BRFSS_HISP_RACE_2016

Let’s set up the library packages we might be using for our analysis

library(tidyverse)
library(haven)
library(janitor)
library(descriptio)
#install.packages("weights")
library(weights)
#install.packages("kableExtra")
library(kableExtra)
library(totalcensus)
#install.packages("cdlTools")
library(cdlTools)

Now we read in the data

df_2016 <- read_xpt("./LLCP2016.XPT_")

variable.names(df_2016)

##   [1] "_STATE"   "FMONTH"   "IDATE"    "IMONTH"   "IDAY"     "IYEAR"   
##   [7] "DISPCODE" "SEQNO"    "_PSU"     "CTELENM1" "PVTRESD1" "COLGHOUS"
##  [13] "STATERES" "CELLFON4" "LADULT"   "NUMADULT" "NUMMEN"   "NUMWOMEN"
##  [19] "CTELNUM1" "CELLFON5" "CADULT"   "PVTRESD3" "CCLGHOUS" "CSTATE1" 
##  [25] "LANDLINE" "HHADULT"  "GENHLTH"  "PHYSHLTH" "MENTHLTH" "POORHLTH"
##  [31] "HLTHPLN1" "PERSDOC2" "MEDCOST"  "CHECKUP1" "EXERANY2" "SLEPTIM1"
##  [37] "CVDINFR4" "CVDCRHD4" "CVDSTRK3" "ASTHMA3"  "ASTHNOW"  "CHCSCNCR"
##  [43] "CHCOCNCR" "CHCCOPD1" "HAVARTH3" "ADDEPEV2" "CHCKIDNY" "DIABETE3"
##  [49] "DIABAGE2" "LASTDEN3" "RMVTETH3" "SEX"      "MARITAL"  "EDUCA"   
##  [55] "RENTHOM1" "NUMHHOL2" "NUMPHON2" "CPDEMO1"  "VETERAN3" "EMPLOY1" 
##  [61] "CHILDREN" "INCOME2"  "INTERNET" "WEIGHT2"  "HEIGHT3"  "PREGNANT"
##  [67] "DEAF"     "BLIND"    "DECIDE"   "DIFFWALK" "DIFFDRES" "DIFFALON"
##  [73] "SMOKE100" "SMOKDAY2" "STOPSMK2" "LASTSMK2" "USENOW3"  "ECIGARET"
##  [79] "ECIGNOW"  "ALCDAY5"  "AVEDRNK2" "DRNK3GE5" "MAXDRNKS" "FLUSHOT6"
##  [85] "FLSHTMY2" "PNEUVAC3" "TETANUS"  "FALL12MN" "FALLINJ2" "SEATBELT"
##  [91] "DRNKDRI2" "HADMAM"   "HOWLONG"  "HADPAP2"  "LASTPAP2" "HPVTEST" 
##  [97] "HPLSTTST" "HADHYST2" "PCPSAAD2" "PCPSADI1" "PCPSARE1" "PSATEST1"
## [103] "PSATIME"  "PCPSARS1" "BLDSTOOL" "LSTBLDS3" "HADSIGM3" "HADSGCO1"
## [109] "LASTSIG3" "HIVTST6"  "HIVTSTD3" "HIVRISK4" "PDIABTST" "PREDIAB1"
## [115] "INSULIN"  "BLDSUGAR" "FEETCHK2" "DOCTDIAB" "CHKHEMO3" "FEETCHK" 
## [121] "EYEEXAM"  "DIABEYE"  "DIABEDU"  "PAINACT2" "QLMENTL2" "QLSTRES2"
## [127] "QLHLTH2"  "MEDICARE" "HLTHCVR1" "DELAYMED" "DLYOTHER" "NOCOV121"
## [133] "LSTCOVRG" "DRVISITS" "MEDSCOST" "CARERCVD" "MEDBILL1" "MEDADVIC"
## [139] "UNDRSTND" "WRITTEN"  "CAREGIV1" "CRGVREL1" "CRGVLNG1" "CRGVHRS1"
## [145] "CRGVPRB2" "CRGVPERS" "CRGVHOUS" "CRGVMST2" "CRGVEXPT" "CIMEMLOS"
## [151] "CDHOUSE"  "CDASSIST" "CDHELP"   "CDSOCIAL" "CDDISCUS" "SSBSUGR2"
## [157] "SSBFRUT2" "CALRINFO" "MARIJANA" "USEMRJNA" "ASTHMAGE" "ASATTACK"
## [163] "ASERVIST" "ASDRVIST" "ASRCHKUP" "ASACTLIM" "ASYMPTOM" "ASNOSLEP"
## [169] "ASTHMED3" "ASINHALR" "IMFVPLAC" "HPVADVC2" "HPVADSHT" "SHINGLE2"
## [175] "NUMBURN2" "CNCRDIFF" "CNCRAGE"  "CNCRTYP1" "CSRVTRT1" "CSRVDOC1"
## [181] "CSRVSUM"  "CSRVRTRN" "CSRVINST" "CSRVINSR" "CSRVDEIN" "CSRVCLIN"
## [187] "CSRVPAIN" "CSRVCTL1" "PROFEXAM" "LENGEXAM" "PCPSADE1" "PCDMDECN"
## [193] "SXORIENT" "TRNSGNDR" "RCSGENDR" "RCSRLTN2" "CASTHDX2" "CASTHNO2"
## [199] "EMTSUPRT" "LSATISFY" "QLACTLM2" "USEEQUIP" "QSTVER"   "QSTLANG" 
## [205] "MSCODE"   "_STSTR"   "_STRWT"   "_RAWRAKE" "_WT2RAKE" "_CHISPNC"
## [211] "_CRACE1"  "_CPRACE"  "_CLLCPWT" "_DUALUSE" "_DUALCOR" "_LLCPWT2"
## [217] "_LLCPWT"  "_RFHLTH"  "_PHYS14D" "_MENT14D" "_HCVU651" "_TOTINDA"
## [223] "_MICHD"   "_LTASTH1" "_CASTHM1" "_ASTHMS1" "_DRDXAR1" "_EXTETH2"
## [229] "_ALTETH2" "_DENVST2" "_PRACE1"  "_MRACE1"  "_HISPANC" "_RACE"   
## [235] "_RACEG21" "_RACEGR3" "_RACE_G1" "_AGEG5YR" "_AGE65YR" "_AGE80"  
## [241] "_AGE_G"   "HTIN4"    "HTM4"     "WTKG3"    "_BMI5"    "_BMI5CAT"
## [247] "_RFBMI5"  "_CHLDCNT" "_EDUCAG"  "_INCOMG"  "_SMOKER3" "_RFSMOK3"
## [253] "_ECIGSTS" "_CURECIG" "DRNKANY5" "DROCDY3_" "_RFBING5" "_DRNKWEK"
## [259] "_RFDRHV5" "_FLSHOT6" "_PNEUMO2" "_RFSEAT2" "_RFSEAT3" "_DRNKDRV"
## [265] "_RFMAM2Y" "_MAM5021" "_RFPAP33" "_RFPSA21" "_RFBLDS3" "_COL10YR"
## [271] "_HFOB3YR" "_FS5YR"   "_FOBTFS"  "_CRCREC"  "_AIDTST3"

