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 select columns from data: columns(mtcars, mpg, vs:carb)

##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$gender)
## 
##    f    m   nb 
## 2280  780   52
table(d2$party_rc)
## 
##  apolitical    democrat independent  republican 
##         436        1579         322         775
# use histograms to visualize continuous data
hist(d2$moa_maturity)

hist(d2$npi)

hist(d2$exploit)

hist(d2$efficacy)

Univariate Normality for Continuous Variables (individually)

describe(d2)
##              vars    n    mean     sd  median trimmed     mad min  max  range
## ResponseID*     1 3112 1556.50 898.50 1556.50 1556.50 1153.46 1.0 3112 3111.0
## gender*         2 3112    1.28   0.49    1.00    1.21    0.00 1.0    3    2.0
## party_rc*       3 3112    2.46   1.01    2.00    2.45    0.00 1.0    4    3.0
## moa_maturity    4 3112    3.59   0.43    3.67    3.65    0.49 1.0    4    3.0
## npi             5 3112    0.28   0.31    0.15    0.24    0.23 0.0    1    1.0
## exploit         6 3112    2.39   1.37    2.00    2.21    1.48 1.0    7    6.0
## efficacy        7 3112    3.13   0.45    3.10    3.13    0.44 1.1    4    2.9
##               skew kurtosis    se
## ResponseID*   0.00    -1.20 16.11
## gender*       1.38     0.84  0.01
## party_rc*     0.42    -1.04  0.02
## moa_maturity -1.20     1.89  0.01
## npi           0.94    -0.69  0.01
## exploit       0.94     0.36  0.02
## efficacy     -0.27     0.53  0.01
## 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 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, party_rc)
 party_rc 
 apolitical   democrat   independent   republican 
 gender 
   f  322 1206 211 541
   m  109 337 101 233
   nb  5 36 10 1
   #Total cases  436 1579 322 775 
# 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$moa_maturity, d2$efficacy, 
     main="Scatterplot of Maturity and Self-Efficacy",
     xlab = "Maturity",
     ylab = "Self-Efficacy")

plot(d2$npi, d2$exploit,
     main="Scatterplot of Narcissism and Exploitativeness",
     xlab = "Narcissism",
     ylab = "Exploitativeness")

# 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, npi~gender,
        main="Boxplot of Gender and Narcissism",
        xlab = "Gender",
        ylab = "Narcissism")

boxplot(data=d2, exploit~party_rc,
        main="Boxplot of Political Party and Exploitativeness",
        xlab = "Political Party",
        ylab = "Exploitativeness")

# 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!!