Piloto_VPH

library(readxl)
BASE_PILOTO <- read_excel("bd_piloto_VPH_12.25 1.xlsx") #31428
library(dplyr)
BASE_PILOTO <- BASE_PILOTO %>% 
  mutate(
    CIUDAD = factor(
      ifelse(ciudad %in% c("Arbeláez", "Tocaima"), "M.peq", "m.grande")
    )
  )
BASE_PILOTO$brazo_est <- factor(BASE_PILOTO$brazo_est)

Test general de independencia colpo_compliance

Opté por este test que podría ser como un chi-cuadrado que permite subestratos, evalua la indepedencia de una variable contra la cambinació de otras variables.

El test de permutaciones, implicaría filtrar la base de datos, aquí la función:

Permutation test

library(coin)

BASE_PILOTO_filt <- BASE_PILOTO %>%  #se filtra la base de datos para quienes tengan desenlace
  filter(!is.na(colpo_compliance)) #1340 observaciones

independence_test(
  colpo_compliance ~ brazo_est  + CIUDAD,
  data = BASE_PILOTO_filt,
  distribution = approximate(B = 10000)
)

## 
##  Approximative General Independence Test
## 
## data:  colpo_compliance by brazo_est, CIUDAD
## maxT = 7.4382, p-value < 1e-04
## alternative hypothesis: two.sided

H₀: Condicionado al estrato por la CIUDAD, el desenlace colpo_compliance es independiente del brazo (brazo_est).

H₀:El compliance es independiente del brazo de estudio y del tipo de ciudad. Es decir, la proporción de mujeres que cumplen con la colposcopía es la misma sin importar en qué brazo estén asignadas ni si viven en una ciudad grande o pequeña.

Constraste

lapply(
  split(BASE_PILOTO_filt, BASE_PILOTO_filt$CIUDAD),
  function(d) {
    independence_test(
      colpo_compliance ~ brazo_est,
      data = d,
      distribution = approximate(B = 5000)
    )
  }
)

## $m.grande
## 
##  Approximative General Independence Test
## 
## data:  colpo_compliance by brazo_est (citologia, VPH+Cito)
## Z = -6.7381, p-value < 2e-04
## alternative hypothesis: two.sided
## 
## 
## $M.peq
## 
##  Approximative General Independence Test
## 
## data:  colpo_compliance by brazo_est (citologia, VPH+Cito)
## Z = -3.0729, p-value = 0.0034
## alternative hypothesis: two.sided

Hay diferencias en ambos brazos en cada tipo de municipio

Test general de independencia short compliance

BASE_PILOTO_filt2 <- BASE_PILOTO %>% 
  filter(!is.na(shortt_compliance)) #919 observaciones

independence_test(
  shortt_compliance ~ brazo_est  + CIUDAD,
  data = BASE_PILOTO_filt,
  distribution = approximate(B = 10000)
)

## 
##  Approximative General Independence Test
## 
## data:  shortt_compliance by brazo_est, CIUDAD
## maxT = 1.7479, p-value = 0.1487
## alternative hypothesis: two.sided

Contraste

lapply(
  split(BASE_PILOTO_filt2, BASE_PILOTO_filt2$CIUDAD),
  function(d) {
    independence_test(
      shortt_compliance ~ brazo_est,
      data = d,
      distribution = approximate(B = 5000)
    )
  }
)

## $m.grande
## 
##  Approximative General Independence Test
## 
## data:  shortt_compliance by brazo_est (citologia, VPH+Cito)
## Z = 4.1348, p-value < 2e-04
## alternative hypothesis: two.sided
## 
## 
## $M.peq
## 
##  Approximative General Independence Test
## 
## data:  shortt_compliance by brazo_est (citologia, VPH+Cito)
## Z = 1.9149, p-value = 0.1186
## alternative hypothesis: two.sided

La asociación está dentro de los municipios grandes

PR shortcompliance

BASE_PILOTO_filt2 <- BASE_PILOTO_filt2 |>
  dplyr::mutate(
    shortt_comp_cat = factor(
      shortt_compliance,
      levels = c(TRUE, FALSE),
      labels = c("Presente", "Ausente")
    )
  )

BASE_PILOTO_filt2 <- BASE_PILOTO_filt2 |>
  dplyr::mutate(
    shortt_comp_num = as.numeric(
      shortt_compliance,
      levels = c(TRUE, FALSE),
      labels = c(1, 0)
    )
  )


tab_SHORT <- with(BASE_PILOTO_filt2,
            table(brazo_est, shortt_comp_cat))
tab_SHORT

##            shortt_comp_cat
## brazo_est   Presente Ausente
##   citologia      478      40
##   VPH+Cito       396       5

PR = 1.095

Ajustando por el resto de variables

BASE_PILOTO_filt2[BASE_PILOTO_filt2$ultimo_tamizaje == 2,] <- NA
BASE_PILOTO_filt2$ultimo_tamizaje <- factor(BASE_PILOTO_filt2$ultimo_tamizaje, levels = c(0,1), 
                                      labels = c(">= 3", "<3"))
BASE_PILOTO_filt2$regimen_afil <- factor(BASE_PILOTO_filt2$regimen_afil, levels = c(0,1,2),
                                   labels = c("Subsidiado", "Contributivo", "No afiliado"))

