In caseybreen/wcensoc:
[^updated]: Last updated: r format(Sys.time(), '%d %B, %Y')
| Page| Variable | Label |
|----:|:--------------------|:---------------------------------------------|
| \hyperlink{page.2}{2} | \hyperlink{page.2}{ssn} |Social Security Number |
| \hyperlink{page.3}{3} | \hyperlink{page.3}{fname} |First Name (Cleaned) |
| \hyperlink{page.4}{4} | \hyperlink{page.4}{mname} |Middle Name (Cleaned) |
| \hyperlink{page.5}{5} | \hyperlink{page.5}{lname} |Last Name (Cleaned) |
| \hyperlink{page.6}{6} | \hyperlink{page.6}{fname_raw} |First Name (Raw) |
| \hyperlink{page.7}{7} | \hyperlink{page.7}{mname_raw} |Middle Name (Raw) |
| \hyperlink{page.8}{8} | \hyperlink{page.8}{lname_raw} |Last Name (Raw) |
| \hyperlink{page.9}{9} | \hyperlink{page.9}{sex} |Sex |
| \hyperlink{page.10}{10} | \hyperlink{page.10}{race_first} |Race on First Application |
| \hyperlink{page.11}{11} | \hyperlink{page.11}{race_first_cyear} |First Race: Application Year |
| \hyperlink{page.12}{12} | \hyperlink{page.12}{race_first_cmonth} |First Race: Application Month |
| \hyperlink{page.13}{13} | \hyperlink{page.13}{race_last} |Race on Last Application |
| \hyperlink{page.14}{14} | \hyperlink{page.14}{race_last_cyear} |Last Race: Application Year |
| \hyperlink{page.15}{15} | \hyperlink{page.15}{race_last_cmonth} |Last Race: Application Month |
| \hyperlink{page.16}{16} | \hyperlink{page.16}{race_change} |Change in Race Response Flag |
| \hyperlink{page.17}{17} | \hyperlink{page.17}{bpl} |Place of Birth |
| \hyperlink{page.18}{18} | \hyperlink{page.18}{byear} |Year of Birth |
| \hyperlink{page.19}{19} | \hyperlink{page.19}{bmonth} |Month of Birth |
| \hyperlink{page.20}{20} | \hyperlink{page.20}{bday} |Day of Birth |
| \hyperlink{page.21}{21} | \hyperlink{page.21}{dyear} |Year of Death |
| \hyperlink{page.22}{22} | \hyperlink{page.22}{dmonth} |Month of Death |
| \hyperlink{page.23}{23} | \hyperlink{page.23}{dday} |Day of Death |
| \hyperlink{page.24}{24} | \hyperlink{page.24}{death_age} |Age at Death (Years) |
| \hyperlink{page.25}{25} | \hyperlink{page.25}{zip_residence} |ZIP Code of Residence at Time of Death |
| \hyperlink{page.26}{26} | \hyperlink{page.26}{socstate} |State where Social Security Number Issued |
| \hyperlink{page.27}{27} | \hyperlink{page.27}{father_fname} |Father's First Name (Cleaned) |
| \hyperlink{page.28}{28} | \hyperlink{page.28}{father_mname} |Father's Middle Name (Cleaned) |
| \hyperlink{page.29}{29} | \hyperlink{page.29}{father_lname} |Father's Last Name (Cleaned) |
| \hyperlink{page.30}{30} | \hyperlink{page.30}{father_fname_raw} |Father's First Name (Raw) |
| \hyperlink{page.31}{31} | \hyperlink{page.31}{father_mname_raw} |Father's Middle Name (Raw) |
| \hyperlink{page.32}{32} | \hyperlink{page.32}{father_lname_raw} |Father's Last Name (Raw) |
| \hyperlink{page.33}{33} | \hyperlink{page.33}{mother_fname} |Mother's First Name (Cleaned) |
| \hyperlink{page.34}{34} | \hyperlink{page.34}{mother_mname} |Mother's Middle Name (Cleaned) |
| \hyperlink{page.35}{35} | \hyperlink{page.35}{mother_lname} |Mother's Last Name (Cleaned) |
| \hyperlink{page.36}{36} | \hyperlink{page.36}{mother_fname_raw} |Mother's First Name (Raw) |
| \hyperlink{page.37}{37} | \hyperlink{page.37}{mother_mname_raw} |Mother's Middle Name (Raw) |
| \hyperlink{page.38}{38} | \hyperlink{page.38}{mother_lname_raw} |Mother's Last Name (Raw) |
| \hyperlink{page.39}{39} | \hyperlink{page.39}{age_first_application} |Age at First Social Security Application|
| \hyperlink{page.40}{40} | \hyperlink{page.40}{number_apps} |Number of Applications |
| \hyperlink{page.41}{41} | \hyperlink{page.41}{number_claims} |Number of Claims |
| \hyperlink{page.42}{42} | \hyperlink{page.42}{weight} |High-Coverage Sub-Sample Weight |
| \hyperlink{page.43}{43} | \hyperlink{page.43}{ccweight} |High-Coverage "Complete Case" Sub-Sample Weight|
## Library Packages
library(ggplot2)
library(dplyr)
library(data.table)
library(kableExtra)
library(here)
## read in the BUNMD
bunmd <- fread("/censoc/data/numident/4_berkeley_unified_mortality_database/bunmd_names_cleaned.csv")
## set path for reading figures
knitr::opts_knit$set(root.dir = here("~/censocdev/codebase/05_create_censoc_codebooks/bunmd_codebook_graphics"))
\newpage
\huge ssn
\normalsize
\vspace{12pt}
Label: Social Security Number
Description: ssn reports a person's Social Security number, as recorded in the Numident death records. Uniquely identifies all records in the dataset.
\newpage
\huge fname
\normalsize
\vspace{12pt}
Label: First Name (Cleaned)
Description: fname reports the first 16 letters of the person's cleaned first name, as recorded in the Numident death records. This variable was cleaned from raw first names by removing titles (e.g., Dr.)
and replacing nicknames with standard names (e.g., Billy to William). Non-alphabetical characters were also
removed.
\newpage
\huge mname
\normalsize
\vspace{12pt}
Label: Middle Name (Cleaned)
Description: mname reports the first 16 letters of the person's cleaned middle name, as recorded in the Numident death records. This variable was cleaned from raw middle names by replacing nicknames with standard names (e.g., Billy to William) and removing non-alphabetical characters.
\newpage
\huge lname
\normalsize
\vspace{12pt}
Label: Last Name (Cleaned)
Description: lname reports the first 21 letters of the person's cleaned last name, as recorded in the Numident death records. This variable was cleaned from the raw middle name variable by removing non-alphabetical characters. Last names with two words were combined into one (e.g. Mc Donald to McDonald).
\newpage
\huge fname_raw
\normalsize
\vspace{12pt}
Label: First Name (Raw)
Description: fname_raw reports the first 16 letters of the person's raw first name, as recorded in the Numident death records. These strings are taken directly from the Social Security application (SSA) records, have not been cleaned, and users should refer to fname if they want cleaned names.
\newpage
\huge mname_raw
\normalsize
\vspace{12pt}
Label: Middle Name (Raw)
Description: mname_raw reports the first 16 letters of the person's raw middle name, as recorded in the Numident death records. These strings are taken directly from the Social Security application (SSA) records, have not been cleaned, and users should refer to mname if they want cleaned names.
\newpage
\huge lname_raw
\normalsize
\vspace{12pt}
Label: Last Name (Raw)
Description: lname_raw reports the first 21 letters of the person's raw last name, as recorded in the Numident death records. These strings are taken directly from the Social Security application (SSA) records, have not been cleaned, and users should refer to lname if they want cleaned names.
\newpage
\huge sex
\normalsize
\vspace{12pt}
Label: Sex
Description: sex reports a person's sex, as recorded in the Numident death, application, or claims Records.
opts_chunk$set(fig.lp = '')
knitr::kable(bunmd %>%
group_by(sex) %>%
tally() %>%
mutate(freq = signif(n*100 / sum(n), 3)) %>%
mutate(label = c("Men", "Women", "Missing")) %>%
select(sex, label, n, `freq %` = freq))
| sex|label | n| freq %|
|---:|:-------|--------:|------:|
| 1|Men | 25769568| 52.20|
| 2|Women | 22686047| 46.00|
| NA|Missing | 882212| 1.79|
\newpage
\huge race_first
\normalsize
\vspace{12pt}
Label: race first
Description: race_first reports a person's race, as recorded on their first application entry.
Note: Before 1980, the race schema in the Social Security application form contained three categories: White, Black, and Other. In 1980, the SSA added three categories: (1) Asian, Asian American, or Pacific Islander, (2) Hispanic, and (3) North American Indian or Alaskan Native. They also removed the Other category.
knitr::kable(bunmd %>%
group_by(race_first) %>%
tally() %>%
mutate(freq = round(n*100 / sum(n), 3)) %>%
mutate(label = c("White", "Black", "Other", "Asian, Asian American, or Pacific Islander", "Hispanic", "North American Indian or Alaskan Native", "Missing")) %>%
select(race_first, label, n, `freq %` = freq))
| race_first|label | n| freq %|
|----------:|:------------------------------------------|--------:|------:|
| 1|White | 28850917| 58.476|
| 2|Black | 4066081| 8.241|
| 3|Other | 689360| 1.397|
| 4|Asian, Asian American, or Pacific Islander | 207656| 0.421|
| 5|Hispanic | 286517| 0.581|
| 6|North American Indian or Alaskan Native | 17485| 0.035|
| NA|Missing | 15219811| 30.848|
\newpage
\huge race_first_cyear
\normalsize
\vspace{12pt}
Label: First Race: Application Year
Description: race_first_cyear is a numeric variable reporting the year of the application on which a person reported their first race.
\vspace{12pt}
\newpage
\huge race_first_cmonth
\normalsize
\vspace{12pt}
Label: First Race: Application Month
Description: race_first_cmonth is a numeric variable reporting the month of the application on which a person reported their first race.
\newpage
\huge race_last
\normalsize
\vspace{12pt}
Label: race last
Description: race_last reports a person's race, as recorded on their most recent application entry.
