P421 HW - Basic Statistics HW

Basic Statistics

Load Libraries

library(psych) # for the describe() command
library(expss) # for the cross_cases() command

## Loading required package: maditr

## 
## To aggregate several columns with one summary: take(mtcars, mpg, hp, fun = mean, by = am)

## 
## Attaching package: 'maditr'

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

## 
## Use 'expss_output_rnotebook()' to display tables inside R Notebooks.
##  To return to the console output, use 'expss_output_default()'.

Import Data

d2 <- read.csv(file="Data/mydata.csv", header = T)

Univariate Plots: Histograms & Tables

table(d2$race_rc) #the table command shows us what the levels of this variable are, and how many participants are in each level

## 
##       asian       black    hispanic multiracial  nativeamer       other 
##         201         234         277         285          10          91 
##       white 
##        1984

table(d2$usdream)

## 
##               american dream is important and achievable for me 
##                                                            1423 
##     american dream is important but maybe not achievable for me 
##                                                             335 
## american dream is not important and maybe not achievable for me 
##                                                             572 
##        american dream is not important but is achievable for me 
##                                                             177 
##                            not sure if american dream important 
##                                                             575

hist(d2$moa_independence) #the hist command creates a histogram of the variable

hist(d2$idea)

hist(d2$support)

hist(d2$socmeduse)

Univariate Normality

We analyzed the skew and kurtosis of our continuous variables and half were within the accepted range (-2/+2). However, two variables (moa_independence, idea) were outside of the accepted range. For this analysis, we will use them anyway, but outside of this class this is bad practice.

describe(d2) #we use this to check univariate normality ... skew and kurtosis, (-2/+2)

##                  vars    n  mean   sd median trimmed  mad min max range  skew
## race_rc*            1 3082  5.56 2.12   7.00    5.90 0.00   1   7     6 -1.00
## usdream*            2 3082  2.40 1.55   2.00    2.25 1.48   1   5     4  0.62
## moa_independence    3 3082  3.54 0.46   3.67    3.61 0.49   1   4     3 -1.44
## idea                4 3082  3.58 0.38   3.62    3.62 0.37   1   4     3 -1.50
## support             5 3082  5.53 1.13   5.75    5.66 0.99   0   7     7 -1.10
## socmeduse           6 3082 34.45 8.60  35.00   34.72 7.41  11  55    44 -0.31
##                  kurtosis   se
## race_rc*            -0.63 0.04
## usdream*            -1.14 0.03
## moa_independence     2.55 0.01
## idea                 4.31 0.01
## support              1.43 0.02
## socmeduse            0.26 0.15

Bivariate Plots

Crosstabs

cross_cases(d2, race_rc, usdream) 

	usdream
	american dream is important and achievable for me	american dream is important but maybe not achievable for me	american dream is not important and maybe not achievable for me	american dream is not important but is achievable for me	not sure if american dream important
race_rc
asian	74	37	33	9	48
black	108	20	55	12	39
hispanic	159	33	27	13	45
multiracial	124	33	58	15	55
nativeamer	5	1	1		3
other	31	6	29	6	19
white	922	205	369	122	366
#Total cases	1423	335	572	177	575

Scatterplots

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

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

Boxplots

boxplot(data=d2, moa_independence~race_rc,
        main="Boxplot of race_rc and moa_independence",
        xlab = "race_rc",
        ylab = "moa_independence")

boxplot(data=d2, idea~usdream,
        main="Boxplot of usdream and idea",
        xlab = "usdream",
        ylab = "idea")