Statistics for Demographic Data II

Author

Jacob Souch

Initialize

library(tidyverse)

── Attaching packages ─────────────────────────────────────── tidyverse 1.3.2 ──
✔ ggplot2 3.4.0      ✔ purrr   1.0.1 
✔ tibble  3.1.8      ✔ dplyr   1.0.10
✔ tidyr   1.3.0      ✔ stringr 1.5.0 
✔ readr   2.1.3      ✔ forcats 0.5.2 
── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
✖ dplyr::filter() masks stats::filter()
✖ dplyr::lag()    masks stats::lag()

library(haven)
library(gtsummary)
library(gt)
library(ggplot2)
library(scales)


Attaching package: 'scales'

The following object is masked from 'package:purrr':

    discard

The following object is masked from 'package:readr':

    col_factor

library(purrr)
library(haven)
library(janitor)


Attaching package: 'janitor'

The following objects are masked from 'package:stats':

    chisq.test, fisher.test

library(viridis)

Loading required package: viridisLite

Attaching package: 'viridis'

The following object is masked from 'package:scales':

    viridis_pal

library(usmap)
library(ggthemes)
library(tigris)

To enable caching of data, set `options(tigris_use_cache = TRUE)`
in your R script or .Rprofile.

setwd("C:/Users/jacob/OneDrive - University of Texas at San Antonio/Courses/Stats for Demographic Data 2/Homework 4")