BASE_PILOTO_filt2$brazo_est <- factor(BASE_PILOTO_filt2$brazo_est, levels = c ("citologia", "VPH+Cito"))


m0 <- glm(shortt_compliance ~ brazo_est, 
          binomial(link = "logit"), data = BASE_PILOTO_filt2)
m1 <- glm(shortt_compliance ~ brazo_est + edad + ultimo_tamizaje + regimen_afil, 
          binomial(link = "logit"), data = BASE_PILOTO_filt2)
m2 <- glm(shortt_compliance ~ brazo_est + edad + ultimo_tamizaje + regimen_afil + CIUDAD, 
          binomial(link = "logit"), data = BASE_PILOTO_filt2)

library(marginaleffects)
avg_comparisons(
  m0,
  variables = "brazo_est",
  comparison = "ratio",
  type = "response"
)

## 
##  Estimate Std. Error    z Pr(>|z|)   S 2.5 % 97.5 %
##      1.07     0.0151 71.2   <0.001 Inf  1.05    1.1
## 
## Term: brazo_est
## Type: response
## Comparison: mean(VPH+Cito) / mean(citologia)

Se usó una función análoga de STATA para ajustar el PR a partir de un modelo multivariado logístico. En este caso el PR fue similar al curdo (PR = 1.07)

Se obtiene el PR por cada uno de los modelos - Uno con las variables: edad , ultimo_tamizaje, regimen_afil - Otros con las variables incluyendo las anteriores variables y municipio (grande vs pequeño)

avg_comparisons(
  m1,
  variables = "brazo_est",
  comparison = "ratio",
  type = "response"
)

## 
##  Estimate Std. Error    z Pr(>|z|)   S 2.5 % 97.5 %
##      1.07     0.0162 66.3   <0.001 Inf  1.04    1.1
## 
## Term: brazo_est
## Type: response
## Comparison: mean(VPH+Cito) / mean(citologia)

avg_comparisons(
  m2,
  variables = "brazo_est",
  comparison = "ratio",
  type = "response"
)

## 
##  Estimate Std. Error    z Pr(>|z|)   S 2.5 % 97.5 %
##      1.07     0.0164 65.5   <0.001 Inf  1.04   1.11
## 
## Term: brazo_est
## Type: response
## Comparison: mean(VPH+Cito) / mean(citologia)

No cambia la magnitud del PR incluyendo más variables.

PR colpo_compliance

BASE_PILOTO_filt <- BASE_PILOTO_filt |>
  dplyr::mutate(
    colpo_compliance_cat = factor(
      colpo_compliance,
      levels = c(TRUE, FALSE),
      labels = c("Presente", "Ausente")
    )
  )

tab_colpo <- with(BASE_PILOTO_filt,
                  table(brazo_est, colpo_compliance_cat))
tab_colpo

##            colpo_compliance_cat
## brazo_est   Presente Ausente
##   citologia      574      25
##   VPH+Cito       614     127

PR = 0.86

Ajustando por el resto de variables

BASE_PILOTO_filt[BASE_PILOTO_filt$ultimo_tamizaje == 2,] <- NA

BASE_PILOTO_filt$ultimo_tamizaje <- factor(BASE_PILOTO_filt$ultimo_tamizaje, levels = c(0,1), 
                                            labels = c(">= 3", "<3"))
BASE_PILOTO_filt$regimen_afil <- factor(BASE_PILOTO_filt$regimen_afil, levels = c(0,1,2),
                                         labels = c("Subsidiado", "Contributivo", "No afiliado"))

BASE_PILOTO_filt$brazo_est <- factor(BASE_PILOTO_filt$brazo_est, levels = c ("citologia", "VPH+Cito"))


m0.1 <- glm(colpo_compliance ~ brazo_est, 
          binomial(link = "logit"), data = BASE_PILOTO_filt)

m1.1 <- glm(colpo_compliance ~ brazo_est + edad + ultimo_tamizaje + regimen_afil, 
            binomial(link = "logit"), data = BASE_PILOTO_filt)

m2.1 <- glm(colpo_compliance ~ brazo_est + edad + ultimo_tamizaje + regimen_afil + CIUDAD * brazo_est, 
          binomial(link = "logit"), data = BASE_PILOTO_filt)

avg_comparisons(
  m0.1,
  variables = "brazo_est",
  comparison = "ratio",
  type = "response"
)

## 
##  Estimate Std. Error    z Pr(>|z|)   S 2.5 % 97.5 %
##     0.873     0.0163 53.6   <0.001 Inf 0.841  0.904
## 
## Term: brazo_est
## Type: response
## Comparison: mean(VPH+Cito) / mean(citologia)

PR = 0.873

Similar al obtenido manualmente, se procede a encontrar el PR ajustado con el resto de variables

avg_comparisons(
  m1.1,
  variables = "brazo_est",
  comparison = "ratio",
  type = "response"
)

## 
##  Estimate Std. Error    z Pr(>|z|)   S 2.5 % 97.5 %
##     0.863     0.0186 46.4   <0.001 Inf 0.826  0.899
## 
## Term: brazo_est
## Type: response
## Comparison: mean(VPH+Cito) / mean(citologia)

avg_comparisons(
  m2.1,
  variables = "brazo_est",
  comparison = "ratio",
  type = "response"
)

## 
##  Estimate Std. Error    z Pr(>|z|)   S 2.5 % 97.5 %
##     0.861     0.0185 46.6   <0.001 Inf 0.824  0.897
## 
## Term: brazo_est
## Type: response
## Comparison: mean(VPH+Cito) / mean(citologia)

Se aproximan al PR original a medida que se incluyen más variables.

