P421 HW - Data Prep & Basic Statistics
Maggie Lowe
2024-02-25
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 all non-grouping columns: take_all(mtcars, mean, 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(race_rc, income, stress, support, swb, moa_independence))
# this is where i will list my variables!!! very important!
# subset creates a subset from data; d = what the subset dataframe will be named; df = dataframe you're taking data from; select = which collumns to grab; =c tells which arguments to grabRecoding 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$race_rc <- as.factor(d$race_rc)
d$income <- as.factor(d$income)
str(d)## 'data.frame': 3182 obs. of 6 variables:
## $ race_rc : Factor w/ 7 levels "asian","black",..: 7 7 7 6 7 7 7 7 4 4 ...
## $ income : Factor w/ 4 levels "1 low","2 middle",..: 1 1 4 4 2 4 1 1 3 4 ...
## $ stress : num 3.3 3.3 4 3.2 3.1 3.5 3.3 2.4 2.9 2.7 ...
## $ support : num 6 6.75 5.17 5.58 6 ...
## $ swb : num 4.33 4.17 1.83 5.17 3.67 ...
## $ moa_independence: num 3.67 3.67 3.5 3 3.83 ...Missing Data
I looked at the missing data in my dataset, and found that about 3% of the participants in the sample skipped at least one item. The variable “moa_independence” had the highest number of missing data, with income being the second most missed data. There were a few other variables that participants did not answer, including stress, swb, and support. Overall, I did not notice any significany patterns in the data. I dropped these participants from our analysis, which is not advisable and runs the risk of dropping vulnerable groups or skewing results. However, I will proceed for the sake of this class using the reduced dataset.
# 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)
# 3079/3182 = 0.97 Exporting 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_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$race_rc)##
## asian black hispanic multiracial nativeamer other
## 201 233 279 285 10 91
## white
## 1980table(d2$income)##
## 1 low 2 middle 3 high rather not say
## 857 866 521 835hist(d2$stress)
hist(d2$support)
hist(d2$swb)
hist(d2$moa_independence)
Univariate Normality
We analyzed the skew and kurotisis of our EAMMI2 data, and all but one were within the accepted range (-2/+2). However, one variable (moa_independence) was outside of the accepted range as it had a kurtosis of 2.51. For this analysis, we will use them anyway, but outside of this class this is bad practice.
describe(d2) #look to see if skew and kurtosis are between -2 and 2 ## vars n mean sd median trimmed mad min max range skew
## race_rc* 1 3079 5.55 2.12 7.00 5.90 0.00 1.0 7.0 6.0 -1.00
## income* 2 3079 2.43 1.16 2.00 2.42 1.48 1.0 4.0 3.0 0.15
## stress 3 3079 3.05 0.60 3.00 3.05 0.59 1.3 4.7 3.4 0.04
## support 4 3079 5.54 1.13 5.75 5.66 0.99 0.0 7.0 7.0 -1.12
## swb 5 3079 4.47 1.32 4.67 4.53 1.48 1.0 7.0 6.0 -0.37
## moa_independence 6 3079 3.54 0.47 3.67 3.61 0.49 1.0 4.0 3.0 -1.44
## kurtosis se
## race_rc* -0.64 0.04
## income* -1.43 0.02
## stress -0.17 0.01
## support 1.50 0.02
## swb -0.45 0.02
## moa_independence 2.51 0.01Bivariate Plots
Crosstabs
cross_cases(d2, race_rc, income) #categorical variables | income | ||||
|---|---|---|---|---|
| 1 low | 2 middle | 3 high | rather not say | |
| race_rc | ||||
| asian | 44 | 45 | 28 | 84 |
| black | 82 | 59 | 21 | 71 |
| hispanic | 100 | 102 | 14 | 63 |
| multiracial | 95 | 77 | 46 | 67 |
| nativeamer | 2 | 3 | 3 | 2 |
| other | 28 | 14 | 8 | 41 |
| white | 506 | 566 | 401 | 507 |
| #Total cases | 857 | 866 | 521 | 835 |
Scatterplots
plot(d2$stress, d2$support,
main="Scatterplot of stress and support",
xlab = "stress",
ylab = "support")
plot(d2$swb, d2$moa_independence,
main="Scatterplot of swb and moa_independence",
xlab = "swb",
ylab = "moa_independence")
Boxplots
boxplot(data=d2, swb~income, # ~ means function of
main="Boxplot of income and swb", #x-axis is categorical, y-axis is continuous
xlab = "x (income)",
ylab = "Y (swb)")
boxplot(data=d2, stress~race_rc, # ~ means function of
main="Boxplot of race_rc and stress", #x-axis is categorical, y-axis is continuous
xlab = "x (race_rc)",
ylab = "Y (stress)")