Import Data

tibble [438,693 × 303] (S3: tbl_df/tbl/data.frame)
 $ _STATE  : num [1:438693] 1 1 1 1 1 1 1 1 1 1 ...
  ..- attr(*, "label")= chr "STATE FIPS CODE"
 $ FMONTH  : num [1:438693] 1 1 1 1 1 1 1 1 2 2 ...
  ..- attr(*, "label")= chr "FILE MONTH"
 $ IDATE   : chr [1:438693] "01192021" "01212021" "01212021" "01172021" ...
  ..- attr(*, "label")= chr "INTERVIEW DATE"
 $ IMONTH  : chr [1:438693] "01" "01" "01" "01" ...
  ..- attr(*, "label")= chr "INTERVIEW MONTH"
 $ IDAY    : chr [1:438693] "19" "21" "21" "17" ...
  ..- attr(*, "label")= chr "INTERVIEW DAY"
 $ IYEAR   : chr [1:438693] "2021" "2021" "2021" "2021" ...
  ..- attr(*, "label")= chr "INTERVIEW YEAR"
 $ DISPCODE: num [1:438693] 1100 1100 1100 1100 1100 1100 1100 1100 1100 1100 ...
  ..- attr(*, "label")= chr "FINAL DISPOSITION"
 $ SEQNO   : chr [1:438693] "2021000001" "2021000002" "2021000003" "2021000004" ...
  ..- attr(*, "label")= chr "ANNUAL SEQUENCE NUMBER"
 $ _PSU    : num [1:438693] 2.02e+09 2.02e+09 2.02e+09 2.02e+09 2.02e+09 ...
  ..- attr(*, "label")= chr "PRIMARY SAMPLING UNIT"
 $ CTELENM1: num [1:438693] 1 1 1 1 1 1 1 1 1 1 ...
  ..- attr(*, "label")= chr "CORRECT TELEPHONE NUMBER?"
 $ PVTRESD1: num [1:438693] 1 1 1 1 1 1 1 1 1 1 ...
  ..- attr(*, "label")= chr "PRIVATE RESIDENCE?"
 $ COLGHOUS: num [1:438693] NA NA NA NA NA NA NA NA NA NA ...
  ..- attr(*, "label")= chr "DO YOU LIVE IN COLLEGE HOUSING?"
 $ STATERE1: num [1:438693] 1 1 1 1 1 1 1 1 1 1 ...
  ..- attr(*, "label")= chr "RESIDENT OF STATE"
 $ CELPHON1: num [1:438693] 2 2 2 2 2 2 2 2 2 2 ...
  ..- attr(*, "label")= chr "CELLULAR TELEPHONE"
 $ LADULT1 : num [1:438693] 1 1 1 1 1 1 1 1 1 1 ...
  ..- attr(*, "label")= chr "ARE YOU 18 YEARS OF AGE OR OLDER?"
 $ COLGSEX : num [1:438693] NA NA NA NA NA NA NA NA NA NA ...
  ..- attr(*, "label")= chr "ARE YOU MALE OR FEMALE?"
 $ NUMADULT: num [1:438693] 2 2 2 2 2 1 2 1 1 2 ...
  ..- attr(*, "label")= chr "NUMBER OF ADULTS IN HOUSEHOLD"
 $ LANDSEX : num [1:438693] NA NA NA NA NA 1 NA 1 2 NA ...
  ..- attr(*, "label")= chr "ARE YOU MALE OR FEMALE?"
 $ NUMMEN  : num [1:438693] 1 1 1 1 1 NA 1 NA NA 1 ...
  ..- attr(*, "label")= chr "NUMBER OF ADULT MEN IN HOUSEHOLD"
 $ NUMWOMEN: num [1:438693] 1 1 1 1 1 NA 1 NA NA 1 ...
  ..- attr(*, "label")= chr "NUMBER OF ADULT WOMEN IN HOUSEHOLD"
 $ RESPSLCT: num [1:438693] 2 2 2 2 1 NA 1 NA NA 2 ...
  ..- attr(*, "label")= chr "RESPONDENT SELECTION"
 $ SAFETIME: num [1:438693] NA NA NA NA NA NA NA NA NA NA ...
  ..- attr(*, "label")= chr "SAFE TIME TO TALK?"
 $ CTELNUM1: num [1:438693] NA NA NA NA NA NA NA NA NA NA ...
  ..- attr(*, "label")= chr "CORRECT PHONE NUMBER?"
 $ CELLFON5: num [1:438693] NA NA NA NA NA NA NA NA NA NA ...
  ..- attr(*, "label")= chr "IS THIS A CELL PHONE?"
 $ CADULT1 : num [1:438693] NA NA NA NA NA NA NA NA NA NA ...
  ..- attr(*, "label")= chr "ARE YOU 18 YEARS OF AGE OR OLDER?"
 $ CELLSEX : num [1:438693] NA NA NA NA NA NA NA NA NA NA ...
  ..- attr(*, "label")= chr "ARE YOU MALE OR FEMALE?"
 $ PVTRESD3: num [1:438693] NA NA NA NA NA NA NA NA NA NA ...
  ..- attr(*, "label")= chr "DO YOU LIVE IN A PRIVATE RESIDENCE?"
 $ CCLGHOUS: num [1:438693] NA NA NA NA NA NA NA NA NA NA ...
  ..- attr(*, "label")= chr "DO YOU LIVE IN COLLEGE HOUSING?"
 $ CSTATE1 : num [1:438693] NA NA NA NA NA NA NA NA NA NA ...
  ..- attr(*, "label")= chr "DO YOU CURRENTLY LIVE IN  ____(STATE)___"
 $ LANDLINE: num [1:438693] NA NA NA NA NA NA NA NA NA NA ...
  ..- attr(*, "label")= chr "DO YOU ALSO HAVE A LANDLINE TELEPHONE?"
 $ HHADULT : num [1:438693] NA NA NA NA NA NA NA NA NA NA ...
  ..- attr(*, "label")= chr "NUMBER OF ADULTS IN HOUSEHOLD"
 $ SEXVAR  : num [1:438693] 2 2 2 2 1 1 1 1 2 2 ...
  ..- attr(*, "label")= chr "SEX OF RESPONDENT"
 $ GENHLTH : num [1:438693] 5 3 2 2 5 3 3 4 2 3 ...
  ..- attr(*, "label")= chr "GENERAL HEALTH"
 $ PHYSHLTH: num [1:438693] 20 88 88 88 30 88 30 88 88 25 ...
  ..- attr(*, "label")= chr "NUMBER OF DAYS PHYSICAL HEALTH NOT GOOD"
 $ MENTHLTH: num [1:438693] 10 88 88 10 88 88 88 88 88 5 ...
  ..- attr(*, "label")= chr "NUMBER OF DAYS MENTAL HEALTH NOT GOOD"
 $ POORHLTH: num [1:438693] 88 NA NA 88 30 NA 2 NA NA 5 ...
  ..- attr(*, "label")= chr "POOR PHYSICAL OR MENTAL HEALTH"
 $ PRIMINSR: num [1:438693] 3 1 2 2 3 3 1 2 3 3 ...
  ..- attr(*, "label")= chr "WHAT IS PRIMARY SOURCE OF HEALTH INSURAN"
 $ PERSDOC3: num [1:438693] 1 2 2 1 1 1 1 1 1 2 ...
  ..- attr(*, "label")= chr "HAVE PERSONAL HEALTH CARE PROVIDER?"
 $ MEDCOST1: num [1:438693] 2 2 2 2 2 2 2 2 2 2 ...
  ..- attr(*, "label")= chr "COULD NOT AFFORD TO SEE DOCTOR"
 $ CHECKUP1: num [1:438693] 2 1 1 1 1 1 1 1 2 1 ...
  ..- attr(*, "label")= chr "LENGTH OF TIME SINCE LAST ROUTINE CHECKU"
 $ EXERANY2: num [1:438693] 2 1 2 1 1 2 2 1 2 1 ...
  ..- attr(*, "label")= chr "EXERCISE IN PAST 30 DAYS"
 $ BPHIGH6 : num [1:438693] 3 1 1 1 4 3 1 1 3 1 ...
  ..- attr(*, "label")= chr "EVER TOLD BLOOD PRESSURE HIGH"
 $ BPMEDS  : num [1:438693] NA 1 1 1 NA NA 1 1 NA 1 ...
  ..- attr(*, "label")= chr "CURRENTLY TAKING BLOOD PRESSURE MEDICATI"
 $ CHOLCHK3: num [1:438693] 2 2 2 2 2 2 2 2 2 2 ...
  ..- attr(*, "label")= chr "HOW LONG SINCE CHOLESTEROL CHECKED"
 $ TOLDHI3 : num [1:438693] 1 1 2 1 1 2 2 1 2 2 ...
  ..- attr(*, "label")= chr "EVER TOLD CHOLESTEROL IS HIGH"
 $ CHOLMED3: num [1:438693] 1 1 2 2 1 2 2 1 2 1 ...
  ..- attr(*, "label")= chr "CURRENTLY TAKING MEDICINE FOR HIGH CHOLE"
 $ CVDINFR4: num [1:438693] 2 2 2 2 1 2 2 1 2 2 ...
  ..- attr(*, "label")= chr "EVER DIAGNOSED WITH HEART ATTACK"
 $ CVDCRHD4: num [1:438693] 2 1 1 2 7 2 2 1 2 2 ...
  ..- attr(*, "label")= chr "EVER DIAGNOSED WITH ANGINA OR CORONARY H"
 $ CVDSTRK3: num [1:438693] 2 2 2 2 1 2 2 2 2 2 ...
  ..- attr(*, "label")= chr "EVER DIAGNOSED WITH A STROKE"
 $ ASTHMA3 : num [1:438693] 1 2 2 2 2 2 2 2 2 2 ...
  ..- attr(*, "label")= chr "EVER TOLD HAD ASTHMA"
 $ ASTHNOW : num [1:438693] 1 NA NA NA NA NA NA NA NA NA ...
  ..- attr(*, "label")= chr "STILL HAVE ASTHMA"
 $ CHCSCNCR: num [1:438693] 2 2 2 2 2 2 2 2 2 2 ...
  ..- attr(*, "label")= chr "(EVER TOLD) YOU HAD SKIN CANCER?"
 $ CHCOCNCR: num [1:438693] 2 2 2 2 2 2 2 2 2 2 ...
  ..- attr(*, "label")= chr "(EVER TOLD) YOU HAD ANY OTHER TYPES OF C"
 $ CHCCOPD3: num [1:438693] 1 2 2 2 2 1 2 1 2 2 ...
  ..- attr(*, "label")= chr "EVER TOLD YOU HAD C.O.P.D. EMPHYSEMA OR"
 $ ADDEPEV3: num [1:438693] 2 2 2 2 2 2 1 2 2 2 ...
  ..- attr(*, "label")= chr "(EVER TOLD) YOU HAD A DEPRESSIVE DISORDE"
 $ CHCKDNY2: num [1:438693] 2 1 2 2 2 2 2 2 2 2 ...
  ..- attr(*, "label")= chr "EVER TOLD YOU HAVE KIDNEY DISEASE?"
 $ DIABETE4: num [1:438693] 3 1 1 1 1 3 3 3 3 3 ...
  ..- attr(*, "label")= chr "(EVER TOLD) YOU HAD DIABETES"
 $ DIABAGE3: num [1:438693] NA 98 98 56 65 NA NA NA NA NA ...
  ..- attr(*, "label")= chr "AGE WHEN TOLD DIABETES"
 $ HAVARTH5: num [1:438693] 1 1 2 2 2 2 1 1 2 1 ...
  ..- attr(*, "label")= chr "TOLD HAVE ARTHRITIS"
 $ ARTHEXER: num [1:438693] 2 1 NA NA NA NA 1 2 NA 1 ...
  ..- attr(*, "label")= chr "DR. SUGGEST USE OF PHYSICAL ACTIVITY OR"
 $ ARTHEDU : num [1:438693] 2 2 NA NA NA NA 2 2 NA 2 ...
  ..- attr(*, "label")= chr "EVER TAKEN CLASS IN MANAGING ARTHRITIS O"
 $ LMTJOIN3: num [1:438693] 2 1 NA NA NA NA 1 2 NA 2 ...
  ..- attr(*, "label")= chr "LIMITED BECAUSE OF JOINT SYMPTOMS"
 $ ARTHDIS2: num [1:438693] 1 1 NA NA NA NA 2 2 NA 2 ...
  ..- attr(*, "label")= chr "DOES ARTHRITIS AFFECT WHETHER YOU WORK"
 $ JOINPAI2: num [1:438693] 8 10 NA NA NA NA 8 8 NA 4 ...
  ..- attr(*, "label")= chr "HOW BAD WAS JOINT PAIN"
 $ MARITAL : num [1:438693] 1 9 3 1 1 1 1 2 2 1 ...
  ..- attr(*, "label")= chr "MARITAL STATUS"
 $ EDUCA   : num [1:438693] 4 6 4 4 3 5 6 3 3 4 ...
  ..- attr(*, "label")= chr "EDUCATION LEVEL"
 $ RENTHOM1: num [1:438693] 1 1 1 1 1 1 1 1 1 1 ...
  ..- attr(*, "label")= chr "OWN OR RENT HOME"
 $ NUMHHOL3: num [1:438693] 1 2 2 2 2 2 2 2 2 2 ...
  ..- attr(*, "label")= chr "HOUSEHOLD TELEPHONES"
 $ NUMPHON3: num [1:438693] 1 NA NA NA NA NA NA NA NA NA ...
  ..- attr(*, "label")= chr "RESIDENTIAL PHONES"
 $ CPDEMO1B: num [1:438693] 1 1 1 1 8 1 2 8 1 2 ...
  ..- attr(*, "label")= chr "DO YOU HAVE A CELL PHONE FOR PERSONAL US"
 $ VETERAN3: num [1:438693] 2 2 2 2 2 2 2 2 2 2 ...
  ..- attr(*, "label")= chr "ARE YOU A VETERAN"
 $ EMPLOY1 : num [1:438693] 7 8 7 7 8 7 8 2 7 7 ...
  ..- attr(*, "label")= chr "EMPLOYMENT STATUS"
 $ CHILDREN: num [1:438693] 88 88 88 88 88 88 88 88 88 88 ...
  ..- attr(*, "label")= chr "NUMBER OF CHILDREN IN HOUSEHOLD"
 $ INCOME3 : num [1:438693] 5 77 3 7 4 6 77 99 77 8 ...
  ..- attr(*, "label")= chr "INCOME LEVEL"
 $ PREGNANT: num [1:438693] NA NA NA NA NA NA NA NA NA NA ...
  ..- attr(*, "label")= chr "PREGNANCY STATUS"
 $ WEIGHT2 : num [1:438693] 72 7777 170 195 206 ...
  ..- attr(*, "label")= chr "REPORTED WEIGHT IN POUNDS"
 $ HEIGHT3 : num [1:438693] 411 506 505 504 511 603 600 509 503 505 ...
  ..- attr(*, "label")= chr "REPORTED HEIGHT IN FEET AND INCHES"
 $ DEAF    : num [1:438693] 2 2 2 2 1 2 1 2 2 2 ...
  ..- attr(*, "label")= chr "ARE YOU DEAF OR DO YOU HAVE SERIOUS DIFF"
 $ BLIND   : num [1:438693] 2 1 2 2 2 2 2 2 2 2 ...
  ..- attr(*, "label")= chr "BLIND OR DIFFICULTY SEEING"
 $ DECIDE  : num [1:438693] 2 1 2 2 2 2 2 1 2 2 ...
