Merge branch 'main' into nsudh-dat-init

Author: szimmer

DESCRIPTION

@@ -11,7 +11,7 @@ Description: Includes datasets for the Residential Energy Consumption
     Survey (2015 and 2020), the American National Election Studies (2020),
     and the National Crime Victimization Study (2021) - household, person,
     and incident files.
-License: CC BY 4.0
+License: CC BY 4.0 + file LICENSE
 Depends: 
     R (>= 3.5)
 Suggests: 

LICENSE

@@ -0,0 +1 @@
+Re-distributing the ANES or NCVS datasets is subject to their policies.

LICENSE.md

@@ -1,4 +1,4 @@
-Attribution 4.0 International
+# Attribution 4.0 International
 
 =======================================================================
 

R/data.R

@@ -31,7 +31,7 @@
 #'    \item{\code{SummerTempAway}}{double Summer thermostat setting or temperature in home when no one is home during the day}
 #'    \item{\code{SummerTempNight}}{double Summer thermostat setting or temperature in home at night}
 #'    \item{\code{NWEIGHT}}{double Final Analysis Weight}
-#'    \item{\code{NWEIGHT1-NWEIGHT60}}{double Final Analysis Weight for replicate 1-60}
+#'    \item{\code{NWEIGHT1 - NWEIGHT60}}{double Final Analysis Weight for replicate 1-60}
 #'    \item{\code{BTUEL}}{double Total electricity use, in thousand Btu, 2020, including self-generation of solar power}
 #'    \item{\code{DOLLAREL}}{double Total electricity cost, in dollars, 2020}
 #'    \item{\code{BTUNG}}{double Total natural gas use, in thousand Btu, 2020}
@@ -43,7 +43,7 @@
 #'    \item{\code{BTUWOOD}}{double Total wood use, in thousand Btu, 2020}
 #'    \item{\code{TOTALBTU}}{double Total usage including electricity, natural gas, propane, and fuel oil, in thousand Btu, 2020}
 #'    \item{\code{TOTALDOL}}{double Total cost including electricity, natural gas, propane, and fuel oil, in dollars, 2020}
-#'}
+#' }
 #' @source \url{https://www.eia.gov/consumption/residential/data/2020/index.php?view=microdata}
 "recs_2020"
 
@@ -81,7 +81,7 @@
 #'   \item{\code{TOTUCSQFT}}{double Total uncooled square footage}
 #'   \item{\code{TOTUSQFT}}{double Total unheated square footage}
 #'   \item{\code{NWEIGHT}}{double Final sample weight}
-#'   \item{\code{BRRWT1-BRRWT96}}{double Replicate weight 1 through 96}
+#'   \item{\code{BRRWT1 - BRRWT96}}{double Replicate weight 1 through 96}
 #'   \item{\code{CDD30YR}}{double Cooling degree days, 30-year average 1981-2010, base temperature 65F}
 #'   \item{\code{CDD65}}{double Cooling degree days in 2015, base temperature 65F}
 #'   \item{\code{CDD80}}{double Cooling degree days in 2015, base temperature 80F (used for garage cooling load estimation only)}
@@ -103,7 +103,7 @@
 #'   \item{\code{TOTALDOL}}{double Total cost, in dollars, 2015 }
 #'   \item{\code{BTUWOOD}}{double Total cordwood usage, in thousand Btu, 2015 (Wood consumption is not included in TOTALBTU or TOTALDOL)}
 #'   \item{\code{BTUPELLET}}{double Total wood pellet usage, in thousand Btu, 2015 (Wood consumption is not included in TOTALBTU or TOTALDOL)}
-#'}
+#' }
 #' @source \url{https://www.eia.gov/consumption/residential/data/2015/index.php?view=microdata}
 "recs_2015"
 
@@ -171,7 +171,7 @@
 #'   \item{\code{V4277E}}{integer C MULT OFF: TEACHER/SCHOOL STAFF (START 2007 Q1) (END 2016 Q4) (START 2021 Q1)}
 #'   \item{\code{V4399}}{integer REPORTED TO POLICE}
 #'   \item{\code{V4529}}{integer TYPE OF CRIME CODE (NEW, NCVS)}
-#'}
+#' }
 #' @source \url{https://doi.org/10.3886/ICPSR38429.v1}
 "ncvs_2021_incident"
 
@@ -191,7 +191,7 @@
 #'   \item{\code{V2126B}}{integer PLACE SIZE CODE - 1990, 2000, 2010 SAMPLE DESIGN (START 1995 Q3)}
 #'   \item{\code{V2127B}}{integer REGION - 1990, 2000, 2010 SAMPLE DESIGN (START 1995 Q3)}
 #'   \item{\code{V2129}}{integer CBSA MSA STATUS}
-#'}
+#' }
 #' @source \url{https://doi.org/10.3886/ICPSR38429.v1}
 "ncvs_2021_household"
 
