# ----------------------------------------------------------------------------- # R programming statements for h206e data # # This file contains programming statements needed to import the ASCII data # file (.dat) into R. The R programming language has the capability to produce # appropriate standard errors for estimates from a survey with a complex sample # design such as the Medical Expenditure Panel Survey (MEPS). # # The input file is the ASCII data file (h206e.dat) supplied in this PUF # release, which can be extracted from the .zip file supplied at the MEPS # website: https://meps.ahrq.gov/mepsweb/data_stats/download_data_files.jsp # # This code imports the MEPS data into R as a data frame called 'h206e'. # # Note that additional packages are needed to successfully run this code. To # install these packages, run the 'install.packages' function (shown below). # Once installed, the packages can be called using the 'library' function. # Packages only need to be installed once, but they must be called using the # 'library' function every time a new R session is started. # # Two options are available to run this code: # # 1. Copy and paste the code into an interactive R session. # # The user must first download the ASCII (.dat) file from the MEPS website # and save it to a local directory, which must be defined in the # 'meps_path' variable below. In this example, the local directory is # called "C:/MEPS". Note that the path structure will differ on Mac and PC. # # # 2. Call this code directly from an interactive R session. # # (a) If the ASCII (.dat) file has already been downloaded from the MEPS # website and saved to a local directory, the following code can be run # (after re-defining the 'meps_path' variable to point to the location # of the h206e.dat file.) # # meps_path <- "C:/MEPS/h206e.dat" # source("https://meps.ahrq.gov/mepsweb/data_stats/download_data/pufs/h206e/h206eru.txt") # head(h206e) # view data # # # (b) Alternatively, the ASCII (.dat) file can be downloaded directly from # the MEPS website. The following code can be used to download and # import the h206e data into R without having to manually download, # unzip, and store the file on your local computer. # # url <- "https://meps.ahrq.gov/mepsweb/data_files/pufs/h206edat.zip" # download.file(url, temp <- tempfile()) # # meps_path <- unzip(temp, exdir = tempdir()) # source("https://meps.ahrq.gov/mepsweb/data_stats/download_data/pufs/h206e/h206eru.txt") # # unlink(temp) # Unlink to delete temporary file # # head(h206e) # view data # # ----------------------------------------------------------------------------- # DEFINE 'meps_path' ----------------------------------------------------------- # 'meps_path' should point to the file path of the ASCII file (h206e.dat) # Here, the 'exists' function checks whether meps_path is already defined. This # feature is useful if calling this file from an external source. if(!exists("meps_path")) meps_path = "C:/MEPS/h206e.dat" # INSTALL PACKAGES ------------------------------------------------------------ # Uncomment and run this portion if packages are not yet installed # # install.packages("readr") # LOAD PACKAGES --------------------------------------------------------------- # Run this for every new R session library(readr) # DATA FILE INFO -------------------------------------------------------------- # Define start and end positions to read fixed-width file pos_start <- c(1, 8, 11, 21, 37, 38, 54, 66, 68, 69, 73, 75, 77, 79, 81, 83, 85, 87, 89, 91, 93, 95, 97, 99, 107, 116, 123, 131, 138, 146, 153, 160, 167, 175, 183, 190, 197, 204, 212, 221, 228, 235, 242, 249, 256, 263, 267, 273, 280, 287, 293, 300, 307, 315, 316, 328, 332) pos_end <- c(7, 10, 20, 36, 37, 53, 65, 67, 68, 72, 74, 76, 78, 80, 82, 84, 86, 88, 90, 92, 94, 96, 98, 106, 115, 122, 130, 137, 145, 152, 159, 166, 174, 182, 189, 196, 203, 211, 220, 227, 234, 241, 248, 255, 262, 266, 272, 279, 286, 292, 299, 306, 314, 315, 327, 331, 332) # Define variable names and types ('c' = character, 'n' = 'numeric') var_names <- c("DUID", "PID", "DUPERSID", "EVNTIDX", "EVENTRN", "ERHEVIDX", "FFEEIDX", "PANEL", "MPCDATA", "ERDATEYR", "ERDATEMM", "VSTCTGRY", "VSTRELCN", "LABTEST_M18", "SONOGRAM_M18", "XRAYS_M18", "MAMMOG_M18", "MRI_M18", "EKG_M18", "RCVVAC_M18", "SURGPROC", "MEDPRESC", "FFERTYPE", "ERXP18X", "ERTC18X", "ERFSF18X", "ERFMR18X", "ERFMD18X", "ERFPV18X", "ERFVA18X", "ERFTR18X", "ERFOF18X", "ERFSL18X", "ERFWC18X", "ERFOR18X", "ERFOU18X", "ERFOT18X", "ERFXP18X", "ERFTC18X", "ERDSF18X", "ERDMR18X", "ERDMD18X", "ERDPV18X", "ERDVA18X", "ERDTR18X", "ERDOF18X", "ERDSL18X", "ERDWC18X", "ERDOR18X", "ERDOU18X", "ERDOT18X", "ERDXP18X", "ERDTC18X", "IMPFLAG", "PERWT18F", "VARSTR", "VARPSU") var_types <- c("n", "n", "c", "c", "n", "c", "c", "n", "n", "n", "n", "n", "n", "n", "n", "n", "n", "n", "n", "n", "n", "n", "n", "n", "n", "n", "n", "n", "n", "n", "n", "n", "n", "n", "n", "n", "n", "n", "n", "n", "n", "n", "n", "n", "n", "n", "n", "n", "n", "n", "n", "n", "n", "n", "n", "n", "n") var_types <- setNames(var_types, var_names) # IMPORT ASCII (.dat) file ---------------------------------------------------- h206e <- read_fwf( meps_path, col_positions = fwf_positions( start = pos_start, end = pos_end, col_names = var_names), col_types = var_types) # OPTIONAL: save as .Rdata file for easier loading ---------------------------- # Run this to save a permanent .Rdata file in the local working directory # # save(h206e, file = "h206e.Rdata") # ----------------------------------------------------------------------------- # NOTES: # # 1. This program has been tested on R version 3.6.0 # # 2. This program will create a temporary data frame in R called 'h206e'. # You must run the 'save' command to permanently save the data to a local # folder # -----------------------------------------------------------------------------