2.5_ChildrenTANF

Loading in Data

library(ipumsr)
library(dplyr)

Attaching package: 'dplyr'

The following objects are masked from 'package:stats':

    filter, lag

The following objects are masked from 'package:base':

    intersect, setdiff, setequal, union

library(ggplot2)
library(survey)

Loading required package: grid

Loading required package: Matrix

Loading required package: survival

Attaching package: 'survey'

The following object is masked from 'package:graphics':

    dotchart

library(srvyr)  

Attaching package: 'srvyr'

The following object is masked from 'package:stats':

    filter

library(readr)

Data was obtained from a data request made to HHSC for individuals under 18 utilizing TANF. This request was made in March of 2025.

data_2023 <- read.csv("raw_data/FY 2023.csv")
data_2024 <- read.csv("raw_data/FY 2024.csv")
locations <- read.csv("../../location_countyNames copy.csv") |>
  select(Location, LocationId)
child_pop_23 <- read.csv("child_population_2023.csv") |>
  select(Location, Data) |>
  rename(child_pop = Data)

Cleaning the Data

2023 - Since there is 2023 child population data from TDC, 2023 percents were able to be calculated using those estimates and the data pulled from the data request.

cleaned_2023 <- data_2023 |>
  select(County, Total.Children.Per.County) |>
  filter(County != "Call Centers" & County != "State Office") |>
  slice_head(n = 255) |>
  mutate(County = ifelse(County == "Total Children Per Age Group", "Texas", County)) |>
  mutate(Total.Children.Per.County = as.numeric(gsub(",", "", Total.Children.Per.County))) |>
  rename(Data = Total.Children.Per.County, 
         Location = County) |>
  left_join(locations, by = "Location") |>
  left_join(child_pop_23) |>
  mutate(DataFormat = "Number") |>
  select(LocationId, Location, DataFormat, Data, child_pop)

Joining with `by = join_by(Location)`

percents_2023 <- cleaned_2023 |>
  mutate(DataFormat = "Percent") |>
  mutate(Percent = Data/child_pop) |>
  select(-Data) |>
  rename(Data = Percent) |>
  select(LocationId, Location, DataFormat, Data, child_pop)

final_tanf_2023 <- rbind(cleaned_2023, percents_2023) |>
  select(-child_pop) |>
  mutate(TimeFrame = 2023, 
         LocationType = ifelse(Location == "Texas", "State", "County")) |>
  arrange(desc(LocationType), Location, DataFormat)

2024 - since at the time of cleaning there are not TDC population estimates, only 2024 numbers are able to be produced.

cleaned_2024 <- data_2024 |>
  select(County, Total.Children.Per.County) |>
  filter(County != "Call Centers" & County != "State Office") |>
  slice_head(n = 255) |>
  mutate(County = ifelse(County == "Total Children Per Age Group", "Texas", County)) |>
  mutate(Total.Children.Per.County = as.numeric(gsub(",", "", Total.Children.Per.County))) |>
  rename(Data = Total.Children.Per.County, 
         Location = County) |>
  left_join(locations, by = "Location") |>
  mutate(TimeFrame = 2024, 
         LocationType = ifelse(Location == "Texas", "State", "County"), 
         DataFormat = "Number") |>
  arrange(desc(LocationType), Location, DataFormat)

Exports

write.csv(file = "CLEANED_2.5_ChildrenReceivingTANF_2023_NumsandPercents.csv", final_tanf_2023, row.names = FALSE)
write.csv(file = "CLEANED_2.5_ChildrenReceivingTANF_2024_Nums.csv", cleaned_2024, row.names = FALSE)