Note: Before 1980, the race schema in the Social Security application form contained three categories: White, Black, and Other. In 1980, the SSA added three categories: (1) Asian, Asian American, or Pacific Islander, (2) Hispanic, and (3) North American Indian or Alaskan Native. They also removed the Other category.
knitr::kable(bunmd %>%
group_by(race_last) %>%
tally() %>%
mutate(freq = round(n*100 / sum(n), 3)) %>%
mutate(label = c("White", "Black", "Other", "Asian, Asian American, or Pacific Islander", "Hispanic", "North American Indian or Alaskan Native", "Missing")) %>%
select(race_last, label, n, `freq %` = freq))
| race_last|label | n| freq %|
|---------:|:------------------------------------------|--------:|------:|
| 1|White | 28417859| 57.599|
| 2|Black | 4040665| 8.190|
| 3|Other | 469636| 0.952|
| 4|Asian, Asian American, or Pacific Islander | 305470| 0.619|
| 5|Hispanic | 794762| 1.611|
| 6|North American Indian or Alaskan Native | 89624| 0.182|
| NA|Missing | 15219811| 30.848|
\newpage
\huge race_last_cyear
\normalsize
\vspace{12pt}
Label: First Race: Application Year
Description: race_last_cyear reports the year of the application on which a person reported their last race.
\newpage
\Huge race_last_cmonth
\normalsize
\vspace{12pt}
Label: Last Race: Application Month
Description: race_last_cmonth is a numeric variable reporting the month of the application on which a person reported their last race.
\newpage
\newpage
\huge race_change
\normalsize
\vspace{12pt}
Label: Change in Race Response Flag
Description: race_change is a numeric dichotomous variable reporting whether an individual changed their race response across their Social Security applications.
knitr::kable(bunmd %>%
group_by(race_change) %>%
tally() %>%
mutate(freq = signif(n*100 / sum(n), 3)) %>%
mutate(label = c("No Change", "Change", "No Race Information")) %>%
select(race_change, label, n, `freq %` = freq))
| race_change|label | n| freq %|
|-----------:|:-------------------|--------:|------:|
| 0|No Change | 33263321| 67.40|
| 1|Change | 855047| 1.73|
| NA|No Race Information | 15219459| 30.80|
\newpage
\huge bpl
\normalsize
\vspace{12pt}
Label: Birthplace
Description: bpl is a numeric variable reporting the person's place of birth, as recorded in the Numident application or claims records. The accompanying bpl_string variable reports the person's place of birth as a character string. The numeric codes match the detailed IPUMS-USA Birthplace codes.
For a complete list of IPUMS Birthplace codes, please see: https://usa.ipums.org/usa-action/variables/BPL
bpl_tabulation <- bunmd %>%
filter(bpl < 10000) %>%
group_by(bpl, bpl_string) %>%
tally() %>%
ungroup() %>%
mutate(freq = round(n*100 / sum(n), 2)) %>%
select(bpl, bpl_string, n, `freq %` = freq)
rows <- seq_len(nrow(bpl_tabulation) %/% 2)
knitr::kable(list(bpl_tabulation[rows,1:4],
matrix(numeric(), nrow=0, ncol=1),
bpl_tabulation[-rows, 1:4]),
caption = "This is the caption.",
label = "tables", format = "latex", booktabs = TRUE)
\vspace{12pt}
\begin{table}[H]
\caption*{Birthplace Frequencies (for Native Born)}
\centering
\begin{tabular}[t]{rlrr}
\toprule
bpl & bpl_string & n & freq \%\
\midrule
100 & Alabama & 916460 & 2.84\
200 & Alaska & 25406 & 0.08\
400 & Arizona & 144300 & 0.45\
500 & Arkansas & 624232 & 1.93\
600 & California & 1115176 & 3.46\
\addlinespace
800 & Colorado & 277268 & 0.86\
900 & Connecticut & 374288 & 1.16\
1000 & Delaware & 64978 & 0.20\
1100 & District of Columbia & 129166 & 0.40\
1200 & Florida & 462174 & 1.43\
\addlinespace
1300 & Georgia & 1011492 & 3.14\
1500 & Hawaii & 91736 & 0.28\
1600 & Idaho & 125177 & 0.39\
1700 & Illinois & 1741873 & 5.40\
1800 & Indiana & 828095 & 2.57\
\addlinespace
1900 & Iowa & 607860 & 1.88\
2000 & Kansas & 476683 & 1.48\
2100 & Kentucky & 866052 & 2.68\
2200 & Louisiana & 718460 & 2.23\
2300 & Maine & 205832 & 0.64\
\addlinespace
2400 & Maryland & 436983 & 1.35\
2500 & Massachusetts & 970896 & 3.01\
2600 & Michigan & 1182488 & 3.67\
2700 & Minnesota & 568850 & 1.76\
2800 & Mississippi & 691061 & 2.14\
\bottomrule
\end{tabular}
\centering
\begin{tabular}[t]{r}
\toprule
\bottomrule
\end{tabular}
\centering
\begin{tabular}[t]{rlrr}
\toprule
bpl & bpl_string & n & freq \%\
\midrule
2900 & Missouri & 953475 & 2.96\
3000 & Montana & 129791 & 0.40\
3100 & Nebraska & 334691 & 1.04\
3200 & Nevada & 24990 & 0.08\
3300 & New Hampshire & 102281 & 0.32\
\addlinespace
3400 & New Jersey & 845462 & 2.62\
3500 & New Mexico & 151357 & 0.47\
3600 & New York & 2646066 & 8.20\
3700 & North Carolina & 1100194 & 3.41\
3800 & North Dakota & 190312 & 0.59\
\addlinespace
3900 & Ohio & 1547059 & 4.80\
4000 & Oklahoma & 691459 & 2.14\
4100 & Oregon & 197939 & 0.61\
4200 & Pennsylvania & 2480466 & 7.69\
4400 & Rhode Island & 160511 & 0.50\
\addlinespace
4500 & South Carolina & 592424 & 1.84\
4600 & South Dakota & 168314 & 0.52\
4700 & Tennessee & 868901 & 2.69\
4800 & Texas & 1726094 & 5.35\
4900 & Utah & 158295 & 0.49\
\addlinespace
5000 & Vermont & 87739 & 0.27\
5100 & Virginia & 790692 & 2.45\
5300 & Washington & 324126 & 1.00\
5400 & West Virginia & 560213 & 1.74\
5500 & Wisconsin & 713743 & 2.21\
\addlinespace
5600 & Wyoming & 57795 & 0.18\
\bottomrule
\end{tabular}
\end{table}
\newpage
\huge byear
\normalsize
\vspace{12pt}
Label: Birth Year
Description: byear is a numeric variable reporting the person's year of birth, as recorded in the Numident death records.
bunmd %>%
group_by(byear) %>%
summarise(n = n()) %>%
ggplot(aes(x = byear, y = n)) +
geom_line() +
geom_point() +
theme_minimal() + #replace with a different theme (theme_bw()) if the bbplot package isn't downloaded
ggtitle("Year of Birth") +
theme(legend.position="bottom") +
xlab("title") +
theme(plot.title = element_text(size=25),
axis.title = element_text(size = 17),
axis.text.y = element_text(size=17),
axis.text.x = element_text(size=17)) +
labs(x = "Year",
y = "Count") +
scale_y_continuous(labels = scales::comma) +
scale_x_continuous(breaks = scales::pretty_breaks(n=5))
\vspace{75pt}
\newpage
\huge bmonth
\normalsize
\vspace{12pt}
Label: Birth Month
Description: bmonth is a numeric variable reporting the person's month of birth, as recorded in the Numident death records.
knitr::kable(bunmd %>%
group_by(bmonth) %>%
tally() %>%
mutate(freq = round(n*100 / sum(n), 2)) %>%
mutate(label = c("January", "February", "March", "April", "May", "June", "July", "August", "September", "October", "November", "December", "Missing")) %>%
select(bmonth, label, n, `freq %` = freq))
| bmonth|label | n| freq %|
|------:|:---------|-------:|------:|
| 1|January | 4181375| 8.47|
| 2|February | 3933555| 7.97|
| 3|March | 4296940| 8.71|
| 4|April | 3976307| 8.06|
| 5|May | 4051432| 8.21|
| 6|June | 3937147| 7.98|
| 7|July | 4221224| 8.56|
| 8|August | 4362872| 8.84|
| 9|September | 4279353| 8.67|
| 10|October | 4173868| 8.46|
| 11|November | 3884566| 7.87|
| 12|December | 4039185| 8.19|
| NA|Missing | 3| 0.00|
\newpage
\huge bday
\normalsize
\vspace{12pt}
Label: Birth Day
Description: bday is a numeric variable reporting the person's day of birth, as recorded in the Numident death records.
Note: It appears from the surplus of counts on the 1st and the 15th of the month that SSA might have done some imputation of missing values to these dates.
knitr::kable(bunmd %>%
group_by(bday) %>%
tally() %>%
mutate(freq = signif(n*100 / sum(n), 2)) %>%
select(bday, n, `freq %` = freq))
| bday| n| freq %|
|----:|-------:|------:|
| 1| 1752583| 3.600|
| 2| 1658244| 3.400|
| 3| 1609261| 3.300|
| 4| 1637955| 3.300|
| 5| 1622040| 3.300|
| 6| 1626699| 3.300|
| 7| 1605110| 3.300|
| 8| 1631598| 3.300|
| 9| 1590390| 3.200|
| 10| 1710297| 3.500|
| 11| 1586088| 3.200|
| 12| 1670822| 3.400|
| 13| 1568796| 3.200|
| 14| 1621064| 3.300|
| 15| 1782188| 3.600|
| 16| 1613051| 3.300|
| 17| 1604846| 3.300|
| 18| 1616778| 3.300|
| 19| 1576661| 3.200|
| 20| 1643349| 3.300|
| 21| 1546797| 3.100|
| 22| 1631722| 3.300|
| 23| 1592459| 3.200|
| 24| 1591364| 3.200|
| 25| 1657548| 3.400|
| 26| 1568447| 3.200|
| 27| 1577419| 3.200|
| 28| 1624799| 3.300|
| 29| 1471946| 3.000|
| 30| 1414317| 2.900|
| 31| 901308| 1.800|
| NA| 31881| 0.065|
\newpage
\huge dyear
\normalsize
\vspace{12pt}
Label: Death Year
Description: dyear is a numeric variable reporting the person's year of death, as recorded in the Numident death records.