Proyecto de autotoma

Se filtra la base con las pacientes positivas

library(readxl)
BASE_AUTOTOMA <- read_excel("BD_proyecto autotoma_19.01.26.xlsx") #532


BASE_AUTOTOMA_filt <- BASE_AUTOTOMA %>% filter(resultado_vph == 1)
BASE_AUTOTOMA_filt[BASE_AUTOTOMA_filt$ult_tamizaje_agr == 0,] <- NA

BASE_AUTOTOMA_filt <- BASE_AUTOTOMA_filt %>% 
    mutate(
      metodo_int_treat_cat = factor(
      metodo_int_treat,
      levels = c(0,1),
      labels = c("Clinician", "Self-collected")
    )
  ) %>% 
  mutate(
    departamento_cat = factor(
      departamento,
      levels = c(1,2),
      labels = c("Putumayo", "Choco")
    )
  ) %>% 
  mutate(
    etnia_cat = factor(
      etnia_agr,
      levels = c(1,2,3),
      labels = c("Indigena", "Afrocolombiano", "Otro")
    )
  ) %>% 
  mutate(
    estrategia_toma_cat = factor(
      estrategia_toma,
      levels = c(1,2),
      labels = c("Campaña", "Tamizaje rutinario")
    )
  ) %>% 
  mutate(
    regimen_agr_cat = factor(
      regimen_agr,
      levels = c(0, 1,2),
      labels = c("No afiliado/NA", "Contributivo/otro", "Subsidiado")
    )
  ) %>% 
mutate(
  ult_tamizaje_agr_cat = factor(
    ult_tamizaje_agr,
    levels = c(1,2, 3),
    labels = c("<= 24 meses", "25-36 meses", ">36 meses")
  )
) %>% 
  mutate(
    area_residencia_cat = factor(
      area_residencia,
      levels = c(1,2),
      labels = c("Urbano", "Rural")
    )
  ) %>% 
  mutate(
    lugar_de_residencia_cat = factor(
      area_residencia,
      levels = c(1,2,3,4),
      labels = c("Nuqui", "Puerto Leguizamo", "Istmina", "Valle Sibundoy")
    )
  ) %>% 
  mutate(ngestaciones_cat = cut(n_gestaciones, 
                           breaks = c (-Inf,3,Inf), 
                           right = T, 
                           labels = c("<=3", ">3")))

Estratificaicón tabla Asistencia al tratamiento

Se estratificó la tabla por asistencia o no al tratamiento (0, 1), método intention to treatment y departamento

BASE_AUTOTOMA_clean <- BASE_AUTOTOMA_filt %>%
  filter(!is.na(metodo_int_treat_cat) & 
         !is.na(departamento_cat) & 
         !is.na(asistio_tratamiento))

BASE_AUTOTOMA_clean <- BASE_AUTOTOMA_clean %>%
  mutate(metodo_deptoA = paste(metodo_int_treat_cat, departamento_cat, sep = " × "))

library(gtsummary)

tabla_personalizada <- BASE_AUTOTOMA_clean %>%
  select(metodo_deptoA, asistio_tratamiento,
         estrategia_toma_cat, etnia_cat) %>%
  tbl_strata(
    strata = asistio_tratamiento,  # Esto va en las FILAS
    .tbl_fun = ~ .x %>%
      tbl_summary(
        by =metodo_deptoA,  # Esto va en las COLUMNAS
        statistic = all_categorical() ~ "{n} ({p}%)",
        missing = "no",
        digits = all_categorical() ~ c(0, 1)
      ) %>%
      add_overall(last = TRUE, col_label = "**Total**") %>%
      modify_header(label ~ "**Variable**") %>%
      bold_labels()
  )

print(tabla_personalizada)

