#Part A

readcsv(HINTSData_2020_clean.csv, header=TRUE)#download data

hintsdata<-HINTSData_2020_clean #renaming the data to something more simple

summary(hintsdata)

neededvariables<-c(“HHID”, “PersonID”, “QualityCare”, “Age”, “BirthGender”, “smokeStat”, “RaceEthn5”, “AvgDrinksPerWeek”, “WeeklyMinutesModerateExercise”, “BMI”)#selecting the variables needed for analysis hintsdataclean<-hintsdata[neededvariables]#putting the needed variables into their own subset

summary(hintsdataclean) #checking output

##OUTPUT

summary(hintsdata) HHID PersonID QualityCare HealthInsurance Age BirthGender
Min. :11000012 Length:2402 Min. :1.000 Min. :1.000 Min. : 18.00 Min. :1.000
1st Qu.:11002591 Class :character 1st Qu.:1.000 1st Qu.:1.000 1st Qu.: 43.00 1st Qu.:1.000
Median :11005968 Mode :character Median :2.000 Median :1.000 Median : 58.00 Median :2.000
Mean :11006770 Mean :2.003 Mean :1.034 Mean : 55.59 Mean :1.585
3rd Qu.:11010856 3rd Qu.:3.000 3rd Qu.:1.000 3rd Qu.: 68.00 3rd Qu.:2.000
Max. :11015347 Max. :5.000 Max. :2.000 Max. :100.00 Max. :2.000
FullTimeOcc_Cat MaritalStatus SexualOrientation AgeGrpB EducA RaceEthn5
Min. :1.000 Min. :1.000 Min. : 1.000 Min. :1.000 Min. :-9.00 Min. :1.000
1st Qu.:1.000 1st Qu.:1.000 1st Qu.: 1.000 1st Qu.:2.000 1st Qu.: 3.00 1st Qu.:1.000
Median :2.000 Median :1.000 Median : 1.000 Median :3.000 Median : 4.00 Median :1.000
Mean :2.974 Mean :2.556 Mean : 2.086 Mean :2.974 Mean : 3.22 Mean :1.695
3rd Qu.:5.000 3rd Qu.:4.000 3rd Qu.: 1.000 3rd Qu.:4.000 3rd Qu.: 4.00 3rd Qu.:2.000
Max. :9.000 Max. :6.000 Max. :91.000 Max. :5.000 Max. : 4.00 Max. :5.000
HHInc BMI smokeStat WeeklyMinutesModerateExercise AvgDrinksPerWeek Min. :1.000 Min. :10.90 Min. :1.000 Min. : 0.0 Min. : 0.000
1st Qu.:2.000 1st Qu.:24.00 1st Qu.:2.000 1st Qu.: 0.0 1st Qu.: 0.000
Median :4.000 Median :27.50 Median :3.000 Median : 90.0 Median : 0.000
Mean :3.654 Mean :28.61 Mean :2.535 Mean : 161.8 Mean : 3.358
3rd Qu.:5.000 3rd Qu.:31.90 3rd Qu.:3.000 3rd Qu.: 210.0 3rd Qu.: 4.000
Max. :5.000 Max. :73.80 Max. :3.000 Max. :4620.0 Max. :70.000

#B.1

#continuous variables in the dataset: age, AvgDrinks, exercise, & BMI attach(hintsdataclean)

#Age Variable

mean(Age) # Provides the mean of the data

sd(Age) # Provides the standard deviation of the data

var(Age)#Provides variance of the variable

min(Age)

median(Age)

quantile(Age)

max(Age)

##OUTPUT

mean(Age) # Provides the mean of the data [1] 55.59117 sd(Age) # Provides the standard deviation of the data [1] 16.57902 var(Age)#Provides variance of the variable [1] 274.864 min(Age) [1] 18 median(Age) [1] 58 quantile(Age) 0% 25% 50% 75% 100% 18 43 58 68 100 max(Age) [1] 100

#Drinks per week variable

mean(AvgDrinksPerWeek)

sd(AvgDrinksPerWeek)

var(AvgDrinksPerWeek)

min(AvgDrinksPerWeek)

max(AvgDrinksPerWeek)

median(AvgDrinksPerWeek)

quantile(AvgDrinksPerWeek)