\vspace{75pt}
\begin{center}
\end{center}
## Get HMD deaths from website
hmd_deaths <- fread("/data/josh/CenSoc/hmd/hmd_statistics/deaths/Deaths_1x1/USA.Deaths_1x1.txt")
## Tabulate deaths in BUNMD for 65+
bunmd.deaths.tabulated <- bunmd %>%
filter(death_age >= 65) %>%
group_by(Year = dyear) %>%
filter(Year > 1960) %>%
summarize(deaths = n()) %>%
mutate(source = "BUNMD")
## Tabulate deaths in BUNMD for 65+
## Restrict to complete cases with sex, birthplace, race
bunmd.deaths.complete.tabulated <- bunmd %>%
filter(dyear %in% c(1988:2005)) %>%
filter(death_age >= 65) %>%
group_by(Year = dyear) %>%
filter(Year > 1960) %>%
filter(!is.na(ccweight)) %>%
summarize(deaths = n()) %>%
mutate(source = "BUNMD Complete Cases")
## Tabulate deaths in HMD for 65+
hmd.deaths.tabulated <- hmd_deaths %>%
filter(Age >= 65) %>%
group_by(Year) %>%
filter(Year > 1960) %>%
summarize(deaths = sum(Total)) %>%
mutate(source = "Human Mortality Database")
## Combine into one data frame
data.for.plot <- hmd.deaths.tabulated %>%
bind_rows(bunmd.deaths.tabulated) %>%
bind_rows(bunmd.deaths.complete.tabulated) %>%
filter(Year > 1970 & Year < 2009)
## Create death coverage plot
ggplot(data.for.plot) +
geom_line((aes(x = Year, y = deaths, linetype=source)), size = .9) +
scale_linetype_manual(values=c( "dashed", "dotted", "solid")) +
theme_minimal() + #replace with a different theme (theme_bw()) if the bbplot package isn't downloaded
theme(legend.position="bottom", legend.title = element_blank()) +
theme(plot.title = element_text(size = 25),
axis.title = element_text(size = 17),
axis.text.y = element_text(size=17),
axis.text.x = element_text(size=17),
legend.text=element_text(size=15)) +
labs(title = "Year of Death 65+",
x = "Year",
y = "Count") +
scale_y_continuous(labels = scales::comma) +
scale_x_continuous(breaks = scales::pretty_breaks(n=5))
\newpage
\huge dmonth
\normalsize
\vspace{12pt}
Label: Death Month
Description: dmonth is a numeric variable reporting the person's month of death, as recorded in the Numident death records.
knitr::kable(bunmd %>%
group_by(dmonth) %>%
tally() %>%
mutate(freq = signif(n*100 / sum(n), 3)) %>%
mutate(label = c("January", "February", "March", "April", "May", "June", "July", "August", "September", "October", "November", "December")) %>%
select(dmonth, label, n, `freq %` = freq))
| dmonth|label | n| freq %|
|------:|:---------|-------:|------:|
| 1|January | 4610022| 9.34|
| 2|February | 4119282| 8.35|
| 3|March | 4353899| 8.82|
| 4|April | 4036794| 8.18|
| 5|May | 4023999| 8.16|
| 6|June | 3828836| 7.76|
| 7|July | 3924851| 7.96|
| 8|August | 3887262| 7.88|
| 9|September | 3835198| 7.77|
| 10|October | 4125914| 8.36|
| 11|November | 4102011| 8.31|
| 12|December | 4489759| 9.10|
\newpage
\huge dday
\normalsize
\vspace{12pt}
Label: Day of Death
Description: dday is a numeric variable reporting the person's day of death, as recorded in the Numident death records.
Note: It appears from the surplus of counts on the 1st, 4th, and the 15th of the month that SSA might have done some imputation of missing values to these dates. Also, different periods have differ allocation patterns.
knitr::kable(bunmd %>%
group_by(dday) %>%
tally() %>%
mutate(freq = signif(n*100 / sum(n), 2)) %>%
select(dday, n, `freq %` = freq))
| dday| n| freq %|
|----:|-------:|------:|
| 1| 1432114| 2.9|
| 2| 1240840| 2.5|
| 3| 1258505| 2.6|
| 4| 1281969| 2.6|
| 5| 1241857| 2.5|
| 6| 1238121| 2.5|
| 7| 1234527| 2.5|
| 8| 1237353| 2.5|
| 9| 1234152| 2.5|
| 10| 1236852| 2.5|
| 11| 1234080| 2.5|
| 12| 1234552| 2.5|
| 13| 1230163| 2.5|
| 14| 1231013| 2.5|
| 15| 3392922| 6.9|
| 16| 1227374| 2.5|
| 17| 1228022| 2.5|
| 18| 1223495| 2.5|
| 19| 1223837| 2.5|
| 20| 1230608| 2.5|
| 21| 1218728| 2.5|
| 22| 1217328| 2.5|
| 23| 1219353| 2.5|
| 24| 1216433| 2.5|
| 25| 1214084| 2.5|
| 26| 1216347| 2.5|
| 27| 1215884| 2.5|
| 28| 1217904| 2.5|
| 29| 1130910| 2.3|
| 30| 1104857| 2.2|
| 31| 713927| 1.4|
| NA| 9559716| 19.0|
\newpage
\huge death_age
\normalsize
\vspace{12pt}
Label: Age at Death (Years)
Description: death_age is a numeric variable reporting the person's age at death in years, calculated using birth and death information recorded in the Numident death records.
\vspace{75pt}
bunmd %>%
filter(death_age %in% c(0:110)) %>%
group_by(death_age) %>%
summarise(n = n()) %>%
ggplot(aes(x = death_age, y = n)) +
geom_point() +
geom_line() +
theme_minimal() +
ggtitle("Age of Death") +
theme(legend.position="bottom") +
xlab("title") +
theme(plot.title = element_text(size = 25),
axis.title = element_text(size = 17),
axis.text.y = element_text(size=17),
axis.text.x = element_text(size=17)) +
labs(x = "Age at Death",
y = "Count") +
scale_y_continuous(labels = scales::comma) +
scale_x_continuous(breaks = scales::pretty_breaks(n=5))
\newpage
\huge zip_residence
\normalsize
\vspace{12pt}
Label: ZIP Code of Residence at Time of Death
Description: zip_residence is a string variable (9-characters) reporting a person's ZIP code of residence at time of death, as reported in the Numident death records.
\newpage
\huge socstate
\normalsize
\vspace{12pt}
Label: State where Social Security Number Issued
Description: The state in which the person's social security card was issued. Determined by first three (3) digits of Social Security number, as recorded in Numident death records. The accompanying socstate_string variable reports the state in which a person's social security card was issued as a character string. The numeric codes match the detailed IPUMS-USA Birthplace codes.
socstate_tabulation <- bunmd %>%
filter(socstate < 10000 | is.na(socstate)) %>%
group_by(socstate, socstate_string) %>%
tally() %>%
ungroup() %>%
mutate(freq = round(n*100 / sum(n), 2)) %>%
select(socstate, socstate_string, n, `freq %` = freq)
rows <- seq_len(nrow(socstate_tabulation) %/% 2)
knitr::kable(list(socstate_tabulation[rows,1:4],
matrix(numeric(), nrow=0, ncol=1),
socstate_tabulation[-rows, 1:4]),
caption = "This is the caption.",
label = "tables", format = "latex", booktabs = TRUE)
\vspace{12pt}
\begin{table}[H]
\caption*{Socstate Frequencies}
\centering
\begin{tabular}[t]{rlrr}
\toprule
socstate & socstate_string & n & freq \%\
\midrule
100 & Alabama & 1010756 & 2.07\
200 & Alaska & 35207 & 0.07\
400 & Arizona & 274363 & 0.56\
500 & Arkansas & 621147 & 1.27\
600 & California & 3381722 & 6.91\
\addlinespace
800 & Colorado & 435935 & 0.89\
900 & Connecticut & 644841 & 1.32\
1000 & Delaware & 103907 & 0.21\
1100 & District of Columbia & 298017 & 0.61\
1200 & Florida & 1119359 & 2.29\
\addlinespace
1300 & Georgia & 1171471 & 2.39\
1500 & Hawaii & 165054 & 0.34\
1600 & Idaho & 179125 & 0.37\
1700 & Illinois & 2855031 & 5.84\
1800 & Indiana & 1248048 & 2.55\
\addlinespace
1900 & Iowa & 764643 & 1.56\
2000 & Kansas & 579408 & 1.18\
2100 & Kentucky & 917858 & 1.88\
2200 & Louisiana & 899017 & 1.84\
2300 & Maine & 283261 & 0.58\
\addlinespace
2400 & Maryland & 728497 & 1.49\
2500 & Massachusetts & 1465566 & 3.00\
2600 & Michigan & 2034399 & 4.16\
2700 & Minnesota & 817858 & 1.67\
2800 & Mississippi & 687994 & 1.41\
\addlinespace
2900 & Missouri & 1299368 & 2.66\
\bottomrule
\end{tabular}
\centering
\begin{tabular}[t]{r}
\toprule
\bottomrule
\end{tabular}
\centering
\begin{tabular}[t]{rlrr}
\toprule
socstate & socstate_string & n & freq \%\
\midrule
3000 & Montana & 163411 & 0.33\
3100 & Nebraska & 390427 & 0.80\
3200 & Nevada & 59479 & 0.12\
3300 & New Hampshire & 154388 & 0.32\
3400 & New Jersey & 1510334 & 3.09\
\addlinespace
3500 & New Mexico & 207319 & 0.42\
3600 & New York & 4980871 & 10.18\
3700 & North Carolina & 1349016 & 2.76\
3800 & North Dakota & 181420 & 0.37\
3900 & Ohio & 2460960 & 5.03\
\addlinespace
4000 & Oklahoma & 779894 & 1.59\
4100 & Oregon & 423383 & 0.87\
4200 & Pennsylvania & 3266642 & 6.68\
4400 & Rhode Island & 252536 & 0.52\
4500 & South Carolina & 637802 & 1.30\
\addlinespace
4600 & South Dakota & 174252 & 0.36\
4700 & Tennessee & 1115600 & 2.28\
4800 & Texas & 2562712 & 5.24\
4900 & Utah & 208380 & 0.43\
5000 & Vermont & 110991 & 0.23\
\addlinespace
5100 & Virginia & 1014527 & 2.07\
5300 & Washington & 675565 & 1.38\
5400 & West Virginia & 646790 & 1.32\
5500 & Wisconsin & 1021002 & 2.09\
5600 & Wyoming & 86773 & 0.18\
\addlinespace
NA & & 471923 & 0.96\
\bottomrule
\end{tabular}
\end{table}
\newpage
\huge father_fname
\normalsize
\vspace{12pt}
Label: Father's First Name (Cleaned)
Description: father_fname is a character variable reporting the first 16 letters of the person's father's cleaned first name, as recorded in the Numident application records. This variable was cleaned from the father's raw first names by removing titles (e.g., Dr.) and replacing nicknames with standard names (e.g., Billy to William). Non-alphabetical characters were also
removed.
