Setup

Load packages

#setwd("/Users/bharathsivaraman/Dropbox/R programming/Prob and statistics/Project1")

library(plyr)
library(dplyr)
library(tidyr)
library(ggplot2)
library(Hmisc)
library(corrplot)

Load data

load("brfss2013.RData")

Part 1: Data

The Behavioral Risk Factor Surveillance System (BRFSS) is an ongoing surveillance system designed to measure behavioral risk factors for the non-institutionalized adult population (18 years of age and older) residing in the US.The BRFSS objective is to collect uniform, state-specific data on preventive health practices and risk behaviors that are linked to chronic diseases, injuries, and preventable infectious diseases that affect the adult population. Factors assessed by the BRFSS in 2013 include tobacco use, HIV/AIDS knowledge and prevention, exercise, immunization, health status, healthy days — health-related quality of life, health care access, inadequate sleep, hypertension awareness, cholesterol awareness, chronic health conditions, alcohol consumption, fruits and vegetables consumption, arthritis burden, and seatbelt use

Part 2: Research questions

Research question 1:

What is the correlation between General Health and Strength Training? Also, do veterans strength train more often than Non Veterans?

Variables used for this analysis:

  1. strength: How Many Times Did You Do Physical Activities Or Exercises To Strengthen Your Muscles
  2. genhlth: General Health
  3. Veteran3 - Identifies whether a person is a veteran or not.

Research question 2:

What is the correlation between Mental Health, Depression, and Heart attact and Mental Health and Physical Health?

Variables used in this analysis:

  1. cvdinfr4: Ever Diagnosed With Heart Attack
  2. addepev2: Ever Told You Had A Depressive Disorder
  3. physhlth: Number Of Days Physical Health Not Good
  4. menthlth: Number Of Days Mental Health Not Good

There are two parts to this analysis:

  1. Analyze the relationship between Mental Health and Depression/ Heart attacks
  2. Analyze the relationship between Mental and Pysical Health

Research question 3:

Does Number of hours slept determine anxiety level?

Variables used in this

  1. misnervs: How Often Feel Nervous Past 30 Days
  2. sleptim1: How Much Time Do You Sleep

Part 3: Exploratory data analysis

  1. Collect all data for answering the three questions.
  2. Strategy for NA handling - Take the mean of the variable by state for all measures. Remove NA rows from categorical variables.
  3. Plot using GGPLOT to find visualize the relationship
veterans.health <-
  brfss2013 %>% select(
  one_of(
  "seqno",
  "X_state",
  "idate",
  "veteran3",
  "genhlth",
  "physhlth",
  "menthlth",
  "poorhlth",
  "strength",
  "bphigh4",
  "sleptim1",
  "alcday5",
  "chckidny",
  "misnervs",
  "addepev2",
  "cvdinfr4",
  "sex",
  "bphigh4"
  )
  )



impute.mean <-
  function(x)
    replace(x, is.na(x), round(mean(x, na.rm = TRUE), 0))


veterans.health.impute <-
  ddply(
    veterans.health,
    ~ X_state,
    transform,
    poorhlth = impute.mean(poorhlth),
    menthlth = impute.mean(menthlth),
    physhlth = impute.mean(physhlth),
    strength = impute.mean(strength),
    sleptim1 = impute.mean(sleptim1),
    alcday5=impute.mean(alcday5)
  )


veterans.health.impute <-
  veterans.health.impute[complete.cases(veterans.health.impute),]

Research question 1:

  1. Group the data set by general health and veteran status
  2. Draw the plot visualizing the trend between general health and strength training and segregate veterans and non veterans
veterans.health.chart <-
veterans.health.impute %>% group_by(genhlth, veteran3) %>%
dplyr::summarize(
avg.strength = mean(strength),
avg.physhlth = mean(physhlth),
menthlth = mean(menthlth)
)



ggplot(veterans.health.chart) + aes(genhlth, (avg.strength)) + geom_point(aes(shape =
veteran3), size =
3, color =
"firebrick")  +  theme(plot.title = element_text(hjust = 0.5, face = "bold")) +
labs(title = "coorelation between\n general health and strength", x = "general health", y =
"strength training days") + theme(legend.title = element_text(color = "Black", face =
"bold")) + scale_shape_discrete(name = "Veteran Status")

** Observations from Question1:**

  1. There seems to be a relatonship between the general health and number of days done in strength - People who have a better health have trained more number of days

  2. Veterans seem to strength train more than non veterans

  3. Veterans have a better health condition than non veterans

Research question 2: 1. To draw up a corelation analysis, there cannot be character variables. Convert the characters variables into binary(yes=1,no=0)

corr.data <-
  veterans.health %>% select(one_of("menthlth", "addepev2", "cvdinfr4","physhlth")) %>%
  mutate(depression = ifelse(tolower(addepev2) == "yes", 1, 0),heartattack=ifelse(tolower(cvdinfr4) == "yes", 1, 0))%>%select(one_of("menthlth","depression","heartattack","physhlth"))
  
corr.data<-na.delete(corr.data)

cor(corr.data)
##               menthlth depression heartattack  physhlth
## menthlth    1.00000000 0.40879519  0.04952884 0.3474583
## depression  0.40879519 1.00000000  0.05276773 0.2385387
## heartattack 0.04952884 0.05276773  1.00000000 0.1570841
## physhlth    0.34745831 0.23853865  0.15708407 1.0000000
Corr.Chart <- cor(corr.data)
corrplot(Corr.Chart, method="ellipse")

Observations from the correlation plot

  1. There is a positive correlation between mental health and Depression. So higher number of days with bad mental health higher is the depression

  2. There is a positive correlation between Physical health and mental health. Bad physical=Bad mental health

Research question 3:

ggplot(veterans.health.impute)+aes(misnervs,(sleptim1))+geom_boxplot(fill="firebrick")+facet_wrap(~sex)+theme(plot.title = element_text(hjust = 0.5, face = "bold")) +
labs(title = "Relationship between sleep and nervousness", x = "Frequency of nervousness", y =
"Number of hours of sleep") + theme(legend.title = element_text(color = "Black", face =
"bold"))

Observation from research question 3

  1. Anxiety level seems to be related to number of hours slept. People who feel nervous all the time have an average sleep time less than those who are less anxious.