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 rows from data: rows(mtcars, am==0)

## 
## Attaching package: 'maditr'

## The following object is masked from 'package:base':
## 
##     sort_by

## 
## 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 "projectdata.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$income)

## 
##          1 low       2 middle         3 high rather not say 
##            870            878            533            843

table(d2$party_rc)

## 
##  apolitical    democrat independent  republican 
##         432        1588         326         778

# use histograms to visualize continuous data
hist(d2$npi)

hist(d2$stress)

hist(d2$swb)

hist(d2$belong)

Univariate Normality for Continuous Variables (individually)

describe(d2)

##             vars    n    mean     sd  median trimmed     mad min    max  range
## ResponseId*    1 3124 1562.50 901.97 1562.50 1562.50 1157.91 1.0 3124.0 3123.0
## income*        2 3124    2.43   1.16    2.00    2.41    1.48 1.0    4.0    3.0
## party_rc*      3 3124    2.46   1.01    2.00    2.46    0.00 1.0    4.0    3.0
## npi            4 3124    0.28   0.31    0.15    0.24    0.23 0.0    1.0    1.0
## stress         5 3124    3.05   0.60    3.00    3.05    0.59 1.3    4.7    3.4
## swb            6 3124    4.48   1.32    4.67    4.53    1.48 1.0    7.0    6.0
## belong         7 3124    3.23   0.60    3.30    3.25    0.59 1.3    5.0    3.7
##              skew kurtosis    se
## ResponseId*  0.00    -1.20 16.14
## income*      0.15    -1.43  0.02
## party_rc*    0.42    -1.04  0.02
## npi          0.95    -0.68  0.01
## stress       0.03    -0.16  0.01
## swb         -0.36    -0.46  0.02
## belong      -0.25    -0.14  0.01

## 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, income, party_rc)

	party_rc
	apolitical	democrat	independent	republican
income
1 low	126	481	96	167
2 middle	90	473	93	222
3 high	41	243	42	207
rather not say	175	391	95	182
#Total cases	432	1588	326	778

find("cross_cases")

## [1] "package:expss"

# 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$swb, d2$belong,
     main="Scatterplot of Satisfaction with Life Scale and Need to Belong Scale",
     xlab = "swb",
     ylab = "belong")

plot(d2$npi, d2$stress,
     main="Scatterplot of Narcissistic Personality Inventory and Perceived Stress Questionairre",
     xlab = "npi",
     ylab = "stress")

# 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, swb~income,
        main="Boxplot of Satisfaction with Life and Income",
        xlab = "income",
        ylab = "swb")

boxplot(data=d2, npi~party_rc,
        main="Boxplot of Political Party and Narcissistic Personality Inventory",
        xlab = "party_rc",
        ylab = "npi")

# 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.

P421 Lab - Basic Statistics Lab

Eli Buckler

2024-09-26