Assignment-9
Title: Socio-economic Index Score(SEI), Family Earning Status and Sex in the Probabilities of Migration between the States of USA
Introduction
There are several push-and-pull factors of migration. People move from one state to another for several economic, social, environmental, political and religious reasons. However, the economic reason was one of the main motivators for moving from residence to another both in case of within and between states. Both income and employment are important factors in understanding people’s migration. Whatever the reason, in most cases people decided to migrate if it is beneficial for the family. So, in addition to person’s demographic and socio-economic status, the economic situation of a family as a whole is also important to understand the likelihood of migration. For this reason, the present study was designed to answer following research questions.
Research questions
- Is there any effect of the socio-economic index(SEI) in the probabilities of migration?
- Is there any effect of family earning status in the probabilities of migration. To be more clarify, whether or not the probabilities of migration differ for people who were only earning persons in their families and who were not?
- Is there any interaction of sex, SEI and person’s status in the family earning in the probabilities of migration?
Method
Source of data
The US census dataset was used in the present study to answer research questions. The dataset was extracted from www.ipums.org. The dataset consisted of people aged between 18 and 66 years who lived in the household. The census years between 2012 and 2016 were included in the dataset.
Defining variables
Dependent variable
Migration: Migration was defined as whether or not people changed their residency in 1 year ago and moved to different states. Migration consisted of two levels: migrated and not migrated. The level “migrated” consisted of people who changed their residency and moved to a different state in 1 year ago. The level “non-migrated” consisted of people who remained in the same house or moved within a state in 1 year ago. People who moved abroad were used as exclusion criteria.
Independent variable
Socio-economic index(SEI) score: The SEI is a measure of occupational status based upon the income level and educational attainment associated with each occupational classification by 1950 Census Bureau.
Family earning status: It has two levels: “Only earning person” and “Not only earning person”. The total personal pre-tax income was deducted from total pre-tax family income to determine person’s status in the family earning. If person’s total personal income was equivalent to total family income, that person was labeled as “Only earning person” and if person’s total family income was greater than total personal income, that person was labeled as “Not only earning person”. It is important to note that both personal and family income loses were excluded before executing deduction.
Sex: Sex reports whether the person was male or female.
Control variable
Age: Age reports the person’s age in years as of the last birthday.
Race: The variable “race” indicated the person’s major race groups: White, Black, Asian, Other.
Educational attainment: It indicates respondents’ educational attainment, as measured by the highest year of school or degree completed.
Employment status: It indicates whether the respondent was a part of the labor force – working or seeking work – and, if so, whether the person was currently unemployed.
Data analysis
The variables used in the present study was re-coded for analysis. Binary logistic regression analysis was conducted by using 3 different models to get the best-fitted model. AIC measures were used for identifying the best fitting models.
library(tidyverse)
migration<-read.csv("migration.csv")
head(migration)## YEAR DATANUM SERIAL HHWT REGION STATEFIP GQ PERNUM PERWT FAMSIZE NCHILD
