This analysis examines whether the number of not-confirmed victims is associated with the number of confirmed victims in Bexar County, Texas, from fiscal years 2016 through 2025.
The analysis includes the Day Care Investigations (DCI) and Residential Child Care Investigations (RCI) programs administered by the Texas Department of Family and Protective Services.
The dependent variable is confirmed victim count. The primary independent variable is not-confirmed victim count. Fiscal year and investigation program are included as additional explanatory variables.
library(tidyverse)
library(car)
library(lmtest)
knitr::opts_chunk$set(
echo = TRUE,
warning = FALSE,
message = FALSE
)
The dataset is publicly available through the Texas Department of Family and Protective Services. The following code imports the information directly from the public data source.
dfps_url <- "https://data.texas.gov/api/v3/views/wv2p-kpcm/export.csv?accessType=DOWNLOAD"
dfps_data <- read_csv(
dfps_url,
show_col_types = FALSE
)
cat("Original dataset observations:", nrow(dfps_data), "\n")
## Original dataset observations: 3121
head(dfps_data)
## # A tibble: 6 × 6
## `Fiscal Year` Program County Region `Confirmed Victims` `# of Victims`
## <dbl> <chr> <chr> <chr> <chr> <dbl>
## 1 2025 DCI Hutchinson 1-Lubbock Not Confirmed 1
## 2 2025 DCI Lubbock 1-Lubbock Not Confirmed 36
## 3 2025 DCI Lubbock 1-Lubbock Confirmed Victim 4
## 4 2025 DCI Ochiltree 1-Lubbock Not Confirmed 1
## 5 2025 DCI Potter 1-Lubbock Not Confirmed 13
## 6 2025 DCI Potter 1-Lubbock Confirmed Victim 1
str(dfps_data)
## spc_tbl_ [3,121 × 6] (S3: spec_tbl_df/tbl_df/tbl/data.frame)
## $ Fiscal Year : num [1:3121] 2025 2025 2025 2025 2025 ...
## $ Program : chr [1:3121] "DCI" "DCI" "DCI" "DCI" ...
## $ County : chr [1:3121] "Hutchinson" "Lubbock" "Lubbock" "Ochiltree" ...
## $ Region : chr [1:3121] "1-Lubbock" "1-Lubbock" "1-Lubbock" "1-Lubbock" ...
## $ Confirmed Victims: chr [1:3121] "Not Confirmed" "Not Confirmed" "Confirmed Victim" "Not Confirmed" ...
## $ # of Victims : num [1:3121] 1 36 4 1 13 1 23 2 1 1 ...
## - attr(*, "spec")=
## .. cols(
## .. `Fiscal Year` = col_double(),
## .. Program = col_character(),
## .. County = col_character(),
## .. Region = col_character(),
## .. `Confirmed Victims` = col_character(),
## .. `# of Victims` = col_number()
## .. )
## - attr(*, "problems")=<pointer: 0x79befe3700>
The original dataset contains information from multiple Texas counties. The following procedure limits the analysis to Bexar County and the selected fiscal years.
bexar_data <- dfps_data |>
filter(County == "Bexar") |>
mutate(
`Fiscal Year` = as.numeric(`Fiscal Year`),
`# of Victims` = as.numeric(`# of Victims`)
) |>
filter(
`Fiscal Year` >= 2016,
`Fiscal Year` <= 2025
)
cat("Bexar County records:", nrow(bexar_data), "\n")
## Bexar County records: 40
head(bexar_data)
## # A tibble: 6 × 6
## `Fiscal Year` Program County Region `Confirmed Victims` `# of Victims`
## <dbl> <chr> <chr> <chr> <chr> <dbl>
## 1 2025 DCI Bexar 8-San Antonio Not Confirmed 115
## 2 2025 DCI Bexar 8-San Antonio Confirmed Victim 16
## 3 2025 RCI Bexar 8-San Antonio Not Confirmed 283
## 4 2025 RCI Bexar 8-San Antonio Confirmed Victim 11
## 5 2024 DCI Bexar 8-San Antonio Not Confirmed 129
## 6 2024 DCI Bexar 8-San Antonio Confirmed Victim 31
summary(bexar_data)
## Fiscal Year Program County Region Confirmed Victims
## Min. :2016 Length :40 Length :40 Length :40 Length :40
## 1st Qu.:2018 N.unique : 2 N.unique : 1 N.unique : 1 N.unique : 2
## Median :2020 N.blank : 0 N.blank : 0 N.blank : 0 N.blank : 0
## Mean :2020 Min.nchar: 3 Min.nchar: 5 Min.nchar:13 Min.nchar:13
## 3rd Qu.:2023 Max.nchar: 3 Max.nchar: 5 Max.nchar:13 Max.nchar:16
## Max. :2025
## # of Victims
## Min. : 7.0
## 1st Qu.: 17.0
## Median : 75.5
## Mean :135.5
## 3rd Qu.:160.2
## Max. :756.0
The original dataset separates confirmed and not-confirmed victims into different records.