df2_2016<- df_2016 %>% select(`_STATE`,DISPCODE,SEX,GENHLTH,PHYSHLTH,`_PHYS14D`,
                              MENTHLTH,`_MENT14D`,ADDEPEV2,DIABETE3,HLTHPLN1,
                              ASTHMA3,`_LTASTH1`,`_MICHD`,CHCSCNCR,CHCOCNCR,
                              `_HISPANC`,`_RACE`,`_RACEGR3`,`_PSU`,`_STSTR`,
                              `_STRWT`,`_LLCPWT`,`_LLCPWT2`)

Let’s look at the structure of our data

str(df2_2016)

## tibble [486,303 × 24] (S3: tbl_df/tbl/data.frame)
##  $ _STATE  : num [1:486303] 1 1 1 1 1 1 1 1 1 1 ...
##   ..- attr(*, "label")= chr "STATE FIPS CODE"
##  $ DISPCODE: num [1:486303] 1100 1100 1100 1100 1100 1100 1100 1100 1100 1100 ...
##   ..- attr(*, "label")= chr "FINAL DISPOSITION"
##  $ SEX     : num [1:486303] 1 2 2 1 1 2 2 2 2 1 ...
##   ..- attr(*, "label")= chr "RESPONDENTS SEX"
##  $ GENHLTH : num [1:486303] 1 2 3 3 5 3 3 3 2 2 ...
##   ..- attr(*, "label")= chr "GENERAL HEALTH"
##  $ PHYSHLTH: num [1:486303] 88 88 88 88 10 88 88 88 88 88 ...
##   ..- attr(*, "label")= chr "NUMBER OF DAYS PHYSICAL HEALTH NOT GOOD"
##  $ _PHYS14D: num [1:486303] 1 1 1 1 2 1 1 1 1 1 ...
##   ..- attr(*, "label")= chr "COMPUTED PHYSICAL HEALTH STATUS"
##  $ MENTHLTH: num [1:486303] 88 88 1 88 3 88 88 88 88 88 ...
##   ..- attr(*, "label")= chr "NUMBER OF DAYS MENTAL HEALTH NOT GOOD"
##  $ _MENT14D: num [1:486303] 1 1 2 1 2 1 1 1 1 1 ...
##   ..- attr(*, "label")= chr "COMPUTED MENTAL HEALTH STATUS"
##  $ ADDEPEV2: num [1:486303] 2 1 2 2 2 2 2 1 2 2 ...
##   ..- attr(*, "label")= chr "EVER TOLD YOU HAD A DEPRESSIVE DISORDER"
##  $ DIABETE3: num [1:486303] 3 3 3 1 3 3 3 1 3 3 ...
##   ..- attr(*, "label")= chr "(EVER TOLD) YOU HAVE DIABETES"
##  $ HLTHPLN1: num [1:486303] 1 1 1 1 1 1 1 1 1 1 ...
##   ..- attr(*, "label")= chr "HAVE ANY HEALTH CARE COVERAGE"
##  $ ASTHMA3 : num [1:486303] 2 2 2 2 1 2 2 1 2 2 ...
##   ..- attr(*, "label")= chr "EVER TOLD HAD ASTHMA"
##  $ _LTASTH1: num [1:486303] 1 1 1 1 2 1 1 2 1 1 ...
##   ..- attr(*, "label")= chr "LIFETIME ASTHMA CALCULATED VARIABLE"
##  $ _MICHD  : num [1:486303] 2 2 1 2 2 2 2 2 2 2 ...
##   ..- attr(*, "label")= chr "RESPONDENTS THAT HAVE EVER REPORTED HAVI"
##  $ CHCSCNCR: num [1:486303] 2 2 1 1 2 2 1 1 2 2 ...
##   ..- attr(*, "label")= chr "(EVER TOLD) YOU HAD SKIN CANCER?"
##  $ CHCOCNCR: num [1:486303] 2 2 2 2 2 2 2 2 2 2 ...
##   ..- attr(*, "label")= chr "(EVER TOLD) YOU HAD ANY OTHER TYPES OF C"
##  $ _HISPANC: num [1:486303] 2 2 2 2 2 2 2 2 2 2 ...
##   ..- attr(*, "label")= chr "HISPANIC, LATINO/A, OR SPANISH ORIGIN CA"
##  $ _RACE   : num [1:486303] 1 1 1 1 1 1 1 1 1 1 ...
##   ..- attr(*, "label")= chr "COMPUTED RACE-ETHNICITY GROUPING"
##  $ _RACEGR3: num [1:486303] 1 1 1 1 1 1 1 1 1 1 ...
##   ..- attr(*, "label")= chr "COMPUTED FIVE LEVEL RACE/ETHNICITY CATEG"
##  $ _PSU    : num [1:486303] 2.02e+09 2.02e+09 2.02e+09 2.02e+09 2.02e+09 ...
##   ..- attr(*, "label")= chr "PRIMARY SAMPLING UNIT"
##  $ _STSTR  : num [1:486303] 11011 11011 11011 11011 11011 ...
##   ..- attr(*, "label")= chr "SAMPLE DESIGN STRATIFICATION VARIABLE"
##  $ _STRWT  : num [1:486303] 37.4 37.4 37.4 37.4 37.4 ...
##   ..- attr(*, "label")= chr "STRATUM WEIGHT"
##  $ _LLCPWT : num [1:486303] 768 330 291 211 1583 ...
##   ..- attr(*, "label")= chr "FINAL WEIGHT: LAND-LINE AND CELL-PHONE D"
##  $ _LLCPWT2: num [1:486303] 395 395 197 395 592 ...
##   ..- attr(*, "label")= chr "TRUNCATED DESIGN WEIGHT USED IN ADULT CO"

df2_2016 <- clean_names(df2_2016)
names(df2_2016)