  ..- attr(*, "label")= chr "DIFFICULTY CONCENTRATING OR REMEMBERING"
 $ DIFFWALK: num [1:438693] 2 1 2 2 1 1 1 2 2 1 ...
  ..- attr(*, "label")= chr "DIFFICULTY WALKING OR CLIMBING STAIRS"
 $ DIFFDRES: num [1:438693] 2 2 2 2 2 2 1 2 2 2 ...
  ..- attr(*, "label")= chr "DIFFICULTY DRESSING OR BATHING"
 $ DIFFALON: num [1:438693] 1 1 2 2 2 2 1 2 1 2 ...
  ..- attr(*, "label")= chr "DIFFICULTY DOING ERRANDS ALONE"
 $ SMOKE100: num [1:438693] 1 2 2 2 2 1 2 1 2 1 ...
  ..- attr(*, "label")= chr "SMOKED AT LEAST 100 CIGARETTES"
 $ SMOKDAY2: num [1:438693] 3 NA NA NA NA 3 NA 3 NA 3 ...
  ..- attr(*, "label")= chr "FREQUENCY OF DAYS NOW SMOKING"
 $ USENOW3 : num [1:438693] 3 3 3 3 2 2 3 3 3 3 ...
  ..- attr(*, "label")= chr "USE OF SMOKELESS TOBACCO PRODUCTS"
 $ ECIGNOW1: num [1:438693] 3 3 3 3 3 3 3 3 3 3 ...
  ..- attr(*, "label")= chr "DO YOU NOW USE E-CIGARETTES, EVERY DAY,"
 $ ALCDAY5 : num [1:438693] 888 888 888 101 888 888 888 888 888 203 ...
  ..- attr(*, "label")= chr "DAYS IN PAST 30 HAD ALCOHOLIC BEVERAGE"
 $ AVEDRNK3: num [1:438693] NA NA NA 3 NA NA NA NA NA 2 ...
  ..- attr(*, "label")= chr "AVG ALCOHOLIC DRINKS PER DAY IN PAST 30"
 $ DRNK3GE5: num [1:438693] NA NA NA 1 NA NA NA NA NA 88 ...
  ..- attr(*, "label")= chr "BINGE DRINKING"
 $ MAXDRNKS: num [1:438693] NA NA NA 6 NA NA NA NA NA 2 ...
  ..- attr(*, "label")= chr "MOST DRINKS ON SINGLE OCCASION PAST 30 D"
 $ FLUSHOT7: num [1:438693] 1 2 2 1 1 1 1 1 1 2 ...
  ..- attr(*, "label")= chr "ADULT FLU SHOT/SPRAY PAST 12 MOS"
 $ FLSHTMY3: num [1:438693] 92020 NA NA 102020 92020 ...
  ..- attr(*, "label")= chr "WHEN RECEIVED MOST RECENT SEASONAL FLU S"
 $ IMFVPLA2: num [1:438693] 1 NA NA 1 1 5 1 1 1 NA ...
  ..- attr(*, "label")= chr "WHERE DID YOU GET YOUR LAST FLU SHOT/VAC"
 $ PNEUVAC4: num [1:438693] 1 2 2 2 1 1 2 1 2 1 ...
  ..- attr(*, "label")= chr "PNEUMONIA SHOT EVER"
 $ HIVTST7 : num [1:438693] 2 2 2 2 1 2 2 2 2 2 ...
  ..- attr(*, "label")= chr "EVER TESTED H.I.V."
 $ HIVTSTD3: num [1:438693] NA NA NA NA 777777 ...
  ..- attr(*, "label")= chr "MONTH AND YEAR OF LAST HIV TEST"
 $ FRUIT2  : num [1:438693] 101 101 101 203 101 202 312 204 202 101 ...
  ..- attr(*, "label")= chr "HOW MANY TIMES DID YOU EAT FRUIT?"
 $ FRUITJU2: num [1:438693] 555 555 555 205 555 555 301 555 101 555 ...
  ..- attr(*, "label")= chr "HOW MANY TIMES DID YOU DRINK 100 PERCENT"
 $ FVGREEN1: num [1:438693] 204 201 555 303 101 201 203 202 555 202 ...
  ..- attr(*, "label")= chr "HOW MANY TIMES DID YOU EAT DARK GREEN VE"
 $ FRENCHF1: num [1:438693] 203 555 201 204 202 555 203 555 777 202 ...
  ..- attr(*, "label")= chr "HOW OFTEN DO YOU EAT FRENCH FRIES OR FRI"
 $ POTATOE1: num [1:438693] 201 201 201 308 202 201 302 204 555 203 ...
  ..- attr(*, "label")= chr "HOW OFTEN DO YOU EAT FRENCH FRIES OR FRI"
 $ VEGETAB2: num [1:438693] 101 207 203 205 101 201 202 204 202 204 ...
  ..- attr(*, "label")= chr "HOW OFTEN DO YOU EAT FRENCH FRIES OR FRI"
 $ PDIABTST: num [1:438693] 2 NA NA NA NA 2 1 1 1 1 ...
  ..- attr(*, "label")= chr "HAD A TEST FOR HIGH BLOOD SUGAR IN PAST"
 $ PREDIAB1: num [1:438693] 3 NA NA NA NA 3 3 3 3 3 ...
  ..- attr(*, "label")= chr "EVER BEEN TOLD YOU HAVE PRE-DIABETES OR"
 $ INSULIN1: num [1:438693] NA NA NA NA NA NA NA NA NA NA ...
  ..- attr(*, "label")= chr "NOW TAKING INSULIN"
 $ BLDSUGAR: num [1:438693] NA NA NA NA NA NA NA NA NA NA ...
  ..- attr(*, "label")= chr "HOW OFTEN CHECK BLOOD FOR GLUCOSE"
 $ FEETCHK3: num [1:438693] NA NA NA NA NA NA NA NA NA NA ...
  ..- attr(*, "label")= chr "HOW OFTEN CHECK FEET FOR SORES OR IRRITA"
 $ DOCTDIAB: num [1:438693] NA NA NA NA NA NA NA NA NA NA ...
  ..- attr(*, "label")= chr "TIMES SEEN HEALTH PROFESSIONAL FOR DIABE"
 $ CHKHEMO3: num [1:438693] NA NA NA NA NA NA NA NA NA NA ...
  ..- attr(*, "label")= chr "TIMES CHECKED FOR GLYCOSYLATED HEMOGLOBI"
 $ FEETCHK : num [1:438693] NA NA NA NA NA NA NA NA NA NA ...
  ..- attr(*, "label")= chr "TIMES FEET CHECK FOR SORES/IRRITATIONS"
 $ EYEEXAM1: num [1:438693] NA NA NA NA NA NA NA NA NA NA ...
  ..- attr(*, "label")= chr "LAST EYE EXAM WHERE PUPILS WERE DILATED"
 $ DIABEYE : num [1:438693] NA NA NA NA NA NA NA NA NA NA ...
  ..- attr(*, "label")= chr "EVER TOLD DIABETES HAS AFFECTED EYES"
 $ DIABEDU : num [1:438693] NA NA NA NA NA NA NA NA NA NA ...
  ..- attr(*, "label")= chr "EVER TAKEN CLASS IN MANAGING DIABETES"
 $ TOLDCFS : num [1:438693] NA NA NA NA NA NA NA NA NA NA ...
  ..- attr(*, "label")= chr "TOLD HAD CHRONIC FATIGUE SYNDROME OR MYA"
 $ HAVECFS : num [1:438693] NA NA NA NA NA NA NA NA NA NA ...
  ..- attr(*, "label")= chr "STILL HAVE CHRONIC FATIGUE SYNDROME OR M"
 $ WORKCFS : num [1:438693] NA NA NA NA NA NA NA NA NA NA ...
  ..- attr(*, "label")= chr "HOW MANY HOURS A WEEK ARE YOU BEEN ABLE"
 $ TOLDHEPC: num [1:438693] NA NA NA NA NA NA NA NA NA NA ...
  ..- attr(*, "label")= chr "TOLD HAD HEPATITIS C"
 $ TRETHEPC: num [1:438693] NA NA NA NA NA NA NA NA NA NA ...
  ..- attr(*, "label")= chr "TREATED FOR HEPATITIS C"
 $ PRIRHEPC: num [1:438693] NA NA NA NA NA NA NA NA NA NA ...
  ..- attr(*, "label")= chr "WERE YOU TREATED FOR HEPATITIS C PRIOR T"
 $ HAVEHEPC: num [1:438693] NA NA NA NA NA NA NA NA NA NA ...
  ..- attr(*, "label")= chr "STILL HAVE HEPATITIS C"
 $ HAVEHEPB: num [1:438693] NA NA NA NA NA NA NA NA NA NA ...
  ..- attr(*, "label")= chr "TOLD  HAD HEPATITIS B"
 $ MEDSHEPB: num [1:438693] NA NA NA NA NA NA NA NA NA NA ...
  ..- attr(*, "label")= chr "CURRENTLY TAKING MEDICINE FOR HEPATITIS"
 $ HPVADVC4: num [1:438693] NA NA NA NA NA NA NA NA NA NA ...
  ..- attr(*, "label")= chr "EVER HAD AN H.P.V. VACCINATION?"
 $ HPVADSHT: num [1:438693] NA NA NA NA NA NA NA NA NA NA ...
  ..- attr(*, "label")= chr "NUMBER OF HPV SHOTS RECEIVED"
 $ TETANUS1: num [1:438693] NA NA NA NA NA NA NA NA NA NA ...
  ..- attr(*, "label")= chr "RECEIVED TETANUS SHOT SINCE 2005?"
 $ SHINGLE2: num [1:438693] NA NA NA NA NA NA NA NA NA NA ...
  ..- attr(*, "label")= chr "HAVE YOU EVER HAD THE SHINGLES OR ZOSTER"
 $ LCSFIRST: num [1:438693] NA NA NA NA NA NA NA NA NA NA ...
  ..- attr(*, "label")= chr "HOW OLD WHEN YOU FIRST STARTED SMOKING?"
 $ LCSLAST : num [1:438693] NA NA NA NA NA NA NA NA NA NA ...
  ..- attr(*, "label")= chr "HOW OLD WHEN YOU LAST SMOKED?"
 $ LCSNUMCG: num [1:438693] NA NA NA NA NA NA NA NA NA NA ...
  ..- attr(*, "label")= chr "ON AVERAGE, HOW MANY CIGARETTES DO YOU S"
 $ LCSCTSCN: num [1:438693] NA NA NA NA NA NA NA NA NA NA ...
  ..- attr(*, "label")= chr "DID YOU HAVE A CT OR CAT SCAN?"
 $ HADMAM  : num [1:438693] NA NA NA NA NA NA NA NA NA NA ...
  ..- attr(*, "label")= chr "HAVE YOU EVER HAD A MAMMOGRAM"
 $ HOWLONG : num [1:438693] NA NA NA NA NA NA NA NA NA NA ...
  ..- attr(*, "label")= chr "HOW LONG SINCE LAST MAMMOGRAM"
 $ CERVSCRN: num [1:438693] NA NA NA NA NA NA NA NA NA NA ...
  ..- attr(*, "label")= chr "HAVE YOU EVER HAD A CERVICAL CANCER SCRE"
 $ CRVCLCNC: num [1:438693] NA NA NA NA NA NA NA NA NA NA ...
  ..- attr(*, "label")= chr "TIME SINCE LAST CERVICAL CANCER SCREENIN"
 $ CRVCLPAP: num [1:438693] NA NA NA NA NA NA NA NA NA NA ...
  ..- attr(*, "label")= chr "HAVE A PAP TEST AND RECENT CERVICAL CANC"
 $ CRVCLHPV: num [1:438693] NA NA NA NA NA NA NA NA NA NA ...
  ..- attr(*, "label")= chr "HAVE AN H.P.V. TEST AND RECENT CERVICAL"
 $ HADHYST2: num [1:438693] NA NA NA NA NA NA NA NA NA NA ...
  ..- attr(*, "label")= chr "HAD HYSTERECTOMY"
 $ PSATEST1: num [1:438693] NA NA NA NA NA NA NA NA NA NA ...
  ..- attr(*, "label")= chr "EVER HAD PSA TEST"
 $ PSATIME1: num [1:438693] NA NA NA NA NA NA NA NA NA NA ...
  ..- attr(*, "label")= chr "TIME SINCE MOST RECENT PSA TEST"
 $ PCPSARS2: num [1:438693] NA NA NA NA NA NA NA NA NA NA ...
  ..- attr(*, "label")= chr "WHAT WAS THE MAIN REASON YOU HAD THIS PS"
 $ PCSTALK : num [1:438693] NA NA NA NA NA NA NA NA NA NA ...
  ..- attr(*, "label")= chr "DID YOU TALK ABOUT THE ADVANTAGES OR DIS"
 $ HADSIGM4: num [1:438693] NA NA NA NA NA NA NA NA NA NA ...
  ..- attr(*, "label")= chr "EVER HAD SIGMOIDOSCOPY/COLONOSCOPY"
 $ COLNSIGM: num [1:438693] NA NA NA NA NA NA NA NA NA NA ...
  ..- attr(*, "label")= chr "EVER HAD A COLONOSCOPY, SIGMOIDOSCOPY, O"
 $ COLNTES1: num [1:438693] NA NA NA NA NA NA NA NA NA NA ...
  ..- attr(*, "label")= chr "HOW LONG HAS IT BEEN SINCE YOU HAD COLON"
 $ SIGMTES1: num [1:438693] NA NA NA NA NA NA NA NA NA NA ...
  ..- attr(*, "label")= chr "HOW LONG HAS IT BEEN SINCE YOU HAD SIGMO"
 $ LASTSIG4: num [1:438693] NA NA NA NA NA NA NA NA NA NA ...
  ..- attr(*, "label")= chr "TIME SINCE LAST SIGMOIDOSCOPY/COLONOSCOP"
 $ COLNCNCR: num [1:438693] NA NA NA NA NA NA NA NA NA NA ...
  ..- attr(*, "label")= chr "EVER HAD ANY OTHER KIND OF TEST FOR COLO"
 $ VIRCOLO1: num [1:438693] NA NA NA NA NA NA NA NA NA NA ...
  ..- attr(*, "label")= chr "HAVE YOU EVER HAD A VIRTUAL COLONOSCOPY?"
 $ VCLNTES1: num [1:438693] NA NA NA NA NA NA NA NA NA NA ...
  ..- attr(*, "label")= chr "HOW LONG HAS IT BEEN SINCE YOU HAD VIRTU"
 $ SMALSTOL: num [1:438693] NA NA NA NA NA NA NA NA NA NA ...
  ..- attr(*, "label")= chr "EVER HAD STOOL TEST?"
 $ STOLTEST: num [1:438693] NA NA NA NA NA NA NA NA NA NA ...
  ..- attr(*, "label")= chr "HOW LONG SINCE YOU HAD STOOL TEST?"
