Homework1_StephanieYang

Adding necessary packages to library

library(pastecs)
library(ggplot2)
library(tidyr)

## 
## Attaching package: 'tidyr'

## The following object is masked from 'package:pastecs':
## 
##     extract

library(car)

## Loading required package: carData

Importing Dataset

#Read in data
myData <- read.table("./Medical_Cost.csv", header = TRUE, sep = ",", dec = ".")

Display of my Data

head(myData)

##   age    sex    bmi children smoker    region   charges
## 1  19 female 27.900        0    yes southwest 16884.924
## 2  18   male 33.770        1     no southeast  1725.552
## 3  28   male 33.000        3     no southeast  4449.462
## 4  33   male 22.705        0     no northwest 21984.471
## 5  32   male 28.880        0     no northwest  3866.855
## 6  31 female 25.740        0     no southeast  3756.622

Explaining the Data

Variables:

age: Age of the primary beneficiary (years)
sex: Gender of primary beneficiary
bmi: Body mass index, an index that compares height to weight (kg / m ^ 2)
children: Number of children covered by health insurance / Number of dependents
smoker: Whether beneficiary smokes or not
region: The beneficiary’s residential area in the US
charges: Individual medical costs billed by health insurance ($USD)

Unit: A single beneficiary (person with insurance)

Sample size: 1338 beneficiaries

Source of Data

Source Link: https://www.kaggle.com/datasets/pritambhakat/medical-cost-dataset

Cleaning the data

#Cast Gender, smoker, and region as factor
myData$GenderFactor <- as.factor(myData$sex)
myData$SmokerFactor <- as.factor(myData$smoker)
myData$RegionFactor <- as.factor(myData$region)

str(myData)

## 'data.frame':    1338 obs. of  10 variables:
##  $ age         : int  19 18 28 33 32 31 46 37 37 60 ...
##  $ sex         : chr  "female" "male" "male" "male" ...
##  $ bmi         : num  27.9 33.8 33 22.7 28.9 ...
##  $ children    : int  0 1 3 0 0 0 1 3 2 0 ...
##  $ smoker      : chr  "yes" "no" "no" "no" ...
##  $ region      : chr  "southwest" "southeast" "southeast" "northwest" ...
##  $ charges     : num  16885 1726 4449 21984 3867 ...
##  $ GenderFactor: Factor w/ 2 levels "female","male": 1 2 2 2 2 1 1 1 2 1 ...
##  $ SmokerFactor: Factor w/ 2 levels "no","yes": 2 1 1 1 1 1 1 1 1 1 ...
##  $ RegionFactor: Factor w/ 4 levels "northeast","northwest",..: 4 3 3 2 2 3 3 2 1 2 ...

#Removing NAs (there are no NAs)
cleanedData <- drop_na(myData)

#View Cleaned Data
head(cleanedData)

##   age    sex    bmi children smoker    region   charges GenderFactor
## 1  19 female 27.900        0    yes southwest 16884.924       female
## 2  18   male 33.770        1     no southeast  1725.552         male
## 3  28   male 33.000        3     no southeast  4449.462         male
## 4  33   male 22.705        0     no northwest 21984.471         male
## 5  32   male 28.880        0     no northwest  3866.855         male
## 6  31 female 25.740        0     no southeast  3756.622       female
##   SmokerFactor RegionFactor
## 1          yes    southwest
## 2           no    southeast
## 3           no    southeast
## 4           no    northwest
## 5           no    northwest
## 6           no    southeast

Descriptive Statistics

Age

#Calculate descriptive statistics
round(stat.desc(cleanedData[ , c(-2,-5,-6,-8,-9,-10)]), 2)

##                   age      bmi children      charges
## nbr.val       1338.00  1338.00  1338.00      1338.00
## nbr.null         0.00     0.00   574.00         0.00
## nbr.na           0.00     0.00     0.00         0.00
## min             18.00    15.96     0.00      1121.87
## max             64.00    53.13     5.00     63770.43
## range           46.00    37.17     5.00     62648.55
## sum          52459.00 41027.62  1465.00  17755824.99
## median          39.00    30.40     1.00      9382.03
## mean            39.21    30.66     1.09     13270.42
## SE.mean          0.38     0.17     0.03       331.07
## CI.mean.0.95     0.75     0.33     0.06       649.47
## var            197.40    37.19     1.45 146652372.15
## std.dev         14.05     6.10     1.21     12110.01
## coef.var         0.36     0.20     1.10         0.91

Age

The median age is 39. This means that half of the beneficiaries are younger than 39 and half of them are 39 or older.

BMI

The mean BMI is 30.66. This means that the average BMI is about 30.66.

Children

The standard deviation of the number of dependents (children) a beneficiary has is 1.21. This means that 68.3% of beneficiares have within 1.21 children away from the mean number of children, 95.45% within 2.42, and 99.73% within 3.63. Standard deviation is a measure of how varied the number of dependents is.

Charges

The coefficient of variation for the amount charged is .91. The coefficient of variation measures how variable the amount charged is. .91 is a large coefficient of variation so the amount is very variable.