@@ -210,7 +210,7 @@
 #'   \item{\code{V3024}}{integer HISPANIC ORIGIN}
 #'   \item{\code{V3084}}{integer SEXUAL ORIENTATION (START 2017 Q1)}
 #'   \item{\code{V3086}}{integer CURRENT GENDER IDENTITY (START 2017 Q1)}
-#'}
+#' }
 #' @source \url{https://doi.org/10.3886/ICPSR38429.v1}
 "ncvs_2021_person"
 
@@ -283,7 +283,7 @@
 #'   \item{\code{V202109x}}{double PRE-POST: SUMMARY: Voter turnout in 2020}
 #'   \item{\code{V202110x}}{double PRE-POST: SUMMARY: 2020 Presidential vote}
 #'   \item{\code{VotedPres2020_selection}}{factor PRE-POST: SUMMARY: 2020 Presidential vote}
-#'}
+#' }
 #' @source \url{https://electionstudies.org/data-center/2020-time-series-study/}
 "anes_2020"
 
@@ -315,4 +315,31 @@
 #'    \item{\code{POVERTY3}}{factor RC-POVERTY LEVEL-NEW INC (% OF US CENSUS POVERTY THRESHOLD)}
 #' }
 #' @source \url{https://www.samhsa.gov/data/data-we-collect/nsduh-national-survey-drug-use-and-health/datafiles}
-"nsduh_2023"
+"nsduh_2023"
+
+#' @title California Health Interview Survey (CHIS) (2023) data
+#' @description A subset of variables from the CHIS 2023 Public Use File
+#' @format A data frame with 21671 rows and 98 variables:
+#' \describe{
+#'    \item{\code{PUF1Y_ID}}{character PUBLIC USE FILE ID - CHIS 1 YEAR DATAFILES}
+#'    \item{\code{AH1V2}}{factor HAVE USUAL SOURCE OF HEALTH CARE}
+#'    \item{\code{AH22}}{factor DELAY/NOT GET OTHER MEDICAL CARE IN PAST 12 MOS}
+#'    \item{\code{SMKCUR30}}{factor CURRENT SMOKER (PAST 30 DAYS)}
+#'    \item{\code{AB1}}{factor GENERAL HEALTH CONDITION}
+#'    \item{\code{DIABETES}}{factor DOCTOR EVER TOLD HAVE DIABETES (NON-GESTATIONAL)}
+#'    \item{\code{BMI_P}}{double BODY MASS INDEX (PUF RECODE)}
+#'    \item{\code{RBMI}}{factor BMI DESCRIPTIVE}
+#'    \item{\code{AB17}}{factor DOCTOR EVER TOLD HAVE ASTHMA}
+#'    \item{\code{DSTRS12}}{factor LIKELY HAS HAD PSYCHOLOGICAL DISTRESS IN THE LAST YEAR}
+#'    \item{\code{AB29V2}}{factor DOCTOR EVER TOLD HAVE HIGH BLOOD PRESSURE}
+#'    \item{\code{SPK_ENG}}{factor ENGLISH USE AND PROFICIENCY}
+#'    \item{\code{POVLL2_P1V2}}{double POVERTY LEVEL AS TIMES OF 100% FPL (PUF RECODE V2)}
+#'    \item{\code{POVLL}}{factor POVERTY LEVEL}
+#'    \item{\code{SRAGE_P1}}{ordered;factor SELF-REPORTED AGE (PUF 1 YR RECODE)}
+#'    \item{\code{SRSEX}}{factor SELF-REPORTED GENDER}
+#'    \item{\code{OMBSRR_P1}}{factor OMB/CURRENT DOF RACE - ETHNICITY (PUF 1 YR RECODE)}
+#'    \item{\code{RAKEDW0}}{double CHIS 2023 FINAL RAKED WEIGHT}
+#'    \item{\code{RAKEDW1 - RAKEDW80}}{CHIS2023 RAKED WEIGHT - REPLICATE 1 through REPLICATE 80}
+#' }
+#' @source \url{https://healthpolicy.ucla.edu/our-work/public-use-files/one-year-public-use-files-pufs}
+"chis_2023"