\newpage
\huge father_mname
\normalsize
\vspace{12pt}
Label: Father's Middle Name (Cleaned)
Description: father_mname is a character variable reporting the first 16 letters of the person's father's cleaned middle name, as recorded in the Numident application records. This variable was cleaned from the father's raw middle names by replacing nicknames with standard names (e.g., Billy to William) and removing non-alphabetical characters.
\newpage
\huge father_lname
\normalsize
\vspace{12pt}
Label: Father's Last Name (Cleaned)
Description: father_lname is a character variable reporting the first 21 letters of the person's father's cleaned last name, as recorded in the Numident application records. This variable was cleaned from the father's raw last names by removing non-alphabetical characters. Last names with two words were combined into one (e.g. Mc Donald to McDonald).
\newpage
\huge father_fname_raw
\normalsize
\vspace{12pt}
Label: Father's First Name (Raw)
Description: father_fname_raw is a character variable reporting the first 16 letters of the person's father's raw first name, as recorded in the Numident application records. These strings are taken directly from SSA records, have not been cleaned, and users should refer to father_fname if they want cleaned names.
\newpage
\huge father_mname_raw
\normalsize
\vspace{12pt}
Label: Father's Middle Name (Raw)
Description: father_mname_raw is a character variable reporting the first 16 letters of the person's raw father's middle name, as recorded in the Numident application records. These strings are taken directly from SSA records, have not been cleaned, and users should refer to father_mname if they want cleaned names.
\newpage
\huge father_lname_raw
\normalsize
\vspace{12pt}
Label: Father's Last Name (Raw)
Description: father_lname_raw is a character variable reporting the first 21 letters of the person's father's raw last name, as recorded in the Numident application records.These strings are taken directly from SSA records, have not been cleaned, and users should refer to father_lname if they want cleaned names.
\newpage
\huge mother_fname
\normalsize
\vspace{12pt}
Label: Mother's First Name (Cleaned)
Description: mother_fname is a character variable reporting the first 16 letters of the person's mother's cleaned first name, as recorded in the Numident application records. This variable was cleaned from the mother's raw first names by removing titles (e.g., Dr.) and replacing nicknames with standard names (e.g., Billy to William). Non-alphabetical characters were also removed.
\newpage
\huge mother_mname
\normalsize
\vspace{12pt}
Label: Mother's Middle Name (Cleaned)
Description: mother_mname is a character variable reporting the first 16 letters of the person's mother's cleaned middle name, as recorded in the Numident application records. This variable was cleaned from the mother's raw middle names by replacing nicknames with standard names (e.g., Billy to William) and removing non-alphabetical characters.
removed.
\newpage
\huge mother_lname
\normalsize
\vspace{12pt}
Label: Mother's Last Name (Cleaned)
Description: mother_lname is a character variable reporting the first 21 letters of the person's mother's cleaned last name, as recorded in the Numident application records. This variable was cleaned from the mother's raw last names by removing non-alphabetical characters. Last names with two words were combined into one (e.g. Mc Donald to McDonald).
\newpage
\huge mother_fname_raw
\normalsize
\vspace{12pt}
Label: Mother's First Name (Raw)
Description: mother_fname is a character variable reporting the first 16 letters of the person's mother's rawfirst name, as recorded in the Numident application records. These strings are taken directly from SSA records, have not been cleaned, and users should refer to mother_fname if they want cleaned names.
\newpage
\huge mother_mname_raw
\normalsize
\vspace{12pt}
Label: Mother's Middle Name (Raw)
Description: mother_mname is a character variable reporting the first 16 letters of the person's mother's raw middle name, as recorded in the Numident application records. These strings are taken directly from SSA records, have not been cleaned, and users should refer to mother_mname if they want cleaned names.
\newpage
\huge mother_lname_raw
\normalsize
\vspace{12pt}
Label: Mother's Last Name (Raw)
Description: mother_lname is a character variable reporting the first 21 letters of the person's mother's raw last name, as recorded in the Numident application records. These strings are taken directly from SSA records, have not been cleaned, and users should refer to mother_lname if they want cleaned names.
\newpage
\huge age_first_application
\normalsize
\vspace{12pt}
Label: Age at First Social Security Application
Description: age_first_application reports the age at which the person submitted their first Social Security Application.
bunmd %>%
group_by(age_first_application) %>%
filter(age_first_application %in% c(0:110)) %>%
summarise(n = n()) %>%
ggplot(aes(x = age_first_application, y = n)) +
geom_line() +
geom_point() +
theme_minimal() + #replace with a different theme (theme_bw()) if the bbplot package isn't downloaded
ggtitle("Age of First Application") +
theme(legend.position="bottom") +
xlab("title") +
theme(plot.title = element_text(size = 25),
axis.title = element_text(size = 17),
axis.text.y = element_text(size=17),
axis.text.x = element_text(size=17)) +
labs(x = "Age of First Application",
y = "Count") +
scale_y_continuous(labels = scales::comma) +
scale_x_continuous(breaks = scales::pretty_breaks(n=5))
\vspace{75pt}
\newpage
\huge number_apps
\normalsize
\vspace{12pt}
Label: Total Number of Applications
Description: number_apps reports the person's total number of Social Security applications, as recorded in the Numident application records. This variable was top-coded at 10.
topcode <- function(a, top) {
return(ifelse(a > top, top, a))
}
## manually switch 10 to 10+
knitr::kable(bunmd %>%
mutate(number_apps = topcode(number_apps, 10)) %>%
group_by(number_apps) %>%
tally() %>%
mutate(freq = signif(n*100 / sum(n), 2)) %>%
select(number_apps, n, `freq %` = freq))
| number_apps| n| freq %|
|-----------:|--------:|------:|
| 0| 14166703| 29.000|
| 1| 17646617| 36.000|
| 2| 10107569| 20.000|
| 3| 4309930| 8.700|
| 4| 1710582| 3.500|
| 5| 719300| 1.500|
| 6| 323112| 0.650|
| 7| 155220| 0.310|
| 8| 80363| 0.160|
| 9| 43690| 0.089|
| 10+| 74741| 0.150|
\newpage
\huge number_claims
\normalsize
\vspace{12pt}
Label: Total Number of Claims
Description: number_claims reports the person's total number of Social Security claims, as recorded in the Numident claim records. This variable was top-coded at 3.
topcode <- function(a, top) {
return(ifelse(a > top, top, a))
}
## manually switch 3 to 3+
knitr::kable(bunmd %>%
mutate(number_claims = topcode(number_claims, 3)) %>%
group_by(number_claims) %>%
tally() %>%
mutate(freq = round(n*100 / sum(n), 2)) %>%
select(number_claims, n, `freq %` = freq))
| number_claims| n| freq %|
|-------------:|--------:|-----:|
| 0| 32931311| 66.75|
| 1| 16360228| 33.16|
| 2| 45187| 0.09|
| 3+| 1101| 0.00|
\newpage
\huge weight
\normalsize
\vspace{12pt}
Label: High Coverage Sample Weight
Description: A post-stratification person-weight to Human Mortality Database (HMD) totals for persons (1) born between 1895-1940 (2) dying between 1988-2005 and (3) dying between ages 65-100 (4) with a non-missing value for sex. Please see the CenSoc methods protocol for more details on weighting procedure.
bunmd %>%
summarize(min(weight, na.rm = T), max(weight, na.rm = T))
bunmd %>%
ggplot() +
geom_histogram(aes(x = weight)) +
theme_minimal() + #replace with a different theme (theme_bw()) if the bbplot package isn't downloaded
ggtitle("Distribution of weights") +
theme(legend.position="bottom") +
theme(plot.title = element_text(size = 25),
axis.title = element_text(size = 17),
axis.text.y = element_text(size=17),
axis.text.x = element_text(size=17)) +
labs(x = "Weight",
y = "Count") +
scale_y_continuous(labels = scales::comma) +
scale_x_continuous(breaks = scales::pretty_breaks(n=5))
\vspace{40pt}
|Value | Label |
|---------------:|---------------:|
| NA | No weight assigned|
| Min Weight | 0.961 |
| Max Weight | 2.383 |
\vspace{30pt}
\begin{figure}[H]
\centering
\includegraphics[width=16cm]{bunmd_codebook_graphics/weights_lexis.png}
\caption*{Average weight by age of death and year of death.}
\end{figure}
\newpage
\huge ccweight
\vspace{12pt}
Label: High Coverage "Complete Case" Sample Weight
Description: A post-stratification person-weight to Human Mortality Database (HMD) totals for persons (1) born between 1895-1940 (2) dying between 1988-2005 (3) dying between ages 65-100 (4) with a non-missing value for sex (5) with a non-missing value for birth place and (6) with a non-missing value for race. Please see the CenSoc methods protocol for more details on weighting procedure.
ccweight_tab <- bunmd %>%
filter(!is.na(ccweight)) %>%
summarize('Min Weight' = round(min(ccweight),2), 'Max Weight' = round(max(ccweight), 2)) %>%
mutate(id = 1:n()) %>%
pivot_longer(-id, names_to = "Label", values_to = "Value") %>%
select(Value, Label) %>%
add_row(Label = "No Weight Assigned", Value = NA) %>%
knitr::kable()
weight_conservative.plot <- bunmd %>%
filter(!is.na(ccweight)) %>%
ggplot() +
geom_boxplot(aes(x=ccweight), fill='grey92') +
ylim(-1,1) +
theme_minimal(15) +
theme(axis.title.y=element_blank(), axis.text.y=element_blank(), axis.ticks.y=element_blank()) +
ggtitle("Distribution of Weights") +
xlab('Weight')
\vspace{40pt}
|Value | Label |
|---------------:|---------------:|
| NA | Incomplete case |
| Min Weight | 1.02 |
| Max Weight | 18.71 |
\vspace{30pt}
\begin{figure}[H]
\centering
\includegraphics[width=16cm]{bunmd_codebook_graphics/ccweights_lexis.png}
\caption*{Average ccweight by age of death and year of death.}
\end{figure}
caseybreen/wcensoc documentation built on Nov. 21, 2024, 5:15 a.m.
