The relationship of 2015 suicidal deaths with demographical variables

The data that has been chosen was downloaded from kaggle.com. This data contains all deaths that occured in 2015. My analysis is to see if the suicidal deaths in 2015 had any strong relationships with education and race.

library(zelig)

Error in library(zelig) : there is no package called ‘zelig’

library(dplyr)
Suicidedata<- Suicide1%>%
mutate(Suicide= ifelse(manner_of_death== 2, 1, 0),
            age= as.numeric(age_recode_12), 
            age= ifelse(age==4,"15-24", 
                         ifelse(age==5,"25-34", 
                         ifelse(age==6,"35-44", 
                         ifelse(age==7,"45-54",
                         ifelse(age==8,"55-64",
                         ifelse(age==9,"65-74",NA)))))),
            education=(education_2003_revision),
            education= ifelse(education==1,"8th grade or less",
                       ifelse(education==2,"9 - 12th grade, no diploma",
                        ifelse(education==3,"high school graduate or GED completed",
                        ifelse(education==4,"some college credit, but no degree",
                        ifelse(education==5,"Associate degree",
                        ifelse(education==6,"Bachelor's degree",
                        ifelse(education==7,"Master's degree",
                        ifelse(education==8,"Doctorate or professional degree",NA)))))))),
              race=(race_recode_3), 
              race= ifelse(race==1,"White",
                           ifelse(race==2,"Black",
                                  ifelse(race==3,"Other",NA))))%>%
select( age, marital_status, sex, education_2003_revision, race_recode_3, Suicide)%>%
  filter(age>3)

package <U+393C><U+3E31>bindrcpp<U+393C><U+3E32> was built under R version 3.4.3

  
head(Suicidedata)

Filter NA’s

Suicidedata2<- Suicidedata %>% 
  filter(!is.na(Suicide),!is.na(race_recode_3),!is.na(education_2003_revision),!is.na(age), !is.na(sex), !is.na(marital_status))

library(Zelig)
zsuicide <- zelig(Suicide ~ education_2003_revision + race_recode_3, model = "logit", data = Suicidedata2, cite = F)

|==========================================================================================|100% ~0 s remaining     

summary(zsuicide)

Model: 

Call:
z5$zelig(formula = Suicide ~ education_2003_revision + race_recode_3, 
    data = Suicidedata2)

Deviance Residuals: 
    Min       1Q   Median       3Q      Max  
-0.3110  -0.2600  -0.2508  -0.2334   3.1164  

Coefficients:
                         Estimate Std. Error z value Pr(>|z|)
(Intercept)             -3.033689   0.020891 -145.21   <2e-16
education_2003_revision  0.073138   0.003041   24.05   <2e-16
race_recode_3           -0.629170   0.013541  -46.46   <2e-16

(Dispersion parameter for binomial family taken to be 1)

    Null deviance: 244686  on 927780  degrees of freedom
Residual deviance: 240949  on 927778  degrees of freedom
AIC: 240955

Number of Fisher Scoring iterations: 7

Next step: Use 'setx' method

The regression shows that suicide as death for dead persons would go up by .0731 for every unit of education increased. This regression also states as race changes from white to black or other, suicide for dead persons decreases by .629 ##Counterfactual Values

x.out <- setx(zsuicide)
s.out <- sim(zsuicide, x = x.out)

Simulate

s.out <- sim(zsuicide, x = x.out)

Results

summary(s.out)

 sim x :
 -----
ev
           mean           sd        50%       2.5%      97.5%
[1,] 0.02677958 0.0001746716 0.02677593 0.02644487 0.02711196
pv
         0     1
[1,] 0.977 0.023

plot(s.out)

This plot shows that most deceased persons education fell between .0266- .0270.

Automatting using Zelig

Range of educational attainment of desceased persons

zsuicide2<- zelig(Suicide ~ education_2003_revision + race_recode_3, data =Suicidedata2, model = "logit", cite = F)

|==========================================================================================|100% ~0 s remaining     

education.range <- min(Suicidedata2$education_2003_revision):max(Suicidedata2$education_2003_revision)
x <- setx(zsuicide2, education_2003_revision = education.range)

|==========================================================================================|100% ~0 s remaining     

s <- sim(zsuicide2, x=x)
ci.plot(s)

The above analysis shows that as educational attainment rises the expected death being suicide rises.

PART 2- Analyzing Independent variables

Education Difference

ed.range = min(Suicidedata2$education_2003_revision):max(Suicidedata2$education_2003_revision)
x <- setx(zsuicide,  education_2003_revision= ed.range)
s <- sim(zsuicide, x = x)
ci.plot(s)

race.range = min(Suicidedata2$race_recode_3):max(Suicidedata2$race_recode_3)
x <- setx(zsuicide, race_recode_3 = race.range)
s <- sim(zsuicide, x = x)
ci.plot(s)

As the race moves from 1: White it decreases in half for 2: Blacks and the least likely to affect the deaths to being suicide was 3: other.