Correction factor for black men and all men 1990

Correction Factor Script

#Calculating rates for Correctional vs Other Institution 

#load packages
library(readr)
library(dplyr)

#read in data extract
ipums <- read_csv('data/FINALFINALDATA.csv', col_types = cols(PERWT=col_double()))

a <- ipums %>% filter((AGE>=15 & AGE<=70) & (STATEFIP!=11) & ((!(STATEFIP %in% c(2,15)) | YEAR >=1960)))

#filter out Female 
e <- a %>% filter(SEX==1)

#data frame for Prison prior to 1990
prison1990 <- e %>% filter(GQTYPE==2) %>% group_by(YEAR) %>% summarise(NumPrison=sum(PERWT))


#data frame for All Institutions to 1990
inst1990 <- e %>% filter(YEAR<=1980 & (GQTYPE==2 | GQTYPE==3 | GQTYPE==4)) %>% group_by(YEAR) %>% summarise(NumGQ=sum(PERWT))

#joining data frame
all1990 <- left_join(prison1990, inst1990)

pct1990 <- all1990 %>% mutate(Percent=NumPrison/NumGQ)

#export data
write_csv(pct1990, 'correctionfactor_all.csv')


#Calculating rates for Correctional vs Other Institution for just Black Men

#load packages
library(readr)
library(dplyr)

#read in data extract
ipums <- read_csv('data/FINALFINALDATA.csv', col_types = cols(PERWT=col_double()))

a <- ipums %>% filter((AGE>=15 & AGE<=70) & (STATEFIP!=11) & ((!(STATEFIP %in% c(2,15)) | YEAR >=1960)))

#recode RACESING
b <- a %>% mutate(Race = factor(ifelse(RACESING==2, 1,
                                       ifelse(RACESING==1, 2, 3)),
                                labels = c('Black', 'White', 'Other')))

#filter for males and Black
e <- b %>% filter(SEX==1 & Race=='Black')

#data frame for Prison prior to 1990
prison1990 <- e %>% filter(GQTYPE==2) %>% group_by(YEAR) %>% summarise(NumPrison=sum(PERWT))


#data frame for All Institutions to 1990
inst1990 <- e %>% filter(YEAR<=1980 & (GQTYPE==2 | GQTYPE==3 | GQTYPE==4)) %>% group_by(YEAR) %>% summarise(NumGQ=sum(PERWT))

#joining data frame
all1990 <- left_join(prison1990, inst1990)

pct1990 <- all1990 %>% mutate(Percent=NumPrison/NumGQ)

#export data
write_csv(pct1990, 'correctionfactor_black.csv')