P421 Lab - Data Prep & Basic Statistics
Heather Perkins
2024-02-22
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 modify variables or add new variables:
## let(mtcars, new_var = 42, new_var2 = new_var*hp) %>% head()##
## 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/arc_data_final-1.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] "X" "gender" "trans"
## [4] "sexual_orientation" "ethnicity" "relationship_status"
## [7] "age" "urban_rural" "income"
## [10] "education" "employment" "treatment"
## [13] "health" "mhealth" "sleep_hours"
## [16] "exercise_cat" "pet" "covid_pos"
## [19] "covid_neg" "big5_open" "big5_con"
## [22] "big5_agr" "big5_neu" "big5_ext"
## [25] "pswq_std" "iou" "mfq_26"
## [28] "mfq_state" "rse" "school_covid_support"
## [31] "school_att" "pas_covid" "pss"
## [34] "phq" "gad" "edeq12"
## [37] "brs" "swemws" "isolation"
## [40] "support"head(df)## X gender trans sexual_orientation ethnicity
## 1 1 female no Heterosexual/Straight White - British, Irish, other
## 2 20 male no Heterosexual/Straight White - British, Irish, other
## 3 30 female no Heterosexual/Straight White - British, Irish, other
## 4 31 female no Heterosexual/Straight White - British, Irish, other
## 5 32 <NA> <NA> <NA> <NA>
## 6 33 female no Heterosexual/Straight White - British, Irish, other
## relationship_status age urban_rural
## 1 In a relationship/married and cohabiting <NA> city
## 2 Prefer not to say 1 under 18 city
## 3 Prefer not to say 1 under 18 city
## 4 In a relationship/married and cohabiting 4 between 36 and 45 town
## 5 <NA> <NA> <NA>
## 6 In a relationship/married and cohabiting 4 between 36 and 45 city
## income education employment
## 1 3 high 6 graduate degree or higher 3 employed
## 2 <NA> prefer not to say 1 high school equivalent
## 3 <NA> 2 equivalent to high school completion 1 high school equivalent
## 4 2 middle 5 undergraduate degree 3 employed
## 5 <NA> <NA> <NA>
## 6 2 middle 6 graduate degree or higher 3 employed
## treatment health mhealth
## 1 no psychological disorders something else or not applicable none or NA
## 2 in treatment something else or not applicable anxiety disorder
## 3 not in treatment something else or not applicable none or NA
## 4 no psychological disorders two conditions none or NA
## 5 <NA> <NA> none or NA
## 6 not in treatment something else or not applicable none or NA
## sleep_hours exercise_cat pet covid_pos covid_neg
## 1 3 7-8 hours 1 less than 1 hour cat 0 0
## 2 2 5-6 hours 2 1-2 hours cat 0 0
## 3 3 7-8 hours 3 2-5 hours dog 0 0
## 4 2 5-6 hours 2 1-2 hours no pets 0 0
## 5 <NA> <NA> <NA> 0 0
## 6 3 7-8 hours 2 1-2 hours multiple types of pet 0 0
## big5_open big5_con big5_agr big5_neu big5_ext pswq_std iou mfq_26
## 1 5.333333 6.000000 4.333333 6.000000 2.000000 2.3094514 3.185185 4.20
## 2 5.333333 3.333333 4.333333 6.666667 1.666667 0.8509744 4.000000 3.35
## 3 5.000000 5.333333 6.666667 4.000000 6.000000 -1.1235082 1.592593 4.65
## 4 6.000000 5.666667 4.666667 4.000000 5.000000 1.1626810 3.370370 4.65
## 5 NA NA NA NA NA NA NA NA
## 6 5.000000 6.000000 6.333333 2.666667 NA -0.3424552 1.703704 4.50
## mfq_state rse school_covid_support school_att pas_covid pss phq
## 1 3.625 2.3 NA NA 3.222222 3.25 1.333333
## 2 3.000 1.6 NA NA 4.555556 3.75 3.333333
## 3 5.875 3.9 NA NA 3.333333 1.00 1.000000
## 4 4.000 1.7 NA NA 4.222222 3.25 2.333333
## 5 NA NA NA NA NA NA NA
## 6 4.625 3.9 NA NA 3.222222 2.00 1.111111
## gad edeq12 brs swemws isolation support
## 1 1.857143 1.583333 NA 2.857143 2.25 2.500000
## 2 3.857143 1.833333 NA 2.285714 3.50 2.166667
## 3 1.142857 1.000000 NA 4.285714 1.00 5.000000
## 4 2.000000 1.666667 NA 3.285714 2.50 2.500000
## 5 NA NA NA NA NA NA
## 6 1.428571 1.416667 NA 4.000000 1.75 3.666667str(df)## 'data.frame': 2073 obs. of 40 variables:
## $ X : int 1 20 30 31 32 33 48 49 57 58 ...
