Basic Statistics

Load Libraries

# if you haven't used a given package before, you'll need to download it first
# delete the "#" before the install function and run it to download
# re-insert the "#" before the install function so that the file will Knit later
# then run the library function calling that package

# install.packages("psych")
# install.packages("expss")

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

##Import Data

# Import the "fakedata.csv" file

d2 <- read.csv("Data/projectdata.csv")


# Note: for the HW, you will import "projectdata.csv" that you created and exported in the Data Prep Lab

Univariate Plots: Histograms & Tables

Tables are used to visualize individual categorical variables. Histograms are used to visualize individual continuous variables.

# use tables to visualize categorical data
table(d2$gender)
## 
##    f    m   nb 
## 1582  543   31
table(d2$age)
## 
## 1 between 18 and 25 2 between 26 and 35 3 between 36 and 45           4 over 45 
##                1985                 115                  38                  18
# use histograms to visualize continuous data
hist(d2$swb)

hist(d2$mindful)

hist(d2$belong)

hist(d2$socmeduse)

Univariate Normality for Continuous Variables (individually)

describe(d2)
##             vars    n    mean     sd  median trimmed    mad   min  max   range
## ResponseId*    1 2156 1078.50 622.53 1078.50 1078.50 799.12  1.00 2156 2155.00
## gender*        2 2156    1.28   0.48    1.00    1.21   0.00  1.00    3    2.00
## age*           3 2156    1.11   0.43    1.00    1.00   0.00  1.00    4    3.00
## swb            4 2156    4.43   1.33    4.50    4.49   1.48  1.00    7    6.00
## mindful        5 2156    3.72   0.84    3.73    3.72   0.79  1.13    6    4.87
## belong         6 2156    3.21   0.61    3.20    3.23   0.59  1.30    5    3.70
## socmeduse      7 2156   34.26   8.59   35.00   34.52   7.41 11.00   55   44.00
##              skew kurtosis    se
## ResponseId*  0.00    -1.20 13.41
## gender*      1.36     0.71  0.01
## age*         4.42    21.12  0.01
## swb         -0.35    -0.50  0.03
## mindful     -0.04    -0.15  0.02
## belong      -0.27    -0.09  0.01
## socmeduse   -0.30     0.20  0.19
## For the required write-up below, choose one of these options to paste and edit below based on your output.

# 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 continuous variables and (#) were within the accepted range (-2/+2). However, (#) variables (list variable name here) were outside of the accepted range. For this analysis, we will use them anyway, but outside of this class this is bad practice.

We analyzed the skew and kurtosis of our continuous variables and all were within the accepted range (-2/+2).

Bivariate Plots

Crosstabs

Crosstabs are used to visualize combinations of two categorical variables.

cross_cases(d2, gender, age)
 age 
 1 between 18 and 25   2 between 26 and 35   3 between 36 and 45   4 over 45 
 gender 
   f  1473 69 28 12
   m  482 46 9 6
   nb  30 1
   #Total cases  1985 115 38 18 
# Note: for HW, replace the two variables with your project's categorical ones)

Scatterplots

Scatterplots are used to visualize combinations of two continuous variables.

plot(d2$swb, d2$mindful,
     main="Scatterplot of swb and mindful",
     xlab = "swb",
     ylab = "mindful")

plot(d2$socmeduse, d2$belong,
     main="Scatterplot of socmeduse and belong",
     xlab = "socmeduse",
     ylab = "belong")

# Note: for HW, you will choose to plot 2 combos of your 4 continuous variables, based on your research questions/hypotheses. You may repeat 1 variable to see its association with 2 others. You will need replace the variable names on the first line of the function as well as the 'main' (aka plot title), 'xlab' and 'ylab' lines to correctly label the graphs.

Boxplots

Boxplots are used to visualize combinations of one categorical and one continuous variable.

# ORDER MATTERS HERE: 'continuous variable' ~ 'categorical variable' 

boxplot(data=d2, socmeduse~gender,
        main="Boxplot of socmeduse and gender",
        xlab = "gender",
        ylab = "socmeduse")

boxplot(data=d2, swb~age,
        main="Boxplot of swb and age",
        xlab = "age",
        ylab = "swb")

# Note: for HW, you will choose to plot 2 combos of any of your 4 continuous variables with either of your 2 categorical variables, based on your research questions/hypotheses. You may repeat 1 variable to see its association with others. Again, you will need replace the variable names on the first line of the function as well as the 'main' (aka plot title), 'xlab' and 'ylab' lines to correctly label the graph.