Basic Statistics HW

Load Libraries

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)

[1] "gender"    "age"       "swb"       "support"   "socmeduse" "stress"   

Univariate Plots: Histograms & Tables

table(d$gender)

   f    m   nb 
1586  544   31 

table(d$age)

1 between 18 and 25 2 between 26 and 35 3 between 36 and 45           4 over 45 
               1989                 116                  38                  18 

hist(d$swb)

hist(d$support)

hist(d$socmeduse)

hist(d$stress)

Univariate Normality

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

describe(d)

          vars    n  mean   sd median trimmed  mad  min  max range  skew
gender*      1 2161  1.28 0.48   1.00    1.21 0.00  1.0  3.0   2.0  1.36
age*         2 2161  1.11 0.43   1.00    1.00 0.00  1.0  4.0   3.0  4.41
swb          3 2161  4.44 1.33   4.50    4.49 1.48  1.0  7.0   6.0 -0.35
support      4 2161  5.53 1.13   5.75    5.65 0.99  0.0  7.0   7.0 -1.08
socmeduse    5 2161 34.25 8.59  35.00   34.51 7.41 11.0 55.0  44.0 -0.31
stress       6 2161  3.07 0.60   3.10    3.07 0.59  1.3  4.6   3.3 -0.02
          kurtosis   se
gender*       0.71 0.01
age*         21.07 0.01
swb          -0.49 0.03
support       1.31 0.02
socmeduse     0.20 0.18
stress       -0.15 0.01

Bivariate Plots

Crosstabs

cross_cases(d, gender, age)

	age
	1 between 18 and 25	2 between 26 and 35	3 between 36 and 45	4 over 45
gender
f	1476	70	28	12
m	483	46	9	6
nb	30		1
#Total cases	1989	116	38	18

Scatterplots

plot(d$swb, d$support,
     main="Scatterplot of Satisfaction with Life Scale and Support",
     xlab = "Satisfaction with Life",
     ylab = "Support")

plot(d$swb, d$socmeduse,
     main="Scatterplot of Satisfaction with Life Scale and Social Media Use",
     xlab = "Satisfaction with Life",
     ylab = "Social Media Use")

plot(d$swb, d$stress,
     main="Scatterplot of Satisfaction with Life Scale and Stress",
     xlab = "Satisfaction with Life",
     ylab = "Stress")

plot(d$support, d$socmeduse,
     main="Scatterplot of Support and Social Media Use",
     xlab = "Support",
     ylab = "Social Media Use")

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

plot(d$socmeduse, d$stress,
     main="Scatterplot of Social Media Use and Stress",
     xlab = "Social Media Use",
     ylab = "Stress")

Boxplots

boxplot(data=d, swb~gender,
        main="Boxplot of Satisfaction with Life and Gender",
        xlab = "Gender",
        ylab = "Satisfaction with Life")

boxplot(data=d, swb~age,
        main="Boxplot of Satisfaction with Life and Age",
        xlab = "Age",
        ylab = "Satisfaction with Life")

Write-Up

If skew and kurtosis have issues: We reviewed plots and descriptive statistics for our six chosen variables. [One catigorical] variable had issues with skew and kurtosis: age scores were positively skewed (4.41) and was kurtotic (21.07). The other [continuous and other categorical] variables had skew and kurtosis within the accepted range (-2/+2).