## <div id="juyuvmubvy" style="padding-left:0px;padding-right:0px;padding-top:10px;padding-bottom:10px;overflow-x:auto;overflow-y:auto;width:auto;height:auto;">
##   <style>#juyuvmubvy table {
##   font-family: system-ui, 'Segoe UI', Roboto, Helvetica, Arial, sans-serif, 'Apple Color Emoji', 'Segoe UI Emoji', 'Segoe UI Symbol', 'Noto Color Emoji';
##   -webkit-font-smoothing: antialiased;
##   -moz-osx-font-smoothing: grayscale;
## }
## 
## #juyuvmubvy thead, #juyuvmubvy tbody, #juyuvmubvy tfoot, #juyuvmubvy tr, #juyuvmubvy td, #juyuvmubvy th {
##   border-style: none;
## }
## 
## #juyuvmubvy p {
##   margin: 0;
##   padding: 0;
## }
## 
## #juyuvmubvy .gt_table {
##   display: table;
##   border-collapse: collapse;
##   line-height: normal;
##   margin-left: auto;
##   margin-right: auto;
##   color: #333333;
##   font-size: 16px;
##   font-weight: normal;
##   font-style: normal;
##   background-color: #FFFFFF;
##   width: auto;
##   border-top-style: solid;
##   border-top-width: 2px;
##   border-top-color: #A8A8A8;
##   border-right-style: none;
##   border-right-width: 2px;
##   border-right-color: #D3D3D3;
##   border-bottom-style: solid;
##   border-bottom-width: 2px;
##   border-bottom-color: #A8A8A8;
##   border-left-style: none;
##   border-left-width: 2px;
##   border-left-color: #D3D3D3;
## }
## 
## #juyuvmubvy .gt_caption {
##   padding-top: 4px;
##   padding-bottom: 4px;
## }
## 
## #juyuvmubvy .gt_title {
##   color: #333333;
##   font-size: 125%;
##   font-weight: initial;
##   padding-top: 4px;
##   padding-bottom: 4px;
##   padding-left: 5px;
##   padding-right: 5px;
##   border-bottom-color: #FFFFFF;
##   border-bottom-width: 0;
## }
## 
## #juyuvmubvy .gt_subtitle {
##   color: #333333;
##   font-size: 85%;
##   font-weight: initial;
##   padding-top: 3px;
##   padding-bottom: 5px;
##   padding-left: 5px;
##   padding-right: 5px;
##   border-top-color: #FFFFFF;
##   border-top-width: 0;
## }
## 
## #juyuvmubvy .gt_heading {
##   background-color: #FFFFFF;
##   text-align: center;
##   border-bottom-color: #FFFFFF;
##   border-left-style: none;
##   border-left-width: 1px;
##   border-left-color: #D3D3D3;
##   border-right-style: none;
##   border-right-width: 1px;
##   border-right-color: #D3D3D3;
## }
## 
## #juyuvmubvy .gt_bottom_border {
##   border-bottom-style: solid;
##   border-bottom-width: 2px;
##   border-bottom-color: #D3D3D3;
## }
## 
## #juyuvmubvy .gt_col_headings {
##   border-top-style: solid;
##   border-top-width: 2px;
##   border-top-color: #D3D3D3;
##   border-bottom-style: solid;
##   border-bottom-width: 2px;
##   border-bottom-color: #D3D3D3;
##   border-left-style: none;
##   border-left-width: 1px;
##   border-left-color: #D3D3D3;
##   border-right-style: none;
##   border-right-width: 1px;
##   border-right-color: #D3D3D3;
## }
## 
## #juyuvmubvy .gt_col_heading {
##   color: #333333;
##   background-color: #FFFFFF;
##   font-size: 100%;
##   font-weight: normal;
##   text-transform: inherit;
##   border-left-style: none;
##   border-left-width: 1px;
##   border-left-color: #D3D3D3;
##   border-right-style: none;
##   border-right-width: 1px;
##   border-right-color: #D3D3D3;
##   vertical-align: bottom;
##   padding-top: 5px;
##   padding-bottom: 6px;
##   padding-left: 5px;
##   padding-right: 5px;
##   overflow-x: hidden;
## }
## 
## #juyuvmubvy .gt_column_spanner_outer {
##   color: #333333;
##   background-color: #FFFFFF;
##   font-size: 100%;
##   font-weight: normal;
##   text-transform: inherit;
##   padding-top: 0;
##   padding-bottom: 0;
##   padding-left: 4px;
##   padding-right: 4px;
## }
## 
## #juyuvmubvy .gt_column_spanner_outer:first-child {
##   padding-left: 0;
## }
## 
## #juyuvmubvy .gt_column_spanner_outer:last-child {
##   padding-right: 0;
## }
## 
## #juyuvmubvy .gt_column_spanner {
##   border-bottom-style: solid;
##   border-bottom-width: 2px;
##   border-bottom-color: #D3D3D3;
##   vertical-align: bottom;
##   padding-top: 5px;
##   padding-bottom: 5px;
##   overflow-x: hidden;
##   display: inline-block;
##   width: 100%;
## }
## 
## #juyuvmubvy .gt_spanner_row {
##   border-bottom-style: hidden;
## }
## 
## #juyuvmubvy .gt_group_heading {
##   padding-top: 8px;
##   padding-bottom: 8px;
##   padding-left: 5px;
##   padding-right: 5px;
##   color: #333333;
##   background-color: #FFFFFF;
##   font-size: 100%;
##   font-weight: initial;
##   text-transform: inherit;
##   border-top-style: solid;
##   border-top-width: 2px;
##   border-top-color: #D3D3D3;
##   border-bottom-style: solid;
##   border-bottom-width: 2px;
##   border-bottom-color: #D3D3D3;
##   border-left-style: none;
##   border-left-width: 1px;
##   border-left-color: #D3D3D3;
##   border-right-style: none;
##   border-right-width: 1px;
##   border-right-color: #D3D3D3;
##   vertical-align: middle;
##   text-align: left;
## }
## 
## #juyuvmubvy .gt_empty_group_heading {
##   padding: 0.5px;
##   color: #333333;
##   