Intro Stuff
library(tidyverse)
## Warning: package 'tidyverse' was built under R version 4.0.2
## -- Attaching packages --------------------------------------- tidyverse 1.3.0 --
## v ggplot2 3.3.2 v purrr 0.3.4
## v tibble 3.0.4 v dplyr 1.0.2
## v tidyr 1.1.2 v stringr 1.4.0
## v readr 1.4.0 v forcats 0.5.0
## Warning: package 'tibble' was built under R version 4.0.3
## Warning: package 'tidyr' was built under R version 4.0.2
## Warning: package 'dplyr' was built under R version 4.0.2
## -- Conflicts ------------------------------------------ tidyverse_conflicts() --
## x dplyr::filter() masks stats::filter()
## x dplyr::lag() masks stats::lag()
library(infer)
## Warning: package 'infer' was built under R version 4.0.2
library(pastecs)
## Warning: package 'pastecs' was built under R version 4.0.3
##
## Attaching package: 'pastecs'
## The following objects are masked from 'package:dplyr':
##
## first, last
## The following object is masked from 'package:tidyr':
##
## extract
library(mosaic)
## Warning: package 'mosaic' was built under R version 4.0.2
## Registered S3 method overwritten by 'mosaic':
## method from
## fortify.SpatialPolygonsDataFrame ggplot2
##
## The 'mosaic' package masks several functions from core packages in order to add
## additional features. The original behavior of these functions should not be affected by this.
##
## Attaching package: 'mosaic'
## The following object is masked from 'package:Matrix':
##
## mean
## The following objects are masked from 'package:infer':
##
## prop_test, t_test
## The following objects are masked from 'package:dplyr':
##
## count, do, tally
## The following object is masked from 'package:purrr':
##
## cross
## The following object is masked from 'package:ggplot2':
##
## stat
## The following objects are masked from 'package:stats':
##
## binom.test, cor, cor.test, cov, fivenum, IQR, median, prop.test,
## quantile, sd, t.test, var
## The following objects are masked from 'package:base':
##
## max, mean, min, prod, range, sample, sum
library(Hmisc)
## Warning: package 'Hmisc' was built under R version 4.0.3
## Loading required package: survival
## Loading required package: Formula
## Warning: package 'Formula' was built under R version 4.0.3
##
## Attaching package: 'Hmisc'
## The following objects are masked from 'package:dplyr':
##
## src, summarize
## The following objects are masked from 'package:base':
##
## format.pval, units
library(gmodels)
## Warning: package 'gmodels' was built under R version 4.0.3
getwd()
## [1] "C:/Users/Jerome/Documents/From_Toshiba_HD_Work_Files/0000_Montgomery_College/Math_217/Final_Project/Working_Folder"
family_z34 <- read.csv ("family_z34.csv")
Examine Variables
table(family_z34$FM_SIZE)
##
## 1 2 3 4 5 6 7 8 9 10
## 70 88 61 56 30 17 5 1 1 1
table(family_z34$FM_TYPE)
##
## 1 2 3 4
## 70 112 36 112
table(family_z34$FM_STRP)
##
## 11 12 21 22 23 31 32 41 42 43 44 45
## 63 7 41 18 53 32 4 30 10 16 48 8
table(family_z34$FM_KIDS)
##
## 0 1 2 3 4 5 6
## 182 49 57 26 11 4 1
table(family_z34$FM_ELDR)
##
## 0 1 2
## 305 20 5
table(family_z34$FM_EDUC1)
##
## 1 2 3 4 5 6 7 8 9
## 1 15 5 66 98 48 16 62 19
table(family_z34$F10DVYN)
##
## 1 2
## 138 192
table(family_z34$FDMEDYN)
##
## 1 2
## 190 140
table(family_z34$FNMEDYN)