R Package Documentation
Browse R Packages
We want your feedback!
Note that we can't provide technical support on individual packages. You should contact the package authors for that.
[^updated]: Last updated: r format(Sys.time(), '%d %B, %Y')
| Page| Variable | Label | |----:|:--------------------|:---------------------------------------------| | \hyperlink{page.2}{2} | \hyperlink{page.2}{ssn} |Social Security Number | | \hyperlink{page.3}{3} | \hyperlink{page.3}{fname} |First Name (Cleaned) | | \hyperlink{page.4}{4} | \hyperlink{page.4}{mname} |Middle Name (Cleaned) | | \hyperlink{page.5}{5} | \hyperlink{page.5}{lname} |Last Name (Cleaned) | | \hyperlink{page.6}{6} | \hyperlink{page.6}{fname_raw} |First Name (Raw) | | \hyperlink{page.7}{7} | \hyperlink{page.7}{mname_raw} |Middle Name (Raw) | | \hyperlink{page.8}{8} | \hyperlink{page.8}{lname_raw} |Last Name (Raw) | | \hyperlink{page.9}{9} | \hyperlink{page.9}{sex} |Sex | | \hyperlink{page.10}{10} | \hyperlink{page.10}{race_first} |Race on First Application | | \hyperlink{page.11}{11} | \hyperlink{page.11}{race_first_cyear} |First Race: Application Year | | \hyperlink{page.12}{12} | \hyperlink{page.12}{race_first_cmonth} |First Race: Application Month | | \hyperlink{page.13}{13} | \hyperlink{page.13}{race_last} |Race on Last Application | | \hyperlink{page.14}{14} | \hyperlink{page.14}{race_last_cyear} |Last Race: Application Year | | \hyperlink{page.15}{15} | \hyperlink{page.15}{race_last_cmonth} |Last Race: Application Month | | \hyperlink{page.16}{16} | \hyperlink{page.16}{race_change} |Change in Race Response Flag | | \hyperlink{page.17}{17} | \hyperlink{page.17}{bpl} |Place of Birth | | \hyperlink{page.18}{18} | \hyperlink{page.18}{byear} |Year of Birth | | \hyperlink{page.19}{19} | \hyperlink{page.19}{bmonth} |Month of Birth | | \hyperlink{page.20}{20} | \hyperlink{page.20}{bday} |Day of Birth | | \hyperlink{page.21}{21} | \hyperlink{page.21}{dyear} |Year of Death | | \hyperlink{page.22}{22} | \hyperlink{page.22}{dmonth} |Month of Death | | \hyperlink{page.23}{23} | \hyperlink{page.23}{dday} |Day of Death | | \hyperlink{page.24}{24} | \hyperlink{page.24}{death_age} |Age at Death (Years) | | \hyperlink{page.25}{25} | \hyperlink{page.25}{zip_residence} |ZIP Code of Residence at Time of Death | | \hyperlink{page.26}{26} | \hyperlink{page.26}{socstate} |State where Social Security Number Issued | | \hyperlink{page.27}{27} | \hyperlink{page.27}{father_fname} |Father's First Name (Cleaned) | | \hyperlink{page.28}{28} | \hyperlink{page.28}{father_mname} |Father's Middle Name (Cleaned) | | \hyperlink{page.29}{29} | \hyperlink{page.29}{father_lname} |Father's Last Name (Cleaned) | | \hyperlink{page.30}{30} | \hyperlink{page.30}{father_fname_raw} |Father's First Name (Raw) | | \hyperlink{page.31}{31} | \hyperlink{page.31}{father_mname_raw} |Father's Middle Name (Raw) | | \hyperlink{page.32}{32} | \hyperlink{page.32}{father_lname_raw} |Father's Last Name (Raw) | | \hyperlink{page.33}{33} | \hyperlink{page.33}{mother_fname} |Mother's First Name (Cleaned) | | \hyperlink{page.34}{34} | \hyperlink{page.34}{mother_mname} |Mother's Middle Name (Cleaned) | | \hyperlink{page.35}{35} | \hyperlink{page.35}{mother_lname} |Mother's Last Name (Cleaned) | | \hyperlink{page.36}{36} | \hyperlink{page.36}{mother_fname_raw} |Mother's First Name (Raw) | | \hyperlink{page.37}{37} | \hyperlink{page.37}{mother_mname_raw} |Mother's Middle Name (Raw) | | \hyperlink{page.38}{38} | \hyperlink{page.38}{mother_lname_raw} |Mother's Last Name (Raw) | | \hyperlink{page.39}{39} | \hyperlink{page.39}{age_first_application} |Age at First Social Security Application| | \hyperlink{page.40}{40} | \hyperlink{page.40}{number_apps} |Number of Applications | | \hyperlink{page.41}{41} | \hyperlink{page.41}{number_claims} |Number of Claims | | \hyperlink{page.42}{42} | \hyperlink{page.42}{weight} |High-Coverage Sub-Sample Weight | | \hyperlink{page.43}{43} | \hyperlink{page.43}{ccweight} |High-Coverage "Complete Case" Sub-Sample Weight|
## Library Packages library(ggplot2) library(dplyr) library(data.table) library(kableExtra) library(here) ## read in the BUNMD bunmd <- fread("/censoc/data/numident/4_berkeley_unified_mortality_database/bunmd_names_cleaned.csv") ## set path for reading figures knitr::opts_knit$set(root.dir = here("~/censocdev/codebase/05_create_censoc_codebooks/bunmd_codebook_graphics"))
\newpage
\huge ssn \normalsize \vspace{12pt}
Label: Social Security Number
Description: ssn reports a person's Social Security number, as recorded in the Numident death records. Uniquely identifies all records in the dataset.
\newpage
\huge fname \normalsize \vspace{12pt}
Label: First Name (Cleaned)
Description: fname reports the first 16 letters of the person's cleaned first name, as recorded in the Numident death records. This variable was cleaned from raw first names by removing titles (e.g., Dr.) and replacing nicknames with standard names (e.g., Billy to William). Non-alphabetical characters were also removed.
\newpage
\huge mname \normalsize \vspace{12pt}
Label: Middle Name (Cleaned)
Description: mname reports the first 16 letters of the person's cleaned middle name, as recorded in the Numident death records. This variable was cleaned from raw middle names by replacing nicknames with standard names (e.g., Billy to William) and removing non-alphabetical characters.
\newpage
\huge lname \normalsize \vspace{12pt}
Label: Last Name (Cleaned)
Description: lname reports the first 21 letters of the person's cleaned last name, as recorded in the Numident death records. This variable was cleaned from the raw middle name variable by removing non-alphabetical characters. Last names with two words were combined into one (e.g. Mc Donald to McDonald).
\newpage \huge fname_raw \normalsize \vspace{12pt}
Label: First Name (Raw)
Description: fname_raw reports the first 16 letters of the person's raw first name, as recorded in the Numident death records. These strings are taken directly from the Social Security application (SSA) records, have not been cleaned, and users should refer to fname if they want cleaned names.
\newpage
\huge mname_raw \normalsize \vspace{12pt}
Label: Middle Name (Raw)
Description: mname_raw reports the first 16 letters of the person's raw middle name, as recorded in the Numident death records. These strings are taken directly from the Social Security application (SSA) records, have not been cleaned, and users should refer to mname if they want cleaned names.
\newpage
\huge lname_raw \normalsize \vspace{12pt}
Label: Last Name (Raw)
Description: lname_raw reports the first 21 letters of the person's raw last name, as recorded in the Numident death records. These strings are taken directly from the Social Security application (SSA) records, have not been cleaned, and users should refer to lname if they want cleaned names.
\newpage \huge sex \normalsize \vspace{12pt}
Label: Sex
Description: sex reports a person's sex, as recorded in the Numident death, application, or claims Records.
opts_chunk$set(fig.lp = '') knitr::kable(bunmd %>% group_by(sex) %>% tally() %>% mutate(freq = signif(n*100 / sum(n), 3)) %>% mutate(label = c("Men", "Women", "Missing")) %>% select(sex, label, n, `freq %` = freq))
| sex|label | n| freq %| |---:|:-------|--------:|------:| | 1|Men | 25769568| 52.20| | 2|Women | 22686047| 46.00| | NA|Missing | 882212| 1.79|
\newpage
\huge race_first \normalsize \vspace{12pt}
Label: race first
Description: race_first reports a person's race, as recorded on their first application entry.
Note: Before 1980, the race schema in the Social Security application form contained three categories: White, Black, and Other. In 1980, the SSA added three categories: (1) Asian, Asian American, or Pacific Islander, (2) Hispanic, and (3) North American Indian or Alaskan Native. They also removed the Other category.
knitr::kable(bunmd %>% group_by(race_first) %>% tally() %>% mutate(freq = round(n*100 / sum(n), 3)) %>% mutate(label = c("White", "Black", "Other", "Asian, Asian American, or Pacific Islander", "Hispanic", "North American Indian or Alaskan Native", "Missing")) %>% select(race_first, label, n, `freq %` = freq))
| race_first|label | n| freq %| |----------:|:------------------------------------------|--------:|------:| | 1|White | 28850917| 58.476| | 2|Black | 4066081| 8.241| | 3|Other | 689360| 1.397| | 4|Asian, Asian American, or Pacific Islander | 207656| 0.421| | 5|Hispanic | 286517| 0.581| | 6|North American Indian or Alaskan Native | 17485| 0.035| | NA|Missing | 15219811| 30.848|
\newpage
\huge race_first_cyear \normalsize \vspace{12pt}
Label: First Race: Application Year
Description: race_first_cyear is a numeric variable reporting the year of the application on which a person reported their first race. \vspace{12pt}
\newpage
\huge race_first_cmonth \normalsize \vspace{12pt}
Label: First Race: Application Month
Description: race_first_cmonth is a numeric variable reporting the month of the application on which a person reported their first race.
\newpage
\huge race_last \normalsize \vspace{12pt}
Label: race last
Description: race_last reports a person's race, as recorded on their most recent application entry.