 $ STOOLDN1: num [1:438693] NA NA NA NA NA NA NA NA NA NA ...
  ..- attr(*, "label")= chr "EVER HAD STOOL DNA TEST?"
 $ BLDSTFIT: num [1:438693] NA NA NA NA NA NA NA NA NA NA ...
  ..- attr(*, "label")= chr "WAS TEST PART OF COLOGUARD TEST?"
 $ SDNATES1: num [1:438693] NA NA NA NA NA NA NA NA NA NA ...
  ..- attr(*, "label")= chr "HOW LONG SINCE YOU HAD STOOL DNA?"
 $ CNCRDIFF: num [1:438693] NA NA NA NA NA NA NA NA NA NA ...
  ..- attr(*, "label")= chr "HOW MANY TYPES OF CANCER?"
 $ CNCRAGE : num [1:438693] NA NA NA NA NA NA NA NA NA NA ...
  ..- attr(*, "label")= chr "AGE TOLD HAD CANCER"
 $ CNCRTYP1: num [1:438693] NA NA NA NA NA NA NA NA NA NA ...
  ..- attr(*, "label")= chr "TYPE OF CANCER"
 $ CSRVTRT3: num [1:438693] NA NA NA NA NA NA NA NA NA NA ...
  ..- attr(*, "label")= chr "CURRENTLY RECEIVING TREATMENT FOR CANCER"
 $ CSRVDOC1: num [1:438693] NA NA NA NA NA NA NA NA NA NA ...
  ..- attr(*, "label")= chr "WHAT TYPE OF DOCTOR PROVIDES MAJORITY OF"
 $ CSRVSUM : num [1:438693] NA NA NA NA NA NA NA NA NA NA ...
  ..- attr(*, "label")= chr "DID YOU RECEIVE A SUMMARY OF CANCER TREA"
 $ CSRVRTRN: num [1:438693] NA NA NA NA NA NA NA NA NA NA ...
  ..- attr(*, "label")= chr "EVER RECEIVE INSTRUCTIONS FROM A DOCTOR"
 $ CSRVINST: num [1:438693] NA NA NA NA NA NA NA NA NA NA ...
  ..- attr(*, "label")= chr "INSTRUCTIONS WRITTEN OR PRINTED"
 $ CSRVINSR: num [1:438693] NA NA NA NA NA NA NA NA NA NA ...
  ..- attr(*, "label")= chr "DID HEALTH INSURANCE PAY FOR ALL OF YOUR"
 $ CSRVDEIN: num [1:438693] NA NA NA NA NA NA NA NA NA NA ...
  ..- attr(*, "label")= chr "EVER DENIED INSURANCE COVERAGE BECAUSE O"
 $ CSRVCLIN: num [1:438693] NA NA NA NA NA NA NA NA NA NA ...
  ..- attr(*, "label")= chr "PARTICIPATE IN CLINICAL TRIAL AS PART OF"
 $ CSRVPAIN: num [1:438693] NA NA NA NA NA NA NA NA NA NA ...
  ..- attr(*, "label")= chr "CURRENTLY HAVE PHYSICAL PAIN FROM CANCER"
 $ CSRVCTL2: num [1:438693] NA NA NA NA NA NA NA NA NA NA ...
  ..- attr(*, "label")= chr "IS PAIN UNDER CONTROL?"
 $ HOMBPCHK: num [1:438693] NA NA NA NA NA NA NA NA NA NA ...
  ..- attr(*, "label")= chr "TOLD CHECK BLOOD PRESSURE AT HOME"
 $ HOMRGCHK: num [1:438693] NA NA NA NA NA NA NA NA NA NA ...
  ..- attr(*, "label")= chr "REGULARLY CHECK BLOOD PRESSURE AT HOME"
 $ WHEREBP : num [1:438693] NA NA NA NA NA NA NA NA NA NA ...
  ..- attr(*, "label")= chr "WHERE DO YOU GET BLOOD PRESSURE TAKEN"
 $ SHAREBP : num [1:438693] NA NA NA NA NA NA NA NA NA NA ...
  ..- attr(*, "label")= chr "HOW DO YOU SHARE YOUR BLOOD PRESSURE NUM"
 $ WTCHSALT: num [1:438693] NA NA NA NA NA NA NA NA NA NA ...
  ..- attr(*, "label")= chr "WATCHING SODIUM OR SALT INTAKE"
 $ DRADVISE: num [1:438693] NA NA NA NA NA NA NA NA NA NA ...
  ..- attr(*, "label")= chr "DOCTOR ADVISED REDUCED SODIUM/SALT INTAK"
 $ CIMEMLOS: num [1:438693] NA NA NA NA NA NA NA NA NA NA ...
  ..- attr(*, "label")= chr "HAVE YOU EXPERIENCED CONFUSION OR MEMORY"
 $ CDHOUSE : num [1:438693] NA NA NA NA NA NA NA NA NA NA ...
  ..- attr(*, "label")= chr "GIVEN UP DAY-TO-DAY CHORES DUE TO CONFUS"
 $ CDASSIST: num [1:438693] NA NA NA NA NA NA NA NA NA NA ...
  ..- attr(*, "label")= chr "NEED ASSISTANCE WITH DAY-TO_DAY ACTIVITI"
 $ CDHELP  : num [1:438693] NA NA NA NA NA NA NA NA NA NA ...
  ..- attr(*, "label")= chr "WHEN YOU NEED HELP WITH DAY-TO-DAY ACTIV"
 $ CDSOCIAL: num [1:438693] NA NA NA NA NA NA NA NA NA NA ...
  ..- attr(*, "label")= chr "DOES CONFUSION OR MEMORY LOSS INTERFERE"
 $ CDDISCUS: num [1:438693] NA NA NA NA NA NA NA NA NA NA ...
  ..- attr(*, "label")= chr "HAVE YOU DISCUSSED YOUR CONFUSION OR MEM"
 $ CAREGIV1: num [1:438693] 2 2 2 2 2 2 2 2 2 1 ...
  ..- attr(*, "label")= chr "PROVIDED REGULAR CARE FOR FAMILY OR FRIE"
 $ CRGVREL4: num [1:438693] NA NA NA NA NA NA NA NA NA 15 ...
  ..- attr(*, "label")= chr "RELATIONSHIP OF PERSON TO WHOM YOU ARE G"
 $ CRGVLNG1: num [1:438693] NA NA NA NA NA NA NA NA NA 2 ...
  ..- attr(*, "label")= chr "HOW LONG PROVIDED CARE FOR PERSON."
 $ CRGVHRS1: num [1:438693] NA NA NA NA NA NA NA NA NA 1 ...
  ..- attr(*, "label")= chr "HOW MANY HOURS DO YOU PROVIDE CARE FOR P"
 $ CRGVPRB3: num [1:438693] NA NA NA NA NA NA NA NA NA 15 ...
  ..- attr(*, "label")= chr "WHAT IS THE MAJOR HEALTH PROBLEM, ILLNES"
 $ CRGVALZD: num [1:438693] NA NA NA NA NA NA NA NA NA 2 ...
  ..- attr(*, "label")= chr "DOES PERSON BEING CARED FOR HAVE ALZHEIM"
 $ CRGVPER1: num [1:438693] NA NA NA NA NA NA NA NA NA 2 ...
  ..- attr(*, "label")= chr "MANAGED PERSONAL CARE"
 $ CRGVHOU1: num [1:438693] NA NA NA NA NA NA NA NA NA 2 ...
  ..- attr(*, "label")= chr "MANAGED HOUSEHOLD TASKS"
 $ CRGVEXPT: num [1:438693] 2 2 2 7 2 2 2 2 7 NA ...
  ..- attr(*, "label")= chr "DO YOU EXPECT TO HAVE A RELATIVE YOU WIL"
 $ ACEDEPRS: num [1:438693] 2 2 2 1 2 2 2 2 2 2 ...
  ..- attr(*, "label")= chr "LIVE WITH ANYONE DEPRESSED, MENTALLY ILL"
 $ ACEDRINK: num [1:438693] 2 2 2 2 2 2 2 2 2 2 ...
  ..- attr(*, "label")= chr "LIVE WITH A PROBLEM DRINKER/ALCOHOLIC?"
 $ ACEDRUGS: num [1:438693] 2 2 2 2 2 2 2 2 2 2 ...
  ..- attr(*, "label")= chr "LIVE WITH ANYONE WHO USED ILLEGAL DRUGS"
 $ ACEPRISN: num [1:438693] 2 2 2 2 2 2 2 2 2 2 ...
  ..- attr(*, "label")= chr "LIVE WITH ANYONE WHO SERVED TIME IN PRIS"
 $ ACEDIVRC: num [1:438693] 1 2 2 2 2 2 2 2 2 2 ...
  ..- attr(*, "label")= chr "WERE YOUR PARENTS DIVORCED/SEPERATED?"
 $ ACEPUNCH: num [1:438693] 1 1 1 1 1 1 1 1 1 1 ...
  ..- attr(*, "label")= chr "HOW OFTEN DID YOUR PARENTS BEAT EACH OTH"
 $ ACEHURT1: num [1:438693] 1 1 1 3 1 1 1 1 1 1 ...
  ..- attr(*, "label")= chr "HOW OFTEN DID A PARENT PHYSICALLY HURT Y"
 $ ACESWEAR: num [1:438693] 1 1 1 1 1 1 1 1 1 3 ...
  ..- attr(*, "label")= chr "HOW OFTEN DID A PARENT SWEAR AT YOU?"
 $ ACETOUCH: num [1:438693] 1 1 1 1 1 1 1 1 1 1 ...
  ..- attr(*, "label")= chr "HOW OFTEN DID ANYONE EVER TOUCH YOU SEXU"
 $ ACETTHEM: num [1:438693] 1 1 1 1 1 1 1 1 1 1 ...
  ..- attr(*, "label")= chr "HOW OFTEN DID ANYONE MAKE YOU TOUCH THEM"
 $ ACEHVSEX: num [1:438693] 1 1 1 1 1 1 1 1 1 1 ...
  ..- attr(*, "label")= chr "HOW OFTEN DID ANYONE EVER FORCE YOU TO H"
 $ ACEADSAF: num [1:438693] 5 5 5 5 5 5 5 5 5 4 ...
  ..- attr(*, "label")= chr "DID AN ADULT MAKE YOU FEEL SAFE AND PROT"
 $ ACEADNED: num [1:438693] 3 5 5 5 5 5 5 5 5 4 ...
  ..- attr(*, "label")= chr "DID AN ADULT MAKE SURE BASIC NEEDS WERE"
 $ MARIJAN1: num [1:438693] NA NA NA NA NA NA NA NA NA NA ...
  ..- attr(*, "label")= chr "DURING THE PAST 30 DAYS, ON HOW MANY DAY"
 $ USEMRJN3: num [1:438693] NA NA NA NA NA NA NA NA NA NA ...
  ..- attr(*, "label")= chr "DURING THE PAST 30 DAYS, HOW DID YOU PRI"
 $ RSNMRJN2: num [1:438693] NA NA NA NA NA NA NA NA NA NA ...
  ..- attr(*, "label")= chr "WHAT WAS THE REASON YOU USED MARIJUANA?"
 $ LASTSMK2: num [1:438693] NA NA NA NA NA NA NA NA NA NA ...
  ..- attr(*, "label")= chr "INTERVAL SINCE LAST SMOKED"
 $ STOPSMK2: num [1:438693] NA NA NA NA NA NA NA NA NA NA ...
  ..- attr(*, "label")= chr "STOPPED SMOKING IN PAST 12 MONTHS"
 $ FIREARM5: num [1:438693] NA NA NA NA NA NA NA NA NA NA ...
  ..- attr(*, "label")= chr "ANY FIREARMS IN HOME"
 $ GUNLOAD : num [1:438693] NA NA NA NA NA NA NA NA NA NA ...
  ..- attr(*, "label")= chr "ANY FIREARMS LOADED"
 $ LOADULK2: num [1:438693] NA NA NA NA NA NA NA NA NA NA ...
  ..- attr(*, "label")= chr "ANY LOADED FIREARMS ALSO UNLOCKED"
 $ RCSGENDR: num [1:438693] NA NA NA NA NA NA NA NA NA NA ...
  ..- attr(*, "label")= chr "GENDER OF CHILD"
 $ RCSRLTN2: num [1:438693] NA NA NA NA NA NA NA NA NA NA ...
  ..- attr(*, "label")= chr "RELATIONSHIP TO CHILD"
 $ CASTHDX2: num [1:438693] NA NA NA NA NA NA NA NA NA NA ...
  ..- attr(*, "label")= chr "HLTH PRO EVER SAID CHILD HAS ASTHMA"
 $ CASTHNO2: num [1:438693] NA NA NA NA NA NA NA NA NA NA ...
  ..- attr(*, "label")= chr "CHILD STILL HAVE ASTHMA?"
 $ BIRTHSEX: num [1:438693] NA NA NA NA NA NA NA NA NA NA ...
  ..- attr(*, "label")= chr "ARE YOU MALE OR FEMALE?"
 $ SOMALE  : num [1:438693] NA NA NA NA NA NA NA NA NA NA ...
  ..- attr(*, "label")= chr "SEXUAL ORIENTATION"
 $ SOFEMALE: num [1:438693] NA NA NA NA NA NA NA NA NA NA ...
  ..- attr(*, "label")= chr "SEXUAL ORIENTATION"
 $ TRNSGNDR: num [1:438693] NA NA NA NA NA NA NA NA NA NA ...
  ..- attr(*, "label")= chr "DO YOU CONSIDER YOURSELF TO BE TRANSGEND"
 $ QSTVER  : num [1:438693] 10 10 10 10 10 10 10 10 10 10 ...
  ..- attr(*, "label")= chr "QUESTIONNAIRE VERSION IDENTIFIER"
 $ QSTLANG : num [1:438693] 1 1 1 1 1 1 1 1 1 1 ...
  ..- attr(*, "label")= chr "LANGUAGE IDENTIFIER"
 $ _METSTAT: num [1:438693] 1 1 1 1 2 2 2 1 1 1 ...
  ..- attr(*, "label")= chr "METROPOLITAN STATUS"
 $ _URBSTAT: num [1:438693] 1 1 1 1 1 2 1 1 1 1 ...
  ..- attr(*, "label")= chr "URBAN/RURAL STATUS"
 $ MSCODE  : num [1:438693] 1 2 1 3 2 5 5 3 1 1 ...
  ..- attr(*, "label")= chr "METROPOLITAN STATUS CODE"
 $ _STSTR  : num [1:438693] 11011 11011 11011 11011 11011 ...
  ..- attr(*, "label")= chr "SAMPLE DESIGN STRATIFICATION VARIABLE"
 $ _STRWT  : num [1:438693] 39.8 39.8 39.8 39.8 39.8 ...
  ..- attr(*, "label")= chr "STRATUM WEIGHT"
 $ _RAWRAKE: num [1:438693] 2 2 2 2 2 1 2 1 1 2 ...
  ..- attr(*, "label")= chr "RAW WEIGHTING FACTOR USED IN RAKING"
 $ _WT2RAKE: num [1:438693] 79.5 79.5 79.5 79.5 79.5 ...