##  [1] "state"    "dispcode" "sex"      "genhlth"  "physhlth" "phys14d" 
##  [7] "menthlth" "ment14d"  "addepev2" "diabete3" "hlthpln1" "asthma3" 
## [13] "ltasth1"  "michd"    "chcscncr" "chcocncr" "hispanc"  "race"    
## [19] "racegr3"  "psu"      "ststr"    "strwt"    "llcpwt"   "llcpwt2"

The results show a tibble (data frame) with 486,303 records and 23 variables of interest. Another point of interest is the variable names, which are a tad messy. We can clean those using the janitor package.

df2_2016 <- clean_names(df2_2016)

names(df2_2016)

##  [1] "state"    "dispcode" "sex"      "genhlth"  "physhlth" "phys14d" 
##  [7] "menthlth" "ment14d"  "addepev2" "diabete3" "hlthpln1" "asthma3" 
## [13] "ltasth1"  "michd"    "chcscncr" "chcocncr" "hispanc"  "race"    
## [19] "racegr3"  "psu"      "ststr"    "strwt"    "llcpwt"   "llcpwt2"

We will start our analysis performing basic exploratory data analysis for variables of interest and perform cross tabulations.

• First let’s look at the distribution of our Race/Ethnicity variables.

  #Let's see the distribution of our variable for identifying those that are Hispanic vs those that are not(_HISPANC). _HISPANC is a calculated variable by the CDC base on reponses to the BRFSS survey.
  #The variable _HISPANC is coded to where 1 = Hispanic, 2 = Non Hispanic, and 9 = Don't know, refused, or missing. To ease analysis we are going to recode the variable to change the numeric coding to character to ease interpretation.
  
  df2_2016$hisp2 <- NA
  df2_2016$hisp2[df2_2016$hispanc == 1] <- "Hispanic"
  df2_2016$hisp2[df2_2016$hispanc == 2] <- "Not Hispanic"
  df2_2016$hisp2[df2_2016$hispanc == 9] <- NA
  
  hisp <- table(df2_2016$hisp2,useNA = "ifany")
  
  #Display table
  hisp %>% 
    kbl() %>% 
    kable_paper(full_width = T) %>%
    scroll_box(width = "100%", height = "200px")

  Var1	Freq
  Hispanic	39224
  Not Hispanic	442452
  NA	4627

  #Barplot with percentages for each group
  barplot(hisp * 100 / nrow(df2_2016))

  

• We can do a similar analysis for our Race variable

  #Let's see the distribution of our variable for identifying 5 major Race categories based on that provided by the survey). _RACE is a calculated variable by the CDC base on reponses to the BRFSS survey.
  #Like the _HISPANC variable, we are going to recode the _RACE variable to ease analysis.
  
  df2_2016$race2 <- NA
  df2_2016$race2[df2_2016$race == 1] <- "White"
  df2_2016$race2[df2_2016$race == 2] <- "Black"
  df2_2016$race2[df2_2016$race == 3] <- "AIAN"
  df2_2016$race2[df2_2016$race == 4] <- "Asian"
  df2_2016$race2[df2_2016$race == 5] <- "NHPI"
  df2_2016$race2[df2_2016$race == 6] <- "Other"
  df2_2016$race2[df2_2016$race == 7] <- "Multi"
  df2_2016$race2[df2_2016$race == 8] <- "Hisp"
  df2_2016$race2[df2_2016$race == 9] <- NA
  
  race <- table(df2_2016$race2,useNA = "ifany")
  
  #Display table
  race %>% 
    kbl() %>% 
    kable_paper(full_width = T) %>%
    scroll_box(width = "100%", height = "200px")

  Var1	Freq
  AIAN	7238
  Asian	10492
  Black	39555
  Hisp	39224
  Multi	9442
  NHPI	1444
  Other	2177
  White	368048
  NA	8683

  #Barplot with percentages for each group
  barplot(race * 100 / nrow(df2_2016))

  

• Total Population Analysis

  #Our analysis will center around the states of New York, Florida, and the territory of Puerto Rico.
  
  selc_state_df <- df2_2016 %>% filter(state == 12 | state == 36 | state == 72)
  
  #Let's recode the State variable to include State Names and Not Fip Codes.
  selc_state_df$state2 <- fips(selc_state_df$state,to = 'Abbreviation')
  
  #Let's calculate the total populations for each state.
  tot_pop <- selc_state_df %>%
    group_by(state) %>%
    summarise(tot_pop = sum(llcpwt))
  
  #Calculate crosstabulation by race.
  pop_race <- xtabs(llcpwt2 ~ state2 + race2, data = selc_state_df)
  
  kbl(round(pop_race,0),
      format.args = list(big.mark = ","),
      align = "c",
      escape = F) %>% 
    kable_classic(full_width = T, html_font = "cambria") %>%
     scroll_box(width = "100%", height = "200px")

  	AIAN	Asian	Black	Hisp	Multi	NHPI	Other	White
  FL	140,011	344,037	1,841,413	3,666,317	170,735	43,529	79,816	9,940,170
  NY	100,698	832,286	1,853,225	2,774,360	227,214	64,534	9,366	9,311,267
  PR	0	29	4,101	2,774,966	607	0	5,899	13,980

• General Health Analysis

  #Let's reacode GENHLTH to make our analysis simpler.
  selc_state_df$genhlth2 <- NA
  selc_state_df$genhlth2[selc_state_df$genhlth == 1] <- "Excellent"
  selc_state_df$genhlth2[selc_state_df$genhlth == 2] <- "Very Good"
  selc_state_df$genhlth2[selc_state_df$genhlth == 3] <- "Good"
  selc_state_df$genhlth2[selc_state_df$genhlth == 4] <- "Fair"
  selc_state_df$genhlth2[selc_state_df$genhlth == 5] <- "Poor"
  selc_state_df$genhlth2[selc_state_df$genhlth == 7] <- NA
  selc_state_df$genhlth2[selc_state_df$genhlth == 9] <- NA
  
  #Calculate the crosstabulation for General Health Variable.
  genhlth_race <- xtabs(llcpwt2 ~ state2 + race2 + genhlth2, data = selc_state_df)
  