## 1 2012 1 5 31 32 1 1 2 62 6 1
## 2 2012 1 5 31 32 1 1 3 61 6 1
## 3 2012 1 58 75 32 1 1 2 53 3 1
## 4 2012 1 69 11 32 1 3 1 11 1 0
## 5 2012 1 119 624 32 1 1 2 635 4 2
## 6 2012 1 135 28 32 1 1 2 77 8 3
## NCHLT5 ELDCH YNGCH SEX AGE MARST RACE RACED CITIZEN RACASIAN RACBLK
## 1 0 13 13 1 44 4 6 663 1 2 1
## 2 0 12 12 1 42 4 6 663 1 2 1
## 3 1 0 0 1 44 1 7 700 3 1 1
## 4 0 99 99 1 23 6 2 200 3 1 2
## 5 0 15 6 2 41 1 1 100 2 1 1
## 6 2 10 2 2 27 1 1 100 3 1 1
## RACWHT HCOVANY EDUC EDUCD EMPSTAT EMPSTATD LABFORCE CLASSWKR CLASSWKRD
## 1 1 1 11 114 3 30 1 1 14
## 2 1 1 4 40 3 30 1 2 22
## 3 1 1 0 2 2 20 2 2 22
## 4 1 1 5 50 3 30 1 2 22
## 5 2 2 8 81 1 10 2 2 22
## 6 2 1 6 63 1 10 2 2 22
## UHRSWORK INCTOT FTOTINC INCEARN POVERTY SEI MIGRATE1 MIGRATE1D
## 1 0 3000 74200 0 237 68 1 10
## 2 40 40000 74200 40000 237 11 1 10
## 3 0 0 9000 0 48 15 1 10
## 4 0 0 9999999 0 0 44 1 10
## 5 40 27700 124950 27000 501 44 1 10
## 6 40 4000 152000 4000 394 15 1 10migration1<-migration[c(1, 7, 10, 15:16,18, 25, 27, 30, 33, 34, 37, 38)]
migration1<-filter(migration1, GQ==1, !(MIGRATE1==4), !(FTOTINC==9999999), !(FTOTINC<0), !(INCTOT<0))
migration1<-migration1 %>%
mutate(Race = sjmisc::rec(RACE, rec = "1=1; 2=2; 4:6=3; 3=4;7:9=4 "))%>%
mutate(Education=sjmisc::rec(EDUC, rec = "0:2=1; 3:6=2; 7:9=3; 10:11=4"))%>%
mutate(Migrate=sjmisc::rec(MIGRATE1,rec = "1=1; 2=1; 3=0" ))
migration1$SEX<-factor(migration1$SEX, levels = c(1, 2),
labels = c("Male","Female"))
migration1$Race<-factor(migration1$Race, levels = c(1, 2, 3, 4),
labels = c("White", "Black", "Asian", "Other"))
migration1$Employed<-factor(migration1$EMPSTAT, levels = c( 1, 2, 3),
labels = c("Employed", "Unemployed", "Not in Labor Force" ))
migration1$Education<-factor(migration1$Education, levels = c(1, 2, 3, 4),
labels = c("Junior school or less", "High School", "college 3y or less", "college 4y or more"))
migration1$Migrate<-factor(migration1$Migrate, levels = c( 1, 0),
labels = c("Migrated", "Not migrated" )) migration1<-migration1 %>%
mutate(inc_diff=(FTOTINC-INCTOT)/1000) %>%
mutate(c_age=AGE-median(AGE))
summary(migration1$inc_diff)## Min. 1st Qu. Median Mean 3rd Qu. Max.
## -634.00 0.00 25.00 43.62 60.40 2156.20migration1<-filter(migration1,!(inc_diff<0))
summary(migration1$SEI)## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 4.00 15.00 44.00 40.83 66.00 96.00migration1<-migration1 %>%
mutate(Family_income = sjmisc::rec(inc_diff, rec = "0.00=1; 0.01:2156.20=2 "))
migration1$Family_income<-factor(migration1$Family_income, levels = c( 1, 2),
labels = c("Only earning person", "Not only earning person" ))
migration1<-na.omit(migration1)m1 <- glm(Migrate~SEI+Family_income+Race+SEX+c_age+Employed+Education, family = binomial, data = migration1)m2 <- glm(Migrate~SEI*Family_income+Race+SEX+c_age+Employed+Education, family = binomial, data = migration1)m3 <- glm(Migrate~SEI*Family_income*SEX+Race+c_age+Employed+Education, family = binomial, data = migration1)library(texreg)
htmlreg(list(m1, m2, m3))| Model 1 | Model 2 | Model 3 | ||
|---|---|---|---|---|
| (Intercept) | -4.53*** | -4.67*** | -4.65*** | |
| (0.03) | (0.04) | (0.04) | ||
| SEI | 0.00*** | 0.01*** | 0.01*** | |
| (0.00) | (0.00) | (0.00) | ||
| Family_incomeNot only earning person | -0.65*** | -0.41*** | -0.49*** | |
| (0.01) | (0.03) | (0.04) | ||
| RaceBlack | 0.18*** | 0.18*** | 0.19*** | |
| (0.02) | (0.02) | (0.02) | ||
| RaceAsian | 0.13*** | 0.13*** | 0.13*** | |
| (0.02) | (0.02) | (0.02) | ||
| RaceOther | -0.13*** | -0.13*** | -0.13*** | |
| (0.02) | (0.02) | (0.02) | ||
| SEXFemale | -0.12*** | -0.12*** | -0.18*** | |
| (0.01) | (0.01) | (0.05) | ||
| c_age | -0.05*** | -0.05*** | -0.05*** | |
| (0.00) | (0.00) | (0.00) | ||
| EmployedUnemployed | 0.68*** | 0.68*** | 0.68*** | |
| (0.03) | (0.03) | (0.03) | ||
| EmployedNot in Labor Force | 0.68*** | 0.68*** | 0.67*** | |
| (0.02) | (0.02) | (0.02) | ||
| EducationHigh School | 0.21*** | 0.21*** | 0.21*** | |
| (0.03) | (0.03) | (0.03) | ||
| Educationcollege 3y or less | 0.37*** | 0.37*** | 0.37*** | |
| (0.03) | (0.03) | (0.03) | ||
| Educationcollege 4y or more | 1.07*** | 1.07*** | 1.07*** | |