Note: Before 1980, the race schema in the Social Security application form contained three categories: White, Black, and Other. In 1980, the SSA added three categories: (1) Asian, Asian American, or Pacific Islander, (2) Hispanic, and (3) North American Indian or Alaskan Native. They also removed the Other category.
knitr::kable(bunmd %>% group_by(race_last) %>% tally() %>% mutate(freq = round(n*100 / sum(n), 3)) %>% mutate(label = c("White", "Black", "Other", "Asian, Asian American, or Pacific Islander", "Hispanic", "North American Indian or Alaskan Native", "Missing")) %>% select(race_last, label, n, `freq %` = freq))
| race_last|label | n| freq %| |---------:|:------------------------------------------|--------:|------:| | 1|White | 28417859| 57.599| | 2|Black | 4040665| 8.190| | 3|Other | 469636| 0.952| | 4|Asian, Asian American, or Pacific Islander | 305470| 0.619| | 5|Hispanic | 794762| 1.611| | 6|North American Indian or Alaskan Native | 89624| 0.182| | NA|Missing | 15219811| 30.848|
\newpage
\huge race_last_cyear \normalsize \vspace{12pt}
Label: First Race: Application Year
Description: race_last_cyear reports the year of the application on which a person reported their last race.
\newpage
\Huge race_last_cmonth \normalsize \vspace{12pt}
Label: Last Race: Application Month
Description: race_last_cmonth is a numeric variable reporting the month of the application on which a person reported their last race.
\newpage
\newpage
\huge race_change \normalsize \vspace{12pt}
Label: Change in Race Response Flag
Description: race_change is a numeric dichotomous variable reporting whether an individual changed their race response across their Social Security applications.
knitr::kable(bunmd %>% group_by(race_change) %>% tally() %>% mutate(freq = signif(n*100 / sum(n), 3)) %>% mutate(label = c("No Change", "Change", "No Race Information")) %>% select(race_change, label, n, `freq %` = freq))
| race_change|label | n| freq %| |-----------:|:-------------------|--------:|------:| | 0|No Change | 33263321| 67.40| | 1|Change | 855047| 1.73| | NA|No Race Information | 15219459| 30.80|
\newpage
\huge bpl \normalsize \vspace{12pt}
Label: Birthplace
Description: bpl is a numeric variable reporting the person's place of birth, as recorded in the Numident application or claims records. The accompanying bpl_string variable reports the person's place of birth as a character string. The numeric codes match the detailed IPUMS-USA Birthplace codes.
For a complete list of IPUMS Birthplace codes, please see: https://usa.ipums.org/usa-action/variables/BPL
bpl_tabulation <- bunmd %>% filter(bpl < 10000) %>% group_by(bpl, bpl_string) %>% tally() %>% ungroup() %>% mutate(freq = round(n*100 / sum(n), 2)) %>% select(bpl, bpl_string, n, `freq %` = freq) rows <- seq_len(nrow(bpl_tabulation) %/% 2) knitr::kable(list(bpl_tabulation[rows,1:4], matrix(numeric(), nrow=0, ncol=1), bpl_tabulation[-rows, 1:4]), caption = "This is the caption.", label = "tables", format = "latex", booktabs = TRUE)
\vspace{12pt}
\begin{table}[H] \caption*{Birthplace Frequencies (for Native Born)} \centering \begin{tabular}[t]{rlrr} \toprule bpl & bpl_string & n & freq \%\ \midrule 100 & Alabama & 916460 & 2.84\ 200 & Alaska & 25406 & 0.08\ 400 & Arizona & 144300 & 0.45\ 500 & Arkansas & 624232 & 1.93\ 600 & California & 1115176 & 3.46\ \addlinespace 800 & Colorado & 277268 & 0.86\ 900 & Connecticut & 374288 & 1.16\ 1000 & Delaware & 64978 & 0.20\ 1100 & District of Columbia & 129166 & 0.40\ 1200 & Florida & 462174 & 1.43\ \addlinespace 1300 & Georgia & 1011492 & 3.14\ 1500 & Hawaii & 91736 & 0.28\ 1600 & Idaho & 125177 & 0.39\ 1700 & Illinois & 1741873 & 5.40\ 1800 & Indiana & 828095 & 2.57\ \addlinespace 1900 & Iowa & 607860 & 1.88\ 2000 & Kansas & 476683 & 1.48\ 2100 & Kentucky & 866052 & 2.68\ 2200 & Louisiana & 718460 & 2.23\ 2300 & Maine & 205832 & 0.64\ \addlinespace 2400 & Maryland & 436983 & 1.35\ 2500 & Massachusetts & 970896 & 3.01\ 2600 & Michigan & 1182488 & 3.67\ 2700 & Minnesota & 568850 & 1.76\ 2800 & Mississippi & 691061 & 2.14\ \bottomrule \end{tabular} \centering \begin{tabular}[t]{r} \toprule
\bottomrule \end{tabular} \centering \begin{tabular}[t]{rlrr} \toprule bpl & bpl_string & n & freq \%\ \midrule 2900 & Missouri & 953475 & 2.96\ 3000 & Montana & 129791 & 0.40\ 3100 & Nebraska & 334691 & 1.04\ 3200 & Nevada & 24990 & 0.08\ 3300 & New Hampshire & 102281 & 0.32\ \addlinespace 3400 & New Jersey & 845462 & 2.62\ 3500 & New Mexico & 151357 & 0.47\ 3600 & New York & 2646066 & 8.20\ 3700 & North Carolina & 1100194 & 3.41\ 3800 & North Dakota & 190312 & 0.59\ \addlinespace 3900 & Ohio & 1547059 & 4.80\ 4000 & Oklahoma & 691459 & 2.14\ 4100 & Oregon & 197939 & 0.61\ 4200 & Pennsylvania & 2480466 & 7.69\ 4400 & Rhode Island & 160511 & 0.50\ \addlinespace 4500 & South Carolina & 592424 & 1.84\ 4600 & South Dakota & 168314 & 0.52\ 4700 & Tennessee & 868901 & 2.69\ 4800 & Texas & 1726094 & 5.35\ 4900 & Utah & 158295 & 0.49\ \addlinespace 5000 & Vermont & 87739 & 0.27\ 5100 & Virginia & 790692 & 2.45\ 5300 & Washington & 324126 & 1.00\ 5400 & West Virginia & 560213 & 1.74\ 5500 & Wisconsin & 713743 & 2.21\ \addlinespace 5600 & Wyoming & 57795 & 0.18\ \bottomrule \end{tabular} \end{table}
\newpage
\huge byear \normalsize \vspace{12pt}
Label: Birth Year
Description: byear is a numeric variable reporting the person's year of birth, as recorded in the Numident death records.
bunmd %>% group_by(byear) %>% summarise(n = n()) %>% ggplot(aes(x = byear, y = n)) + geom_line() + geom_point() + theme_minimal() + #replace with a different theme (theme_bw()) if the bbplot package isn't downloaded ggtitle("Year of Birth") + theme(legend.position="bottom") + xlab("title") + theme(plot.title = element_text(size=25), axis.title = element_text(size = 17), axis.text.y = element_text(size=17), axis.text.x = element_text(size=17)) + labs(x = "Year", y = "Count") + scale_y_continuous(labels = scales::comma) + scale_x_continuous(breaks = scales::pretty_breaks(n=5))
\vspace{75pt}
\newpage
\huge bmonth \normalsize \vspace{12pt}
Label: Birth Month
Description: bmonth is a numeric variable reporting the person's month of birth, as recorded in the Numident death records.
knitr::kable(bunmd %>% group_by(bmonth) %>% tally() %>% mutate(freq = round(n*100 / sum(n), 2)) %>% mutate(label = c("January", "February", "March", "April", "May", "June", "July", "August", "September", "October", "November", "December", "Missing")) %>% select(bmonth, label, n, `freq %` = freq))
| bmonth|label | n| freq %| |------:|:---------|-------:|------:| | 1|January | 4181375| 8.47| | 2|February | 3933555| 7.97| | 3|March | 4296940| 8.71| | 4|April | 3976307| 8.06| | 5|May | 4051432| 8.21| | 6|June | 3937147| 7.98| | 7|July | 4221224| 8.56| | 8|August | 4362872| 8.84| | 9|September | 4279353| 8.67| | 10|October | 4173868| 8.46| | 11|November | 3884566| 7.87| | 12|December | 4039185| 8.19| | NA|Missing | 3| 0.00|
\newpage
\huge bday \normalsize \vspace{12pt}
Label: Birth Day
Description: bday is a numeric variable reporting the person's day of birth, as recorded in the Numident death records.
Note: It appears from the surplus of counts on the 1st and the 15th of the month that SSA might have done some imputation of missing values to these dates.
knitr::kable(bunmd %>% group_by(bday) %>% tally() %>% mutate(freq = signif(n*100 / sum(n), 2)) %>% select(bday, n, `freq %` = freq))
| bday| n| freq %| |----:|-------:|------:| | 1| 1752583| 3.600| | 2| 1658244| 3.400| | 3| 1609261| 3.300| | 4| 1637955| 3.300| | 5| 1622040| 3.300| | 6| 1626699| 3.300| | 7| 1605110| 3.300| | 8| 1631598| 3.300| | 9| 1590390| 3.200| | 10| 1710297| 3.500| | 11| 1586088| 3.200| | 12| 1670822| 3.400| | 13| 1568796| 3.200| | 14| 1621064| 3.300| | 15| 1782188| 3.600| | 16| 1613051| 3.300| | 17| 1604846| 3.300| | 18| 1616778| 3.300| | 19| 1576661| 3.200| | 20| 1643349| 3.300| | 21| 1546797| 3.100| | 22| 1631722| 3.300| | 23| 1592459| 3.200| | 24| 1591364| 3.200| | 25| 1657548| 3.400| | 26| 1568447| 3.200| | 27| 1577419| 3.200| | 28| 1624799| 3.300| | 29| 1471946| 3.000| | 30| 1414317| 2.900| | 31| 901308| 1.800| | NA| 31881| 0.065|
\newpage
\huge dyear \normalsize \vspace{12pt}
Label: Death Year
Description: dyear is a numeric variable reporting the person's year of death, as recorded in the Numident death records.