  ..- attr(*, "label")= chr "DESIGN WEIGHT USED IN RAKING"
 $ _IMPRACE: num [1:438693] 1 2 2 1 6 1 1 1 1 1 ...
  ..- attr(*, "label")= chr "IMPUTED RACE/ETHNICITY VALUE"
 $ _CHISPNC: num [1:438693] 9 9 9 9 9 9 9 9 9 9 ...
  ..- attr(*, "label")= chr "CHILD HISPANIC, LATINO/A, OR SPANISH ORI"
 $ _CRACE1 : num [1:438693] NA NA NA NA NA NA NA NA NA NA ...
  ..- attr(*, "label")= chr "CHILD NON-HISPANIC RACE INCLUDING MULTIR"
 $ _CPRACE1: num [1:438693] NA NA NA NA NA NA NA NA NA NA ...
  ..- attr(*, "label")= chr "PREFERRED CHILD RACE CATEGORIES"
 $ CAGEG   : num [1:438693] NA NA NA NA NA NA NA NA NA NA ...
  ..- attr(*, "label")= chr "FOUR LEVEL CHILD AGE"
 $ _CLLCPWT: num [1:438693] NA NA NA NA NA NA NA NA NA NA ...
  ..- attr(*, "label")= chr "FINAL CHILD WEIGHT: LAND-LINE AND CELL-P"
 $ _DUALUSE: num [1:438693] 1 1 1 1 9 1 1 9 1 1 ...
  ..- attr(*, "label")= chr "DUAL PHONE USE CATEGORIES"
 $ _DUALCOR: num [1:438693] 0.519 0.519 0.519 0.519 NA ...
  ..- attr(*, "label")= chr "DUAL PHONE USE CORRECTION FACTOR"
 $ _LLCPWT2: num [1:438693] 874 874 874 874 2145 ...
  ..- attr(*, "label")= chr "TRUNCATED DESIGN WEIGHT USED IN ADULT CO"
 $ _LLCPWT : num [1:438693] 745 299 588 1100 1712 ...
  ..- attr(*, "label")= chr "FINAL WEIGHT: LAND-LINE AND CELL-PHONE D"
 $ _RFHLTH : num [1:438693] 2 1 1 1 2 1 1 2 1 1 ...
  ..- attr(*, "label")= chr "ADULTS WITH GOOD OR BETTER HEALTH"
 $ _PHYS14D: num [1:438693] 3 1 1 1 3 1 3 1 1 3 ...
  ..- attr(*, "label")= chr "COMPUTED PHYSICAL HEALTH STATUS"
 $ _MENT14D: num [1:438693] 2 1 1 2 1 1 1 1 1 2 ...
  ..- attr(*, "label")= chr "COMPUTED MENTAL HEALTH STATUS"
 $ _HLTHPLN: num [1:438693] 1 1 1 1 1 1 1 1 1 1 ...
  ..- attr(*, "label")= chr "HAVE ANY HEALTH INSURANCE"
 $ _HCVU652: num [1:438693] 9 9 9 1 9 9 1 1 9 9 ...
  ..- attr(*, "label")= chr "RESPONDENTS AGED 18-64 WITH HEALTH INSUR"
 $ _TOTINDA: num [1:438693] 2 1 2 1 1 2 2 1 2 1 ...
  ..- attr(*, "label")= chr "LEISURE TIME PHYSICAL ACTIVITY CALCULATE"
 $ _RFHYPE6: num [1:438693] 1 2 2 2 1 1 2 2 1 2 ...
  ..- attr(*, "label")= chr "HIGH BLOOD PRESSURE CALCULATED VARIABLE"
 $ _CHOLCH3: num [1:438693] 1 1 1 1 1 1 1 1 1 1 ...
  ..- attr(*, "label")= chr "CHOLESTEROL CHECKED CALCULATED VARIABLE"
 $ _RFCHOL3: num [1:438693] 2 2 1 2 2 1 1 2 1 1 ...
  ..- attr(*, "label")= chr "HIGH CHOLESTEROL CALCULATED VARIABLE"
 $ _MICHD  : num [1:438693] 2 1 1 2 1 2 2 1 2 2 ...
  ..- attr(*, "label")= chr "RESPONDENTS THAT HAVE EVER REPORTED HAVI"
 $ _LTASTH1: num [1:438693] 2 1 1 1 1 1 1 1 1 1 ...
  ..- attr(*, "label")= chr "LIFETIME ASTHMA CALCULATED VARIABLE"
 $ _CASTHM1: num [1:438693] 2 1 1 1 1 1 1 1 1 1 ...
  ..- attr(*, "label")= chr "CURRENT ASTHMA CALCULATED VARIABLE"
 $ _ASTHMS1: num [1:438693] 1 3 3 3 3 3 3 3 3 3 ...
  ..- attr(*, "label")= chr "COMPUTED ASTHMA STATUS"
 $ _DRDXAR3: num [1:438693] 1 1 2 2 2 2 1 1 2 1 ...
  ..- attr(*, "label")= chr "RESPONDENTS DIAGNOSED WITH ARTHRITIS"
 $ _LMTACT3: num [1:438693] 2 1 3 3 3 3 1 2 3 2 ...
  ..- attr(*, "label")= chr "LIMITED USUAL ACTIVITIES"
 $ _LMTWRK3: num [1:438693] 1 1 3 3 3 3 2 2 3 2 ...
  ..- attr(*, "label")= chr "LIMITED WORK ACTIVITIES"
 $ _PRACE1 : num [1:438693] 1 2 2 1 1 1 1 1 1 1 ...
  ..- attr(*, "label")= chr "COMPUTED PREFERRED RACE"
 $ _MRACE1 : num [1:438693] 1 2 2 1 7 1 1 1 1 1 ...
  ..- attr(*, "label")= chr "CALCULATED NON-HISPANIC RACE INCLUDING M"
 $ _HISPANC: num [1:438693] 2 2 2 2 2 2 2 2 2 2 ...
  ..- attr(*, "label")= chr "HISPANIC, LATINO/A, OR SPANISH ORIGIN CA"
 $ _RACE   : num [1:438693] 1 2 2 1 7 1 1 1 1 1 ...
  ..- attr(*, "label")= chr "COMPUTED RACE-ETHNICITY GROUPING"
 $ _RACEG21: num [1:438693] 1 2 2 1 2 1 1 1 1 1 ...
  ..- attr(*, "label")= chr "COMPUTED NON-HISPANIC WHITES/ALL OTHERS"
 $ _RACEGR3: num [1:438693] 1 2 2 1 4 1 1 1 1 1 ...
  ..- attr(*, "label")= chr "COMPUTED FIVE LEVEL RACE/ETHNICITY CATEG"
 $ _RACEPRV: num [1:438693] 1 2 2 1 7 1 1 1 1 1 ...
  ..- attr(*, "label")= chr "COMPUTED RACE GROUPS USED FOR INTERNET P"
 $ _SEX    : num [1:438693] 2 2 2 2 1 1 1 1 2 2 ...
  ..- attr(*, "label")= chr "CALCULATED SEX VARIABLE"
 $ _AGEG5YR: num [1:438693] 11 10 11 9 12 13 9 9 12 10 ...
  ..- attr(*, "label")= chr "REPORTED AGE IN FIVE-YEAR AGE CATEGORIES"
 $ _AGE65YR: num [1:438693] 2 2 2 1 2 2 1 1 2 2 ...
  ..- attr(*, "label")= chr "REPORTED AGE IN TWO AGE GROUPS CALCULATE"
 $ _AGE80  : num [1:438693] 70 67 72 62 76 80 63 62 78 65 ...
  ..- attr(*, "label")= chr "IMPUTED AGE VALUE COLLAPSED ABOVE 80"
 $ _AGE_G  : num [1:438693] 6 6 6 5 6 6 5 5 6 6 ...
  ..- attr(*, "label")= chr "IMPUTED AGE IN SIX GROUPS"
 $ HTIN4   : num [1:438693] 59 66 65 64 71 75 72 69 63 65 ...
  ..- attr(*, "label")= chr "COMPUTED HEIGHT IN INCHES"
 $ HTM4    : num [1:438693] 150 168 165 163 180 191 183 175 160 165 ...
  ..- attr(*, "label")= chr "COMPUTED HEIGHT IN METERS"
 $ WTKG3   : num [1:438693] 3266 NA 7711 8845 9344 ...
  ..- attr(*, "label")= chr "COMPUTED WEIGHT IN KILOGRAMS"
 $ _BMI5   : num [1:438693] 1454 NA 2829 3347 2873 ...
  ..- attr(*, "label")= chr "COMPUTED BODY MASS INDEX"
 $ _BMI5CAT: num [1:438693] 1 NA 3 4 3 2 4 2 NA 4 ...
  ..- attr(*, "label")= chr "COMPUTED BODY MASS INDEX CATEGORIES"
 $ _RFBMI5 : num [1:438693] 1 9 2 2 2 1 2 1 9 2 ...
  ..- attr(*, "label")= chr "OVERWEIGHT OR OBESE CALCULATED VARIABLE"
 $ _CHLDCNT: num [1:438693] 1 1 1 1 1 1 1 1 1 1 ...
  ..- attr(*, "label")= chr "COMPUTED NUMBER OF CHILDREN IN HOUSEHOLD"
 $ _EDUCAG : num [1:438693] 2 4 2 2 1 3 4 1 1 2 ...
  ..- attr(*, "label")= chr "COMPUTED LEVEL OF EDUCATION COMPLETED CA"
 $ _INCOMG1: num [1:438693] 3 9 2 5 2 4 9 9 9 5 ...
  ..- attr(*, "label")= chr "COMPUTED INCOME CATEGORIES"
 $ _SMOKER3: num [1:438693] 3 4 4 4 4 3 4 3 4 3 ...
  ..- attr(*, "label")= chr "COMPUTED SMOKING STATUS"
 $ _RFSMOK3: num [1:438693] 1 1 1 1 1 1 1 1 1 1 ...
  ..- attr(*, "label")= chr "CURRENT SMOKING CALCULATED VARIABLE"
 $ _CURECI1: num [1:438693] 1 1 1 1 1 1 1 1 1 1 ...
  ..- attr(*, "label")= chr "CURRENT E-CIGARETTE USER CALCULATED VARI"
 $ DRNKANY5: num [1:438693] 2 2 2 1 2 2 2 2 2 1 ...
  ..- attr(*, "label")= chr "DRINK ANY ALCOHOLIC BEVERAGES IN PAST 30"
 $ DROCDY3_: num [1:438693] 0 0 0 14 0 0 0 0 0 10 ...
  ..- attr(*, "label")= chr "COMPUTED DRINK-OCCASIONS-PER-DAY"
 $ _RFBING5: num [1:438693] 1 1 1 2 1 1 1 1 1 1 ...
  ..- attr(*, "label")= chr "BINGE DRINKING CALCULATED VARIABLE"
 $ _DRNKWK1: num [1:438693] 0 0 0 300 0 0 0 0 0 140 ...
  ..- attr(*, "label")= chr "COMPUTED NUMBER OF DRINKS OF ALCOHOL BEV"
 $ _RFDRHV7: num [1:438693] 1 1 1 1 1 1 1 1 1 1 ...
  ..- attr(*, "label")= chr "HEAVY ALCOHOL CONSUMPTION  CALCULATED VA"
 $ _FLSHOT7: num [1:438693] 1 2 2 NA 1 1 NA NA 1 2 ...
  ..- attr(*, "label")= chr "FLU SHOT CALCULATED VARIABLE"
 $ _PNEUMO3: num [1:438693] 1 2 2 NA 1 1 NA NA 2 1 ...
  ..- attr(*, "label")= chr "PNEUMONIA VACCINATION CALCULATED VARIABL"
 $ _AIDTST4: num [1:438693] 2 2 2 2 1 2 2 2 2 2 ...
  ..- attr(*, "label")= chr "EVER BEEN TESTED FOR HIV CALCULATED VARI"
 $ FTJUDA2_: num [1:438693] 0 0 0 71 0 0 3 0 100 0 ...
  ..- attr(*, "label")= chr "COMPUTED FRUIT JUICE INTAKE IN TIMES PER"
 $ FRUTDA2_: num [1:438693] 100 100 100 43 100 29 40 57 29 100 ...
  ..- attr(*, "label")= chr "COMPUTED FRUIT INTAKE IN TIMES PER DAY"
 $ GRENDA1_: num [1:438693] 57 14 0 10 100 14 43 29 0 29 ...
  ..- attr(*, "label")= chr "COMPUTED DARK GREEN VEGETABLE INTAKE IN"
 $ FRNCHDA_: num [1:438693] 43 0 14 57 29 0 43 0 NA 29 ...
  ..- attr(*, "label")= chr "FRENCH FRY INTAKE IN TIMES PER DAY"
 $ POTADA1_: num [1:438693] 14 14 14 27 29 14 7 57 0 43 ...
  ..- attr(*, "label")= chr "COMPUTED POTATO SERVINGS PER DAY"
 $ VEGEDA2_: num [1:438693] 100 100 43 71 100 14 29 57 29 57 ...
  ..- attr(*, "label")= chr "COMPUTED OTHER VEGETABLE INTAKE IN TIMES"
 $ _MISFRT1: num [1:438693] 0 0 0 0 0 0 0 0 0 0 ...
  ..- attr(*, "label")= chr "THE NUMBER OF MISSING FRUIT RESPONSES"
 $ _MISVEG1: num [1:438693] 0 0 0 0 0 0 0 0 1 0 ...
  ..- attr(*, "label")= chr "THE NUMBER OF MISSING VEGETABLE RESPONSE"
 $ _FRTRES1: num [1:438693] 1 1 1 1 1 1 1 1 1 1 ...
  ..- attr(*, "label")= chr "MISSING ANY FRUIT RESPONSES"
 $ _VEGRES1: num [1:438693] 1 1 1 1 1 1 1 1 0 1 ...
  ..- attr(*, "label")= chr "MISSING ANY VEGETABLE RESPONSES"
 $ _FRUTSU1: num [1:438693] 100 100 100 114 100 29 43 57 129 100 ...
  ..- attr(*, "label")= chr "TOTAL FRUITS CONSUMED PER DAY"
 $ _VEGESU1: num [1:438693] 214 128 71 165 258 42 122 143 NA 158 ...
  ..- attr(*, "label")= chr "TOTAL VEGETABLES CONSUMED PER DAY"
 $ _FRTLT1A: num [1:438693] 1 1 1 1 1 2 2 2 1 1 ...
  ..- attr(*, "label")= chr "CONSUME FRUIT 1 OR MORE TIMES PER DAY"
 $ _VEGLT1A: num [1:438693] 1 1 2 1 1 2 1 1 9 1 ...
  ..- attr(*, "label")= chr "CONSUME VEGETABLES 1 OR MORE TIMES PER D"
 $ _FRT16A : num [1:438693] 1 1 1 1 1 1 1 1 1 1 ...
  ..- attr(*, "label")= chr "REPORTED CONSUMING FRUIT >16/DAY"
 $ _VEG23A : num [1:438693] 1 1 1 1 1 1 1 1 1 1 ...
  ..- attr(*, "label")= chr "REPORTED CONSUMING VEGETABLES >23/DAY"
 $ _FRUITE1: num [1:438693] 0 0 0 0 0 0 0 0 0 0 ...
  ..- attr(*, "label")= chr "FRUIT EXCLUSION FROM ANALYSES"
 $ _VEGETE1: num [1:438693] 0 0 0 0 0 0 0 0 1 0 ...
  ..- attr(*, "label")= chr "VEGETABLE EXCLUSION FROM ANALYSES"