##OUPUT

mean(AvgDrinksPerWeek) [1] 3.358035 sd(AvgDrinksPerWeek) [1] 6.588142 var(AvgDrinksPerWeek) [1] 43.40362 min(AvgDrinksPerWeek) [1] 0 max(AvgDrinksPerWeek) [1] 70 median(AvgDrinksPerWeek) [1] 0 quantile(AvgDrinksPerWeek) 0% 25% 50% 75% 100% 0 0 0 4 70

#Exercise Variable

mean(WeeklyMinutesModerateExercise)

sd(WeeklyMinutesModerateExercise)

var(WeeklyMinutesModerateExercise)

min(WeeklyMinutesModerateExercise)

max(WeeklyMinutesModerateExercise)

median(WeeklyMinutesModerateExercise)

quantile(WeeklyMinutesModerateExercise)

##OUTPUT

mean(WeeklyMinutesModerateExercise) [1] 161.7818 sd(WeeklyMinutesModerateExercise) [1] 271.1893 var(WeeklyMinutesModerateExercise) [1] 73543.61 min(WeeklyMinutesModerateExercise) [1] 0 max(WeeklyMinutesModerateExercise) [1] 4620 median(WeeklyMinutesModerateExercise) [1] 90 quantile(WeeklyMinutesModerateExercise) 0% 25% 50% 75% 100% 0 0 90 210 4620

#BMI Variable

mean(BMI)

sd(BMI)

var(BMI)

min(BMI)

max(BMI)

median(BMI)

quantile(BMI)

##OUTPUT

mean(BMI) [1] 28.60704 sd(BMI) [1] 6.538369 var(BMI) [1] 42.75028 min(BMI) [1] 10.9 max(BMI) [1] 73.8 median(BMI) [1] 27.5 quantile(BMI) 0% 25% 50% 75% 100% 10.9 24.0 27.5 31.9 73.8

#B.2.1

Dyplr library(dplyr) #load dyplr

help(dplyr) #tells me more about how to use dplyr

summary(Age) #gives all components needed (min, max, median, mean, and 1st quartile) EXCEPT variance

summary(AvgDrinksPerWeek)

summary(WeeklyMinutesModerateExercise)

summary(BMI)

##OUTPUT

summary(Age)#gives all components of the 5 number summary(min, max, median, mean, and 1st quartile)

Min. 1st Qu. Median Mean 3rd Qu. Max. 18.00 43.00 58.00 55.59 68.00 100.00 summary(AvgDrinksPerWeek)

Min. 1st Qu. Median Mean 3rd Qu. Max. 0.000 0.000 0.000 3.358 4.000 70.000 summary(WeeklyMinutesModerateExercise)

Min. 1st Qu. Median Mean 3rd Qu. Max. 0.0 0.0 90.0 161.8 210.0 4620.0

summary(BMI)

Min. 1st Qu. Median Mean 3rd Qu. Max. 10.90 24.00 27.50 28.61 31.90 73.80

#using group_by from dyplr allows me to include what is not in the summary function for each cont. variable, while stratifying by smoking

#Age

summary_continuous_Age<-hintsdataclean %>%

group_by(smokeStat) %>%

summarize(

min_Age = min(Age),

max_Age = max(Age),

Median = median(Age),

Q1_Age = quantile(Age, 0.25),

Q3_Age = quantile(Age, 0.75),

mean_Age = mean(Age),

sd_Age = sd(Age),

var_Age = var(Age)

)

print(summary_continuous_Age)

##OUTPUT

A tibble: 3 × 9

smokeStat min_Age max_Age Median Q1_Age Q3_Age mean_Age sd_Age var_Age 1 1 19 87 57 44 65 54.5 14.5 212. 2 2 21 98 64 52 72 61.4 14.8 219. 3 3 18 100 55 39 66 53.4 17.0 290.

