library(dplyr)
library(tidyr)
library(psych)
library(Hmisc)
library(plyr)
library(ggplot2)2 Demographics
Loading in data from data cleaning page
load("INDI_data.Rdata")Age
print(psych::describeBy(indi.data$Age, group = indi.data$Group))
Descriptive statistics by group
group: OA
vars n mean sd median trimmed mad min max range skew kurtosis se
X1 1 152 72.91 6 72.5 72.7 6.67 60 89 29 0.28 -0.57 0.49
------------------------------------------------------------
group: YA
vars n mean sd median trimmed mad min max range skew kurtosis se
X1 1 211 18.89 1.09 19 18.69 1.48 18 24 6 1.51 2.65 0.08
print(psych::describe(indi.data$Age)) vars n mean sd median trimmed mad min max range skew kurtosis se
X1 1 363 41.51 26.98 20 39.5 2.97 18 89 71 0.39 -1.77 1.42
ggplot(indi.data, aes(x = Age, fill = Group)) +
geom_histogram(color = "black")Years of Education
print(psych::describeBy(indi.data$Edu.years, group = indi.data$Group))
Descriptive statistics by group
group: OA
vars n mean sd median trimmed mad min max range skew kurtosis se
X1 1 152 16.72 2.61 18 16.75 2.97 12 21 9 -0.15 -0.72 0.21
------------------------------------------------------------
group: YA
vars n mean sd median trimmed mad min max range skew kurtosis se
X1 1 211 12.61 0.96 12 12.4 0 12 16 4 1.5 1.19 0.07
print(psych::describe(indi.data$Edu.years)) vars n mean sd median trimmed mad min max range skew kurtosis se
X1 1 363 14.33 2.74 13 13.95 1.48 12 21 9 0.97 -0.23 0.14
Gender
table(indi.data$gender, indi.data$Group)
OA YA
F 101 143
M 51 67
Nonbinary 0 1
table(indi.data$gender)
F M Nonbinary
244 118 1
round(prop.table(table(indi.data$gender)), 3)
F M Nonbinary
0.672 0.325 0.003
Ethnicity
table(indi.data$Ethnicity, indi.data$Group)
OA YA
Hispanic Or Latino 1 20
Not Hispanic Or Latino 144 186
Prefer Not To Answer 7 5
table(indi.data$Ethnicity)
Hispanic Or Latino Not Hispanic Or Latino Prefer Not To Answer
21 330 12
round(prop.table(table(indi.data$Ethnicity)), 3)
Hispanic Or Latino Not Hispanic Or Latino Prefer Not To Answer
0.058 0.909 0.033
Race
Note: Recoded original categories (see below).
indi.data$Race.modified = case_when(
indi.data$Race == "American Indian Or Alaskan Native, White" |
indi.data$Race == "Asian, Black Or African American" |
indi.data$Race == "Asian, White, More Than One" |
indi.data$Race == "Asian, White" |
indi.data$Race == "Black Or African American, White" ~
"More Than One Race",
TRUE ~ indi.data$Race
)
table(indi.data$Race.modified, indi.data$Group)
OA YA
Asian 0 34
Black Or African American 2 9
More Than One Race 1 15
Other Or Unknown 0 2
Prefer Not To Answer 5 3
White 144 148
table(indi.data$Race.modified)
Asian Black Or African American More Than One Race
34 11 16
Other Or Unknown Prefer Not To Answer White
2 8 292
round(prop.table(table(indi.data$Race.modified)), 3)
Asian Black Or African American More Than One Race
0.094 0.030 0.044
Other Or Unknown Prefer Not To Answer White
0.006 0.022 0.804