##
## 1 2
## 172 158
table(family_z34$FLIADLCT)
##
## 0 1 2
## 279 49 2
table(family_z34$FWKLIMCT)
##
## 0 1 2 3
## 189 117 19 5
table(family_z34$FHSTATEX)
##
## 0 1 2 3 4 5 6
## 221 47 30 11 12 5 4
family_z35 <- mutate(family_z34, health_ins = ifelse(FHIPRVCT > 0 | FHISINCT > 0 |FHICARCT > 0 | FHICADCT >0 |FHICHPCT >0 | FHIMILCT >0 | FHIPUBCT > 0 | FHIOGVCT > 0 | FHIIHSCT> 0 | FHIEXCT > 0, 1,0))
table(family_z35$health_ins)
##
## 1
## 330
table(family_z34$FHIPRVCT)
##
## 0 1 2 3 4 5 6 7
## 2 165 81 39 19 15 6 3
table(family_z34$FHISINCT)
##
## 0 1 2 3 4 5 6 7
## 139 89 45 23 13 14 5 2
table(family_z34$FHICARCT)
##
## 0 1 2
## 277 45 8
table(family_z34$FHICADCT)
##
## 0 1 2 3 4 5 6
## 229 36 30 18 10 5 2
table(family_z34$FHICHPCT)
##
## 0 1 2 3 4
## 321 3 3 2 1
table(family_z34$FHIMILCT)
##
## 0 1 2 3
## 319 9 1 1
table(family_z34$FHIPUBCT)
##
## 0 1 2
## 326 2 2
table(family_z34$FHIOGVCT)
##
## 0
## 330
table(family_z34$FHIIHSCT)
##
## 0 1
## 329 1
table(family_z34$FHIEXCT)
##
## 0 1 2
## 322 7 1
table(family_z35$INCGRP5)
##
## 1 2 3 4
## 135 160 15 20
table(family_z35$RAT_CAT5)
##
## 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18
## 14 12 11 26 20 33 22 49 48 26 25 10 6 11 8 6 1 2
table(family_z34$COVCONF)
##
## 1 2 3 4
## 6 17 44 263
table(family_z34$FHICOST)
##
## 0 1 2 3 4 5
## 13 56 133 47 38 43
table(family_z34$FMEDBNOP)
##
## 1 2
## 227 103
table(family_z34$FSAF)
##
## 1 2 9
## 49 278 3
table(family_z34$FHICOVCT)
##
## 1 2 3 4 5 6 7 8 10
## 86 90 61 48 25 13 4 2 1
table(family_z34$FHICOVYN)
##
## 1
## 330
table(family_z34$FHIEBCCT)
##
## 1 2 3 4 5 6 7
## 175 76 36 17 16 5 3
table(family_z34$FMEDBILL)
##
## 1
## 330
write.csv(family_z35, file = "family_z35.csv", row.names = FALSE)
family_z35 <- read.csv("family_z35.csv")
family_z31 <- read.csv("family_z31.csv")
family_z50 <- mutate(family_z31, food_sec = ifelse(FSRUNOUT == 1 & FSLAST == 1 & FSSKIP == 1 & FSBALANC == 1 & FSLESS == 1 & FSHUNGRY == 1 & FSWEIGHT == 1 & FSNOTEAT == 1, 1,0))
table(family_z50$food_sec)
##
## 0 1
## 321 9
family_z51 <- mutate(family_z31, health_ins = ifelse(FHIPRVCT > 0 & FHISINCT > 0 & FHICARCT > 0 & FHICADCT >0 |FHICHPCT >0 & FHIMILCT >0 & FHIPUBCT > 0 & FHIOGVCT > 0 & FHIIHSCT> 0 & FHIEXCT > 0, 1,0))
table(family_z51$health_ins)
##
## 0 1
## 318 12
family_z17 <- read.csv("family_z17.csv")
family_z52 <- mutate(family_z17, health_ins = ifelse(FHIPRVCT > 0 & FHISINCT > 0 & FHICARCT > 0 & FHICADCT >0 & FHICHPCT >0 & FHIMILCT >0 & FHIPUBCT > 0 & FHIOGVCT > 0 & FHIIHSCT> 0 & FHIEXCT > 0, 1,0))
table(family_z52$health_ins)
##
## 0
## 2357
family_z52 <- mutate(family_z17, health_ins = ifelse(FHIPRVCT > 0 | FHISINCT > 0 | FHICARCT > 0 | FHICADCT >0 | FHICHPCT >0 | FHIMILCT >0 | FHIPUBCT > 0 | FHIOGVCT > 0 | FHIIHSCT> 0 | FHIEXCT > 0, 1,0))
table(family_z52$health_ins)
##
## 0 1
## 230 2127
family_0 <- read.csv("family_0.csv")
private_ins <- filter(family_0, FHIPRVCT > 0)
family_z53 <- mutate(family_0, health_ins = ifelse(FHIPRVCT > 0 | FHISINCT > 0 | FHICARCT > 0 | FHICADCT >0 | FHICHPCT >0 | FHIMILCT >0 | FHIPUBCT > 0 | FHIOGVCT > 0 | FHIIHSCT> 0 | FHIEXCT > 0, 1,0))
table(family_z53$health_ins)