background-color: #FFFFFF;
##   font-size: 100%;
##   font-weight: initial;
##   border-top-style: solid;
##   border-top-width: 2px;
##   border-top-color: #D3D3D3;
##   border-bottom-style: solid;
##   border-bottom-width: 2px;
##   border-bottom-color: #D3D3D3;
##   vertical-align: middle;
## }
## 
## #juyuvmubvy .gt_from_md > :first-child {
##   margin-top: 0;
## }
## 
## #juyuvmubvy .gt_from_md > :last-child {
##   margin-bottom: 0;
## }
## 
## #juyuvmubvy .gt_row {
##   padding-top: 8px;
##   padding-bottom: 8px;
##   padding-left: 5px;
##   padding-right: 5px;
##   margin: 10px;
##   border-top-style: solid;
##   border-top-width: 1px;
##   border-top-color: #D3D3D3;
##   border-left-style: none;
##   border-left-width: 1px;
##   border-left-color: #D3D3D3;
##   border-right-style: none;
##   border-right-width: 1px;
##   border-right-color: #D3D3D3;
##   vertical-align: middle;
##   overflow-x: hidden;
## }
## 
## #juyuvmubvy .gt_stub {
##   color: #333333;
##   background-color: #FFFFFF;
##   font-size: 100%;
##   font-weight: initial;
##   text-transform: inherit;
##   border-right-style: solid;
##   border-right-width: 2px;
##   border-right-color: #D3D3D3;
##   padding-left: 5px;
##   padding-right: 5px;
## }
## 
## #juyuvmubvy .gt_stub_row_group {
##   color: #333333;
##   background-color: #FFFFFF;
##   font-size: 100%;
##   font-weight: initial;
##   text-transform: inherit;
##   border-right-style: solid;
##   border-right-width: 2px;
##   border-right-color: #D3D3D3;
##   padding-left: 5px;
##   padding-right: 5px;
##   vertical-align: top;
## }
## 
## #juyuvmubvy .gt_row_group_first td {
##   border-top-width: 2px;
## }
## 
## #juyuvmubvy .gt_row_group_first th {
##   border-top-width: 2px;
## }
## 
## #juyuvmubvy .gt_summary_row {
##   color: #333333;
##   background-color: #FFFFFF;
##   text-transform: inherit;
##   padding-top: 8px;
##   padding-bottom: 8px;
##   padding-left: 5px;
##   padding-right: 5px;
## }
## 
## #juyuvmubvy .gt_first_summary_row {
##   border-top-style: solid;
##   border-top-color: #D3D3D3;
## }
## 
## #juyuvmubvy .gt_first_summary_row.thick {
##   border-top-width: 2px;
## }
## 
## #juyuvmubvy .gt_last_summary_row {
##   padding-top: 8px;
##   padding-bottom: 8px;
##   padding-left: 5px;
##   padding-right: 5px;
##   border-bottom-style: solid;
##   border-bottom-width: 2px;
##   border-bottom-color: #D3D3D3;
## }
## 
## #juyuvmubvy .gt_grand_summary_row {
##   color: #333333;
##   background-color: #FFFFFF;
##   text-transform: inherit;
##   padding-top: 8px;
##   padding-bottom: 8px;
##   padding-left: 5px;
##   padding-right: 5px;
## }
## 
## #juyuvmubvy .gt_first_grand_summary_row {
##   padding-top: 8px;
##   padding-bottom: 8px;
##   padding-left: 5px;
##   padding-right: 5px;
##   border-top-style: double;
##   border-top-width: 6px;
##   border-top-color: #D3D3D3;
## }
## 
## #juyuvmubvy .gt_last_grand_summary_row_top {
##   padding-top: 8px;
##   padding-bottom: 8px;
##   padding-left: 5px;
##   padding-right: 5px;
##   border-bottom-style: double;
##   border-bottom-width: 6px;
##   border-bottom-color: #D3D3D3;
## }
## 
## #juyuvmubvy .gt_striped {
##   background-color: rgba(128, 128, 128, 0.05);
## }
## 
## #juyuvmubvy .gt_table_body {
##   border-top-style: solid;
##   border-top-width: 2px;
##   border-top-color: #D3D3D3;
##   border-bottom-style: solid;
##   border-bottom-width: 2px;
##   border-bottom-color: #D3D3D3;
## }
## 
## #juyuvmubvy .gt_footnotes {
##   color: #333333;
##   background-color: #FFFFFF;
##   border-bottom-style: none;
##   border-bottom-width: 2px;
##   border-bottom-color: #D3D3D3;
##   border-left-style: none;
##   border-left-width: 2px;
##   border-left-color: #D3D3D3;
##   border-right-style: none;
##   border-right-width: 2px;
##   border-right-color: #D3D3D3;
## }
## 
## #juyuvmubvy .gt_footnote {
##   margin: 0px;
##   font-size: 90%;
##   padding-top: 4px;
##   padding-bottom: 4px;
##   padding-left: 5px;
##   padding-right: 5px;
## }
## 
## #juyuvmubvy .gt_sourcenotes {
##   color: #333333;
##   background-color: #FFFFFF;
##   border-bottom-style: none;
##   border-bottom-width: 2px;
##   border-bottom-color: #D3D3D3;
##   border-left-style: none;
##   border-left-width: 2px;
##   border-left-color: #D3D3D3;
##   border-right-style: none;
##   border-right-width: 2px;
##   border-right-color: #D3D3D3;
## }
## 
## #juyuvmubvy .gt_sourcenote {
##   font-size: 90%;
##   padding-top: 4px;
##   padding-bottom: 4px;
##   padding-left: 5px;
##   padding-right: 5px;
## }
## 
## #juyuvmubvy .gt_left {
##   text-align: left;
## }
## 
## #juyuvmubvy .gt_center {
##   text-align: center;
## }
## 
## #juyuvmubvy .gt_right {
##   text-align: right;
##   font-variant-numeric: tabular-nums;
## }
## 
## #juyuvmubvy .gt_font_normal {
##   font-weight: normal;
## }
## 
## #juyuvmubvy .gt_font_bold {
##   font-weight: bold;
## }
## 
## #juyuvmubvy .gt_font_italic {
##   font-style: italic;