The following procedure reorganizes the information so both classifications appear in the same program-year observation. Duplicate records within a program-year classification are combined by adding their victim counts.
bexar_long <- bexar_data |>
select(
`Fiscal Year`,
Program,
`Confirmed Victims`,
`# of Victims`
) |>
group_by(
`Fiscal Year`,
Program,
`Confirmed Victims`
) |>
summarise(
Victims = sum(`# of Victims`, na.rm = TRUE),
.groups = "drop"
)
required_categories <- c(
"Not Confirmed",
"Confirmed Victim"
)
if (!all(required_categories %in%
unique(bexar_long$`Confirmed Victims`))) {
stop("One or both victim classifications are missing.")
}
bexar_wide <- bexar_long |>
pivot_wider(
names_from = `Confirmed Victims`,
values_from = Victims
) |>
rename(
Fiscal.Year = `Fiscal Year`,
Not.Confirmed = `Not Confirmed`,
Confirmed = `Confirmed Victim`
) |>
mutate(
Program = as.factor(Program),
Fiscal.Year.c = Fiscal.Year - 2020
) |>
arrange(Fiscal.Year, Program)
print(bexar_wide)
## # A tibble: 20 × 5
## Fiscal.Year Program Confirmed Not.Confirmed Fiscal.Year.c
## <dbl> <fct> <dbl> <dbl> <dbl>
## 1 2016 DCI 24 109 -4
## 2 2016 RCI 16 359 -4
## 3 2017 DCI 15 109 -3
## 4 2017 RCI 12 414 -3
## 5 2018 DCI 19 101 -2
## 6 2018 RCI 7 349 -2
## 7 2019 DCI 27 81 -1
## 8 2019 RCI 17 336 -1
## 9 2020 DCI 30 103 0
## 10 2020 RCI 21 603 0
## 11 2021 DCI 17 77 1
## 12 2021 RCI 74 756 1
## 13 2022 DCI 30 88 2
## 14 2022 RCI 10 382 2
## 15 2023 DCI 16 85 3
## 16 2023 RCI 11 254 3
## 17 2024 DCI 31 129 4
## 18 2024 RCI 20 264 4
## 19 2025 DCI 16 115 5
## 20 2025 RCI 11 283 5
cat(
"Final analytic observations:",
nrow(bexar_wide),
"\n"
)
## Final analytic observations: 20
if (nrow(bexar_wide) != 20) {
stop("Expected 20 program-year observations. Check the dataset.")
}
str(bexar_wide)
## tibble [20 × 5] (S3: tbl_df/tbl/data.frame)
## $ Fiscal.Year : num [1:20] 2016 2016 2017 2017 2018 ...
## $ Program : Factor w/ 2 levels "DCI","RCI": 1 2 1 2 1 2 1 2 1 2 ...
## $ Confirmed : num [1:20] 24 16 15 12 19 7 27 17 30 21 ...
## $ Not.Confirmed: num [1:20] 109 359 109 414 101 349 81 336 103 603 ...
## $ Fiscal.Year.c: num [1:20] -4 -4 -3 -3 -2 -2 -1 -1 0 0 ...
The following procedures examine missing values, duplicate observations, and the final structure of the dataset.
colSums(
is.na(
bexar_wide[, c(
"Fiscal.Year",
"Program",
"Not.Confirmed",
"Confirmed"
)]
)
)
## Fiscal.Year Program Not.Confirmed Confirmed
## 0 0 0 0
Check for duplicate program-year observations.
bexar_wide |>
count(Fiscal.Year, Program) |>
filter(n > 1)
## # A tibble: 0 × 3
## # ℹ 3 variables: Fiscal.Year <dbl>, Program <fct>, n <int>
Examine the fiscal years and investigation programs included in the final dataset.