#Drinks

summary_continuous_AvgDrinksPerWeek<-hintsdataclean %>%

group_by(smokeStat) %>%

summarize(

min_Drinks = min(AvgDrinksPerWeek),

max_Drinks = max(AvgDrinksPerWeek),

Median_Drinks = median(AvgDrinksPerWeek),

Q1_Drinks = quantile(AvgDrinksPerWeek, 0.25),

Q3_Drinks = quantile(AvgDrinksPerWeek, 0.75),

mean_Drinks = mean(AvgDrinksPerWeek),

sd_Drinks = sd(AvgDrinksPerWeek),

var_Drinks = var(AvgDrinksPerWeek)

)

print(summary_continuous_AvgDrinksPerWeek)

##OUTPUT

print(summary_continuous_AvgDrinksPerWeek)

# A tibble: 3 × 9 smokeStat min_Drinks max_Drinks Median_Drinks Q1_Drinks Q3_Drinks mean_Drinks sd_Drinks var_Drinks 1 1 0 70 0 0 6 4.87 9.31 86.7 2 2 0 56 1 0 6 4.41 7.78 60.5 3 3 0 63 0 0 3 2.68 5.31 28.2

#Exercise

summary_continuous_WeeklyMinutesModerateExcercise<-hintsdataclean %>%

group_by(smokeStat) %>%

summarize(

min_Exercise = min(WeeklyMinutesModerateExercise),

max_Exercise = max(WeeklyMinutesModerateExercise),

Median_Exercise = median(WeeklyMinutesModerateExercise),

Q1_Exercise = quantile(WeeklyMinutesModerateExercise, 0.25),

Q3_Exercise = quantile(WeeklyMinutesModerateExercise, 0.75),

mean_Exercise = mean(WeeklyMinutesModerateExercise),

sd_Exercise = sd(WeeklyMinutesModerateExercise),

var_Exercise = var(WeeklyMinutesModerateExercise)

)

print(summary_continuous_WeeklyMinutesModerateExcercise)

##OUTPUT

print(summary_continuous_WeeklyMinutesModerateExcercise)

# A tibble: 3 × 9 smokeStat min_Exercise max_Exercise Median_Exercise Q1_Exercise Q3_Exercise mean_Exercise sd_Exercise 1 1 0 3500 60 0 180 154. 310. 2 2 0 3360 90 0 210 174. 305. 3 3 0 4620 90 20 210 158. 249. # ℹ 1 more variable: var_Exercise

#BMI

summary_continuous_BMI<-hintsdataclean %>%

group_by(smokeStat) %>%

summarize(

min_BMI = min(BMI),

max_BMI = max(BMI),

Median_BMI = median(BMI),

Q1_BMI = quantile(BMI, 0.25),

Q3_BMI = quantile(BMI, 0.75),

mean_BMI = mean(BMI),

sd_BMI = sd(BMI),

var_BMI = var(BMI)

)

print(summary_continuous_BMI)

##OUTPUT

print(summary_continuous_BMI)

# A tibble: 3 × 9 smokeStat min_BMI max_BMI Median_BMI Q1_BMI Q3_BMI mean_BMI sd_BMI var_BMI 1 1 15.1 58.7 27.6 23.9 33.3 28.7 6.60 43.6 2 2 13.8 56.7 27.8 24.2 32.1 28.8 6.34 40.2 3 3 10.9 73.8 27.5 23.8 31.6 28.5 6.61 43.7

#Interpretation

The output for B.1 indicates that the average age of the data set is about 56 years. Participants generally reported positive experiences with their quality of care, with most ratings between “very good” and “good.” Most participants seemed to range from nonsmokers to former smokers and reported low alcohol consumption, with many indicating no drinks per week. On average, participants engaged in moderate physical activity for around162 minutes per week, though there are participants who reported very high and low levels of exercise. The mean BMI was 28.6.

#B.2.2

library(skimr) #the skim function shows the whole 5 number summary(median, min, max, 1st, and 3rd quartiles), as well as the standard deviation

help(skimr) #to help understand how to get variance into the skimr function

my_skim <- skim_with( numeric = sfl( mean = mean, sd = sd, var = var, min = min, quart25 = ~quantile(., 0.25), median = median, quartp75 = ~quantile(., 0.75), max = max ), append=FALSE )

#the above makes a custom skimmer, as the original skimr function does not include variance

my_skim(hintsdataclean, Age)

my_skim(hintsdataclean, BMI)

my_skim(hintsdataclean, WeeklyMinutesModerateExercise)

my_skim(hintsdataclean, AvgDrinksPerWeek) #running each of the categorical variables above to make sure the output is right