NULL

Demographics

Sex

tabyl(brfss21$SEX)

 brfss21$SEX      n   percent
           1 203760 0.4644706
           2 234933 0.5355294

Imputed Race

tabyl(brfss21$IMPRACE)  %>% gt()

brfss21$IMPRACE	n	percent
1	332222	0.75729952
2	33132	0.07552434
3	11557	0.02634416
4	7410	0.01689108
5	38688	0.08818923
6	15684	0.03575165

Geography

states <- rename(fips_codes, STATE = state_code) %>% select(state, STATE, state_name) %>% unique()


brfss21$MONTH_file <- brfss21$MONTH

Warning: Unknown or uninitialised column: `MONTH`.

brfss21$MONTH_1A <- brfss21$ADULT1

Warning: Unknown or uninitialised column: `ADULT1`.

brfss21$MONTH <-  NULL
brfss21$ADULT1 <- NULL

states$STATE <- as.numeric(states$STATE)


brfss21.c <- left_join(brfss21, states, by = "STATE")

tabyl(brfss21.c$state_name) %>% gt() %>% gt::cols_label(`brfss21.c$state_name`   = "State",n= "n",percent= "%")

State	n	%
Alabama	4586	0.010453780
Alaska	5493	0.012521285
Arizona	10654	0.024285776
Arkansas	5372	0.012245466
California	6735	0.015352422
Colorado	10476	0.023880025
Connecticut	8341	0.019013296
Delaware	3640	0.008297374
District of Columbia	3198	0.007289836
Georgia	8186	0.018659974
Guam	1658	0.003779408
Hawaii	7787	0.017750454
Idaho	6788	0.015473235
Illinois	3210	0.007317190
Indiana	9929	0.022633140
Iowa	9625	0.021940172
Kansas	17565	0.040039390
Kentucky	5429	0.012375397
Louisiana	5102	0.011630001
Maine	11808	0.026916317
Maryland	15627	0.035621722
Massachusetts	7683	0.017513386
Michigan	9425	0.021484273
Minnesota	15959	0.036378515
Mississippi	4421	0.010077663
Missouri	12266	0.027960328
Montana	6243	0.014230909
Nebraska	14923	0.034016955
Nevada	2739	0.006243546
New Hampshire	6536	0.014898802
New Jersey	7965	0.018156205
New Mexico	6362	0.014502169
New York	39095	0.089116991
North Carolina	4939	0.011258443
North Dakota	5909	0.013469556
Ohio	14308	0.032615063
Oklahoma	5451	0.012425546
Oregon	5378	0.012259142
Pennsylvania	6419	0.014632100
Puerto Rico	4014	0.009149907
Rhode Island	5609	0.012785707
South Carolina	10057	0.022924916
South Dakota	7290	0.016617543
Tennessee	4788	0.010914238
Texas	10815	0.024652775
U.S. Virgin Islands	1382	0.003150267
Utah	10621	0.024210553
Vermont	6580	0.014999100
Virginia	9902	0.022571593
Washington	13142	0.029957168
West Virginia	6744	0.015372937
Wisconsin	6106	0.013918617
Wyoming	4413	0.010059427

Select Respondents by DDEPEV3 and 5YRAGE

DDEPEV3 [Ever told you have depression]

brfss21.c$DDEPEV3

Warning: Unknown or uninitialised column: `DDEPEV3`.

