Basic Statistics Lab

Load Libraries

# remember, you might need to install packages

library(psych) # for the describe() command
library(expss) # for the cross_cases() command

Load Data

d <- read.csv(file="Data/mydata.csv", header=T)
# names(d)

Univariate Plots: Histograms & Tables

table(d$urban_rural)

             city isolated dwelling              town           village 
              282                30               559               382 

table(d$sexual_orientation)

              Asexual                    Bi           Gay/Lesbian 
                   33                   158                    50 
Heterosexual/Straight    I use another term     Prefer not to say 
                  894                    33                    85 

hist(d$gad)

hist(d$support)

hist(d$pss)

hist(d$isolation)

Univariate Normality

Check skew and kurtosis. Cutoffs are -2 and +2; if skew or kurtosis are higher or lower than those values, I need to mention it in my writeup

describe(d)

                    vars    n mean   sd median trimmed  mad min max range  skew
urban_rural*           1 1253 2.83 1.10   3.00    2.91 1.48   1 4.0   3.0 -0.69
sexual_orientation*    2 1253 3.79 1.02   4.00    3.82 0.00   1 6.0   5.0 -0.50
gad                    3 1253 2.04 0.91   1.71    1.95 0.85   1 4.0   3.0  0.69
support                4 1253 3.57 0.95   3.67    3.63 0.99   1 5.0   4.0 -0.45
pss                    5 1253 2.93 0.95   3.00    2.92 1.11   1 5.0   4.0  0.08
isolation              6 1253 2.15 0.84   2.00    2.12 1.11   1 3.5   2.5  0.17
                    kurtosis   se
urban_rural*           -0.85 0.03
sexual_orientation*     1.27 0.03
gad                    -0.71 0.03
support                -0.53 0.03
pss                    -0.75 0.03
isolation              -1.28 0.02

Bivariate Plots

Crosstabs

cross_cases(d, urban_rural, sexual_orientation)

	sexual_orientation
	Asexual	Bi	Gay/Lesbian	Heterosexual/Straight	I use another term	Prefer not to say
urban_rural
city	6	41	12	189	7	27
isolated dwelling	1	5		24
town	19	69	26	398	17	30
village	7	43	12	283	9	28
#Total cases	33	158	50	894	33	85

# I want to meet the lone ace living in the middle of nowhere, sounds like an interesting person

Scatterplots

plot(d$gad, d$support,
     main="Scatterplot of Anxiety and Social Support",
     xlab = "Anxiety",
     ylab = "Social Support")

plot(d$gad, d$pss,
     main="Scatterplot of Anxiety and Stress",
     xlab = "Anxiety",
     ylab = "Stress")

plot(d$gad, d$isolation,
     main="Scatterplot of Anxiety and Isolation",
     xlab = "Anxiety",
     ylab = "Isolation")

plot(d$support, d$pss,
     main="Scatterplot of Social Support and Stress",
     xlab = "Social Support",
     ylab = "Stress")

plot(d$support, d$isolation,
     main="Scatterplot of Social Support and Isolation",
     xlab = "Social Support",
     ylab = "Isolation")

plot(d$pss, d$isolation,
     main="Scatterplot of Stress and Isolation",
     xlab = "Stress",
     ylab = "Isolation")

Boxplots

boxplot(data=d, pss~urban_rural,
        main="Boxplot of Stress and Living Location",
        xlab = "Stress",
        ylab = "Living Location")

boxplot(data=d, pss~sexual_orientation,
        main="Boxplot of Stress and Sexual Orientation",
        xlab = "Stress",
        ylab = "Sexual Orientation")

Write-Up

We reviewed plots and descriptive statistics for our six chosen variables. All four of our continuous variables had skew and kurtosis within the accepted range (-2/+2).