over 45
## 189
hist(d2$big5_agr) # variable 5 #creates histogram of variable
hist(d2$big5_ext)
hist(d2$rse)
hist(d2$pas_covid)
We analyzed the skew and kurtosis of our continuous variables and most were within the accepted range. However, one variable (trans) was outside of the accepted range. For the purpose of this class we will use it anyway.
describe(d2)
## vars n mean sd median trimmed mad min max range skew kurtosis
## trans* 1 1009 1.10 0.39 1.00 1.00 0.00 1 3 2 4.08 15.93
## age* 2 1009 2.07 1.64 1.00 1.84 0.00 1 5 4 1.01 -0.83
## big5_agr 3 1009 5.01 1.12 5.00 5.05 0.99 1 7 6 -0.39 -0.03
## big5_ext 4 1009 4.34 1.45 4.33 4.38 1.48 1 7 6 -0.23 -0.77
## rse 5 1009 2.65 0.71 2.70 2.67 0.74 1 4 3 -0.20 -0.74
## pas_covid 6 1009 3.24 0.68 3.22 3.26 0.66 1 5 4 -0.23 0.12
## se
## trans* 0.01
## age* 0.05
## big5_agr 0.04
## big5_ext 0.05
## rse 0.02
## pas_covid 0.02
cross_cases(d2, trans, age) #Update with categorical variables for HW
|  age | |||||
|---|---|---|---|---|---|
| Â 1 under 18Â | Â 2 between 18 and 25Â | Â 3 between 26 and 35Â | Â 4 between 36 and 45Â | Â 5 over 45Â | |
|  trans | |||||
|    Prefer not to say | 31 | 1 | 5 | ||
|    no | 613 | 52 | 6 | 86 | 184 |
|    yes | 29 | 2 | |||
|    #Total cases | 673 | 54 | 6 | 87 | 189 |
plot(d2$big5_agr, d2$rse,
main="Scatterplot of big5_agr and rse",
xlab = "big5_agr",
ylab = "rse")
plot(d2$big5_ext, d2$pas_covid,
main="Scatterplot of big5_ext and pas_covid",
xlab = "big5_ext",
ylab = "pas_covid")
#One categorical and one continuous
#Continuous variable first!!!
boxplot(data=d2, big5_ext~trans,
main="Boxplot of trans and big5_ext",
xlab = "trans",
ylab = "big5_ext")
boxplot(data=d2, pas_covid~age,
main="Boxplot of age and pas_covid",
xlab = "age",
ylab = "pas_covid")