## Download of ATUS files using the lodown library
atus_cat = get_catalog("atus",output_dir = file.path(path.expand( "~" ) , "ATUS" ))
atus_cat = subset(atus_cat,directory == 2016)
atus_cat = lodown("atus",atus_cat)
## Load libraries
library(lodown)
library(psych)
## Data load
## Parsing to read ATUS files
atusact <- readRDS( file.path( path.expand( "~" ) , "ATUS" , "2016/atusact.rds" ) )
atusact <- atusact[ c( 'tucaseid' , 'tutier1code' , 'tutier2code' , 'tuactdur24' ) ]
atusresp <- readRDS( file.path( path.expand( "~" ) , "ATUS" , "2016/atusresp.rds" ) )
atusresp <- atusresp[ c( 'tucaseid' , 'telfs' , 'tulineno' ) ]
atusrost <- readRDS( file.path( path.expand( "~" ) , "ATUS" , "2016/atusrost.rds" ) )
atusrost <- atusrost[ , c( 'tucaseid' , 'tulineno' , 'teage' , 'tesex' ) ]
atuswgts <- readRDS( file.path( path.expand( "~" ) , "ATUS" , "2016/atuswgts.rds" ) )
atuswgts <- atuswgts[ , c( 1 , grep( 'finlwgt' , names( atuswgts ) ) ) ]
## Filter into two separate dfs
atusactF = atusact[atusact$tutier1code==5|atusact$tutier1code==12,]
atusact[atusact$tutier1code==5|atusact$tutier1code==12,'tutier1code']=
atusact[atusact$tutier1code==5|atusact$tutier1code==12,'tutier2code']
agg_table = aggregate(tuactdur24~tucaseid+tutier1code,data = atusactF,sum)
wide_table = reshape(agg_table,idvar = 'tucaseid' ,
timevar = 'tutier1code' , direction = 'wide' )
wide_table[is.na(wide_table)] = 0
wide_table[,-1] = wide_table[,-1]/60
#####
merge_table_one_resp = merge(atusresp,wide_table)
merge_table_one_rost = merge(merge_table_one_resp,atusrost)
names(merge_table_one_rost) = gsub("\\.","_",names(merge_table_one_rost))
merge_table_one_rost$Gender = ifelse(merge_table_one_rost$tesex == 1,"male","female")
merge_table_one_rost$Employment_Status =
ifelse((merge_table_one_rost$telfs==1)|(merge_table_one_rost$telfs==2),"Employed",
ifelse((merge_table_one_rost$telfs==3)|(merge_table_one_rost$telfs==4),"Unemployed","Out of Work Force"))
Does working more than average affect your work life balance?
For the purpose of the project proposal, it is prudent to examine the general time spent on leisure relative to general hours worked to formulate a high level perspective on the most basic interpretation of “work life balance.” My intention for the final project is to expand the definition of “work life balance” to include all time spent outside of work and to examine key areas of interest at the 3rd tier level, or most detailed level according to the ATUS Lexicon. (i.e. religious activities, chores, communication, time spent alone; all of the aforementioned data points are provided in the ATUS data set)
Given that the survey is a random sample of the population it would be prudent to create multiple strata to analyze homogenous data points without a strong skew.
Each case represents a household in the U.S. There are 10493 cases in the primary dataset (atusresp file).
Data collection is sponsored by the Bureau of Labor Statistics as part of the American Time Use Survey (ATUS) and is conducted by the U.S Census Bureau. “In ATUS, individuals are randomly selected from a subset of households that have completed their eighth and final month of interviews for the Current Population Survey(CPS). ATUS respondents are interviewed only one time about how they spent their time on the previous day, where they were, and whom they were with.” - Quoted from the ATUS User Guide
This is an observational study.
Data is collected by the U.S Census Bureau and is available online at two sources, http://asdfree.com/american-time-use-survey-atus.html and https://www.bls.gov/tus/datafiles_2016.htm. In order to collect this data in an efficient and reproducible manner I utilized the lodown library to download the files.
(June 2018). American Time Use Survey User’s Guide. https://www.bls.gov/tus/atususersguide.pdf#page=33 (2003-2017). The American Time Use Survey (ATUS) is sponsored by the Bureau of Labor Statistics and conducted by the U.S. Census Bureau. Retrieved October 30th, 2018 from https://www.bls.gov/tus/datafiles_2016.htm
The response variable is time dedicated to leisure and it is numerical.
The explanatory variable is hours worked per day and it is numerical.
describe(merge_table_one_rost$tuactdur24_5)
describe(merge_table_one_rost$tuactdur24_12)
describe(merge_table_one_rost$teage)
table(merge_table_one_rost$Gender,useNA = "ifany")
##
## female male
## 5701 4614
table(merge_table_one_rost$Employment_Status,useNA = "ifany")
##
## Employed Out of Work Force Unemployed
## 6282 3699 334
prop.table(table(merge_table_one_rost$Employment_Status,useNA = "ifany"))*100
##
## Employed Out of Work Force Unemployed
## 60.901600 35.860397 3.238003
## Description of general work hours by employment status
## Tier One Code of 5 composes the general working hours according to the Lexicon
describeBy(merge_table_one_rost$tuactdur24_5,group =
merge_table_one_rost$Employment_Status, mat = TRUE)
## Description of general work hours by employment status
## Tier One Code of 12 composes the general leisure hours according to the Lexicon
describeBy(merge_table_one_rost$tuactdur24_12,group =
merge_table_one_rost$Employment_Status, mat = TRUE)
## Description of general work hours by age
describeBy(merge_table_one_rost$tuactdur24_5,group = merge_table_one_rost$teage, mat = TRUE)
## Description of general leisure hours by age
describeBy(merge_table_one_rost$tuactdur24_12,group = merge_table_one_rost$teage, mat = TRUE)
## Description of general work hours by gender
describeBy(merge_table_one_rost$tuactdur24_5,group = merge_table_one_rost$Gender, mat = TRUE)
## Description of general leisure hours by gender
describeBy(merge_table_one_rost$tuactdur24_12,group = merge_table_one_rost$Gender, mat = TRUE)
## Histograms
hist(merge_table_one_rost$tuactdur24_5)
hist(merge_table_one_rost$tuactdur24_12)
Condensed estimates for activity by average hours per day from the 2016 survey can be found at https://www.bls.gov/tus/a1_2016.pdf