  #Create display table.
  kbl(round(genhlth_race,0),
      format.args = list(big.mark = ","),
      align = "c",
      escape = F) %>% 
    kable_classic(full_width = T, html_font = "cambria") %>%
     scroll_box(width = "100%", height = "200px")

  state2	race2	genhlth2	Freq
  FL	AIAN	Excellent	35,871
  NY	AIAN	Excellent	14,754
  PR	AIAN	Excellent	0
  FL	Asian	Excellent	86,818
  NY	Asian	Excellent	176,539
  PR	Asian	Excellent	0
  FL	Black	Excellent	389,300
  NY	Black	Excellent	307,694
  PR	Black	Excellent	636
  FL	Hisp	Excellent	749,879
  NY	Hisp	Excellent	376,644
  PR	Hisp	Excellent	400,294
  FL	Multi	Excellent	32,401
  NY	Multi	Excellent	42,440
  PR	Multi	Excellent	0
  FL	NHPI	Excellent	11,224
  NY	NHPI	Excellent	10,467
  PR	NHPI	Excellent	0
  FL	Other	Excellent	19,896
  NY	Other	Excellent	2,382
  PR	Other	Excellent	1,688
  FL	White	Excellent	2,089,903
  NY	White	Excellent	2,058,368
  PR	White	Excellent	3,695
  FL	AIAN	Fair	20,760
  NY	AIAN	Fair	22,849
  PR	AIAN	Fair	0
  FL	Asian	Fair	15,620
  NY	Asian	Fair	86,783
  PR	Asian	Fair	0
  FL	Black	Fair	235,582
  NY	Black	Fair	238,970
  PR	Black	Fair	1,761
  FL	Hisp	Fair	695,774
  NY	Hisp	Fair	564,595
  PR	Hisp	Fair	902,824
  FL	Multi	Fair	19,581
  NY	Multi	Fair	37,724
  PR	Multi	Fair	0
  FL	NHPI	Fair	2,958
  NY	NHPI	Fair	9,212
  PR	NHPI	Fair	0
  FL	Other	Fair	12,775
  NY	Other	Fair	2,269
  PR	Other	Fair	1,879
  FL	White	Fair	1,233,214
  NY	White	Fair	958,872
  PR	White	Fair	3,291
  FL	AIAN	Good	40,635
  NY	AIAN	Good	23,601
  PR	AIAN	Good	0
  FL	Asian	Good	134,313
  NY	Asian	Good	306,809
  PR	Asian	Good	0
  FL	Black	Good	640,969
  NY	Black	Good	661,271
  PR	Black	Good	1,097
  FL	Hisp	Good	1,178,523
  NY	Hisp	Good	1,091,523
  PR	Hisp	Good	979,148
  FL	Multi	Good	45,686
  NY	Multi	Good	60,442
  PR	Multi	Good	607
  FL	NHPI	Good	12,390
  NY	NHPI	Good	22,807
  PR	NHPI	Good	0
  FL	Other	Good	20,096
  NY	Other	Good	2,110
  PR	Other	Good	1,486
  FL	White	Good	2,783,798
  NY	White	Good	2,602,654
  PR	White	Good	3,566
  FL	AIAN	Poor	10,466
  NY	AIAN	Poor	12,873
  PR	AIAN	Poor	0
  FL	Asian	Poor	11,965
  NY	Asian	Poor	16,170
  PR	Asian	Poor	0
  FL	Black	Poor	112,400
  NY	Black	Poor	76,677
  PR	Black	Poor	0
  FL	Hisp	Poor	168,559
  NY	Hisp	Poor	191,718
  PR	Hisp	Poor	147,510
  FL	Multi	Poor	19,819
  NY	Multi	Poor	14,788
  PR	Multi	Poor	0
  FL	NHPI	Poor	1,470
  NY	NHPI	Poor	0
  PR	NHPI	Poor	0
  FL	Other	Poor	1,102
  NY	Other	Poor	154
  PR	Other	Poor	0
  FL	White	Poor	536,580
  NY	White	Poor	366,006
  PR	White	Poor	58
  FL	AIAN	Very Good	29,061
  NY	AIAN	Very Good	26,550
  PR	AIAN	Very Good	0
  FL	Asian	Very Good	95,096
  NY	Asian	Very Good	239,198
  PR	Asian	Very Good	29
  FL	Black	Very Good	458,317
  NY	Black	Very Good	558,348
  PR	Black	Very Good	607
  FL	Hisp	Very Good	861,650
  NY	Hisp	Very Good	526,273
  PR	Hisp	Very Good	335,013
  FL	Multi	Very Good	53,101
  NY	Multi	Very Good	71,736
  PR	Multi	Very Good	0
  FL	NHPI	Very Good	15,487
  NY	NHPI	Very Good	20,328
  PR	NHPI	Very Good	0
  FL	Other	Very Good	25,902
  NY	Other	Very Good	2,451
  PR	Other	Very Good	846
  FL	White	Very Good	3,267,148
  NY	White	Very Good	3,294,717
  PR	White	Very Good	3,369

  #write.csv(genhlth_race,"genhlth_race.csv")

• Physical Health Analysis

  #We can see a barplot of the distribution of given answers to reported days experiencing not good physical health using the _PHYS14D variable. This is a calculated variable that breaks down days reported into 4 groups.
  
  #First we will recode the variable to ease interpretation.
  selc_state_df$phys2 <- NA
  selc_state_df$phys2[selc_state_df$phys14d==1] <- "Zero Days"
  selc_state_df$phys2[selc_state_df$phys14d==2] <- "1-13 Days"
  selc_state_df$phys2[selc_state_df$phys14d==3] <- "14+ Days"
  
  #Now we can create a barplot to explore the results for the population included in our states of interest.
  phys14d <- table(selc_state_df$phys2,useNA = "ifany")
  barplot(phys14d * 100 / nrow(selc_state_df))