NULL

brfss21.c <- brfss21.c %>% filter(!(ADDEPEV3 %in% c(7,9, NULL))) 
brfss21.c <-filter(brfss21.c, AGEG5YR != 14)
brfss21.c <- filter(brfss21.c,EDUCAG !=9)


brfss21.c$newagecat<- car::recode(brfss21.c$AGEG5YR, "1=21;2=27;3=32;4=37;5=42;6=47;7=52;8=57;9=62;10=67;11=72;12=77;13=82")

brfss21.c$ADDEPEV3 <- car::recode(brfss21.c$ADDEPEV3, "1=1;2=0")

tabyl(brfss21.c, ADDEPEV3, SEX)

 ADDEPEV3      1      2
        0 169530 171670
        1  28091  56197

tabyl(brfss21.c, ADDEPEV3, state_name) %>% gt()

ADDEPEV3	Alabama	Alaska	Arizona	Arkansas	California	Colorado	Connecticut	Delaware	District of Columbia	Georgia	Guam	Hawaii	Idaho	Illinois	Indiana	Iowa	Kansas	Kentucky	Louisiana	Maine	Maryland	Massachusetts	Michigan	Minnesota	Mississippi	Missouri	Montana	Nebraska	Nevada	New Hampshire	New Jersey	New Mexico	New York	North Carolina	North Dakota	Ohio	Oklahoma	Oregon	Pennsylvania	Puerto Rico	Rhode Island	South Carolina	South Dakota	Tennessee	Texas	U.S. Virgin Islands	Utah	Vermont	Virginia	Washington	West Virginia	Wisconsin	Wyoming
0	3562	4299	8521	4093	5566	8102	6457	2955	2492	6452	1468	6725	5204	2578	7368	7859	13948	3968	3778	8922	12405	5888	7106	12303	3490	9265	4857	12457	2179	5045	6255	5054	29809	3784	4863	10974	4114	3891	4954	3315	4162	7929	6018	3462	8358	1215	8034	4883	7729	9808	4939	4783	3555
1	936	983	1861	1113	1051	2042	1579	573	589	1426	164	921	1393	522	2152	1537	3213	1326	1206	2588	2555	1495	1985	3242	837	2655	1232	2227	478	1282	1299	1209	7576	1002	912	2987	1196	1298	1254	650	1260	1755	1066	1198	2145	103	2312	1524	1838	2936	1681	1198	726

tabyl(brfss21.c, RACE, state_name) %>% gt()

RACE	Alabama	Alaska	Arizona	Arkansas	California	Colorado	Connecticut	Delaware	District of Columbia	Georgia	Guam	Hawaii	Idaho	Illinois	Indiana	Iowa	Kansas	Kentucky	Louisiana	Maine	Maryland	Massachusetts	Michigan	Minnesota	Mississippi	Missouri	Montana	Nebraska	Nevada	New Hampshire	New Jersey	New Mexico	New York	North Carolina	North Dakota	Ohio	Oklahoma	Oregon	Pennsylvania	Puerto Rico	Rhode Island	South Carolina	South Dakota	Tennessee	Texas	U.S. Virgin Islands	Utah	Vermont	Virginia	Washington	West Virginia	Wisconsin	Wyoming
1	3038	3731	7092	4155	3026	7157	5790	2407	1467	4838	198	2557	5632	2148	7589	7924	14522	4391	3403	10671	9407	5317	7224	13028	2596	10276	5096	12892	1812	5789	4036	2931	27517	3052	5127	11979	3844	4172	4703	12	4111	6889	5516	3768	5608	179	8605	5887	7041	9981	6046	5184	3812
2	1155	91	273	560	337	304	542	538	1118	1966	17	88	32	373	755	187	760	533	1053	57	3294	417	869	611	1539	726	18	235	136	28	907	68	2763	889	74	811	278	75	694	4	246	1880	50	469	952	804	79	46	1370	266	184	226	13
3	38	615	492	60	47	81	31	28	12	57	0	19	65	22	61	63	155	40	55	100	82	29	66	165	27	109	486	167	30	31	25	629	267	141	261	83	383	64	25	1	34	76	1060	53	76	10	123	55	53	127	37	165	46
4	38	110	156	32	592	184	252	73	95	129	530	2392	33	151	141	101	193	38	51	35	398	370	183	434	19	101	14	111	82	80	509	57	1028	73	47	146	48	111	189	0	94	66	43	58	291	14	125	32	242	565	33	70	16
5	6	28	23	3	25	22	9	3	5	16	588	708	15	2	6	11	18	10	10	6	24	6	7	18	4	14	6	6	18	2	13	15	59	5	9	16	8	22	6	0	3	8	3	4	15	3	49	3	8	62	4	2	1
6	15	82	67	43	82	95	127	12	51	89	18	21	46	29	125	14	106	20	40	61	158	52	135	56	31	87	37	31	22	74	168	8	732	24	26	71	11	39	37	12	93	111	37	25	102	33	41	77	60	133	15	25	22
7	86	290	192	130	217	199	149	76	79	172	160	1205	108	32	180	97	335	74	85	149	269	105	176	259	18	206	148	160	63	82	116	84	731	76	68	285	282	103	102	0	92	168	111	95	195	31	106	102	185	355	94	75	59
8	82	183	1879	129	2188	1795	961	328	180	450	92	543	494	281	487	813	822	97	174	193	1018	933	256	739	39	247	144	899	420	122	1584	2259	3492	465	92	315	349	436	331	3934	602	318	161	113	2965	203	1019	90	450	974	85	162	199
9	40	152	208	94	103	307	175	63	74	161	29	113	172	62	176	186	250	91	113	238	310	154	175	235	54	154	140	183	74	119	196	212	796	61	71	255	107	167	121	2	147	168	103	75	299	41	199	115	158	281	122	72	113

tabyl(brfss21.c, EDUCA, state_name) %>% gt()

EDUCA	Alabama	Alaska	Arizona	Arkansas	California	Colorado	Connecticut	Delaware	District of Columbia	Georgia	Guam	Hawaii	Idaho	Illinois	Indiana	Iowa	Kansas	Kentucky	Louisiana	Maine	Maryland	Massachusetts	Michigan	Minnesota	Mississippi	Missouri	Montana	Nebraska	Nevada	New Hampshire	New Jersey	New Mexico	New York	North Carolina	North Dakota	Ohio	Oklahoma	Oregon	Pennsylvania	Puerto Rico	Rhode Island	South Carolina	South Dakota	Tennessee	Texas	U.S. Virgin Islands	Utah	Vermont	Virginia	Washington	West Virginia	Wisconsin	Wyoming
1	3	4	20	2	48	27	9	11	1	10	2	6	9	1	12	11	5	20	2	7	27	14	4	15	0	5	4	24	2	5	18	12	60	15	2	4	11	9	5	15	12	14	5	3	49	0	8	1	3	21	3	4	1
2	64	36	226	107	488	245	161	90	37	171	17	34	95	27	155	308	133	151	90	81	243	160	52	126	118	219	60	262	42	42	249	216	873	155	84	135	82	90	65	290	129	189	71	99	474	96	148	51	117	245	116	44	32
3	286	191	393	277	374	439	225	130	99	466	80	161	300	82	412	342	468	278	294	293	546	231	304	369	326	606	189	429	103	164	287	426	1752	273	182	587	263	170	199	243	207	510	240	228	561	90	327	170	296	369	362	157	87
4	1237	1365	2242	1658	1167	2019	1794	904	455	2102	582	1938	1677	695	2829	2929	4273	1727	1365	2966	3548	1382	2369	3225	1272	3792	1558	4240	706	1512	1699	1651	10396	1124	1627	4410	1407	1051	1742	923	1136	2544	2000	1303	2452	444	2459	1503	2067	2537	2323	1665	1125
5	1267	1580	3388	1466	1538	2527	1888	939	408	2056	375	2154	2182	789	2527	2716	5263	1507	1369	3188	3368	1770	2578	4681	1252	3465	1832	4567	870	1626	1735	1718	9664	1285	1896	3900	1657	1714	1478	982	1316	2606	2228	1311	2817	242	3202	1505	2462	3662	1680	1723	1415
6	1641	2106	4113	1696	3002	4887	3959	1454	2081	3073	576	3353	2334	1506	3585	3090	7019	1611	1864	4975	7228	3826	3784	7129	1359	3833	2446	5162	934	2978	3566	2240	14640	1934	1984	4925	1890	2155	2719	1512	2622	3821	2540	1716	4150	446	4202	3177	4622	5910	2136	2388	1621

Chi-Square

chi_data = data.frame(brfss21.c$ADDEPEV3,brfss21.c$SEX)           
chi_data = table(brfss21.c$ADDEPEV3,brfss21.c$SEX)                
print(chi_data)

   
         1      2
  0 169530 171670
  1  28091  56197

chisq.test(chi_data)


    Pearson's Chi-squared test with Yates' continuity correction

data:  chi_data
X-squared = 7271.5, df = 1, p-value < 2.2e-16

Probability of Being Told You Have Depression by Sex and Education Level

ageprobs<- brfss21.c %>% filter(EDUCAG !=9) %>%
    group_by(AGE80, EDUCAG,SEXVAR) %>%
    summarize(p=mean(ADDEPEV3),n=n())

`summarise()` has grouped output by 'AGE80', 'EDUCAG'. You can override using
the `.groups` argument.

ageprobs$num <- ageprobs$p*(1-ageprobs$p)

ageprobs$sep <- sqrt(ageprobs$num/ageprobs$n)

ageprobs$me <- 2*ageprobs$sep
  
ggplot(data =ageprobs, aes(x = AGE80, y = p, ymin=p-me, ymax=p+me, group= EDUCAG)) +
     geom_line(aes(color =  factor(EDUCAG))) + ylim(0,1) + geom_ribbon(alpha=0.03,aes()) +
labs(title="Mental Health by Age and Education Level", 
       subtitle="Sex", 
       caption="Source: 2021 BRFSS Data") +
       xlab(label="Age at Survey") +
  ylab(label="Proportion of Respondents who Report Ever being Told They Have Depression")+
  facet_wrap(~SEXVAR)+
  theme_bw()

ageprobs<- brfss21.c %>% filter(EDUCAG !=9) %>% filter(CHCSCNCR %in% c(1,2))%>%
    group_by(AGE80, RACE,SEXVAR) %>%
    summarize(p=mean(CHCSCNCR-1),n=n())

`summarise()` has grouped output by 'AGE80', 'RACE'. You can override using the
`.groups` argument.

ageprobs$num <- ageprobs$p*(1-ageprobs$p)

ageprobs$sep <- sqrt(ageprobs$num/ageprobs$n)

ageprobs$me <- 2*ageprobs$sep
  
ggplot(data =ageprobs, aes(x = AGE80, y = p, ymin=p-me, ymax=p+me, group= RACE)) +
     geom_line(aes(color =  factor(RACE))) + ylim(0,1) + geom_ribbon(alpha=0.03,aes()) +
labs(title="Mental Health by Race and Education Level", 
       subtitle="Sex", 
       caption="Source: 2021 BRFSS Data") +
       xlab(label="Age at Survey") +
  ylab(label="Proportion of Respondents who Report Ever being Told They Have Depression")+
  facet_wrap(~SEXVAR)+
  theme_bw()

#looking at association between categorical and numeric variable

boxplot(brfss21.c$AGE80 ~ brfss21.c$ADDEPEV3,
                col='steelblue',
        xlab='Depression Status',
        ylab='Age at Survey')

OLS Models

#OLS models of bad mental health

brfss21.c$AGE80SQ<-brfss21.c$AGE80**2

L.model <- lm(ADDEPEV3 ~ AGE80 + factor(EDUCAG), data = brfss21.c)
summary(L.model)


