mortality.Rmd

---
output: html_document
editor_options: 
  chunk_output_type: console
---
```{r Variable description, warning=TRUE}
# # Variable frequencies
# 
# #ELIGSTAT: Eligibility Status for Mortality Follow-up
# table(dsn$eligstat)
# #1 = "Eligible"
# #2 = "Under age 18, not available for public release"
# #3 = "Ineligible"
# 
# #MORTSTAT: Final Mortality Status
# table(dsn$mortstat, useNA="ifany")
# # 0 = Assumed alive
# # 1 = Assumed deceased
# # <NA> = Ineligible or under age 18
# 
# #UCOD_LEADING: Underlying Cause of Death: Recode
# table(dsn$ucod_leading, useNA="ifany")
# # 1 = Diseases of heart (I00-I09, I11, I13, I20-I51)
# # 2 = Malignant neoplasms (C00-C97)
# # 3 = Chronic lower respiratory diseases (J40-J47)
# # 4 = Accidents (unintentional injuries) (V01-X59, Y85-Y86)
# # 5 = Cerebrovascular diseases (I60-I69)
# # 6 = Alzheimer's disease (G30)
# # 7 = Diabetes mellitus (E10-E14)
# # 8 = Influenza and pneumonia (J09-J18)
# # 9 = Nephritis, nephrotic syndrome and nephrosis (N00-N07, N17-N19, N25-N27)
# # 10 = All other causes (residual)
# # <NA> = Ineligible, under age 18, assumed alive, or no cause of death data
# 
# #DIABETES: Diabetes Flag from Multiple Cause of Death (MCOD)
# table(dsn$diabetes, useNA="ifany")
# # 0 = No - Condition not listed as a multiple cause of death
# # 1 = Yes - Condition listed as a multiple cause of death
# # <NA> = Assumed alive, under age 18, ineligible for mortality follow-up, or MCOD not available
# 
# #HYPERTEN: Hypertension Flag from Multiple Cause of Death (MCOD)
# table(dsn$hyperten, useNA="ifany")
# # 0 = No - Condition not listed as a multiple cause of death
# # 1 = Yes - Condition listed as a multiple cause of death
# # <NA> = Assumed alive, under age 18, ineligible for mortality follow-up, or MCOD not available
```
```{r Load libraries, warning=TRUE}
library(readr)
library(dplyr)
library(feather)
```

```{r Define surveys, warning=TRUE}
SURVEYS = c(
  "NHANES_1999_2000", 
  "NHANES_2001_2002", 
  "NHANES_2003_2004", 
  "NHANES_2005_2006", 
  "NHANES_2007_2008", 
  "NHANES_2009_2010",
  "NHANES_2011_2012", 
  "NHANES_2013_2014",
  "NHANES_III"
  )
```


```{r Load the surveys and save them, warning=TRUE}
for (survey in SURVEYS){
  srvyin <- paste0("./data/mortality/raw/", survey, "_MORT_2015_PUBLIC.dat")
  
  dsn <- read_fwf(file=srvyin,
                    col_types = "ciiiiiiiddii",
                    fwf_cols(publicid = c(1,14),
                             eligstat = c(15,15),
                             mortstat = c(16,16),
                             ucod_leading = c(17,19),
                             diabetes = c(20,20),
                             hyperten = c(21,21),
                             dodqtr = c(22,22),
                             dodyear = c(23,26),
                             wgt_new = c(27,34),
                             sa_wgt_new = c(35,42),
                             permth_int = c(43,45),
                             permth_exm = c(46,48)
                    ),
                    na = "."
    )
  
  # create the ID (SEQN) for the NHANES surveys
  dsn$seqn <- substr(dsn$publicid,1,5)
  # NOTE:   SEQN is the unique ID for NHANES.
  
  #Drop NHIS variables and useful variables
  dsn <- select(dsn, -publicid)
  dsn <- select(dsn, -dodqtr)
  dsn <- select(dsn, -dodyear)
  dsn <- select(dsn, -wgt_new)
  dsn <- select(dsn, -sa_wgt_new)
  dsn <- select(dsn, -eligstat)
  dsn <- select(dsn, -diabetes)
  dsn <- select(dsn, -hyperten)
  
  write_feather(dsn, paste0("./data/mortality/", survey, ".feather"))
}
```