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 aggregate all non-grouping columns: take_all(mtcars, mean, by = am)
## 
## Use 'expss_output_viewer()' to display tables in the RStudio Viewer.
##  To return to the console output, use 'expss_output_default()'.

##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$gender)
## 
##    f    m   nb 
## 2256  770   52
table(d2$income)
## 
##          1 low       2 middle         3 high rather not say 
##            857            867            520            834
# use histograms to visualize continuous data
hist(d2$efficacy)

hist(d2$stress)

hist(d2$moa_independence)

hist(d2$support)

Univariate Normality for Continuous Variables (individually)

describe(d2)
##                  vars    n    mean     sd  median trimmed     mad min    max
## ResponseID*         1 3078 1539.50 888.69 1539.50 1539.50 1140.86 1.0 3078.0
## gender*             2 3078    1.28   0.49    1.00    1.21    0.00 1.0    3.0
## income*             3 3078    2.43   1.16    2.00    2.42    1.48 1.0    4.0
## efficacy            4 3078    3.13   0.45    3.10    3.13    0.44 1.1    4.0
## stress              5 3078    3.05   0.60    3.00    3.05    0.59 1.3    4.7
## moa_independence    6 3078    3.54   0.47    3.67    3.61    0.49 1.0    4.0
## support             7 3078    5.54   1.13    5.75    5.66    0.99 0.0    7.0
##                   range  skew kurtosis    se
## ResponseID*      3077.0  0.00    -1.20 16.02
## gender*             2.0  1.39     0.86  0.01
## income*             3.0  0.15    -1.43  0.02
## efficacy            2.9 -0.25     0.48  0.01
## stress              3.4  0.03    -0.17  0.01
## moa_independence    3.0 -1.44     2.52  0.01
## support             7.0 -1.11     1.48  0.02
## For the required write-up below, choose one of these options to paste and edit below based on your output.

## OPTION 1
# We analyzed the skew and kurtosis of our continuous variables and all were within the accepted range (-2/+2).

## OPTION 2
# We analyzed the skew and kurtosis of our continuous variables and (#) were within the accepted range (-2/+2). However, (#) variables (list variable name(s) 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 (5) were within the accepted range (-2/+2). However, (1) variables (moa_independence) were outside of the accepted range. For this analysis, we will use them anyway, but outside of this class this is bad practice.

Bivariate Plots

Crosstabs

Crosstabs are used to visualize combinations of two categorical variables.

cross_cases(d2, gender, income)
 income 
 1 low   2 middle   3 high   rather not say 
 gender 
   f  630 653 363 610
   m  210 202 153 205
   nb  17 12 4 19
   #Total cases  857 867 520 834 
# Note: for HW, replace the two lab variables with your project ones)

Scatterplots

Scatterplots are used to visualize combinations of two continuous variables.

plot(d2$moa_independence, d2$efficacy, 
     main="Scatterplot of efficacy and moa_independence",
     xlab = "efficacy",
     ylab = "moa_independence")

plot(d2$support, d2$stress,
     main="Scatterplot of stress and support",
     xlab = "stress",
     ylab = "support")

# Note: for HW, you will choose to plot 2 combos of your 4 continuous variables, based on your 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 -- remember to use the actual variable names, not their scales, so someone reading your plots can understand them.

Boxplots

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

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

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

boxplot(data=d2, stress~income,
        main="Boxplot of stress and income",
        xlab = "income",
        ylab = "stress")

# 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 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 graphs -- remember to use the actual variable names, not their scales, so someone reading your plots can understand them.

We did it!!