In caseybreen/censocdev:

[^updated]: Last updated: r format(Sys.time(), '%d %B, %Y')

| Page| Variable | Label | |----:|:-------------|:---------------------------------------------| | \hyperlink{page.2}{2} | \hyperlink{page.2}{HISTID} |Historical unique identifier | | \hyperlink{page.3}{3} | \hyperlink{page.3}{byear} |Year of birth | | \hyperlink{page.4}{4} | \hyperlink{page.4}{bmonth} |Month of birth | | \hyperlink{page.5}{5} | \hyperlink{page.5}{dyear} |Year of death | | \hyperlink{page.6}{6} | \hyperlink{page.6}{dmonth} |Month of death | | \hyperlink{page.7}{7} | \hyperlink{page.7}{death_age} |Age at death (years) | | \hyperlink{page.8}{8} | \hyperlink{page.8}{weight} |CenSoc weight |

\vspace{300pt}

Summary: The CenSoc-DMF Version 4.0 dataset (N = 5,301,200) links the full-count 1940 Census to the Death Master File (DMF) 1975-2020, a collection of death records reported to the Social Security Administration. Records were linked using the conservative variant of the ABE method developed by Abramitzky, Boustan, and Eriksson (\textcolor{blue}{2012}, \textcolor{blue}{2014}, \textcolor{blue}{2017}). To merge 1940 Census variables with this dataset, researchers can obtain a copy of the 1940 Census from IPUMS-USA and link on the individual-level, unique identifier HISTID variable.

\newpage

\huge HISTID \normalsize \vspace{12pt}

Label: Historical Unique Identifier

Description: HISTID is a unique individual-level identifier. It can be used to merge the CenSoc-DMF file with the 1940 Full-Count Census from IPUMS.

\newpage

\huge byear \normalsize \vspace{12pt}

Label: Birth Year

Description: byear reports a person's year of birth, as recorded in the Social Security Death Master File.

## Library Packages
library(tidyverse)
library(data.table)

## input path (to update)
input_path <- "/global/scratch/p2p3/pl1_demography/censoc/censoc_data_releases/censoc_dmf/censoc_dmf_v4/censoc_dmf_v4.csv"

## read in censoc dmf data file
censoc_dmf <- read_csv(input_path)

byear_plot <- censoc_dmf %>%
    group_by(byear) %>%
    summarise(n = n()) %>%
    ggplot(aes(x = byear, y = n)) + 
    geom_line() + 
    geom_point() +
    theme_minimal(base_size = 15) + #replace with a different theme (theme_bw()) if the bbplot package isn't downloaded 
  ggtitle("Year of Birth") + 
  theme(legend.position="bottom") +
  xlab("title") + 
  labs(x = "Year", 
       y = "Count") + 
  scale_y_continuous(labels = scales::comma) + 
  scale_x_continuous(breaks = scales::pretty_breaks(n=5))

\vspace{75pt}

byear_plot

\newpage \huge bmonth \normalsize \vspace{12pt}

Label: Birth Month

Description: bmonth reports a person's month of birth, as recorded in the Social Security Death Master File.

## run in the console and copy and paste into documentation
bmonth_tabulated <- knitr::kable(censoc_dmf %>%
    filter(bmonth != 0) %>% 
    group_by(bmonth) %>%
    tally() %>%
    mutate(freq = signif(n*100 / sum(n), 2)) %>%
    mutate(label = c("January", "February", "March", "April", "May", "June", "July", "August", "September", "October", "November", "December")) %>%
    select(bmonth, label, n, `freq %` = freq))

\vspace{30pt}

bmonth_tabulated

\newpage

\huge dyear \normalsize \vspace{12pt}

Label: Death Year

Description: dyear reports a person's year of death, as recorded in the Social Security Death Master File.

dyear_plot <- censoc_dmf %>%
    group_by(dyear) %>%
    summarise(n = n()) %>%
    ggplot(aes(x = dyear, y = n)) + 
    geom_line() + 
    geom_point() +
    theme_minimal(base_size = 15) +  
  ggtitle("Year of Death") + 
  theme(legend.position="bottom") +
  xlab("title") + 
  labs(x = "Year", 
       y = "Count") + 
  scale_y_continuous(labels = scales::comma, limits = c(0, 200000)) + 
  scale_x_continuous(breaks = scales::pretty_breaks(n=5))