##
## 0 1
## 1591 31566
family_z54 <- mutate(family_z53, food_sec = ifelse(FSRUNOUT == 1 | FSLAST == 1 | FSSKIP == 1 | FSBALANC == 1 | FSLESS == 1 | FSHUNGRY == 1 | FSWEIGHT == 1 | FSNOTEAT == 1, 1,0))
table(family_z54$food_sec)
##
## 1
## 2967
table(family_z54$health_ins)
##
## 0 1
## 1591 31566
write.csv(family_z54, file = "family_z54.csv", row.names = FALSE)
family_z54 <- read.csv("family_z54.csv")
table(family_z54$food_sec, family_z54$health_ins)
##
## 0 1
## 1 273 2694
201201 Ready to Clean
Remove Variables
family_z55 <- family_z54[,-c(1:6)]
family_z55$FM_STRCP <- NULL
#family_z55$TELN_FLG <- NULL
family_z55$CURWRKN <- NULL
family_z55$TELCELN <- NULL
family_z55$WRKCELN <- NULL
family_z55$PHONEUSE <- NULL
family_z55$WTFA_FAM <- NULL
family_z55$F10DVCT <- NULL
family_z55$FDMEDCT <- NULL
family_z55$FHCDVCT <- NULL
family_z55$FHCDVYN <- NULL
family_z55$FHCHMCT <- NULL
family_z55$FHCHMYN <- NULL
family_z55$FHCPHRCT <- NULL
family_z55$FHCPHRYN <- NULL
family_z55$FHOSP2CT <- NULL
family_z55$FHOSP2YN <- NULL
family_z55$FNMEDCT <- NULL
family_z55$FSSKDAYS <- NULL
family_z55$FSNEDAYS <- NULL
family_z55$FHDSTCT <- NULL
family_z55$FDGLWCT1 <- NULL
family_z55$FDGLWCT2 <- NULL
family_z55$FWRKLWCT <- NULL
family_z55$FCHLMYN <- NULL
family_z55$FSPEDYN <- NULL
family_z55$FLAADLYN <- NULL
family_z55$FLIADLYN <- NULL
write.csv(family_z55, file = "family_z55.csv", row.names = FALSE)
At this point, deleted columns in Excel
family_z56 <- read.csv("family_z56.csv")
table(family_z56$FM_SIZE)
##
## 1 2 3 4 5 6 7 8 9 10 11 12 13
## 10799 10989 4582 3937 1841 653 211 86 33 18 3 3 1
## 14
## 1
table(family_z56$FM_TYPE)
##
## 1 2 3 4
## 10799 12755 1567 8036
table(family_z56$FLNGINTV)
##
## 1 2 3 4 8
## 31598 883 465 198 13
table(family_z56$FM_KIDS)
##
## 0 1 2 3 4 5 6 7 8 10
## 23550 4054 3521 1424 427 129 37 11 3 1
table(family_z56$FM_ELDR)
##
## 0 1 2 3 5
## 23220 6531 3361 44 1
table(family_z56$FM_EDUC1)
##
## 1 2 3 4 5 6 7 8 9 97 99
## 753 1694 620 5776 6094 2849 1572 7817 5812 118 52
family_z57 <- filter(family_z56, FM_EDUC1 < 10)
table(family_z57$FM_EDUC1)
##
## 1 2 3 4 5 6 7 8 9
## 753 1694 620 5776 6094 2849 1572 7817 5812
write.csv(family_z57, file = "family_z57.csv", row.names = FALSE)
table(family_z57$HOUSEOWN)
##
## 1 2 3 7 8 9
## 20733 10914 997 105 225 13
family_z58 <- filter(family_z57, HOUSEOWN < 4)
table(family_z58$HOUSEOWN)
##
## 1 2 3
## 20733 10914 997
write.csv(family_z58, file = "family_z58.csv", row.names = FALSE)
table(family_z58$FNMEDYN)
##
## 1 2 7 9
## 2879 29748 6 11
family_z59 <- filter(family_z58, FNMEDYN < 3)
table(family_z59$FNMEDYN)
##
## 1 2
## 2879 29748
table(family_z59$FANYLCT)
##
## 0 1 2 3 4 5 6
## 23355 7358 1641 229 33 10 1
table(family_z59$INCGRP5)
##
## 1 2 3 4 96 99
## 10083 8696 3409 7244 1633 1562
table(family_z59$RAT_CAT5)
##
## 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16
## 1394 947 1243 1252 1086 1276 975 2288 1813 2034 1399 1681 1250 7763 499 919
## 17 18 96 99
## 961 1324 961 1562
family_z60 <- filter(family_z59, INCGRP5 < 05)
table(family_z60$INCGRP5)
##
## 1 2 3 4
## 10083 8696 3409 7244
table(family_z60$RAT_CAT5)
##
## 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16
## 1394 947 1243 1252 1086 1276 975 2288 1813 2034 1399 1681 1250 7763 476 736
## 17 18 96
## 404 1153 262
family_z61 <- filter(family_z60, RAT_CAT5 < 19)