table(bexar_wide$Fiscal.Year)
##
## 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025
## 2 2 2 2 2 2 2 2 2 2
table(bexar_wide$Program)
##
## DCI RCI
## 10 10
summary(bexar_wide)
## Fiscal.Year Program Confirmed Not.Confirmed Fiscal.Year.c
## Min. :2016 DCI:10 Min. : 7.00 Min. : 77.0 Min. :-4.0
## 1st Qu.:2018 RCI:10 1st Qu.:14.25 1st Qu.:102.5 1st Qu.:-2.0
## Median :2020 Median :17.00 Median :191.5 Median : 0.5
## Mean :2020 Mean :21.20 Mean :249.8 Mean : 0.5
## 3rd Qu.:2023 3rd Qu.:24.75 3rd Qu.:351.5 3rd Qu.: 3.0
## Max. :2025 Max. :74.00 Max. :756.0 Max. : 5.0
Descriptive statistics provide an initial understanding of the distribution of confirmed and not-confirmed victim counts.
summary(bexar_wide$Not.Confirmed)
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 77.0 102.5 191.5 249.8 351.5 756.0
summary(bexar_wide$Confirmed)
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 7.00 14.25 17.00 21.20 24.75 74.00
mean(bexar_wide$Not.Confirmed)
## [1] 249.85
median(bexar_wide$Not.Confirmed)
## [1] 191.5
sd(bexar_wide$Not.Confirmed)
## [1] 189.7007
mean(bexar_wide$Confirmed)
## [1] 21.2
median(bexar_wide$Confirmed)
## [1] 17
sd(bexar_wide$Confirmed)
## [1] 14.25556
The following analysis compares average victim counts across the two investigation programs.
program_statistics <- bexar_wide |>
group_by(Program) |>
summarise(
Observations = n(),
Mean_Not_Confirmed = mean(Not.Confirmed),
Mean_Confirmed = mean(Confirmed),
Median_Not_Confirmed = median(Not.Confirmed),
Median_Confirmed = median(Confirmed),
.groups = "drop"
)
program_statistics
## # A tibble: 2 × 6
## Program Observations Mean_Not_Confirmed Mean_Confirmed Median_Not_Confirmed
## <fct> <int> <dbl> <dbl> <dbl>
## 1 DCI 10 99.7 22.5 102
## 2 RCI 10 400 19.9 354
## # ℹ 1 more variable: Median_Confirmed <dbl>
Histograms provide a visual examination of the distributions of the two victim-count variables.
hist(
bexar_wide$Not.Confirmed,
main = "Distribution of Not-Confirmed Victims",
xlab = "Not-Confirmed Victim Count",
col = "steelblue",
border = "black"
)
hist(
bexar_wide$Confirmed,
main = "Distribution of Confirmed Victims",
xlab = "Confirmed Victim Count",
col = "darkseagreen",
border = "black"
)
The boxplot provides a visual comparison of confirmed victim counts across investigation programs.
boxplot(
Confirmed ~ Program,
data = bexar_wide,
main = "Confirmed Victims by Investigation Program",
xlab = "Investigation Program",
ylab = "Confirmed Victim Count",
col = "lightblue"
)
The following scatterplot examines the relationship between confirmed and not-confirmed victim counts.
ggplot(
bexar_wide,
aes(
x = Not.Confirmed,
y = Confirmed,
color = Program
)
) +
geom_point(size = 3) +
geom_smooth(method = "lm") +
labs(
title = "Relationship Between Confirmed and Not-Confirmed Victims",
x = "Not-Confirmed Victim Count",
y = "Confirmed Victim Count",
color = "Investigation Program"
)
The Pearson correlation examines the direction and strength of the linear association between the two victim-count variables.
cor(
bexar_wide$Not.Confirmed,
bexar_wide$Confirmed
)
## [1] 0.3724998
correlation_result <- cor.test(
bexar_wide$Not.Confirmed,
bexar_wide$Confirmed,
method = "pearson"
)
correlation_result
##
## Pearson's product-moment correlation
##
## data: bexar_wide$Not.Confirmed and bexar_wide$Confirmed
## t = 1.7029, df = 18, p-value = 0.1058
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
## -0.08384129 0.69968523
## sample estimates:
## cor
## 0.3724998
ANOVA examines whether average confirmed victim counts differ across the investigation programs.