## }
## 
## #juyuvmubvy .gt_super {
##   font-size: 65%;
## }
## 
## #juyuvmubvy .gt_footnote_marks {
##   font-size: 75%;
##   vertical-align: 0.4em;
##   position: initial;
## }
## 
## #juyuvmubvy .gt_asterisk {
##   font-size: 100%;
##   vertical-align: 0;
## }
## 
## #juyuvmubvy .gt_indent_1 {
##   text-indent: 5px;
## }
## 
## #juyuvmubvy .gt_indent_2 {
##   text-indent: 10px;
## }
## 
## #juyuvmubvy .gt_indent_3 {
##   text-indent: 15px;
## }
## 
## #juyuvmubvy .gt_indent_4 {
##   text-indent: 20px;
## }
## 
## #juyuvmubvy .gt_indent_5 {
##   text-indent: 25px;
## }
## 
## #juyuvmubvy .katex-display {
##   display: inline-flex !important;
##   margin-bottom: 0.75em !important;
## }
## 
## #juyuvmubvy div.Reactable > div.rt-table > div.rt-thead > div.rt-tr.rt-tr-group-header > div.rt-th-group:after {
##   height: 0px !important;
## }
## </style>
##   <table class="gt_table" data-quarto-disable-processing="false" data-quarto-bootstrap="false">
##   <thead>
##     <tr class="gt_col_headings gt_spanner_row">
##       <th class="gt_col_heading gt_columns_bottom_border gt_left" rowspan="2" colspan="1" scope="col" id="label"><span class='gt_from_md'><strong>Variable</strong></span></th>
##       <th class="gt_center gt_columns_top_border gt_column_spanner_outer" rowspan="1" colspan="4" scope="colgroup" id="level 1; stat_1_1">
##         <div class="gt_column_spanner"><span class='gt_from_md'><strong>0</strong></span></div>
##       </th>
##       <th class="gt_center gt_columns_top_border gt_column_spanner_outer" rowspan="1" colspan="5" scope="colgroup" id="level 1; stat_1_2">
##         <div class="gt_column_spanner"><span class='gt_from_md'><strong>1</strong></span></div>
##       </th>
##     </tr>
##     <tr class="gt_col_headings">
##       <th class="gt_col_heading gt_columns_bottom_border gt_center" rowspan="1" colspan="1" scope="col" id="stat_1_1"><span class='gt_from_md'><strong>Clinician × Choco</strong><br />
## N = 2</span><span class="gt_footnote_marks" style="white-space:nowrap;font-style:italic;font-weight:normal;line-height:0;"><sup>1</sup></span></th>
##       <th class="gt_col_heading gt_columns_bottom_border gt_center" rowspan="1" colspan="1" scope="col" id="stat_2_1"><span class='gt_from_md'><strong>Self-collected × Choco</strong><br />
## N = 4</span><span class="gt_footnote_marks" style="white-space:nowrap;font-style:italic;font-weight:normal;line-height:0;"><sup>1</sup></span></th>
##       <th class="gt_col_heading gt_columns_bottom_border gt_center" rowspan="1" colspan="1" scope="col" id="stat_3_1"><span class='gt_from_md'><strong>Self-collected × Putumayo</strong><br />
## N = 8</span><span class="gt_footnote_marks" style="white-space:nowrap;font-style:italic;font-weight:normal;line-height:0;"><sup>1</sup></span></th>
##       <th class="gt_col_heading gt_columns_bottom_border gt_center" rowspan="1" colspan="1" scope="col" id="stat_0_1"><span class='gt_from_md'><strong>Total</strong></span><span class="gt_footnote_marks" style="white-space:nowrap;font-style:italic;font-weight:normal;line-height:0;"><sup>1</sup></span></th>
##       <th class="gt_col_heading gt_columns_bottom_border gt_center" rowspan="1" colspan="1" scope="col" id="stat_1_2"><span class='gt_from_md'><strong>Clinician × Choco</strong><br />
## N = 12</span><span class="gt_footnote_marks" style="white-space:nowrap;font-style:italic;font-weight:normal;line-height:0;"><sup>1</sup></span></th>
##       <th class="gt_col_heading gt_columns_bottom_border gt_center" rowspan="1" colspan="1" scope="col" id="stat_2_2"><span class='gt_from_md'><strong>Clinician × Putumayo</strong><br />
## N = 22</span><span class="gt_footnote_marks" style="white-space:nowrap;font-style:italic;font-weight:normal;line-height:0;"><sup>1</sup></span></th>
##       <th class="gt_col_heading gt_columns_bottom_border gt_center" rowspan="1" colspan="1" scope="col" id="stat_3_2"><span class='gt_from_md'><strong>Self-collected × Choco</strong><br />
## N = 31</span><span class="gt_footnote_marks" style="white-space:nowrap;font-style:italic;font-weight:normal;line-height:0;"><sup>1</sup></span></th>
##       <th class="gt_col_heading gt_columns_bottom_border gt_center" rowspan="1" colspan="1" scope="col" id="stat_4_2"><span class='gt_from_md'><strong>Self-collected × Putumayo</strong><br />
## N = 54</span><span class="gt_footnote_marks" style="white-space:nowrap;font-style:italic;font-weight:normal;line-height:0;"><sup>1</sup></span></th>
##       <th class="gt_col_heading gt_columns_bottom_border gt_center" rowspan="1" colspan="1" scope="col" id="stat_0_2"><span class='gt_from_md'><strong>Total</strong></span><span class="gt_footnote_marks" style="white-space:nowrap;font-style:italic;font-weight:normal;line-height:0;"><sup>1</sup></span></th>
##     </tr>
##   </thead>
##   <tbody class="gt_table_body">
##     <tr><td headers="label" class="gt_row gt_left" style="font-weight: bold;">estrategia_toma_cat</td>