##OUTPUT

my_skim(hintsdataclean, Age) ── Data Summary ──────────────────────── Values
Name hintsdataclean Number of rows 2402
Number of columns 10
_______________________
Column type frequency:
numeric 1
________________________
Group variables None

── Variable type: numeric ─────────────────────────────────────────────────────────────────────────────── skim_variable n_missing complete_rate mean sd var min quart25 median quartp75 max 1 Age 0 1 55.6 16.6 275. 18 43 58 68 100 > my_skim(hintsdataclean, BMI) ── Data Summary ──────────────────────── Values
Name hintsdataclean Number of rows 2402
Number of columns 10
_______________________
Column type frequency:
numeric 1
________________________
Group variables None

── Variable type: numeric ─────────────────────────────────────────────────────────────────────────────── skim_variable n_missing complete_rate mean sd var min quart25 median quartp75 max 1 BMI 0 1 28.6 6.54 42.8 10.9 24 27.5 31.9 73.8 > my_skim(hintsdataclean, WeeklyMinutesModerateExercise) ── Data Summary ──────────────────────── Values
Name hintsdataclean Number of rows 2402
Number of columns 10
_______________________
Column type frequency:
numeric 1
________________________
Group variables None

── Variable type: numeric ─────────────────────────────────────────────────────────────────────────────── skim_variable n_missing complete_rate mean sd var min quart25 median quartp75 max 1 WeeklyMinutesModerateExercise 0 1 162. 271. 73544. 0 0 90 210 4620 > my_skim(hintsdataclean, AvgDrinksPerWeek) ── Data Summary ──────────────────────── Values
Name hintsdataclean Number of rows 2402
Number of columns 10
_______________________
Column type frequency:
numeric 1
________________________
Group variables None

#interpretation

Based on this analysis, former smokers are older on average compared to current smokers. Alcohol consumption is generally low across all groups, and there does not seem to be a major difference in physical activity or BMI when stratified by smoking status. These results suggest that while age differs by smoking category, other health variables remain relatively consistent in these participants.

#B.3

my_summary_func<- function(x) { list( mean_x = mean(x), #gives the mean

sd_x = sd(x), #gives the standard deviation

min_x = min(x), #finds the minimum

max_x = max(x),#finds the maximum

median_x = median(x),

quantile_x = quantile(x),

var_x = var(x))

}#closes the function

my_summary_func(Age) my_summary_func(BMI)

my_summary_func(WeeklyMinutesModerateExercise)

my_summary_func(AvgDrinksPerWeek)

##OUTPUT

my_summary_func(Age)

$mean_x [1] 55.59117

$sd_x [1] 16.57902

$min_x [1] 18

$max_x [1] 100

$median_x [1] 58

$quantile_x 0% 25% 50% 75% 100% 18 43 58 68 100

$var_x [1] 274.864

my_summary_func(BMI)

$mean_x [1] 28.60704

$sd_x [1] 6.538369

$min_x [1] 10.9

$max_x [1] 73.8

$median_x [1] 27.5

$quantile_x 0% 25% 50% 75% 100% 10.9 24.0 27.5 31.9 73.8

$var_x [1] 42.75028

my_summary_func(WeeklyMinutesModerateExercise)

$mean_x [1] 161.7818

$sd_x [1] 271.1893

$min_x [1] 0

$max_x [1] 4620

$median_x [1] 90

$quantile_x 0% 25% 50% 75% 100% 0 0 90 210 4620

$var_x [1] 73543.61

my_summary_func(AvgDrinksPerWeek)

$mean_x [1] 3.358035

$sd_x [1] 6.588142

$min_x [1] 0

$max_x [1] 70

$median_x [1] 0

$quantile_x 0% 25% 50% 75% 100% 0 0 0 4 70

$var_x [1] 43.40362

#B.4.1

#Pie Chart for Race and Ethnicity

pie_RaceEthn5 <- hintsdataclean$RaceEthn5 #selecting and plotting the race variable

pie_raceEthn_table <- table(pie_RaceEthn5)#freq table of selected variables

labels <- c(‘Non-Hispanic White’, ‘Non-Hispanic Black or African American’, ‘Hispanic’, ‘Non-Hispanic Asian’, ‘Non-Hispanic Other’)#plotting the chart and adding labels, all labels are from the HINTS data codebook

pie(pie_raceEthn_table, labels, main=“HINTS Data Race and Ethnicity Pie Chart”, col=rainbow(length(pie_raceEthn_table))) legend(“topright”, c(‘Non-Hispanic White’, ‘Non-Hispanic Black or African American’, ‘Hispanic’, ‘Non-Hispanic Asian’, ‘Non-Hispanic Other’), cex=.4, fill=rainbow(length(pie_raceEthn_table)))

