P421 hw - Data Prep & Basic Statistics
Jianhongjing Ou
2024-02-24
Data Prep
Load Libraries
# if you haven't run this code before, you'll need to download the below packages first
# instructions on how to do this are included in the video
# but as a reminder, you use the packages tab to the right
library(psych) # for the describe() command
library(naniar) # for the gg_miss-upset() command
library(expss) # for the cross_cases() command## Loading required package: maditr##
## To aggregate data: take(mtcars, mean_mpg = mean(mpg), by = am)##
## Use 'expss_output_rnotebook()' to display tables inside R Notebooks.
## To return to the console output, use 'expss_output_default()'.##
## Attaching package: 'expss'## The following object is masked from 'package:naniar':
##
## is_naImport Data
# for the lab, you'll import the CSV file you downloaded along with the current file we're working in (an RMD file)
# for the homework, you'll download the CSV file from your chosen README page (should be titled arc_data_final.csv or eammi2_data_final.csv)
df <- read.csv(file="DATA/eammi2_data_final.csv", header=T)Viewing Data
# these are commands useful for viewing a dataframe
# you can also click the object in the environment tab to view it in a new window
names(df)## [1] "ResponseId" "gender" "race_rc" "age"
## [5] "income" "edu" "sibling" "party_rc"
## [9] "disability" "marriage5" "phys_sym" "pipwd"
## [13] "moa_independence" "moa_role" "moa_safety" "moa_maturity"
## [17] "idea" "swb" "mindful" "belong"
## [21] "efficacy" "support" "socmeduse" "usdream"
## [25] "npi" "exploit" "stress"head(df)## ResponseId gender race_rc age income
## 1 R_BJN3bQqi1zUMid3 f white 1 between 18 and 25 1 low
## 2 R_2TGbiBXmAtxywsD m white 1 between 18 and 25 1 low
## 3 R_12G7bIqN2wB2N65 m white 1 between 18 and 25 rather not say
## 4 R_39pldNoon8CePfP f other 1 between 18 and 25 rather not say
## 5 R_1QiKb2LdJo1Bhvv m white 1 between 18 and 25 2 middle
## 6 R_pmwDTZyCyCycXwB f white 1 between 18 and 25 rather not say
## edu sibling party_rc disability
## 1 2 Currently in college at least one sibling democrat <NA>
## 2 5 Completed Bachelors Degree at least one sibling independent <NA>
## 3 2 Currently in college at least one sibling apolitical psychiatric
## 4 2 Currently in college at least one sibling apolitical <NA>
## 5 2 Currently in college at least one sibling apolitical <NA>
## 6 2 Currently in college at least one sibling apolitical <NA>
## marriage5 phys_sym pipwd
## 1 are currently divorced from one another high number of symptoms NA
## 2 are currently married to one another high number of symptoms NA
## 3 are currently married to one another high number of symptoms 2.333333
## 4 are currently married to one another high number of symptoms NA
## 5 are currently married to one another low number of symptoms NA
## 6 are currently married to one another high number of symptoms NA
## moa_independence moa_role moa_safety moa_maturity idea swb mindful
## 1 3.666667 3.000000 2.75 3.666667 3.750 4.333333 2.4
## 2 3.666667 2.666667 3.25 3.333333 3.875 4.166667 1.8
## 3 3.500000 2.500000 3.00 3.666667 3.750 1.833333 2.2
## 4 3.000000 2.000000 1.25 3.000000 3.750 5.166667 2.2
## 5 3.833333 2.666667 2.25 3.666667 3.500 3.666667 3.2
## 6 3.500000 3.333333 2.50 4.000000 3.250 4.000000 3.4
## belong efficacy support socmeduse
## 1 2.8 3.4 6.000000 47
## 2 4.2 3.4 6.750000 23
## 3 3.6 2.2 5.166667 34
## 4 4.0 2.8 5.583333 35
## 5 3.4 3.0 6.000000 