README.Rmd

@@ -17,8 +17,8 @@ knitr::opts_chunk$set(
   warning = FALSE,
   message = FALSE,
   fig.retina = 2,
-  fig.align = 'center',
-  tidy = 'styler'
+  fig.align = "center",
+  tidy = "styler"
 )
 ```
 
@@ -46,7 +46,7 @@ This package includes data from three surveys including the American National El
 
 ### ANES
 
-The ANES data is based on the publicly available 2020 ANES data with additional derived variables and is subset to people who completed both pre and post-election interviews. The ANES Times Series Studies collect data on political polling in the United States and has been conducted since 1948.For more information about the 2020 study, see the [American National Election Studies website](https://electionstudies.org/data-center/2020-time-series-study/). On the ANES website, you can learn more about the study, see codebooks and methodology reports, and download the data (after registering). We received permission to distribute this data for the purpose of the book. Once the package is loaded, you can use the data immediately as follows:
+The ANES data is based on the publicly available 2020 ANES data with additional derived variables and is subset to people who completed both pre and post-election interviews. The ANES Times Series Studies collect data on political polling in the United States and has been conducted since 1948. For more information about the 2020 study, see the [American National Election Studies website](https://electionstudies.org/data-center/2020-time-series-study/). On the ANES website, you can learn more about the study, see codebooks and methodology reports, and download the data (after registering). We received permission to distribute this data for the purpose of the book. Once the package is loaded, you can use the data immediately as follows:
 
 ```{r}
 #| label: show-anes
@@ -61,7 +61,7 @@ Also, included in the package is a Stata version of the ANES data with a subset
 ```{r}
 #| label: anes-stata
 
-anes_stata <- haven::read_dta(system.file("extdata", "anes_2020_stata_example.dta", package="srvyrexploR"))
+anes_stata <- haven::read_dta(system.file("extdata", "anes_2020_stata_example.dta", package = "srvyrexploR"))
 ```
 
 ### NCVS
@@ -98,6 +98,19 @@ head(recs_2020)
 head(recs_2020_raw)
 ```
 
+### CHIS
+
+The CHIS data is a subset of variables from the 2023 California Health Interview Survey Adult Public Use File. CHIS is an annual survey of people in households in California with several topics related to [health and social determinants of health](https://healthpolicy.ucla.edu/our-work/california-health-interview-survey-chis/chis-design-and-methods/survey-topics-and-questionnaires). For more information about the study, refer to the [CHIS website](https://healthpolicy.ucla.edu/our-work/california-health-interview-survey-chis). To download a full version of the data with all variables or view codebooks, create an account and [download the public use files](https://healthpolicy.ucla.edu/our-work/public-use-files). See a snippet of the data below:
+
+```{r}
+#| label: show-chis
+
+head(chis_2023)
+```
+
+See `?chis_2023` for more information about the data.
+
+
 ## Examples
 
 To analyze the survey data, we recommend using the {srvyr} package as follows:
@@ -112,16 +125,18 @@ pak::pak("gergness/srvyr")
 library(srvyr)
 
 recs_des <- recs_2020 %>%
-  as_survey_rep(weights = NWEIGHT, repweights = NWEIGHT1:NWEIGHT60,
-                type = "JK1", scale = 59/60, mse = TRUE, 
-                variables=c(ACUsed, Region))
+  as_survey_rep(
+    weights = NWEIGHT, repweights = NWEIGHT1:NWEIGHT60,
+    type = "JK1", scale = 59 / 60, mse = TRUE,
+    variables = c(ACUsed, Region)
+  )
 
 recs_des
 
 recs_des %>%
   group_by(Region) %>%
   summarize(
-    p=survey_mean(ACUsed, vartype="ci", proportion = TRUE, prop_method = "logit")
+    p = survey_mean(ACUsed, vartype = "ci", proportion = TRUE, prop_method = "logit")
   )
 ```
 
@@ -148,6 +163,10 @@ ANES:
 
 + American National Election Studies, 2021. ANES 2020 Time Series Study Full Release [dataset and documentation]. July 19, 2021 version. https://www.electionstudies.org
 
+CHIS:
+
++ California Health Interview Survey. CHIS 2023 Adult Public Use Files. [Computer file]. UCLA Center for Health Policy Research, Los Angeles, CA. February 2025	version
+
 NCVS:
 
 + United States. Bureau of Justice Statistics. National Crime Victimization Survey, [United States], 2021. Inter-university Consortium for Political and Social Research [distributor], 2022-09-19. https://doi.org/10.3886/ICPSR38429.v1
@@ -160,4 +179,4 @@ and Health: Public use file data users’ guide. https://www.samhsa.gov/data/dat
 RECS:
 