## <td headers="stat_1_1" class="gt_row gt_center"><br /></td>
## <td headers="stat_2_1" class="gt_row gt_center"><br /></td>
## <td headers="stat_3_1" class="gt_row gt_center"><br /></td>
## <td headers="stat_0_1" class="gt_row gt_center"><br /></td>
## <td headers="stat_1_2" class="gt_row gt_center"><br /></td>
## <td headers="stat_2_2" class="gt_row gt_center"><br /></td>
## <td headers="stat_3_2" class="gt_row gt_center"><br /></td>
## <td headers="stat_4_2" class="gt_row gt_center"><br /></td>
## <td headers="stat_0_2" class="gt_row gt_center"><br /></td></tr>
##     <tr><td headers="label" class="gt_row gt_left">    Campaña</td>
## <td headers="stat_1_1" class="gt_row gt_center">2 (100.0%)</td>
## <td headers="stat_2_1" class="gt_row gt_center">3 (75.0%)</td>
## <td headers="stat_3_1" class="gt_row gt_center">6 (75.0%)</td>
## <td headers="stat_0_1" class="gt_row gt_center">11 (78.6%)</td>
## <td headers="stat_1_2" class="gt_row gt_center">12 (100.0%)</td>
## <td headers="stat_2_2" class="gt_row gt_center">21 (95.5%)</td>
## <td headers="stat_3_2" class="gt_row gt_center">28 (90.3%)</td>
## <td headers="stat_4_2" class="gt_row gt_center">25 (46.3%)</td>
## <td headers="stat_0_2" class="gt_row gt_center">86 (72.3%)</td></tr>
##     <tr><td headers="label" class="gt_row gt_left">    Tamizaje rutinario</td>
## <td headers="stat_1_1" class="gt_row gt_center">0 (0.0%)</td>
## <td headers="stat_2_1" class="gt_row gt_center">1 (25.0%)</td>
## <td headers="stat_3_1" class="gt_row gt_center">2 (25.0%)</td>
## <td headers="stat_0_1" class="gt_row gt_center">3 (21.4%)</td>
## <td headers="stat_1_2" class="gt_row gt_center">0 (0.0%)</td>
## <td headers="stat_2_2" class="gt_row gt_center">1 (4.5%)</td>
## <td headers="stat_3_2" class="gt_row gt_center">3 (9.7%)</td>
## <td headers="stat_4_2" class="gt_row gt_center">29 (53.7%)</td>
## <td headers="stat_0_2" class="gt_row gt_center">33 (27.7%)</td></tr>
##     <tr><td headers="label" class="gt_row gt_left" style="font-weight: bold;">etnia_cat</td>
## <td headers="stat_1_1" class="gt_row gt_center"><br /></td>
## <td headers="stat_2_1" class="gt_row gt_center"><br /></td>
## <td headers="stat_3_1" class="gt_row gt_center"><br /></td>
## <td headers="stat_0_1" class="gt_row gt_center"><br /></td>
## <td headers="stat_1_2" class="gt_row gt_center"><br /></td>
## <td headers="stat_2_2" class="gt_row gt_center"><br /></td>
## <td headers="stat_3_2" class="gt_row gt_center"><br /></td>
## <td headers="stat_4_2" class="gt_row gt_center"><br /></td>
## <td headers="stat_0_2" class="gt_row gt_center"><br /></td></tr>
##     <tr><td headers="label" class="gt_row gt_left">    Indigena</td>
## <td headers="stat_1_1" class="gt_row gt_center">0 (0.0%)</td>
## <td headers="stat_2_1" class="gt_row gt_center">0 (0.0%)</td>
## <td headers="stat_3_1" class="gt_row gt_center">5 (62.5%)</td>
## <td headers="stat_0_1" class="gt_row gt_center">5 (35.7%)</td>
## <td headers="stat_1_2" class="gt_row gt_center">0 (0.0%)</td>
## <td headers="stat_2_2" class="gt_row gt_center">5 (22.7%)</td>
## <td headers="stat_3_2" class="gt_row gt_center">1 (3.2%)</td>
## <td headers="stat_4_2" class="gt_row gt_center">19 (35.2%)</td>
## <td headers="stat_0_2" class="gt_row gt_center">25 (21.0%)</td></tr>
##     <tr><td headers="label" class="gt_row gt_left">    Afrocolombiano</td>
## <td headers="stat_1_1" class="gt_row gt_center">2 (100.0%)</td>
## <td headers="stat_2_1" class="gt_row gt_center">4 (100.0%)</td>
## <td headers="stat_3_1" class="gt_row gt_center">0 (0.0%)</td>
## <td headers="stat_0_1" class="gt_row gt_center">6 (42.9%)</td>
## <td headers="stat_1_2" class="gt_row gt_center">12 (100.0%)</td>
## <td headers="stat_2_2" class="gt_row gt_center">0 (0.0%)</td>
## <td headers="stat_3_2" class="gt_row gt_center">27 (87.1%)</td>
## <td headers="stat_4_2" class="gt_row gt_center">2 (3.7%)</td>
## <td headers="stat_0_2" class="gt_row gt_center">41 (34.5%)</td></tr>
##     <tr><td headers="label" class="gt_row gt_left">    Otro</td>
## <td headers="stat_1_1" class="gt_row gt_center">0 (0.0%)</td>
## <td headers="stat_2_1" class="gt_row gt_center">0 (0.0%)</td>
## <td headers="stat_3_1" class="gt_row gt_center">3 (37.5%)</td>
## <td headers="stat_0_1" class="gt_row gt_center">3 (21.4%)</td>
## <td headers="stat_1_2" class="gt_row gt_center">0 (0.0%)</td>
## <td headers="stat_2_2" class="gt_row gt_center">17 (77.3%)</td>
## <td headers="stat_3_2" class="gt_row gt_center">3 (9.7%)</td>
## <td headers="stat_4_2" class="gt_row gt_center">33 (61.1%)</td>
## <td headers="stat_0_2" class="gt_row gt_center">53 (44.5%)</td></tr>
##   </tbody>
##   
##   <tfoot class="gt_footnotes">
##     <tr>
##       <td class="gt_footnote" colspan="10"><span class="gt_footnote_marks" style="white-space:nowrap;font-style:italic;font-weight:normal;line-height:0;"><sup>1</sup></span> <span class='gt_from_md'>n (%)</span></td>
##     </tr>
##   </tfoot>
## </table>
## </div>