\vspace{75pt}
\begin{center}
\end{center}
## Get HMD deaths from website hmd_deaths <- fread("/data/josh/CenSoc/hmd/hmd_statistics/deaths/Deaths_1x1/USA.Deaths_1x1.txt") ## Tabulate deaths in BUNMD for 65+ bunmd.deaths.tabulated <- bunmd %>% filter(death_age >= 65) %>% group_by(Year = dyear) %>% filter(Year > 1960) %>% summarize(deaths = n()) %>% mutate(source = "BUNMD") ## Tabulate deaths in BUNMD for 65+ ## Restrict to complete cases with sex, birthplace, race bunmd.deaths.complete.tabulated <- bunmd %>% filter(dyear %in% c(1988:2005)) %>% filter(death_age >= 65) %>% group_by(Year = dyear) %>% filter(Year > 1960) %>% filter(!is.na(ccweight)) %>% summarize(deaths = n()) %>% mutate(source = "BUNMD Complete Cases") ## Tabulate deaths in HMD for 65+ hmd.deaths.tabulated <- hmd_deaths %>% filter(Age >= 65) %>% group_by(Year) %>% filter(Year > 1960) %>% summarize(deaths = sum(Total)) %>% mutate(source = "Human Mortality Database") ## Combine into one data frame data.for.plot <- hmd.deaths.tabulated %>% bind_rows(bunmd.deaths.tabulated) %>% bind_rows(bunmd.deaths.complete.tabulated) %>% filter(Year > 1970 & Year < 2009) ## Create death coverage plot ggplot(data.for.plot) + geom_line((aes(x = Year, y = deaths, linetype=source)), size = .9) + scale_linetype_manual(values=c( "dashed", "dotted", "solid")) + theme_minimal() + #replace with a different theme (theme_bw()) if the bbplot package isn't downloaded theme(legend.position="bottom", legend.title = element_blank()) + theme(plot.title = element_text(size = 25), axis.title = element_text(size = 17), axis.text.y = element_text(size=17), axis.text.x = element_text(size=17), legend.text=element_text(size=15)) + labs(title = "Year of Death 65+", x = "Year", y = "Count") + scale_y_continuous(labels = scales::comma) + scale_x_continuous(breaks = scales::pretty_breaks(n=5))
\newpage
\huge dmonth \normalsize \vspace{12pt}
Label: Death Month
Description: dmonth is a numeric variable reporting the person's month of death, as recorded in the Numident death records.
knitr::kable(bunmd %>% group_by(dmonth) %>% tally() %>% mutate(freq = signif(n*100 / sum(n), 3)) %>% mutate(label = c("January", "February", "March", "April", "May", "June", "July", "August", "September", "October", "November", "December")) %>% select(dmonth, label, n, `freq %` = freq))
| dmonth|label | n| freq %| |------:|:---------|-------:|------:| | 1|January | 4610022| 9.34| | 2|February | 4119282| 8.35| | 3|March | 4353899| 8.82| | 4|April | 4036794| 8.18| | 5|May | 4023999| 8.16| | 6|June | 3828836| 7.76| | 7|July | 3924851| 7.96| | 8|August | 3887262| 7.88| | 9|September | 3835198| 7.77| | 10|October | 4125914| 8.36| | 11|November | 4102011| 8.31| | 12|December | 4489759| 9.10|
\newpage
\huge dday \normalsize \vspace{12pt}
Label: Day of Death
Description: dday is a numeric variable reporting the person's day of death, as recorded in the Numident death records.
Note: It appears from the surplus of counts on the 1st, 4th, and the 15th of the month that SSA might have done some imputation of missing values to these dates. Also, different periods have differ allocation patterns.
knitr::kable(bunmd %>% group_by(dday) %>% tally() %>% mutate(freq = signif(n*100 / sum(n), 2)) %>% select(dday, n, `freq %` = freq))
| dday| n| freq %| |----:|-------:|------:| | 1| 1432114| 2.9| | 2| 1240840| 2.5| | 3| 1258505| 2.6| | 4| 1281969| 2.6| | 5| 1241857| 2.5| | 6| 1238121| 2.5| | 7| 1234527| 2.5| | 8| 1237353| 2.5| | 9| 1234152| 2.5| | 10| 1236852| 2.5| | 11| 1234080| 2.5| | 12| 1234552| 2.5| | 13| 1230163| 2.5| | 14| 1231013| 2.5| | 15| 3392922| 6.9| | 16| 1227374| 2.5| | 17| 1228022| 2.5| | 18| 1223495| 2.5| | 19| 1223837| 2.5| | 20| 1230608| 2.5| | 21| 1218728| 2.5| | 22| 1217328| 2.5| | 23| 1219353| 2.5| | 24| 1216433| 2.5| | 25| 1214084| 2.5| | 26| 1216347| 2.5| | 27| 1215884| 2.5| | 28| 1217904| 2.5| | 29| 1130910| 2.3| | 30| 1104857| 2.2| | 31| 713927| 1.4| | NA| 9559716| 19.0|
\newpage
\huge death_age \normalsize \vspace{12pt}
Label: Age at Death (Years)
Description: death_age is a numeric variable reporting the person's age at death in years, calculated using birth and death information recorded in the Numident death records.
\vspace{75pt}
bunmd %>% filter(death_age %in% c(0:110)) %>% group_by(death_age) %>% summarise(n = n()) %>% ggplot(aes(x = death_age, y = n)) + geom_point() + geom_line() + theme_minimal() + ggtitle("Age of Death") + theme(legend.position="bottom") + xlab("title") + theme(plot.title = element_text(size = 25), axis.title = element_text(size = 17), axis.text.y = element_text(size=17), axis.text.x = element_text(size=17)) + labs(x = "Age at Death", y = "Count") + scale_y_continuous(labels = scales::comma) + scale_x_continuous(breaks = scales::pretty_breaks(n=5))
\newpage
\huge zip_residence
\normalsize
\vspace{12pt}
Label: ZIP Code of Residence at Time of Death
Description: zip_residence is a string variable (9-characters) reporting a person's ZIP code of residence at time of death, as reported in the Numident death records.
\newpage \huge socstate
\normalsize
\vspace{12pt}
Label: State where Social Security Number Issued
Description: The state in which the person's social security card was issued. Determined by first three (3) digits of Social Security number, as recorded in Numident death records. The accompanying socstate_string variable reports the state in which a person's social security card was issued as a character string. The numeric codes match the detailed IPUMS-USA Birthplace codes.
socstate_tabulation <- bunmd %>% filter(socstate < 10000 | is.na(socstate)) %>% group_by(socstate, socstate_string) %>% tally() %>% ungroup() %>% mutate(freq = round(n*100 / sum(n), 2)) %>% select(socstate, socstate_string, n, `freq %` = freq) rows <- seq_len(nrow(socstate_tabulation) %/% 2) knitr::kable(list(socstate_tabulation[rows,1:4], matrix(numeric(), nrow=0, ncol=1), socstate_tabulation[-rows, 1:4]), caption = "This is the caption.", label = "tables", format = "latex", booktabs = TRUE)
\vspace{12pt}
\begin{table}[H] \caption*{Socstate Frequencies} \centering \begin{tabular}[t]{rlrr} \toprule socstate & socstate_string & n & freq \%\ \midrule 100 & Alabama & 1010756 & 2.07\ 200 & Alaska & 35207 & 0.07\ 400 & Arizona & 274363 & 0.56\ 500 & Arkansas & 621147 & 1.27\ 600 & California & 3381722 & 6.91\ \addlinespace 800 & Colorado & 435935 & 0.89\ 900 & Connecticut & 644841 & 1.32\ 1000 & Delaware & 103907 & 0.21\ 1100 & District of Columbia & 298017 & 0.61\ 1200 & Florida & 1119359 & 2.29\ \addlinespace 1300 & Georgia & 1171471 & 2.39\ 1500 & Hawaii & 165054 & 0.34\ 1600 & Idaho & 179125 & 0.37\ 1700 & Illinois & 2855031 & 5.84\ 1800 & Indiana & 1248048 & 2.55\ \addlinespace 1900 & Iowa & 764643 & 1.56\ 2000 & Kansas & 579408 & 1.18\ 2100 & Kentucky & 917858 & 1.88\ 2200 & Louisiana & 899017 & 1.84\ 2300 & Maine & 283261 & 0.58\ \addlinespace 2400 & Maryland & 728497 & 1.49\ 2500 & Massachusetts & 1465566 & 3.00\ 2600 & Michigan & 2034399 & 4.16\ 2700 & Minnesota & 817858 & 1.67\ 2800 & Mississippi & 687994 & 1.41\ \addlinespace 2900 & Missouri & 1299368 & 2.66\ \bottomrule \end{tabular} \centering \begin{tabular}[t]{r} \toprule
\bottomrule \end{tabular} \centering \begin{tabular}[t]{rlrr} \toprule socstate & socstate_string & n & freq \%\ \midrule 3000 & Montana & 163411 & 0.33\ 3100 & Nebraska & 390427 & 0.80\ 3200 & Nevada & 59479 & 0.12\ 3300 & New Hampshire & 154388 & 0.32\ 3400 & New Jersey & 1510334 & 3.09\ \addlinespace 3500 & New Mexico & 207319 & 0.42\ 3600 & New York & 4980871 & 10.18\ 3700 & North Carolina & 1349016 & 2.76\ 3800 & North Dakota & 181420 & 0.37\ 3900 & Ohio & 2460960 & 5.03\ \addlinespace 4000 & Oklahoma & 779894 & 1.59\ 4100 & Oregon & 423383 & 0.87\ 4200 & Pennsylvania & 3266642 & 6.68\ 4400 & Rhode Island & 252536 & 0.52\ 4500 & South Carolina & 637802 & 1.30\ \addlinespace 4600 & South Dakota & 174252 & 0.36\ 4700 & Tennessee & 1115600 & 2.28\ 4800 & Texas & 2562712 & 5.24\ 4900 & Utah & 208380 & 0.43\ 5000 & Vermont & 110991 & 0.23\ \addlinespace 5100 & Virginia & 1014527 & 2.07\ 5300 & Washington & 675565 & 1.38\ 5400 & West Virginia & 646790 & 1.32\ 5500 & Wisconsin & 1021002 & 2.09\ 5600 & Wyoming & 86773 & 0.18\ \addlinespace NA & & 471923 & 0.96\ \bottomrule \end{tabular} \end{table}
\newpage
\huge father_fname \normalsize \vspace{12pt}
Label: Father's First Name (Cleaned)
Description: father_fname is a character variable reporting the first 16 letters of the person's father's cleaned first name, as recorded in the Numident application records. This variable was cleaned from the father's raw first names by removing titles (e.g., Dr.) and replacing nicknames with standard names (e.g., Billy to William). Non-alphabetical characters were also removed.