Call:
lm(formula = ADDEPEV3 ~ AGE80 + factor(EDUCAG), data = brfss21.c)

Residuals:
    Min      1Q  Median      3Q     Max 
-0.3116 -0.2159 -0.1763 -0.1344  0.8788 

Coefficients:
                  Estimate Std. Error t value Pr(>|t|)    
(Intercept)      3.513e-01  3.109e-03 112.979   <2e-16 ***
AGE80           -2.204e-03  3.431e-05 -64.233   <2e-16 ***
factor(EDUCAG)2 -3.508e-02  2.754e-03 -12.738   <2e-16 ***
factor(EDUCAG)3 -6.147e-03  2.736e-03  -2.247   0.0247 *  
factor(EDUCAG)4 -5.381e-02  2.656e-03 -20.262   <2e-16 ***
---
Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1

Residual standard error: 0.3961 on 425483 degrees of freedom
Multiple R-squared:  0.01242,   Adjusted R-squared:  0.01241 
F-statistic:  1337 on 4 and 425483 DF,  p-value: < 2.2e-16

Q.model <- lm(ADDEPEV3 ~ AGE80 +AGE80SQ + factor(EDUCAG), data = brfss21.c)
summary(Q.model)


Call:
lm(formula = ADDEPEV3 ~ AGE80 + AGE80SQ + factor(EDUCAG), data = brfss21.c)

Residuals:
    Min      1Q  Median      3Q     Max 
-0.2779 -0.2210 -0.1830 -0.1178  0.9051 

Coefficients:
                  Estimate Std. Error t value Pr(>|t|)    
(Intercept)      2.298e-01  5.766e-03  39.851   <2e-16 ***
AGE80            3.156e-03  2.170e-04  14.543   <2e-16 ***
AGE80SQ         -5.172e-05  2.068e-06 -25.013   <2e-16 ***
factor(EDUCAG)2 -3.338e-02  2.753e-03 -12.123   <2e-16 ***
factor(EDUCAG)3 -6.566e-03  2.734e-03  -2.402   0.0163 *  
factor(EDUCAG)4 -5.634e-02  2.656e-03 -21.217   <2e-16 ***
---
Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1

Residual standard error: 0.3958 on 425482 degrees of freedom
Multiple R-squared:  0.01387,   Adjusted R-squared:  0.01385 
F-statistic:  1197 on 5 and 425482 DF,  p-value: < 2.2e-16

summary(Q.model)


Call:
lm(formula = ADDEPEV3 ~ AGE80 + AGE80SQ + factor(EDUCAG), data = brfss21.c)

Residuals:
    Min      1Q  Median      3Q     Max 
-0.2779 -0.2210 -0.1830 -0.1178  0.9051 

Coefficients:
                  Estimate Std. Error t value Pr(>|t|)    
(Intercept)      2.298e-01  5.766e-03  39.851   <2e-16 ***
AGE80            3.156e-03  2.170e-04  14.543   <2e-16 ***
AGE80SQ         -5.172e-05  2.068e-06 -25.013   <2e-16 ***
factor(EDUCAG)2 -3.338e-02  2.753e-03 -12.123   <2e-16 ***
factor(EDUCAG)3 -6.566e-03  2.734e-03  -2.402   0.0163 *  
factor(EDUCAG)4 -5.634e-02  2.656e-03 -21.217   <2e-16 ***
---
Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1

Residual standard error: 0.3958 on 425482 degrees of freedom
Multiple R-squared:  0.01387,   Adjusted R-squared:  0.01385 
F-statistic:  1197 on 5 and 425482 DF,  p-value: < 2.2e-16

Binomial Models

Model 1 | Linear Age Specification

L.model_b <- glm(ADDEPEV3 ~ AGE80 + factor(EDUCAG), family = "binomial", data = brfss21.c)
summary(L.model_b)


Call:
glm(formula = ADDEPEV3 ~ AGE80 + factor(EDUCAG), family = "binomial", 
    data = brfss21.c)

Deviance Residuals: 
    Min       1Q   Median       3Q      Max  
-0.8910  -0.6905  -0.6181  -0.5485   2.0196  

Coefficients:
                  Estimate Std. Error z value Pr(>|z|)    
(Intercept)     -0.4727986  0.0187143 -25.264   <2e-16 ***
AGE80           -0.0136685  0.0002154 -63.448   <2e-16 ***
factor(EDUCAG)2 -0.2136027  0.0167963 -12.717   <2e-16 ***
factor(EDUCAG)3 -0.0350639  0.0165122  -2.124   0.0337 *  
factor(EDUCAG)4 -0.3337135  0.0162221 -20.572   <2e-16 ***
---
Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1

(Dispersion parameter for binomial family taken to be 1)

    Null deviance: 423576  on 425487  degrees of freedom
Residual deviance: 418352  on 425483  degrees of freedom
AIC: 418362

Number of Fisher Scoring iterations: 4

exp(L.model_b$coefficients)

    (Intercept)           AGE80 factor(EDUCAG)2 factor(EDUCAG)3 factor(EDUCAG)4 
      0.6232556       0.9864245       0.8076692       0.9655437       0.7162589

Holding all else constant, each additional year of life is associated with a 2% reduction in the odds of reporting depression. Holding all else constant, those who graduated from high school were associated with a 20% reduction in the odds of reporting that they’ve ever been told they have depression, compared to non-high school graduates. Holding all else constant, those who attended college but did not graduate were associated with a marginal 3.4% reducing in the odds of reporting they’ve even been told they have depression compared to non-high school graduates. College graduates were associated with a 29% reduction in the odds of reporting they’ve ever been told they have depression compared to non-high school graduates.

Model 2 | Quadratic Age Specification

Q.model_b <- glm(ADDEPEV3 ~ AGE80 + AGE80SQ + factor(EDUCAG), family = "binomial", data = brfss21.c)
summary(Q.model_b)


Call:
glm(formula = ADDEPEV3 ~ AGE80 + AGE80SQ + factor(EDUCAG), family = "binomial", 
    data = brfss21.c)

Deviance Residuals: 
    Min       1Q   Median       3Q      Max  
-0.8196  -0.7020  -0.6309  -0.5099   2.1174  

Coefficients:
                  Estimate Std. Error z value Pr(>|z|)    
(Intercept)     -1.348e+00  3.552e-02 -37.960   <2e-16 ***
AGE80            2.593e-02  1.373e-03  18.886   <2e-16 ***
AGE80SQ         -3.909e-04  1.338e-05 -29.206   <2e-16 ***
factor(EDUCAG)2 -1.988e-01  1.682e-02 -11.821   <2e-16 ***
factor(EDUCAG)3 -3.632e-02  1.653e-02  -2.197    0.028 *  
factor(EDUCAG)4 -3.535e-01  1.625e-02 -21.749   <2e-16 ***
---
Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1

(Dispersion parameter for binomial family taken to be 1)

    Null deviance: 423576  on 425487  degrees of freedom
Residual deviance: 417482  on 425482  degrees of freedom
AIC: 417494

Number of Fisher Scoring iterations: 4

exp(Q.model_b$coefficients)

    (Intercept)           AGE80         AGE80SQ factor(EDUCAG)2 factor(EDUCAG)3 
      0.2596888       1.0262664       0.9996092       0.8196879       0.9643274 
factor(EDUCAG)4 
      0.7022215

Holding all else constant, each additional year of life is associated with a 2% increase in the odds of reporting that ever told they had depression.

Holding all else constant, respondents who graduated from high school had 18% lower odds of reporting that they ever told they had depression compared to those who did not graduate school. Ceteris paribus, those who attended college but did not graduate had 3% lower odds of reporting that they had depression compared to those who did not graduate from high schoo, cet. par. Those respondents who did graduate from college were 29% less likely to report ever being told they had depression than those who did not graduate from high school, cet. par.

One interpretation of this is that starting college but not finishing is marginally more protective of mental health than not graduating from high school at all. By far, college graduates have the most protection.

L.model_b <- glm(ADDEPEV3 ~ AGE80 +factor(EDUCAG) + factor(SEXVAR), family = "binomial", data = brfss21.c)
summary(L.model_b)


Call:
glm(formula = ADDEPEV3 ~ AGE80 + factor(EDUCAG) + factor(SEXVAR), 
    family = "binomial", data = brfss21.c)

Deviance Residuals: 
    Min       1Q   Median       3Q      Max  
-1.0385  -0.7045  -0.5942  -0.4560   2.2215  

Coefficients:
                  Estimate Std. Error z value Pr(>|z|)    
(Intercept)     -0.7870419  0.0193054 -40.768  < 2e-16 ***
AGE80           -0.0153111  0.0002186 -70.036  < 2e-16 ***
factor(EDUCAG)2 -0.2145348  0.0169776 -12.636  < 2e-16 ***
factor(EDUCAG)3 -0.0736168  0.0167018  -4.408 1.04e-05 ***
factor(EDUCAG)4 -0.3669207  0.0164084 -22.362  < 2e-16 ***
factor(SEXVAR)2  0.7267146  0.0081732  88.914  < 2e-16 ***
---
Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1

(Dispersion parameter for binomial family taken to be 1)

    Null deviance: 423576  on 425487  degrees of freedom
Residual deviance: 410089  on 425482  degrees of freedom
AIC: 410101

Number of Fisher Scoring iterations: 4

exp(coef(L.model_b))

    (Intercept)           AGE80 factor(EDUCAG)2 factor(EDUCAG)3 factor(EDUCAG)4 
      0.4551893       0.9848055       0.8069167       0.9290277       0.6928646 
factor(SEXVAR)2 
      2.0682743

Q.model_b <- glm(ADDEPEV3 ~ AGE80 + AGE80SQ + factor(EDUCAG)+factor(SEXVAR), family = "binomial", data = brfss21.c)
summary(Q.model_b)


Call:
glm(formula = ADDEPEV3 ~ AGE80 + AGE80SQ + factor(EDUCAG) + factor(SEXVAR), 
    family = "binomial", data = brfss21.c)

Deviance Residuals: 
    Min       1Q   Median       3Q      Max  
-0.9513  -0.7067  -0.5845  -0.4373   2.3168  

Coefficients:
                  Estimate Std. Error z value Pr(>|z|)    
(Intercept)     -1.680e+00  3.614e-02 -46.484  < 2e-16 ***
AGE80            2.506e-02  1.388e-03  18.055  < 2e-16 ***
AGE80SQ         -3.981e-04  1.352e-05 -29.455  < 2e-16 ***
factor(EDUCAG)2 -1.991e-01  1.700e-02 -11.711  < 2e-16 ***
factor(EDUCAG)3 -7.589e-02  1.672e-02  -4.539 5.65e-06 ***
factor(EDUCAG)4 -3.897e-01  1.645e-02 -23.695  < 2e-16 ***
factor(SEXVAR)2  7.275e-01  8.174e-03  89.010  < 2e-16 ***
---
Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1

(Dispersion parameter for binomial family taken to be 1)

    Null deviance: 423576  on 425487  degrees of freedom
Residual deviance: 409205  on 425481  degrees of freedom
AIC: 409219

Number of Fisher Scoring iterations: 4