  

  physhlth_race <- xtabs(llcpwt2 ~ state2 + race2 + phys2, 
                         data = selc_state_df)
  
  kbl(round(physhlth_race,0),
      format.args = list(big.mark = ","),
      align = "c",
      escape = F) %>% 
    kable_classic(full_width = T, html_font = "cambria") %>%
     scroll_box(width = "100%", height = "200px")

  state2	race2	phys2	Freq
  FL	AIAN	1-13 Days	22,124
  NY	AIAN	1-13 Days	26,568
  PR	AIAN	1-13 Days	0
  FL	Asian	1-13 Days	55,307
  NY	Asian	1-13 Days	180,880
  PR	Asian	1-13 Days	0
  FL	Black	1-13 Days	378,637
  NY	Black	1-13 Days	455,649
  PR	Black	1-13 Days	2,828
  FL	Hisp	1-13 Days	574,292
  NY	Hisp	1-13 Days	767,006
  PR	Hisp	1-13 Days	461,989
  FL	Multi	1-13 Days	40,788
  NY	Multi	1-13 Days	78,747
  PR	Multi	1-13 Days	0
  FL	NHPI	1-13 Days	6,622
  NY	NHPI	1-13 Days	12,338
  PR	NHPI	1-13 Days	0
  FL	Other	1-13 Days	20,170
  NY	Other	1-13 Days	2,098
  PR	Other	1-13 Days	607
  FL	White	1-13 Days	1,973,603
  NY	White	1-13 Days	2,370,251
  PR	White	1-13 Days	1,695
  FL	AIAN	14+ Days	24,060
  NY	AIAN	14+ Days	20,063
  PR	AIAN	14+ Days	0
  FL	Asian	14+ Days	15,750
  NY	Asian	14+ Days	49,668
  PR	Asian	14+ Days	0
  FL	Black	14+ Days	203,767
  NY	Black	14+ Days	199,209
  PR	Black	14+ Days	29
  FL	Hisp	14+ Days	431,381
  NY	Hisp	14+ Days	364,582
  PR	Hisp	14+ Days	471,651
  FL	Multi	14+ Days	34,615
  NY	Multi	14+ Days	38,373
  PR	Multi	14+ Days	0
  FL	NHPI	14+ Days	1,768
  NY	NHPI	14+ Days	4,493
  PR	NHPI	14+ Days	0
  FL	Other	14+ Days	3,631
  NY	Other	14+ Days	2,269
  PR	Other	14+ Days	58
  FL	White	14+ Days	1,394,863
  NY	White	14+ Days	1,063,789
  PR	White	14+ Days	1,815
  FL	AIAN	Zero Days	86,835
  NY	AIAN	Zero Days	50,983
  PR	AIAN	Zero Days	0
  FL	Asian	Zero Days	268,614
  NY	Asian	Zero Days	575,274
  PR	Asian	Zero Days	29
  FL	Black	Zero Days	1,188,701
  NY	Black	Zero Days	1,117,099
  PR	Black	Zero Days	636
  FL	Hisp	Zero Days	2,574,314
  NY	Hisp	Zero Days	1,519,671
  PR	Hisp	Zero Days	1,816,414
  FL	Multi	Zero Days	89,297
  NY	Multi	Zero Days	106,670
  PR	Multi	Zero Days	607
  FL	NHPI	Zero Days	33,298
  NY	NHPI	Zero Days	44,787
  PR	NHPI	Zero Days	0
  FL	Other	Zero Days	55,454
  NY	Other	Zero Days	4,999
  PR	Other	Zero Days	4,627
  FL	White	Zero Days	6,363,013
  NY	White	Zero Days	5,674,781
  PR	White	Zero Days	10,470

  #write.csv(physhlth_race,"physhlth_race.csv")

• Mental Health

  #To measure mental health we are basing analysis on teh ADDEPEV2 variable, which measures whether the repondent had ever been told they had a depressive 
  #disorder.
  
  #Again we can look at the distribution of responses for all individuals in the selected states. First we will again recode the variables for analysis.
  selc_state_df$menthlth2 <- NA
  selc_state_df$menthlth2[selc_state_df$addepev2==1] <- "Yes"
  selc_state_df$menthlth2[selc_state_df$addepev2==2] <- "No"
  
  addepev <- table(selc_state_df$menthlth2,useNA = "ifany")
  barplot(addepev * 100 / nrow(selc_state_df))

  

  #Now let's calculate our crosstabs.
  menthlth_race <- xtabs(llcpwt2 ~ state2 + race2 + menthlth2, 
                         data = selc_state_df)
  #We can visualize our data in table.
  kbl(round(menthlth_race,0),
      format.args = list(big.mark = ","),
      align = "c",
      escape = F) %>% 
    kable_classic(full_width = T, html_font = "cambria") %>%
     scroll_box(width = "100%", height = "200px")

  state2	race2	menthlth2	Freq
  FL	AIAN	No	112,231
  NY	AIAN	No	76,466
  PR	AIAN	No	0
  FL	Asian	No	330,723
  NY	Asian	No	789,200
  PR	Asian	No	29
  FL	Black	No	1,652,652
  NY	Black	No	1,661,323
  PR	Black	No	4,071
  FL	Hisp	No	3,190,437
  NY	Hisp	No	2,425,207
  PR	Hisp	No	2,216,524
  FL	Multi	No	126,595
  NY	Multi	No	182,714
  PR	Multi	No	607
  FL	NHPI	No	40,790
  NY	NHPI	No	61,913
  PR	NHPI	No	0
  FL	Other	No	76,969
  NY	Other	No	9,213
  PR	Other	No	5,292
  FL	White	No	8,294,173
  NY	White	No	8,014,145
  PR	White	No	11,486
  FL	AIAN	Yes	27,087
  NY	AIAN	Yes	24,232
  PR	AIAN	Yes	0
  FL	Asian	Yes	12,190
  NY	Asian	Yes	33,966
  PR	Asian	Yes	0
  FL	Black	Yes	185,104
  NY	Black	Yes	179,434
  PR	Black	Yes	29
  FL	Hisp	Yes	450,790
  NY	Hisp	Yes	326,062
  PR	Hisp	Yes	551,812
  FL	Multi	Yes	43,807
  NY	Multi	Yes	42,159
  PR	Multi	Yes	0
  FL	NHPI	Yes	2,739
  NY	NHPI	Yes	2,621
  PR	NHPI	Yes	0
  FL	Other	Yes	2,847
  NY	Other	Yes	154
  PR	Other	Yes	607
  FL	White	Yes	1,609,306
  NY	White	Yes	1,256,753
  PR	White	Yes	2,494

  #write.csv(menthlth_race,"menthlth_race.csv")

• Asthma Analysis

  #We will measure Adults who have ever been told they have asthma. Again we will first recode the variable to ease analysis. 
  
  selc_state_df$asthm2 <- NA
  selc_state_df$asthm2[selc_state_df$ltasth1==1] <- "No"
  selc_state_df$asthm2[selc_state_df$ltasth1==2] <- "Yes"
  
  #Now we can plot individuals that reported ever being told they had asthma or not.
  