table(family_z61$RAT_CAT5)
##
## 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16
## 1394 947 1243 1252 1086 1276 975 2288 1813 2034 1399 1681 1250 7763 476 736
## 17 18
## 404 1153
table(family_z61$COVCONF)
##
## 1 2 3 4 7 9
## 2669 4246 3859 5282 6 225
table(family_z61$FHICOST)
##
## 0 1 2 3 4 5 7 9
## 4031 9943 8156 2531 1958 2161 24 366
table(family_z61$FMEDBILL)
##
## 1 2 7 9
## 3917 25215 3 35
table(family_z61$FMEDBNOP)
##
## 1 2 7 9
## 1998 1924 3 30
table(family_z61$FSAF)
##
## 1 2 7 9
## 3765 25134 6 265
table(family_z61$FHICOVCT)
##
## 0 1 2 3 4 5 6 7 8 9 10 11
## 1518 9863 9238 3719 2896 1301 434 124 51 16 9 1
table(family_z61$FHICOVYN)
##
## 1 2 7 8 9
## 27652 1474 9 1 34
table(family_z61$FHIEBCCT)
##
## 0 1 2 3 4 5 6 7 8 9 10 11
## 4057 6246 4982 2099 1857 742 208 38 16 8 1 1
family_z62 <- filter(family_z61, FHICOST <6)
table(family_z62$FHICOST)
##
## 0 1 2 3 4 5
## 4031 9943 8156 2531 1958 2161
table(family_z62$COVCONF)
##
## 1 2 3 4 7 9
## 2637 4195 3815 5216 5 214
family_z63 <- filter(family_z62, COVCONF < 5)
table(family_z63$FHICOST)
##
## 0 1 2 3 4 5
## 1165 5042 5122 1724 1375 1435
table(family_z63$COVCONF)
##
## 1 2 3 4
## 2637 4195 3815 5216
table(family_z63$COVCONF)
##
## 1 2 3 4
## 2637 4195 3815 5216
table(family_z63$FHICOST)
##
## 0 1 2 3 4 5
## 1165 5042 5122 1724 1375 1435
table(family_z63$FMEDBILL)
##
## 1 2 9
## 1877 13982 4
table(family_z63$FMEDBNOP)
##
## 1 2 7 9
## 817 1052 1 11
table(family_z63$FSAF)
##
## 1 2 7 9
## 3386 12302 2 173
table(family_z63$FHICOVCT)
##
## 0 1 2 3 4 5 6 7 8 9 10 11
## 16 4342 5394 2554 2178 932 310 85 35 10 6 1
table(family_z63$FHICOVYN)
##
## 1 2
## 15847 16
table(family_z63$FHIEBCCT)
##
## 0 1 2 3 4 5 6 7 8 9 10 11
## 36 6015 4847 2055 1818 728 199 37 16 8 1 1
family_z64 <- filter(family_z63, FSAF < 3)
table(family_z64$COVCONF)
##
## 1 2 3 4
## 2607 4138 3782 5161
table(family_z64$FHICOST)
##
## 0 1 2 3 4 5
## 1147 4961 5081 1708 1366 1425
table(family_z64$FMEDBILL)
##
## 1 2 9
## 1862 13822 4
table(family_z64$FMEDBNOP)
##
## 1 2 7 9
## 810 1044 1 11
table(family_z64$FSAF)
##
## 1 2
## 3386 12302
table(family_z64$FHICOVCT)
##
## 0 1 2 3 4 5 6 7 8 9 10 11
## 16 4273 5355 2532 2144 925 308 85 33 10 6 1
table(family_z64$FHICOVYN)
##
## 1 2
## 15672 16
table(family_z64$FHIEBCCT)
##
## 0 1 2 3 4 5 6 7 8 9 10 11
## 36 5930 4814 2030 1795 722 198 37 14 8 1 1
family_z65 <- filter(family_z64, FMEDBNOP < 3)
table(family_z65$FMEDBILL)
##
## 1 9
## 1850 4
table(family_z65$FMEDBNOP)
##
## 1 2
## 810 1044
family_z66 <- filter(family_z65, FMEDBILL < 3)
table(family_z66$FMEDBILL)
##
## 1
## 1850
write.csv(family_z66, file = "family_z66.csv", row.names = FALSE)
write.csv(family_z63, file = "family_z63.csv", row.names = FALSE)
family_z63$FMEDBNOP <- NULL
family_z63$FSAF <- NULL
write.csv(family_z63, file = "family_z63.csv", row.names = FALSE)
table(family_z63$COVCONF)
##
## 1 2 3 4
## 2637 4195 3815 5216
table(family_z63$FHICOST)
##
## 0 1 2 3 4 5
## 1165 5042 5122 1724 1375 1435
table(family_z63$FMEDBILL)
##
## 1 2 9
## 1877 13982 4
table(family_z64$FHICOVYN)
##
## 1 2
## 15672 16
family_z70 <- filter(family_z63, FMEDBILL < 3)
table(family_z70$FMEDBILL)
##
## 1 2
## 1877 13982
write.csv(family_z70, file = "family_z70.csv", row.names = FALSE)