| (0.03) | (0.03) | (0.03) | ||
| SEI:Family_incomeNot only earning person | -0.00*** | -0.00*** | ||
| (0.00) | (0.00) | |||
| SEI:SEXFemale | -0.00 | |||
| (0.00) | ||||
| Family_incomeNot only earning person:SEXFemale | 0.19** | |||
| (0.06) | ||||
| SEI:Family_incomeNot only earning person:SEXFemale | -0.00 | |||
| (0.00) | ||||
| AIC | 213258.80 | 213179.03 | 213155.00 | |
| BIC | 213414.63 | 213346.86 | 213358.79 | |
| Log Likelihood | -106616.40 | -106575.52 | -106560.50 | |
| Deviance | 213232.80 | 213151.03 | 213121.00 | |
| Num. obs. | 1187446 | 1187446 | 1187446 | |
| p < 0.001, p < 0.01, p < 0.05 | ||||
library(ggplot2)
ggplot(migration1, aes(SEX, SEI, fill = Migrate)) +
geom_boxplot()+facet_grid(.~Family_income)+theme_bw()+ggtitle("Factors affecting migration")+
theme(plot.title = element_text(color="blue", size=18, face="bold")) + theme(legend.title = element_text(colour="blue", size=10,
face="bold")) + theme(legend.text = element_text(colour="black", size=10,
face="bold"))
Results
According to AIC of the above models, model 3 was considered as the best fitting models and was used for analyzing the results. In this model, the baseline group consisted of employed white males with age of 43 years and whose SEI score was 40.83 and were the only earning persons in their families. According to this model, the baseline group had exp(4.6459016) times less likelihood of being migrated. When controlling for all other variables, every 1 unit increased on SEI score led exp(0.0072164) times increase in the likelihood of being migrated to baseline group. The likelihood of being migrated of baseline group was also found to decrease by exp (0.4947211) times when they were not only the earning persons in their family. Being a female, the likelihood of probability was decreased by exp( 0.1832657) times compared to males of the baseline group. In case of when the persons were not only the earning members of the family, the likelihood of being migrated was reduced exp(0.0042213) times with every one unit increase of SEI score. The likelihood of being migrated was also found to increase exp(0.1927320) times in case of females if they were not only the earning persons in their families than males who were the only earning persons of their families.
Discussion
The purpose of the present study was to see the effect of SEI in the probability of being migrated as well as to see whether this effect differs in response to person’s gender and their earning status in the family income. The results suggested a significant positive effect of SEI score on the probabilities of being migrated. People with higher SEI score more likely to move than people with lower SEI. The gender difference was also found in the probability of being migrated. Females were less likely to migrate than males. Persons’ status in the family earning was found also a significant factor in determining the likelihood of migration. People were more likely to migrate when they were the only earning persons in their family compared to when other family members contributed to family income. Both SEI and gender were found to have an interaction effect on person’s status in family income in determining the likelihood of migration. When other members of the family contributed to family income, people were less likely to migrate as their SEI increase. When other members of the family contributed to family income, females were more likely to migrate than male.
Conclusion
Both personal socio-economic status and contribution of other members of the family income are important in understanding the likelihood of being migrated.
Limitation
The findings of the present study only generalized for people aged between 18 and 66 years. In addition, the present analysis did not take into account for some other political, social, environmental push factors of migration.
References:
- www.ipums.org
- Molloy, Raven, Christopher L. Smith, and Abigail Wozniak (2011). “Internal Migration in the United States.” Journal of Economic Perspectives, 25 (3): 173-96.