program_anova <- aov(
Confirmed ~ Program,
data = bexar_wide
)
summary(program_anova)
## Df Sum Sq Mean Sq F value Pr(>F)
## Program 1 34 33.8 0.159 0.695
## Residuals 18 3827 212.6
ANOVA is a special case of a linear model. The following analysis
examines the same differences between investigation programs using the
lm() command.
program_lm <- lm(
Confirmed ~ Program,
data = bexar_wide
)
summary(program_lm)
##
## Call:
## lm(formula = Confirmed ~ Program, data = bexar_wide)
##
## Residuals:
## Min 1Q Median 3Q Max
## -12.90 -7.60 -3.70 2.25 54.10
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 22.500 4.611 4.879 0.000121 ***
## ProgramRCI -2.600 6.521 -0.399 0.694807
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 14.58 on 18 degrees of freedom
## Multiple R-squared: 0.008754, Adjusted R-squared: -0.04632
## F-statistic: 0.159 on 1 and 18 DF, p-value: 0.6948
The primary research model examines whether not-confirmed victim counts are associated with confirmed victim counts after accounting for fiscal year and investigation program.
The regression model is:
Confirmed = β0 + β1(Not-Confirmed) + β2(Fiscal Year) + β3(Program) + ε
research_model <- lm(
Confirmed ~ Not.Confirmed +
Fiscal.Year.c +
Program,
data = bexar_wide
)
summary(research_model)
##
## Call:
## lm(formula = Confirmed ~ Not.Confirmed + Fiscal.Year.c + Program,
## data = bexar_wide)
##
## Residuals:
## Min 1Q Median 3Q Max
## -19.225 -5.861 1.021 5.512 17.334
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 11.91036 3.64398 3.269 0.004829 **
## Not.Confirmed 0.10213 0.01987 5.140 9.89e-05 ***
## Fiscal.Year.c 0.81441 0.74647 1.091 0.291428
## ProgramRCI -33.26986 7.32164 -4.544 0.000332 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 9.486 on 16 degrees of freedom
## Multiple R-squared: 0.6271, Adjusted R-squared: 0.5572
## F-statistic: 8.97 on 3 and 16 DF, p-value: 0.00102
The following procedures examine the regression coefficients, confidence intervals, and overall model fit.
summary(research_model)$coefficients
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 11.9103614 3.64397939 3.268504 0.0048292225
## Not.Confirmed 0.1021307 0.01987138 5.139590 0.0000988666
## Fiscal.Year.c 0.8144076 0.74647441 1.091005 0.2914282749
## ProgramRCI -33.2698612 7.32163785 -4.544046 0.0003319212
confint(research_model)
## 2.5 % 97.5 %
## (Intercept) 4.1854702 19.6352527
## Not.Confirmed 0.0600053 0.1442562
## Fiscal.Year.c -0.7680475 2.3968627
## ProgramRCI -48.7910400 -17.7486823
summary(research_model)$r.squared
## [1] 0.6271249
summary(research_model)$adj.r.squared
## [1] 0.5572109
summary(research_model)$fstatistic
## value numdf dendf
## 8.969939 3.000000 16.000000
Multiple linear regression relies on several assumptions. These include linearity, independence of errors, homoscedasticity, normality of residuals, and the absence of problematic multicollinearity.
The residual plot provides an initial examination of whether the relationship is linear.
plot(
research_model,
which = 1
)
The Durbin-Watson test examines potential correlation between regression errors.
durbinWatsonTest(research_model)
## lag Autocorrelation D-W Statistic p-value
## 1 -0.03029906 2.047995 0.904
## Alternative hypothesis: rho != 0
Because the observations are repeated across fiscal years within two programs, this test should be interpreted cautiously. It does not establish that all observations are independent.
The following plot examines whether the variance of the residuals remains relatively constant.
plot(
research_model,
which = 3
)
The Breusch-Pagan test provides an additional examination of residual variance.
bptest(research_model)
##
## studentized Breusch-Pagan test
##
## data: research_model
## BP = 14.943, df = 3, p-value = 0.001866
The Q-Q plot examines whether the regression residuals approximately follow a normal distribution.
plot(
research_model,
which = 2
)
The Shapiro-Wilk test provides an additional examination of residual normality.
shapiro.test(
research_model$residuals
)
##
## Shapiro-Wilk normality test
##
## data: research_model$residuals
## W = 0.98213, p-value = 0.9585
The variance inflation factor examines whether the independent variables are excessively correlated with one another.
vif(research_model)
## Not.Confirmed Fiscal.Year.c Program
## 3.000418 1.021758 2.978659
Values below 5 are generally considered less concerning. However, these values should be interpreted cautiously because the analysis contains only 20 observations.