 + U.S. Energy Information Administration, 2024. Residential Energy Consumption 2020 Survey Data. [dataset and documentation]. January 2024 version. https://www.eia.gov/consumption/residential/data/2020/index.php?view=microdata
-+ U.S. Energy Information Administration, 2018 Residential Energy Consumption 2015 Survey Data. [dataset and documentation]. December 2018 version. https://www.eia.gov/consumption/residential/data/2015/index.php?view=microdata 
++ U.S. Energy Information Administration, 2018 Residential Energy Consumption 2015 Survey Data. [dataset and documentation]. December 2018 version. https://www.eia.gov/consumption/residential/data/2015/index.php?view=microdata 

README.md

@@ -37,7 +37,7 @@ The ANES data is based on the publicly available 2020 ANES data with
 additional derived variables and is subset to people who completed both
 pre and post-election interviews. The ANES Times Series Studies collect
 data on political polling in the United States and has been conducted
-since 1948.For more information about the 2020 study, see the [American
+since 1948. For more information about the 2020 study, see the [American
 National Election Studies
 website](https://electionstudies.org/data-center/2020-time-series-study/).
 On the ANES website, you can learn more about the study, see codebooks
@@ -280,6 +280,42 @@ head(recs_2020_raw)
 #> #   STUDIO <dbl>, WALLTYPE <dbl>, ROOFTYPE <dbl>, HIGHCEIL <dbl>, …
 ```
 
+### CHIS
+
+The CHIS data is a subset of variables from the 2023 California Health
+Interview Survey Adult Public Use File. CHIS is an annual survey of
+people in households in California with several topics related to
+[health and social determinants of
+health](https://healthpolicy.ucla.edu/our-work/california-health-interview-survey-chis/chis-design-and-methods/survey-topics-and-questionnaires).
+For more information about the study, refer to the [CHIS
+website](https://healthpolicy.ucla.edu/our-work/california-health-interview-survey-chis).
+To download a full version of the data with all variables or view
+codebooks, create an account and [download the public use
+files](https://healthpolicy.ucla.edu/our-work/public-use-files). See a
+snippet of the data below:
+
+``` r
+head(chis_2023)
+#> # A tibble: 6 × 98
+#>   PUF1Y_ID AH1V2 AH22  SMKCUR30 AB1    DIABETES BMI_P RBMI  AB17  DSTRS12 AB29V2
+#>   <chr>    <fct> <fct> <fct>    <fct>  <fct>    <dbl> <fct> <fct> <fct>   <fct> 
+#> 1 23021436 Yes   No    No       Very … No        35.6 Obes… No    No      No    
+#> 2 23009146 Yes   No    No       Excel… No        23.0 Norm… No    No      No    
+#> 3 23005039 Yes   No    No       Good   No        25.6 Over… Yes   No      Borde…
+#> 4 23025815 Yes   Yes   No       Fair   No        42.5 Obes… No    No      Borde…
+#> 5 23010158 Yes   No    No       Good   Yes       24.7 Norm… No    No      Yes   
+#> 6 23006250 Yes   No    No       Excel… No        19.1 Norm… No    No      No    
+#> # ℹ 87 more variables: SPK_ENG <fct>, POVLL2_P1V2 <dbl>, POVLL <fct>,
+#> #   SRAGE_P1 <ord>, SRSEX <fct>, OMBSRR_P1 <fct>, RAKEDW0 <dbl>, RAKEDW1 <dbl>,
+#> #   RAKEDW2 <dbl>, RAKEDW3 <dbl>, RAKEDW4 <dbl>, RAKEDW5 <dbl>, RAKEDW6 <dbl>,
+#> #   RAKEDW7 <dbl>, RAKEDW8 <dbl>, RAKEDW9 <dbl>, RAKEDW10 <dbl>,
+#> #   RAKEDW11 <dbl>, RAKEDW12 <dbl>, RAKEDW13 <dbl>, RAKEDW14 <dbl>,
+#> #   RAKEDW15 <dbl>, RAKEDW16 <dbl>, RAKEDW17 <dbl>, RAKEDW18 <dbl>,
+#> #   RAKEDW19 <dbl>, RAKEDW20 <dbl>, RAKEDW21 <dbl>, RAKEDW22 <dbl>, …
+```
+
+See `?chis_2023` for more information about the data.
+
 ## Examples
 
 To analyze the survey data, we recommend using the {srvyr} package as
@@ -362,6 +398,12 @@ ANES:
   Full Release \[dataset and documentation\]. July 19, 2021 version.
   <https://www.electionstudies.org>
 
+CHIS:
+
+- California Health Interview Survey. CHIS 2023 Adult Public Use Files.
+  \[Computer file\]. UCLA Center for Health Policy Research, Los
+  Angeles, CA. February 2025 version
+
 NCVS:
 
 - United States. Bureau of Justice Statistics. National Crime