  asth <- table(selc_state_df$asthm2,useNA = "ifany")
  barplot(asth * 100 / nrow(selc_state_df))

  

  #We can also perform our crosstabulation.
  asthma_race <- xtabs(llcpwt2 ~ state2 + race2 + asthm2, data = selc_state_df)
  
  kbl(round(asthma_race,0),
      format.args = list(big.mark = ","),
      align = "c",
      escape = F) %>% 
    kable_classic(full_width = T, html_font = "cambria") %>%
     scroll_box(width = "100%", height = "200px")

  state2	race2	asthm2	Freq
  FL	AIAN	No	110,333
  NY	AIAN	No	78,621
  PR	AIAN	No	0
  FL	Asian	No	324,153
  NY	Asian	No	748,814
  PR	Asian	No	29
  FL	Black	No	1,628,826
  NY	Black	No	1,555,805
  PR	Black	No	1,644
  FL	Hisp	No	3,212,649
  NY	Hisp	No	2,339,696
  PR	Hisp	No	2,291,851
  FL	Multi	No	142,994
  NY	Multi	No	170,273
  PR	Multi	No	607
  FL	NHPI	No	40,151
  NY	NHPI	No	61,311
  PR	NHPI	No	0
  FL	Other	No	76,329
  NY	Other	No	9,213
  PR	Other	No	4,685
  FL	White	No	8,855,142
  NY	White	No	8,037,881
  PR	White	No	11,523
  FL	AIAN	Yes	25,291
  NY	AIAN	Yes	22,077
  PR	AIAN	Yes	0
  FL	Asian	Yes	19,707
  NY	Asian	Yes	80,145
  PR	Asian	Yes	0
  FL	Black	Yes	209,112
  NY	Black	Yes	295,020
  PR	Black	Yes	2,457
  FL	Hisp	Yes	442,069
  NY	Hisp	Yes	426,359
  PR	Hisp	Yes	481,849
  FL	Multi	Yes	27,741
  NY	Multi	Yes	56,877
  PR	Multi	Yes	0
  FL	NHPI	Yes	3,378
  NY	NHPI	Yes	3,223
  PR	NHPI	Yes	0
  FL	Other	Yes	2,044
  NY	Other	Yes	154
  PR	Other	Yes	1,214
  FL	White	Yes	1,055,297
  NY	White	Yes	1,257,149
  PR	White	Yes	2,457

  #write.csv(asthma_race,"asthma_race.csv")

• Diabetes Analysis

  #We will measure Adults who have ever been told they have diabetes. Again we will first recode the variable to ease analysis. 
  
  selc_state_df$diab2 <- NA
  selc_state_df$diab2[selc_state_df$diabete3==1] <- "Yes"
  selc_state_df$diab2[selc_state_df$diabete3==2] <- "Yes, during pregnancy"
  selc_state_df$diab2[selc_state_df$diabete3==3] <- "No"
  selc_state_df$diab2[selc_state_df$diabete3==4] <- "Pre-diabetes"
  
  #Now we can plot individuals that reported ever being told they had asthma or not.
  
  diab <- table(selc_state_df$diab2,useNA = "ifany")
  barplot(diab * 100 / nrow(selc_state_df))

  

  #We can also perform our crosstabulation.
  diab_race <- xtabs(llcpwt2 ~ state2 + race2 + diab2, data = selc_state_df)
  
  kbl(round(diab_race,0),
      format.args = list(big.mark = ","),
      align = "c",
      escape = F) %>% 
    kable_classic(full_width = T, html_font = "cambria") %>%
     scroll_box(width = "100%", height = "200px")

  state2	race2	diab2	Freq
  FL	AIAN	No	116,863
  NY	AIAN	No	74,884
  PR	AIAN	No	0
  FL	Asian	No	306,880
  NY	Asian	No	724,302
  PR	Asian	No	0
  FL	Black	No	1,463,739
  NY	Black	No	1,505,886
  PR	Black	No	3,435
  FL	Hisp	No	3,157,694
  NY	Hisp	No	2,341,778
  PR	Hisp	No	2,134,242
  FL	Multi	No	147,571
  NY	Multi	No	182,719
  PR	Multi	No	0
  FL	NHPI	No	35,380
  NY	NHPI	No	53,608
  PR	NHPI	No	0
  FL	Other	No	68,481
  NY	Other	No	9,213
  PR	Other	No	5,292
  FL	White	No	8,408,598
  NY	White	No	8,219,194
  PR	White	No	10,787
  FL	AIAN	Pre-diabetes	1,796
  NY	AIAN	Pre-diabetes	5,357
  PR	AIAN	Pre-diabetes	0
  FL	Asian	Pre-diabetes	2,242
  NY	Asian	Pre-diabetes	21,126
  PR	Asian	Pre-diabetes	0
  FL	Black	Pre-diabetes	41,121
  NY	Black	Pre-diabetes	43,171
  PR	Black	Pre-diabetes	29
  FL	Hisp	Pre-diabetes	48,724
  NY	Hisp	Pre-diabetes	57,555
  PR	Hisp	Pre-diabetes	97,625
  FL	Multi	Pre-diabetes	5,026
  NY	Multi	Pre-diabetes	7,853
  PR	Multi	Pre-diabetes	0
  FL	NHPI	Pre-diabetes	0
  NY	NHPI	Pre-diabetes	3,936
  PR	NHPI	Pre-diabetes	0
  FL	Other	Pre-diabetes	1,297
  NY	Other	Pre-diabetes	0
  PR	Other	Pre-diabetes	0
  FL	White	Pre-diabetes	159,714
  NY	White	Pre-diabetes	93,161
  PR	White	Pre-diabetes	929
  FL	AIAN	Yes	19,208
  NY	AIAN	Yes	18,967
  PR	AIAN	Yes	0
  FL	Asian	Yes	31,760
  NY	Asian	Yes	75,394
  PR	Asian	Yes	29
  FL	Black	Yes	313,031
  NY	Black	Yes	284,026
  PR	Black	Yes	636
  FL	Hisp	Yes	410,034
  NY	Hisp	Yes	336,767
  PR	Hisp	Yes	527,914
  FL	Multi	Yes	16,141
  NY	Multi	Yes	32,318
  PR	Multi	Yes	607
  FL	NHPI	Yes	8,149
  NY	NHPI	Yes	5,131
  PR	NHPI	Yes	0
  FL	Other	Yes	9,785
  NY	Other	Yes	154
  PR	Other	Yes	607
  FL	White	Yes	1,243,709
  NY	White	Yes	938,184
  PR	White	Yes	2,265
  FL	AIAN	Yes, during pregnancy	1,795
  NY	AIAN	Yes, during pregnancy	671
  PR	AIAN	Yes, during pregnancy	0
  FL	Asian	Yes, during pregnancy	1,490
  NY	Asian	Yes, during pregnancy	8,724
  PR	Asian	Yes, during pregnancy	0
  FL	Black	Yes, during pregnancy	19,331
  NY	Black	Yes, during pregnancy	11,577
  PR	Black	Yes, during pregnancy	0
  FL	Hisp	Yes, during pregnancy	41,677
  NY	Hisp	Yes, during pregnancy	32,067
  PR	Hisp	Yes, during pregnancy	11,415
  FL	Multi	Yes, during pregnancy	1,943
  NY	Multi	Yes, during pregnancy	4,324
  PR	Multi	Yes, during pregnancy	0
  FL	NHPI	Yes, during pregnancy	0
  NY	NHPI	Yes, during pregnancy	1,858
  PR	NHPI	Yes, during pregnancy	0
  FL	Other	Yes, during pregnancy	228
  NY	Other	Yes, during pregnancy	0
  PR	Other	Yes, during pregnancy	0
  FL	White	Yes, during pregnancy	115,082
  NY	White	Yes, during pregnancy	47,641
  PR	White	Yes, during pregnancy	0

