FinalProject,Spring2018
RocioClara
February20,2018
Taking into account the pressures of today’s society, I decided to explore the variables of education, income level and martial status. I believe in our current society the pressures to further your education and career are significantly greater than they were just a decade ago. This increased pressure to climb the ladder and become someone wealthy/successful has effects on your everyday life. Whether it be spending more time focusing on work than family, or even postponing making a family. With this in mind, these increased pressures have also significantly changed marriage rates and marriage dynamics in the past decade. Women are waiting more to commit to a having a spouse, making a family, all which, for most cases, are tied into education/career choices.Thus, I would like to explore the correlation between these variables and depression.
The data I have chosen was taken from the MATH 130 data set file for the Spring 2018 semester. This data set is from the first set of interviews of prospective study of depression in adult residents of Los Angeles County which includes 294 observations.
library(ggplot2)
library(knitr)
library(descr)
depress <-read.delim("file:///C:/Users/Roci/Desktop/MATH 130/depress_081217.txt", header=TRUE,sep="\t")
The following graph and table shows the different levels of education among the participants reporting some level of depression.
ggplot(depress, aes(x=educat)) +geom_bar(color="black", fill="pink") +ggtitle("Edcucaion Level") +xlab("Education") +ylab("Count")+geom_text(aes(y=..count.. +10, label=..count..), stat='count', size =5)
round(prop.table(table(depress$educat)),2)
##
## <HS BS HS Grad MS PhD
## 0.02 0.15 0.39 0.05 0.03
## Some college Some HS
## 0.16 0.21
Looking at the graph and table, the greatest count of participants (at 39%) with depression reported high school as their highes level of education. Interestingly, 16% of individuals reported having some high school education while only 2% had an education lower than high school.At higher levels of education the percentage decreases with increasing degree prestige. 15% were had Bachelors, 5% had Masters and 3% had PhDs.
The following graph and table compares the count of individuals within an income level.
boxplot(depress$income, horizontal =TRUE, main ="Income Status", xlab ="income")
round(prop.table(table(depress$income)),2)
##
## 2 4 5 6 7 8 9 11 12 13 15 16 18 19 20
## 0.02 0.03 0.03 0.04 0.06 0.05 0.07 0.06 0.01 0.06 0.08 0.00 0.00 0.09 0.01
## 23 24 25 26 27 28 31 32 35 36 37 42 45 55 65
## 0.09 0.01 0.00 0.00 0.00 0.06 0.00 0.00 0.08 0.00 0.00 0.00 0.05 0.03 0.03
Looking at the graph for income status the range is pretty broad with individuals earning an annual income of anywhere between $2,000 - $65,000. However, the majority of individuals fall in the range of $9-28,000 annual income. None reported earning over $65,000.
The following graph and table shows relationship between marital status and depression.
ggplot(depress, aes(x=marital)) +geom_bar(color="black", fill="light blue")+ggtitle("Marital Status") +geom_text(aes(y=..count.. +10, label=..count..), stat='count', size =5)
round(prop.table(table(depress$marital)),2)
##
## Divorced Married Never Married Separated Widowed
## 0.15 0.43 0.25 0.04 0.13
127 of indivuduals reporting depression were married and the lowest, at 4%, were separated. Divorced and widowed individuals range in approximately the same percetages and individuals who have neve been married were the second highest percentage ay 25%.
Education v Income level
cc<-table(depress$marital, depress$educat)
barplot(cc, main="Marital Status vs Education", beside=TRUE, col=rainbow(5),legend=rownames(cc), xlab="Education Level",ylab="Count")
table(depress$educat, depress$marital)
##
## Divorced Married Never Married Separated Widowed
## <HS 1 2 0 0 2
## BS 6 15 18 2 2
## HS Grad 14 56 27 1 16
## MS 2 9 2 1 0
## PhD 3 3 1 1 1
## Some college 9 18 16 2 3
## Some HS 8 24 9 6 14
In each different educational level, married individuals seem to make up the higher percentage per category, for the exception of individuals holding Bachelor degrees.This correlation may not however be absolute.
Summary of data analysis
There are many factors that may lead an individual into depression. Sometimes it may not be one single factor but multiple. My reasoning for exploring these factors were that in today’s society the pressure to further your education and earn a higher income WHILE having a successful relationship/marriage is at an all time high. I did find it interesting to see a higher percentile of individuals report that they are currently married. Of course this may not be solely be due to the marriage itself.
Another interesting trend seen is in the educational level of the individual. A higher percentage of participants with depression held high school diplomas with a smaller percent had reached a level of education LOWER than high school.
I believe that many of these factors are tied closely with one another thus making it difficult to separate which may be most responsible for causing depression.