Cook’s distance identifies observations that may have an unusually large influence on the regression model.
plot(
research_model,
which = 4
)
cooks.distance(research_model)
## 1 2 3 4 5 6
## 0.0183305293 0.0182347803 0.0223369283 0.0298340001 0.0013225490 0.0195022048
## 7 8 9 10 11 12
## 0.0242322834 0.0120061081 0.0200217687 0.5458949232 0.0045951275 4.9935729391
## 13 14 15 16 17 18
## 0.0224568850 0.0347920582 0.0255060989 0.0152815952 0.0054444470 0.1375995103
## 19 20
## 0.1479565319 0.0005002478
Residuals represent the differences between the observed confirmed victim counts and the values predicted by the regression model.
hist(
residuals(research_model),
main = "Distribution of Regression Residuals",
xlab = "Residuals",
col = "lightblue",
border = "black"
)
The primary coefficient of interest is the coefficient for not-confirmed victims.
Null Hypothesis:
There is no association between not-confirmed victim counts and confirmed victim counts after accounting for fiscal year and investigation program.
Alternative Hypothesis:
There is an association between not-confirmed victim counts and confirmed victim counts after accounting for fiscal year and investigation program.
regression_results <- summary(research_model)$coefficients
primary_result <- regression_results[
"Not.Confirmed",
]
primary_result
## Estimate Std. Error t value Pr(>|t|)
## 0.1021307398 0.0198713791 5.1395899270 0.0000988666
The significance level is 0.05.
p_value <- primary_result["Pr(>|t|)"]
if (p_value < 0.05) {
cat(
"The primary regression coefficient is statistically significant at the 0.05 level. Reject the null hypothesis."
)
} else {
cat(
"The primary regression coefficient is not statistically significant at the 0.05 level. Fail to reject the null hypothesis."
)
}
## The primary regression coefficient is statistically significant at the 0.05 level. Reject the null hypothesis.
The following section summarizes the primary findings from the descriptive statistics, correlation analysis, and multiple regression model.
cat("RESEARCH RESULTS SUMMARY\n\n")
## RESEARCH RESULTS SUMMARY
cat(
"Number of observations:",
nrow(bexar_wide),
"\n"
)
## Number of observations: 20
cat(
"Mean not-confirmed victims:",
round(mean(bexar_wide$Not.Confirmed), 2),
"\n"
)
## Mean not-confirmed victims: 249.85
cat(
"Mean confirmed victims:",
round(mean(bexar_wide$Confirmed), 2),
"\n"
)
## Mean confirmed victims: 21.2
cat(
"Pearson correlation:",
round(
cor(
bexar_wide$Not.Confirmed,
bexar_wide$Confirmed
),
4
),
"\n"
)
## Pearson correlation: 0.3725
cat(
"Regression coefficient:",
round(primary_result["Estimate"], 4),
"\n"
)
## Regression coefficient: 0.1021
cat(
"Regression standard error:",
round(primary_result["Std. Error"], 4),
"\n"
)
## Regression standard error: 0.0199
cat(
"Regression p-value:",
round(primary_result["Pr(>|t|)"], 4),
"\n"
)
## Regression p-value: 1e-04
cat(
"R-squared:",
round(summary(research_model)$r.squared, 4),
"\n"
)
## R-squared: 0.6271
cat(
"Adjusted R-squared:",
round(summary(research_model)$adj.r.squared, 4),
"\n"
)
## Adjusted R-squared: 0.5572
This analysis examined the relationship between confirmed and not-confirmed victim counts in Bexar County child abuse and neglect investigations from fiscal years 2016 through 2025.
The analysis included descriptive statistics, histograms, boxplots, Pearson correlation, ANOVA, and multiple linear regression.
Fiscal year and investigation program were included as additional explanatory variables to examine whether the relationship between confirmed and not-confirmed victim counts remains after accounting for these differences.
The findings should be interpreted cautiously because the analysis uses a relatively small number of aggregated program-year observations. The data do not contain individual-level information, and the statistical analysis cannot establish causation.
The findings provide an exploratory examination of administrative patterns in child welfare investigations and may help identify areas where additional demographic and program-level information could improve future research.