  #write.csv(diab_race,"diab_race.csv")

• Heart Condition Analysis

  #To analyze Heart Conditions we are using the _MICHD variable, which captures whether the respondent have ever reported having coronary heart disease or myocardial infarction.
  
  #Again we will perform some recoding to ease analisis. 
  selc_state_df$michd2 <- NA
  selc_state_df$michd2[selc_state_df$michd==1] <- "Yes"
  selc_state_df$michd2[selc_state_df$michd==2] <- "No"
  
  #Now we can plot individuals that reported ever being told they had asthma or not.
  michd <- table(selc_state_df$michd2,useNA = "ifany")
  barplot(michd * 100 / nrow(selc_state_df))

  

  #Let's perform our crosstabs.
  michd_race <- xtabs(llcpwt2 ~ state2 + race2 + michd2, data = selc_state_df)
  
  kbl(round(michd_race,0),
      format.args = list(big.mark = ","),
      align = "c",
      escape = F) %>% 
    kable_classic(full_width = T, html_font = "cambria") %>%
     scroll_box(width = "100%", height = "200px")

  state2	race2	michd2	Freq
  FL	AIAN	No	124,405
  NY	AIAN	No	83,483
  PR	AIAN	No	0
  FL	Asian	No	324,399
  NY	Asian	No	790,677
  PR	Asian	No	29
  FL	Black	No	1,693,698
  NY	Black	No	1,728,806
  PR	Black	No	3,494
  FL	Hisp	No	3,451,601
  NY	Hisp	No	2,595,800
  PR	Hisp	No	2,406,335
  FL	Multi	No	155,210
  NY	Multi	No	206,329
  PR	Multi	No	607
  FL	NHPI	No	41,333
  NY	NHPI	No	58,580
  PR	NHPI	No	0
  FL	Other	No	72,647
  NY	Other	No	7,097
  PR	Other	No	5,899
  FL	White	No	8,889,148
  NY	White	No	8,545,919
  PR	White	No	11,201
  FL	AIAN	Yes	14,979
  NY	AIAN	Yes	13,233
  PR	AIAN	Yes	0
  FL	Asian	Yes	13,755
  NY	Asian	Yes	25,376
  PR	Asian	Yes	0
  FL	Black	Yes	119,136
  NY	Black	Yes	102,531
  PR	Black	Yes	607
  FL	Hisp	Yes	186,214
  NY	Hisp	Yes	144,222
  PR	Hisp	Yes	360,066
  FL	Multi	Yes	15,228
  NY	Multi	Yes	17,762
  PR	Multi	Yes	0
  FL	NHPI	Yes	2,162
  NY	NHPI	Yes	4,096
  PR	NHPI	Yes	0
  FL	Other	Yes	5,156
  NY	Other	Yes	0
  PR	Other	Yes	0
  FL	White	Yes	986,575
  NY	White	Yes	713,002
  PR	White	Yes	2,779

  #write.csv(michd_race,"michd_race.csv")

• Cancer Analysis

  #The BRFSS measures cancer divinf into two variables. One that measures whether the respondent has ever had skin cancer (CHCSCNCR) and another that measures whether the respondent has had any other type of cancer (CHCOCNCR).
  
  #Again we will perform some recoding to ease analisis. 
  
  #First let's look at Skin Cancer
  selc_state_df$skncncr2 <- NA
  selc_state_df$skncncr2[selc_state_df$chcscncr==1] <- "Yes"
  selc_state_df$skncncr2[selc_state_df$chcscncr==2] <- "No"
  
  #Now we can plot individuals that reported ever being told they had asthma or not.
  skncncr <- table(selc_state_df$skncncr2,useNA = "ifany")
  barplot(skncncr * 100 / nrow(selc_state_df))

  

  #Let's perform our crosstabs.
  skncancr_race <- xtabs(llcpwt2 ~ state2 + race2 + skncncr2, 
                         data = selc_state_df)
  
  kbl(round(skncancr_race,0),
      format.args = list(big.mark = ","),
      align = "c",
      escape = F) %>% 
    kable_classic(full_width = T, html_font = "cambria") %>%
     scroll_box(width = "100%", height = "200px")

  state2	race2	skncncr2	Freq
  FL	AIAN	No	122,335
  NY	AIAN	No	97,902
  PR	AIAN	No	0
  FL	Asian	No	341,416
  NY	Asian	No	830,075
  PR	Asian	No	29
  FL	Black	No	1,828,574
  NY	Black	No	1,842,772
  PR	Black	No	4,101
  FL	Hisp	No	3,565,662
  NY	Hisp	No	2,742,833
  PR	Hisp	No	2,727,521
  FL	Multi	No	160,003
  NY	Multi	No	222,853
  PR	Multi	No	607
  FL	NHPI	No	42,689
  NY	NHPI	No	64,293
  PR	NHPI	No	0
  FL	Other	No	72,694
  NY	Other	No	9,366
  PR	Other	No	5,899
  FL	White	No	8,277,436
  NY	White	No	8,560,764
  PR	White	No	13,503
  FL	AIAN	Yes	16,875
  NY	AIAN	Yes	2,796
  PR	AIAN	Yes	0
  FL	Asian	Yes	551
  NY	Asian	Yes	2,131
  PR	Asian	Yes	0
  FL	Black	Yes	10,409
  NY	Black	Yes	6,700
  PR	Black	Yes	0
  FL	Hisp	Yes	93,211
  NY	Hisp	Yes	23,867
  PR	Hisp	Yes	44,534
  FL	Multi	Yes	10,702
  NY	Multi	Yes	4,362
  PR	Multi	Yes	0
  FL	NHPI	Yes	840
  NY	NHPI	Yes	241
  PR	NHPI	Yes	0
  FL	Other	Yes	7,097
  NY	Other	Yes	0
  PR	Other	Yes	0
  FL	White	Yes	1,627,186
  NY	White	Yes	731,058
  PR	White	Yes	477