Graphs

Age

ggplot(cleanedData, aes(x=age)) +
  geom_histogram(binwidth = 5, colour="black", fill = "darkseagreen3") +
  ggtitle("Distribution of Age") +
  xlab("Age (years)") +
  ylab("Frequency") +
  theme_dark()

Description

You can see that the distribution of Age is slightly right skewed. The minimum value is 18 and the maximum is 64. The data could potentially be bimodal since there is a mode around 20, but the data also increases again close to 50.

Sex

ggplot(cleanedData, aes(x=GenderFactor)) +
  geom_histogram(colour="black", fill = "cornflowerblue", stat = "count") +
  ggtitle("Distibution of Gender") +
  xlab("Gender") +
  ylab("Frequency") +
  theme_grey()

## Warning in geom_histogram(colour = "black", fill = "cornflowerblue", stat =
## "count"): Ignoring unknown parameters: `binwidth`, `bins`, and `pad`

Description

There seems to be a similar amount of females and males.

BMI

ggplot(cleanedData, aes(x=bmi)) +
  geom_histogram(binwidth = 2, colour="black", fill = "slateblue") +
  ggtitle("Distribution of BMI") +
  xlab("BMI (kg / m ^ 2)") +
  ylab("Frequency") +
  theme_minimal()

Description

The distribution of BMI appears to be normal with a slight right skew. The mode and mean both seem to be around 28 or 30.

Number of Children/Dependents

ggplot(cleanedData, aes(x=children)) +
  geom_histogram(binwidth = 1, colour="black", fill = "midnightblue") +
  ggtitle("Distribution of Number of Children") +
  xlab("Children") +
  ylab("Frequency") +
  theme_light()

Description

The distribution is heavily right skewed.

Smoker/Nonsmoker

ggplot(cleanedData, aes(x=SmokerFactor)) +
  geom_histogram(colour="black", fill = "hotpink", stat = "count") +
  ggtitle("Distibution of Smokers and Nonsmokers") +
  xlab("Smoker Status") +
  ylab("Frequency") +
  theme_linedraw()

## Warning in geom_histogram(colour = "black", fill = "hotpink", stat = "count"):
## Ignoring unknown parameters: `binwidth`, `bins`, and `pad`

Description

There are more non-smokers than smokers.

Region

ggplot(cleanedData, aes(x=RegionFactor)) +
  geom_histogram(colour="black", fill = "deeppink4", stat = "count") +
  ggtitle("Distibution of Region") +
  xlab("Region") +
  ylab("Frequency") +
  theme_classic()

## Warning in geom_histogram(colour = "black", fill = "deeppink4", stat =
## "count"): Ignoring unknown parameters: `binwidth`, `bins`, and `pad`

Description

There is a relatively even distribution between regions; however, there are slightly more beneficiaries from the southeast.

Charges

ggplot(cleanedData, aes(x=charges)) +
  geom_histogram(binwidth = 5000, colour="black", fill = "darkorange") +
  ggtitle("Distribution of Charges") +
  xlab("Charges ($USD)") +
  ylab("Frequency") +
  theme_grey()

Description

The distribution of charges is heavily right skewed. This distribution also appears to be bimodal. There is a mode around 8000 and also at 40000.

Other Graphs

ggplot(cleanedData, aes(x=SmokerFactor, y=charges)) +
  geom_boxplot(binwidth = 5000, colour="black", fill = "palegreen") +
  ggtitle("Charges by Smoker Status") +
  theme_dark()

## Warning in geom_boxplot(binwidth = 5000, colour = "black", fill = "palegreen"):
## Ignoring unknown parameters: `binwidth`

Description

When you compare charges to whether or not the beneficiary smokes, you can see that smokers tend to have much higher medical costs. The charges of smokers all seem to be more than the bottom 75% (3rd Quartile) of non-smokers.

ggplot(cleanedData, aes(x=charges)) +
  geom_histogram(binwidth = 5000, colour="black", fill = "violet") +
  facet_wrap(~RegionFactor:GenderFactor, ncol = 2) + 
  ylab("Frequency") +
  theme_dark()

Description

Comparing region and gender to medical charges, there doesn’t seem to be any significant differences. All are right skewed and have modes around 8000. Some also do seem to have a second mode around 40000, but not as much as the 8000 mode.

scatterplot(charges ~ age, 
            ylab = "Charges ($USD)", 
            xlab = "Age (Years)", 
            smooth = FALSE, 
            data = cleanedData)

scatterplot(charges ~ age | SmokerFactor, 
            ylab = "Charges ($USD)", 
            xlab = "Age (Years)", 
            smooth = FALSE, 
            data = cleanedData)

Description

Overall, there doesn’t seem to be any trends in the scatter plot between age and medical charges. There could be a slight positive relationship, but it does look unrelated. When you differentiate even further by smoker status, you can see two positive trends between smokers and non-smokers between age and charges with the smokers having higher charges than non-smokers.

Homework1_StephanieYang

Stephanie Yang

2024-04-02

Importing Dataset

Display of my Data

Explaining the Data

Source of Data

Cleaning the data

Descriptive Statistics

Graphs