\newpage
\huge father_mname \normalsize \vspace{12pt}
Label: Father's Middle Name (Cleaned)
Description: father_mname is a character variable reporting the first 16 letters of the person's father's cleaned middle name, as recorded in the Numident application records. This variable was cleaned from the father's raw middle names by replacing nicknames with standard names (e.g., Billy to William) and removing non-alphabetical characters.
\newpage
\huge father_lname \normalsize \vspace{12pt}
Label: Father's Last Name (Cleaned)
Description: father_lname is a character variable reporting the first 21 letters of the person's father's cleaned last name, as recorded in the Numident application records. This variable was cleaned from the father's raw last names by removing non-alphabetical characters. Last names with two words were combined into one (e.g. Mc Donald to McDonald).
\newpage
\huge father_fname_raw \normalsize \vspace{12pt}
Label: Father's First Name (Raw)
Description: father_fname_raw is a character variable reporting the first 16 letters of the person's father's raw first name, as recorded in the Numident application records. These strings are taken directly from SSA records, have not been cleaned, and users should refer to father_fname if they want cleaned names.
\newpage
\huge father_mname_raw \normalsize \vspace{12pt}
Label: Father's Middle Name (Raw)
Description: father_mname_raw is a character variable reporting the first 16 letters of the person's raw father's middle name, as recorded in the Numident application records. These strings are taken directly from SSA records, have not been cleaned, and users should refer to father_mname if they want cleaned names.
\newpage
\huge father_lname_raw \normalsize \vspace{12pt}
Label: Father's Last Name (Raw)
Description: father_lname_raw is a character variable reporting the first 21 letters of the person's father's raw last name, as recorded in the Numident application records.These strings are taken directly from SSA records, have not been cleaned, and users should refer to father_lname if they want cleaned names.
\newpage
\huge mother_fname \normalsize \vspace{12pt}
Label: Mother's First Name (Cleaned)
Description: mother_fname is a character variable reporting the first 16 letters of the person's mother's cleaned first name, as recorded in the Numident application records. This variable was cleaned from the mother's raw first names by removing titles (e.g., Dr.) and replacing nicknames with standard names (e.g., Billy to William). Non-alphabetical characters were also removed.
\newpage
\huge mother_mname \normalsize \vspace{12pt}
Label: Mother's Middle Name (Cleaned)
Description: mother_mname is a character variable reporting the first 16 letters of the person's mother's cleaned middle name, as recorded in the Numident application records. This variable was cleaned from the mother's raw middle names by replacing nicknames with standard names (e.g., Billy to William) and removing non-alphabetical characters.
removed.
\newpage
\huge mother_lname \normalsize \vspace{12pt}
Label: Mother's Last Name (Cleaned)
Description: mother_lname is a character variable reporting the first 21 letters of the person's mother's cleaned last name, as recorded in the Numident application records. This variable was cleaned from the mother's raw last names by removing non-alphabetical characters. Last names with two words were combined into one (e.g. Mc Donald to McDonald).
\newpage
\huge mother_fname_raw \normalsize \vspace{12pt}
Label: Mother's First Name (Raw)
Description: mother_fname is a character variable reporting the first 16 letters of the person's mother's rawfirst name, as recorded in the Numident application records. These strings are taken directly from SSA records, have not been cleaned, and users should refer to mother_fname if they want cleaned names.
\newpage
\huge mother_mname_raw \normalsize \vspace{12pt}
Label: Mother's Middle Name (Raw)
Description: mother_mname is a character variable reporting the first 16 letters of the person's mother's raw middle name, as recorded in the Numident application records. These strings are taken directly from SSA records, have not been cleaned, and users should refer to mother_mname if they want cleaned names.
\newpage
\huge mother_lname_raw \normalsize \vspace{12pt}
Label: Mother's Last Name (Raw)
Description: mother_lname is a character variable reporting the first 21 letters of the person's mother's raw last name, as recorded in the Numident application records. These strings are taken directly from SSA records, have not been cleaned, and users should refer to mother_lname if they want cleaned names.
\newpage
\huge age_first_application
\normalsize
\vspace{12pt}
Label: Age at First Social Security Application
Description: age_first_application reports the age at which the person submitted their first Social Security Application.
bunmd %>% group_by(age_first_application) %>% filter(age_first_application %in% c(0:110)) %>% summarise(n = n()) %>% ggplot(aes(x = age_first_application, y = n)) + geom_line() + geom_point() + theme_minimal() + #replace with a different theme (theme_bw()) if the bbplot package isn't downloaded ggtitle("Age of First Application") + theme(legend.position="bottom") + xlab("title") + theme(plot.title = element_text(size = 25), axis.title = element_text(size = 17), axis.text.y = element_text(size=17), axis.text.x = element_text(size=17)) + labs(x = "Age of First Application", y = "Count") + scale_y_continuous(labels = scales::comma) + scale_x_continuous(breaks = scales::pretty_breaks(n=5))
\vspace{75pt}
\newpage
\huge number_apps
\normalsize
\vspace{12pt}
Label: Total Number of Applications
Description: number_apps reports the person's total number of Social Security applications, as recorded in the Numident application records. This variable was top-coded at 10.
topcode <- function(a, top) { return(ifelse(a > top, top, a)) } ## manually switch 10 to 10+ knitr::kable(bunmd %>% mutate(number_apps = topcode(number_apps, 10)) %>% group_by(number_apps) %>% tally() %>% mutate(freq = signif(n*100 / sum(n), 2)) %>% select(number_apps, n, `freq %` = freq))
| number_apps| n| freq %| |-----------:|--------:|------:| | 0| 14166703| 29.000| | 1| 17646617| 36.000| | 2| 10107569| 20.000| | 3| 4309930| 8.700| | 4| 1710582| 3.500| | 5| 719300| 1.500| | 6| 323112| 0.650| | 7| 155220| 0.310| | 8| 80363| 0.160| | 9| 43690| 0.089| | 10+| 74741| 0.150|
\newpage
\huge number_claims
\normalsize
\vspace{12pt}
Label: Total Number of Claims
Description: number_claims reports the person's total number of Social Security claims, as recorded in the Numident claim records. This variable was top-coded at 3.
topcode <- function(a, top) { return(ifelse(a > top, top, a)) } ## manually switch 3 to 3+ knitr::kable(bunmd %>% mutate(number_claims = topcode(number_claims, 3)) %>% group_by(number_claims) %>% tally() %>% mutate(freq = round(n*100 / sum(n), 2)) %>% select(number_claims, n, `freq %` = freq))
| number_claims| n| freq %| |-------------:|--------:|-----:| | 0| 32931311| 66.75| | 1| 16360228| 33.16| | 2| 45187| 0.09| | 3+| 1101| 0.00|
\newpage
\huge weight
\normalsize
\vspace{12pt}
Label: High Coverage Sample Weight
Description: A post-stratification person-weight to Human Mortality Database (HMD) totals for persons (1) born between 1895-1940 (2) dying between 1988-2005 and (3) dying between ages 65-100 (4) with a non-missing value for sex. Please see the CenSoc methods protocol for more details on weighting procedure.
bunmd %>% summarize(min(weight, na.rm = T), max(weight, na.rm = T)) bunmd %>% ggplot() + geom_histogram(aes(x = weight)) + theme_minimal() + #replace with a different theme (theme_bw()) if the bbplot package isn't downloaded ggtitle("Distribution of weights") + theme(legend.position="bottom") + theme(plot.title = element_text(size = 25), axis.title = element_text(size = 17), axis.text.y = element_text(size=17), axis.text.x = element_text(size=17)) + labs(x = "Weight", y = "Count") + scale_y_continuous(labels = scales::comma) + scale_x_continuous(breaks = scales::pretty_breaks(n=5))
\vspace{40pt}
|Value | Label |
|---------------:|---------------:|
| NA | No weight assigned|
| Min Weight | 0.961 |
| Max Weight | 2.383 |
\vspace{30pt}
\begin{figure}[H] \centering \includegraphics[width=16cm]{bunmd_codebook_graphics/weights_lexis.png} \caption*{Average weight by age of death and year of death.} \end{figure}
\newpage
\huge ccweight
\vspace{12pt}
Label: High Coverage "Complete Case" Sample Weight
Description: A post-stratification person-weight to Human Mortality Database (HMD) totals for persons (1) born between 1895-1940 (2) dying between 1988-2005 (3) dying between ages 65-100 (4) with a non-missing value for sex (5) with a non-missing value for birth place and (6) with a non-missing value for race. Please see the CenSoc methods protocol for more details on weighting procedure.
ccweight_tab <- bunmd %>% filter(!is.na(ccweight)) %>% summarize('Min Weight' = round(min(ccweight),2), 'Max Weight' = round(max(ccweight), 2)) %>% mutate(id = 1:n()) %>% pivot_longer(-id, names_to = "Label", values_to = "Value") %>% select(Value, Label) %>% add_row(Label = "No Weight Assigned", Value = NA) %>% knitr::kable() weight_conservative.plot <- bunmd %>% filter(!is.na(ccweight)) %>% ggplot() + geom_boxplot(aes(x=ccweight), fill='grey92') + ylim(-1,1) + theme_minimal(15) + theme(axis.title.y=element_blank(), axis.text.y=element_blank(), axis.ticks.y=element_blank()) + ggtitle("Distribution of Weights") + xlab('Weight')
\vspace{40pt}
|Value | Label |
|---------------:|---------------:|
| NA | Incomplete case |
| Min Weight | 1.02 |
| Max Weight | 18.71 |
\vspace{30pt}
\begin{figure}[H] \centering \includegraphics[width=16cm]{bunmd_codebook_graphics/ccweights_lexis.png} \caption*{Average ccweight by age of death and year of death.} \end{figure}
R Package Documentation
Browse R Packages
We want your feedback!
Note that we can't provide technical support on individual packages. You should contact the package authors for that.
Embedding an R snippet on your website
Add the following code to your website.
For more information on customizing the embed code, read Embedding Snippets.