##OUTPUT

#Interpretation

The pie chart for race and ethnicity shows that the predominant group seems to be non-hispanic white individuals, followed by Hispanic black or African American and Hispanic where around the same amount of the participants fall. The final group is Non hispanic other and non hispanic Asian which are the 2 lowest categories of race and ethincity.

#Bar Plot of Quality of Care

bar_Qualitycare <- hintsdataclean$QualityCare bar_Qualitycare_table <- table(bar_Qualitycare) labels_qualitycare <- c(‘Excellent’, ‘Very Good’, ‘Good’, ‘Fair’, ‘Poor’)#labels for the quality of care variable barplot(bar_Qualitycare_table, names.arg=labels_qualitycare, xlab=“Quality of Care”, ylab=“Count”, col=“pink”, main=“Quality of Care Bar Chart”, border=“black”) #creating a bar plot for the quality of care variable

##OUTPUT

#Interpretation

This bar chart shows that most participants fell into the excellent and very good groups for quality of care, indicating that most participants may have been satisfied with their quality of care.

#B.4.2.

#scatterplot of Age

plot(hintsdataclean$Age, main=“Age Scatterplot”)

##OUTPUT

#Interpretation

This scatter plot would indicate that there may be a trend around the age of 60, meaning that more participants may be between 40 and

#Histogram of BMI

hist(hintsdataclean$BMI, main=“BMI Frequency”) #histogram for BMI

##OUTPUT

#Interpretation

This histogram indicates that most participants had a BMI from 20 to 35, indicating that most participants may be normal to overweight.

#B.4.3

library(ggplot2)#opening ggplot for the session #Histogram for Race and Ethnicity, as Pie Chart function unavailable in ggplot2

#Histogram Race and Ethnicity with GGplot

ggplot(hintsdataclean, aes(x=RaceEthn5)) + geom_histogram(binwidth=2, fill=“blue”, color=“black”)+ labs(title=“Histogram of Race and Ethnicity”, x = “Race and Ethnicity”, y = “Count”)

##OUTPUT

#Bar chart for Quality of Care with GGplot

ggplot(hintsdataclean, aes(x = QualityCare, fill = QualityCare)) + #creates a base for a bar plot with days geom_bar() +
labs(title = ” Distribution of Quality of Care”, # plot title

x = “Quality of Care”, # x-axis label

y = “Frequency”) + # y-axis

label theme_bw()

##OUTPUT

#Histogram of BMI

ggplot(hintsdataclean, aes(x=BMI)) +

geom_histogram(binwidth=50, fill=“blue”, color=“black”)+

labs(title=“Histogram of BMI”,

x = “BMI”,

y = “Count”)

#OUTPUT

#Scatter/boxplot Plot for Age

ggplot(hintsdataclean, aes(x=Age, fill=Age))+

geom_boxplot()+

theme(legend.position=“top”)

##OUTPUT

#B.4.4

my_visual_func_I <- function(data, var) {

variable <- as.factor(data[[var]]) #convert variable to factor barplot(table(variable), #for the barplot function main = paste(“Distribution of”, var),

xlab = var,

ylab = “Frequency”)

}

my_visual_func_I(hintsdataclean, “QualityCare”) #checking output

##OUTPUT

my_visual_func_I(hintsdataclean, “RaceEthn5”)#checking output

##OUTPUT

#function number 2, continuous data

my_visual_func_II <- function(data, var) {

variable <- data[[var]] hist(variable, main = paste(“Distribution of”, var),

xlab = var,

ylab = “Frequency”)

}

my_visual_func_II(hintsdataclean, “Age”) #checking appropriate output

##OUTPUT

my_visual_func_II(hintsdataclean, “BMI”)#checking output