## $ gender : chr "female" "male" "female" "female" ...
## $ trans : chr "no" "no" "no" "no" ...
## $ sexual_orientation : chr "Heterosexual/Straight" "Heterosexual/Straight" "Heterosexual/Straight" "Heterosexual/Straight" ...
## $ ethnicity : chr "White - British, Irish, other" "White - British, Irish, other" "White - British, Irish, other" "White - British, Irish, other" ...
## $ relationship_status : chr "In a relationship/married and cohabiting" "Prefer not to say" "Prefer not to say" "In a relationship/married and cohabiting" ...
## $ age : chr NA "1 under 18" "1 under 18" "4 between 36 and 45" ...
## $ urban_rural : chr "city" "city" "city" "town" ...
## $ income : chr "3 high" NA NA "2 middle" ...
## $ education : chr "6 graduate degree or higher" "prefer not to say" "2 equivalent to high school completion" "5 undergraduate degree" ...
## $ employment : chr "3 employed" "1 high school equivalent" "1 high school equivalent" "3 employed" ...
## $ treatment : chr "no psychological disorders" "in treatment" "not in treatment" "no psychological disorders" ...
## $ health : chr "something else or not applicable" "something else or not applicable" "something else or not applicable" "two conditions" ...
## $ mhealth : chr "none or NA" "anxiety disorder" "none or NA" "none or NA" ...
## $ sleep_hours : chr "3 7-8 hours" "2 5-6 hours" "3 7-8 hours" "2 5-6 hours" ...
## $ exercise_cat : chr "1 less than 1 hour" "2 1-2 hours" "3 2-5 hours" "2 1-2 hours" ...
## $ pet : chr "cat" "cat" "dog" "no pets" ...
## $ covid_pos : int 0 0 0 0 0 0 0 0 0 0 ...
## $ covid_neg : int 0 0 0 0 0 0 0 0 0 0 ...
## $ big5_open : num 5.33 5.33 5 6 NA ...
## $ big5_con : num 6 3.33 5.33 5.67 NA ...
## $ big5_agr : num 4.33 4.33 6.67 4.67 NA ...
## $ big5_neu : num 6 6.67 4 4 NA ...
## $ big5_ext : num 2 1.67 6 5 NA ...
## $ pswq_std : num 2.309 0.851 -1.124 1.163 NA ...
## $ iou : num 3.19 4 1.59 3.37 NA ...
## $ mfq_26 : num 4.2 3.35 4.65 4.65 NA 4.5 NA 4.3 5.25 4.45 ...
## $ mfq_state : num 3.62 3 5.88 4 NA ...
## $ rse : num 2.3 1.6 3.9 1.7 NA 3.9 NA 2.4 1.8 NA ...
## $ school_covid_support: num NA NA NA NA NA NA NA NA NA NA ...
## $ school_att : num NA NA NA NA NA NA NA NA NA NA ...
## $ pas_covid : num 3.22 4.56 3.33 4.22 NA ...
## $ pss : num 3.25 3.75 1 3.25 NA 2 NA 2 4 1.25 ...
## $ phq : num 1.33 3.33 1 2.33 NA ...
## $ gad : num 1.86 3.86 1.14 2 NA ...
## $ edeq12 : num 1.58 1.83 1 1.67 NA ...
## $ brs : num NA NA NA NA NA NA NA NA NA NA ...
## $ swemws : num 2.86 2.29 4.29 3.29 NA ...
## $ isolation : num 2.25 3.5 1 2.5 NA 1.75 NA 2 1.25 1 ...
## $ support : num 2.5 2.17 5 2.5 NA ...Subsetting Data
I had to change one of my variables, as covid_neg had 0’s for every value and was not functional for this purpose. I replaced it with the GAD as I feel it will still give me similar results for analysis
# 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(health, mhealth, gad, phq, iou, pas_covid))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$health <- as.factor(d$health)
d$mhealth <- as.factor(d$mhealth)
str(d)## 'data.frame': 2073 obs. of 6 variables:
## $ health : Factor w/ 11 levels "cancer","diabetes",..: 9 9 9 11 NA 9 9 9 11 11 ...
## $ mhealth : Factor w/ 8 levels "anxiety disorder",..: 5 1 5 5 5 5 3 5 1 5 ...
## $ gad : num 1.86 3.86 1.14 2 NA ...
## $ phq : num 1.33 3.33 1 2.33 NA ...
## $ iou : num 3.19 4 1.59 3.37 NA ...
## $ pas_covid: num 3.22 4.56 3.33 4.22 NA ...Missing Data
When looking at the missing variables, we’re able to see that nearly 500 people did not answer or finish answering the questions for three of the variables on top of the 300+ others who didn’t answer a combination of other questions. This leaves us with only 54% of our variables left to use. For this course we’ll continue to use this data even if it isn’t advisable
# 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)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/Covid_Data_Final.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$health)##
## cancer diabetes
## 2 3
## heart disease high blood pressure
## 2 22
## lung disease other chronic health condition
## 52 27
## other disability prefer not to say
## 27 22
## something else or not applicable three or more conditions
## 908 9
## two conditions
## 39table(d2$mhealth)##
## anxiety disorder bipolar
## 114 3
## depression eating disorders
## 29 26
## none or NA obsessive compulsive disorder
## 862 27
## other ptsd
## 30 22hist(d2$gad)
hist(d2$phq)
hist(d2$iou)
hist(d2$pas_covid)
Univariate Normality
For our four continuous variables, we see that they fall within the range of -2/+2, so everything seems to be in order for our data usage.
describe(d2)## vars n mean sd median trimmed mad min max range skew kurtosis
## health* 1 1113 8.61 1.37 9.00 8.92 0.00 1 11 10 -2.32 6.08
## mhealth* 2 1113 4.64 1.41 5.00 4.88 0.00 1 8 7 -1.42 2.59
## gad 3 1113 2.04 0.92 1.71 1.95 0.85 1 4 3 0.69 -0.72
## phq 4 1113 2.07 0.87 1.89 1.99 0.99 1 4 3 0.64 -0.68
## iou 5 1113 2.56 0.91 2.41 2.50 0.99 1 5 4 0.51 -0.56
## pas_covid 6 1113 3.23 0.69 3.22 3.24 0.66 1 5 4 -0.18 -0.03
## se
## health* 0.04
## mhealth* 0.04
## gad 0.03
## phq 0.03
## iou 0.03
## pas_covid 0.02Bivariate Plots
Crosstabs
cross_cases(d2, health, mhealth)|  mhealth | ||||||||
|---|---|---|---|---|---|---|---|---|
|  anxiety disorder |  bipolar |  depression |  eating disorders |  none or NA |  obsessive compulsive disorder |  other |  ptsd | |
|  health | ||||||||
|    cancer | 2 | |||||||
|    diabetes | 1 | 2 | ||||||
|    heart disease | 1 | 1 | ||||||
|    high blood pressure | 2 | 1 | 18 | 1 | ||||
|    lung disease | 6 | 46 | ||||||
|    other chronic health condition | 5 | 1 | 1 | 19 | 1 | |||
|    other disability | 6 | 2 | 1 | 11 | 4 | 2 | 1 | |
|    prefer not to say | 3 | 2 | 12 | 2 | 1 | 2 | ||
|    something else or not applicable | 83 | 3 | 21 | 22 | 729 | 19 | 17 | 14 |
|    three or more conditions | 1 | 1 | 1 | 5 | 1 | |||
|    two conditions | 8 | 2 | 1 | 21 | 4 | 3 | ||
|    #Total cases | 114 | 3 | 29 | 26 | 862 | 27 | 30 | 22 |
Scatterplots
plot(d2$gad, d2$iou,
main="Scatterplot of IOU and GAD",
xlab = "IOU",
ylab = "GAD")
plot(d2$phq, d2$pas_covid,
main="Scatterplot of PAS and PHQ",
xlab = "PAS",
ylab = "PHQ")
Boxplots
boxplot(data=d2, gad~mhealth,
main="Boxplot of gad and mhealth",
xlab = "mhealth (Categorical)",
ylab = "gad (Continuous)")
boxplot(data=d2, phq~health,
main="Boxplot of health and phq",
xlab = "health (Categorical)",
ylab = "phq (Continuous)")
boxplot(data=d2, iou~mhealth,
main="Boxplot of mhealth and iou",
xlab = "mhealth (Categorical)",
ylab = "iou (Continuous)")