Lab916

Question 1 Create the vectors

x<- c(5,10,15,20,25,30)
y<- c(-1,NA,75,3,5,8)
z<- c(5)

Question 2. Multiply the first two vector by the z vector, ans store these in new objects. Print these new vectors

A<- c(x*z)
print(A)

## [1]  25  50  75 100 125 150

B<- c(y*z)
print(B)

## [1]  -5  NA 375  15  25  40

Question 3

library(haven)
library(readr)
library(dplyr)

## 
## Attaching package: 'dplyr'

## The following objects are masked from 'package:stats':
## 
##     filter, lag

## The following objects are masked from 'package:base':
## 
##     intersect, setdiff, setequal, union

stata<- read_dta("C:/Users/chris/Downloads/stata_PSID_w1.dta")
View(stata)
assignment1<-subset(x=stata,select=c("id","age","marpi","adjwlth2","educ","h_race_ethnic_new","race5"))

Question 3.1 How many variables are there in this data and what are the variable names, and how many observations in the data file?

ncol(assignment1)

## [1] 7

names(assignment1)

## [1] "id"                "age"               "marpi"            
## [4] "adjwlth2"          "educ"              "h_race_ethnic_new"
## [7] "race5"

nrow(assignment1)

## [1] 131361

Question 3.2 show frequency distribution of race/ethnicity variaable

hist(assignment1$race5, main="Frequency Distribution of Race/Ethnicity")

assignment1$race5<-factor(assignment1$race5,
                   levels=c(1,2,3,4,5),
                   labels=c("Latino","Asian","Black", "Other","White" ))
barplot(table(assignment1$race5), main="Frequency Distribution of Race")

Question 3.3 What’s the mean and median for adjwlth2(wealth including homeequity)?

mean(assignment1$adjwlth2,na.rm = T)

## [1] 187.1656

median(assignment1$adjwlth2,na.rm = T)

## [1] 32.804

Question 3.4, Generate five summary for age(i.e., min, max, mean, and median)

summary(assignment1$age)

##    Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
##    1.00   14.00   29.00   32.03   47.00  999.00

Question 3.5, How many people in the data received public assistance? How many Latino received public assistance?

PublicAsst<-subset(stata,select=c("id","pubhs","h_race_ethnic_new","race5"))
View(PublicAsst)
sum(PublicAsst$pubhs == 1, na.rm = T)

## [1] 6961

unique(PublicAsst$race5)

## <labelled<double>[5]>: Race/ethnicity updated codes (5/26/14)
## [1] 5 3 1 4 2
## 
## Labels:
##  value            label
##      1 Latino- Any Race
##      2         NL Asian
##      3         NL Black
##      4         NL Other
##      5         NL White

PublicAsstLatinoRace5<-subset(filter(PublicAsst,race5 == 1)) 
View(PublicAsstLatinoRace5)
sum(PublicAsstLatinoRace5$pubhs == 1, na.rm = T)

## [1] 366

Question 3.6 Anything you wish to know about individuals’ experiences that are not included in the data set? (Note: unit of analysis is individual here. Open-ended question. E.g., occupation, childhood maltreatment, neighborhood characteristics, etc). List three variables that you wish you had access to.

"occupation, child and parent information, Literacy level,Household size, Educational level of Parents/Guardian
Number of Children, Type of occupation/occupation" 

## [1] "occupation, child and parent information, Literacy level,Household size, Educational level of Parents/Guardian\nNumber of Children, Type of occupation/occupation"