\vspace{75pt}

dyear_plot

\newpage

\huge dmonth \normalsize \vspace{12pt}

Label: Death Month

Description: dmonth reports a person's month of death, as recorded in the Social Security Death Master File.

dmonth_tabulated <- knitr::kable(censoc_dmf %>%
    group_by(dmonth) %>%
    tally() %>%
    mutate(freq = signif(n*100 / sum(n), 2)) %>%
    mutate(label = c("January", "February", "March", "April", "May", "June", "July", "August", "September", "October", "November", "December")) %>%
    select(dmonth, label, n, `freq %` = freq))

\vspace{30pt}

dmonth_tabulated

\newpage

\huge death_age \normalsize \vspace{12pt}

Label: Age at Death (Years)

Description: death_age reports a person's age at death in years, calculated using the birth and death information recorded in the Social Security Death Master File.

death_age_plot <- censoc_dmf %>%
    group_by(death_age) %>%
    summarise(n = n()) %>%
    ggplot(aes(x = death_age, y = n)) + 
    geom_line() + 
    geom_point() +
    theme_minimal(base_size = 15) + #replace with a different theme (theme_bw()) if the bbplot package isn't downloaded 
  ggtitle("Age at Death") + 
  theme(legend.position="bottom") +
  xlab("title") + 
  labs(x = "Age at Death", 
       y = "Count") + 
  scale_y_continuous(labels = scales::comma) + 
  scale_x_continuous(breaks = scales::pretty_breaks(n=5))

\vspace{75pt}

death_age_plot

\newpage

\huge weight \normalsize

\vspace{12pt}

Label: Sample Weights

Description: A person-weight to National Center for Health Statistics (NCHS) totals for persons (1) dying between 1975-2020 (2) dying between ages 65-100 (3) born before 1939. Weights are based on age at death, year of death, race, and place of birth.

Weights are higher at the end of the this period due to decreased death coverage in the DMF. Please see the \textcolor{blue}{technical documentation on our website} for more information on how the DMF and how weights are created for this dataset.

# min/max -- do this by year maybe?
weights_tabulated <- censoc_dmf %>%
  filter(!is.na(weight)) %>% 
  summarize('Min Weight' = round(min(weight),2), 'Max Weight' = round(max(weight), 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()

# box and whisker plot
weight.plot <- censoc_dmf %>%
  filter(!is.na(weight)) %>% 
  ggplot(aes(weight)) +
    geom_boxplot() +
    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')

# line plot 

weights_lineplot <- censoc_dmf %>% 
  filter(!is.na(weight)) %>% 
  mutate(age_decade = as.factor((death_age %/% 10)*10)) %>% 
  group_by(dyear) %>% 
  summarize(m = mean(weight)) %>% 
  ggplot(aes(dyear, m)) +
  ylim(0, 90) +
  geom_line() +
  geom_point() +
  theme_minimal(base_size = 16)  +
  ggtitle("Mean Weight by Year")+
  xlab("Year") +
  ylab("Mean")

## plot mortality on Lexis surface
weights_lexis <- censoc_dmf %>% 
  filter(!is.na(weight)) %>% 
  group_by(death_age, dyear) %>% 
  summarize(weight = mean(weight)) %>% 
  ggplot() +
  geom_raster(aes(x = dyear, y = death_age,
                  fill = weight)) +
  ## Lexis grid
  geom_hline(yintercept = seq(65, 100, 10),
             alpha = 0.4, lty = "dotted") +
  geom_vline(xintercept = seq(1975, 2005, 10),
             alpha = 0.4, lty = "dotted") +
  geom_abline(intercept = seq(-100, 100, 10)-1910,
              alpha = 0.4, lty = "dotted") +
  scale_fill_viridis_c(option = "magma") +
  scale_x_continuous("Year", expand = c(0.02, 0),
                     breaks = seq(1975, 2005, 5)) +
  scale_y_continuous("Age", expand = c(0, 0),
                     breaks = seq(65, 100, 10)) +
  guides(fill = guide_legend(reverse = TRUE)) +
  # coord
  coord_equal() +
  # theme
  theme_void() +
  theme(
    axis.text = element_text(colour = "black"),
    axis.text.y = element_text(size = 10),
    axis.text.x = element_text(size = 10, angle = 45, hjust = .5), 
    plot.title = element_text(size = 10, vjust = 2),
    legend.text = element_text(size = 10), 
    axis.title=element_text(size = 10,face="bold")
  ) + 
  labs(X = "Year",
       Y = "Age",
       title = "Average weight by age at death and year of death")