37
## 6 4.2 2.4 4.500000 13
## usdream npi
## 1 american dream is important and achievable for me 0.69230769
## 2 american dream is important and achievable for me 0.15384615
## 3 american dream is not important and maybe not achievable for me 0.07692308
## 4 american dream is not important and maybe not achievable for me 0.07692308
## 5 not sure if american dream important 0.76923077
## 6 american dream is not important and maybe not achievable for me 0.23076923
## exploit stress
## 1 2.000000 3.3
## 2 3.666667 3.3
## 3 4.333333 4.0
## 4 1.666667 3.2
## 5 4.000000 3.1
## 6 1.333333 3.5str(df)## 'data.frame': 3182 obs. of 27 variables:
## $ ResponseId : chr "R_BJN3bQqi1zUMid3" "R_2TGbiBXmAtxywsD" "R_12G7bIqN2wB2N65" "R_39pldNoon8CePfP" ...
## $ gender : chr "f" "m" "m" "f" ...
## $ race_rc : chr "white" "white" "white" "other" ...
## $ age : chr "1 between 18 and 25" "1 between 18 and 25" "1 between 18 and 25" "1 between 18 and 25" ...
## $ income : chr "1 low" "1 low" "rather not say" "rather not say" ...
## $ edu : chr "2 Currently in college" "5 Completed Bachelors Degree" "2 Currently in college" "2 Currently in college" ...
## $ sibling : chr "at least one sibling" "at least one sibling" "at least one sibling" "at least one sibling" ...
## $ party_rc : chr "democrat" "independent" "apolitical" "apolitical" ...
## $ disability : chr NA NA "psychiatric" NA ...
## $ marriage5 : chr "are currently divorced from one another" "are currently married to one another" "are currently married to one another" "are currently married to one another" ...
## $ phys_sym : chr "high number of symptoms" "high number of symptoms" "high number of symptoms" "high number of symptoms" ...
## $ pipwd : num NA NA 2.33 NA NA ...
## $ moa_independence: num 3.67 3.67 3.5 3 3.83 ...
## $ moa_role : num 3 2.67 2.5 2 2.67 ...
## $ moa_safety : num 2.75 3.25 3 1.25 2.25 2.5 4 3.25 2.75 3.5 ...
## $ moa_maturity : num 3.67 3.33 3.67 3 3.67 ...
## $ idea : num 3.75 3.88 3.75 3.75 3.5 ...
## $ swb : num 4.33 4.17 1.83 5.17 3.67 ...
## $ mindful : num 2.4 1.8 2.2 2.2 3.2 ...
## $ belong : num 2.8 4.2 3.6 4 3.4 4.2 3.9 3.6 2.9 2.5 ...
## $ efficacy : num 3.4 3.4 2.2 2.8 3 2.4 2.3 3 3 3.7 ...
## $ support : num 6 6.75 5.17 5.58 6 ...
## $ socmeduse : int 47 23 34 35 37 13 37 43 37 29 ...
## $ usdream : chr "american dream is important and achievable for me" "american dream is important and achievable for me" "american dream is not important and maybe not achievable for me" "american dream is not important and maybe not achievable for me" ...
## $ npi : num 0.6923 0.1538 0.0769 0.0769 0.7692 ...
## $ exploit : num 2 3.67 4.33 1.67 4 ...
## $ stress : num 3.3 3.3 4 3.2 3.1 3.5 3.3 2.4 2.9 2.7 ...Subsetting Data
# for the HW: use the codebook you created in the codebook activity to get the names of your variables (first column)
# enter this list of names in the select=c() argument to subset those columns from the dataframe
# variables for the lab: id, variable2, variable3, variable5, variable8, variable10, variable11
d <- subset(df, select=c(gender, income, moa_maturity, idea, support, npi))
# this is where I will list my own variables, very important!Recoding Variables
# categorical variables need to be recoded as factors
# the content of the variable will stay the same, but R will treat the variable differently at times
d$gender <- as.factor(d$gender)
d$income <- as.factor(d$income)
str(d)## 'data.frame': 3182 obs. of 6 variables:
## $ gender : Factor w/ 3 levels "f","m","nb": 1 2 2 1 2 1 1 1 1 1 ...
## $ income : Factor w/ 4 levels "1 low","2 middle",..: 1 1 4 4 2 4 1 1 3 4 ...
## $ moa_maturity: num 3.67 3.33 3.67 3 3.67 ...
## $ idea : num 3.75 3.88 3.75 3.75 3.5 ...
## $ support : num 6 6.75 5.17 5.58 6 ...
## $ npi : num 0.6923 0.1538 0.0769 0.0769 0.7692 ...Missing Data
We lose 71 data, and current sample size is 3111.31 participants skip question about moa_maturity; 21 participants skip questions about income. Those scenarios are worth to be discussed.
# use the gg_miss_upset() command for a visualization of your missing data
gg_miss_upset(d[-1], nsets = 6)
# use the na.omit() command to create a new dataframe in which any participants with missing data are dropped from the dataframe
d2 <- na.omit(d)
3111/3182## [1] 0.9776870.978## [1] 0.978Exporting Data
# last step is to export the data after you've dropped NAs
# for the HW, the file you're exporting here is what you'll use for all future HW assignments (labs will use the files I provide you)
# make sure you give it a name that is memorable!
# and make sure you save it to your Data folder!
write.csv(d2, file="DATA/eammi2_data_final_cleaned.csv", row.names = F)
# since we've created a cleaned dataframe in d2, we'll use that for the rest of the lab/HWBasic Statistics
Univariate Plots: Histograms & Tables
table(d2$gender)##
## f m nb
## 2278 780 53table(d2$income)##
## 1 low 2 middle 3 high rather not say
## 864 872 529 846hist(d2$moa_maturity)
hist(d2$idea)
hist(d2$support)
hist(d2$npi)
Univariate Normality
Talk about skew and kurtosis here: we analyzed the skew and kurtosis of our variables and all were wthin the acceptance range (-2 to +2) except to the kurtosis of “idea”, which is 4.48.However, for this analysis, we will use them anyway.
describe(d2)## vars n mean sd median trimmed mad min max range skew
## gender* 1 3111 1.28 0.49 1.00 1.21 0.00 1 3 2 1.39
## income* 2 3111 2.44 1.16 2.00 2.42 1.48 1 4 3 0.14
## moa_maturity 3 3111 3.59 0.43 3.67 3.65 0.49 1 4 3 -1.20
## idea 4 3111 3.58 0.38 3.62 3.62 0.37 1 4 3 -1.53
## support 5 3111 5.54 1.12 5.75 5.66 0.99 0 7 7 -1.10
## npi 6 3111 0.28 0.31 0.15 0.24 0.23 0 1 1 0.94
## kurtosis se
## gender* 0.85 0.01
## income* -1.43 0.02
## moa_maturity 1.90 0.01
## idea 4.48 0.01
## support 1.44 0.02
## npi -0.69 0.01Bivariate Plots
Crosstabs
cross_cases(d2, gender, income)| income | ||||
|---|---|---|---|---|
| 1 low | 2 middle | 3 high | rather not say | |
| gender | ||||
| f | 631 | 657 | 371 | 619 |
| m | 216 | 203 | 154 | 207 |
| nb | 17 | 12 | 4 | 20 |
| #Total cases | 864 | 872 | 529 | 846 |
Scatterplots
plot(d2$support, d2$npi,
main="Scatterplot of support and npi",
xlab = "support",
ylab = "npi")
plot(d2$idea, d2$moa_maturity,
main="Scatterplot of idea and moa_maturity",
xlab = "idea",
ylab = "moa_maturity")
Boxplots
boxplot(data=d2, gender~npi,
main="Boxplot of npi and gender",
xlab = "npi",
ylab = "gender")