  #write.csv(skncancr_race,"skncancr_race.csv")
  
  ###############################################################################
  
  #Now let's look at Other Cancer
  selc_state_df$othcncr2 <- NA
  selc_state_df$othcncr2[selc_state_df$chcocncr==1] <- "Yes"
  selc_state_df$othcncr2[selc_state_df$chcocncr==2] <- "No"
  
  #Now we can plot individuals that reported ever being told they had asthma or not.
  othcncr <- table(selc_state_df$othcncr2,useNA = "ifany")
  barplot(othcncr * 100 / nrow(selc_state_df))

  

  #Let's perform our crosstabs.
  othcancr_race <- xtabs(llcpwt2 ~ state2 + race2 + othcncr2, 
                         data = selc_state_df)
  
  kbl(round(othcancr_race,0),
      format.args = list(big.mark = ","),
      align = "c",
      escape = F) %>% 
    kable_classic(full_width = T, html_font = "cambria")%>%
     scroll_box(width = "100%", height = "200px")

  state2	race2	othcncr2	Freq
  FL	AIAN	No	119,931
  NY	AIAN	No	89,124
  PR	AIAN	No	0
  FL	Asian	No	338,185
  NY	Asian	No	820,432
  PR	Asian	No	0
  FL	Black	No	1,740,008
  NY	Black	No	1,727,639
  PR	Black	No	4,101
  FL	Hisp	No	3,472,117
  NY	Hisp	No	2,685,760
  PR	Hisp	No	2,589,076
  FL	Multi	No	156,560
  NY	Multi	No	218,299
  PR	Multi	No	607
  FL	NHPI	No	40,570
  NY	NHPI	No	64,090
  PR	NHPI	No	0
  FL	Other	No	70,898
  NY	Other	No	9,366
  PR	Other	No	5,292
  FL	White	No	8,834,246
  NY	White	No	8,427,400
  PR	White	No	13,922
  FL	AIAN	Yes	18,885
  NY	AIAN	Yes	11,575
  PR	AIAN	Yes	0
  FL	Asian	Yes	5,675
  NY	Asian	Yes	11,854
  PR	Asian	Yes	29
  FL	Black	Yes	96,564
  NY	Black	Yes	121,088
  PR	Black	Yes	0
  FL	Hisp	Yes	188,103
  NY	Hisp	Yes	83,549
  PR	Hisp	Yes	180,382
  FL	Multi	Yes	14,146
  NY	Multi	Yes	8,915
  PR	Multi	Yes	0
  FL	NHPI	Yes	2,959
  NY	NHPI	Yes	444
  PR	NHPI	Yes	0
  FL	Other	Yes	8,891
  NY	Other	Yes	0
  PR	Other	Yes	607
  FL	White	Yes	1,077,549
  NY	White	Yes	864,722
  PR	White	Yes	58

  #write.csv(othcancr_race,"othcancr_race.csv")

• Health Care

  #We will measure respondents that have any kind of health care. Again we will first recode the variable to ease analysis. 
  
  selc_state_df$hlth2 <- NA
  selc_state_df$hlth2[selc_state_df$hlthpln1==1] <- "No"
  selc_state_df$hlth2[selc_state_df$hlthpln1==2] <- "Yes"
  
  hlthcr <- table(selc_state_df$hlth2,useNA = "ifany")
  barplot(hlthcr * 100 / nrow(selc_state_df))

  

  hlthcr_race <- xtabs(llcpwt2 ~ state2 + race2 + hlth2, data = selc_state_df)
  
  kbl(round(hlthcr_race,0),
      format.args = list(big.mark = ","),
      align = "c",
      escape = F) %>% 
    kable_classic(full_width = T, html_font = "cambria") %>%
     scroll_box(width = "100%", height = "200px")

  state2	race2	hlth2	Freq
  FL	AIAN	No	110,230
  NY	AIAN	No	90,644
  PR	AIAN	No	0
  FL	Asian	No	302,685
  NY	Asian	No	755,271
  PR	Asian	No	29
  FL	Black	No	1,517,289
  NY	Black	No	1,668,326
  PR	Black	No	4,101
  FL	Hisp	No	2,636,895
  NY	Hisp	No	2,206,993
  PR	Hisp	No	2,619,051
  FL	Multi	No	137,981
  NY	Multi	No	198,979
  PR	Multi	No	607
  FL	NHPI	No	31,058
  NY	NHPI	No	50,454
  PR	NHPI	No	0
  FL	Other	No	59,366
  NY	Other	No	6,818
  PR	Other	No	5,870
  FL	White	No	9,023,700
  NY	White	No	8,883,704
  PR	White	No	13,951
  FL	AIAN	Yes	29,178
  NY	AIAN	Yes	9,461
  PR	AIAN	Yes	0
  FL	Asian	Yes	38,678
  NY	Asian	Yes	69,968
  PR	Asian	Yes	0
  FL	Black	Yes	315,626
  NY	Black	Yes	168,277
  PR	Black	Yes	0
  FL	Hisp	Yes	1,010,205
  NY	Hisp	Yes	549,898
  PR	Hisp	Yes	150,030
  FL	Multi	Yes	32,753
  NY	Multi	Yes	26,840
  PR	Multi	Yes	0
  FL	NHPI	Yes	12,250
  NY	NHPI	Yes	12,359
  PR	NHPI	Yes	0
  FL	Other	Yes	20,415
  NY	Other	Yes	2,548
  PR	Other	Yes	29
  FL	White	Yes	859,266
  NY	White	Yes	391,650
  PR	White	Yes	29

  #write.csv(hlthcr_race,"hlthcr_race.csv")