Se ven diferencias en la asistencia al tratamiento en putumayo por cada tipo de method intention treatment.

Cochran-Mantel-Haenszel

BASE_AUTOTOMA_clean <- BASE_AUTOTOMA_clean %>%
  mutate(estrato_mh = paste(metodo_int_treat_cat, departamento_cat, sep = " × "))

tabla_3d_estrategia <- table(
  BASE_AUTOTOMA_clean$estrategia_toma_cat,  # Variable de resultado
  BASE_AUTOTOMA_clean$asistio_tratamiento,    # Variable de comparación
  BASE_AUTOTOMA_clean$estrato_mh             # Estratos
)


mh_estrategia <- mantelhaen.test(tabla_3d_estrategia)


tabla_3d_etnia <- table(
  BASE_AUTOTOMA_clean$etnia_cat,
  BASE_AUTOTOMA_clean$asistio_tratamiento,
  BASE_AUTOTOMA_clean$estrato_mh
)

mh_etnia <- mantelhaen.test(tabla_3d_etnia)
print(mh_estrategia)

## 
##  Mantel-Haenszel chi-squared test with continuity correction
## 
## data:  tabla_3d_estrategia
## Mantel-Haenszel X-squared = 0.42816, df = 1, p-value = 0.5129
## alternative hypothesis: true common odds ratio is not equal to 1
## 95 percent confidence interval:
##  0.4841733 7.5114963
## sample estimates:
## common odds ratio 
##          1.907057

print(mh_etnia)

## 
##  Cochran-Mantel-Haenszel test
## 
## data:  tabla_3d_etnia
## Cochran-Mantel-Haenszel M^2 = 2.0497, df = 2, p-value = 0.3588

No se encontró asociación

Tabla estartificada seguimiento

BASE_AUTOTOMA_clean <- BASE_AUTOTOMA_clean %>%
  mutate(
    metodo_depto2 = paste(metodo_int_treat_cat, departamento_cat, sep = " - ")
  )

# Tabla con asistencia en filas y método×departamento en columnas
tabla_personalizada2 <- BASE_AUTOTOMA_clean %>%
  select(metodo_depto2, asiste_seguimiento,
         estrategia_toma_cat, etnia_cat) %>%
  tbl_strata(
    strata = asiste_seguimiento,  # Esto va en las FILAS
    .tbl_fun = ~ .x %>%
      tbl_summary(
        by = metodo_depto2,  # Esto va en las COLUMNAS
        statistic = all_categorical() ~ "{n} ({p}%)",
        missing = "no",
        digits = all_categorical() ~ c(0, 1)
      ) %>%
      add_overall(last = TRUE, col_label = "**Total**") %>%
      modify_header(label ~ "**Variable**") %>%
      bold_labels()
  )

print(tabla_personalizada2)

## <div id="parkyipszx" style="padding-left:0px;padding-right:0px;padding-top:10px;padding-bottom:10px;overflow-x:auto;overflow-y:auto;width:auto;height:auto;">
##   <style>#parkyipszx table {
##   font-family: system-ui, 'Segoe UI', Roboto, Helvetica, Arial, sans-serif, 'Apple Color Emoji', 'Segoe UI Emoji', 'Segoe UI Symbol', 'Noto Color Emoji';
##   -webkit-font-smoothing: antialiased;
##   -moz-osx-font-smoothing: grayscale;
## }
## 
## #parkyipszx thead, #parkyipszx tbody, #parkyipszx tfoot, #parkyipszx tr, #parkyipszx td, #parkyipszx th {
##   border-style: none;
## }
## 
## #parkyipszx p {
##   margin: 0;
##   padding: 0;
## }
## 
## #parkyipszx .gt_table {
##   display: table;
##   border-collapse: collapse;
##   line-height: normal;
##   margin-left: auto;
##   margin-right: auto;
##   color: #333333;
##   font-size: 16px;
##   font-weight: normal;
##   font-style: normal;
##   background-color: #FFFFFF;
##   width: auto;
##   border-top-style: solid;
##   border-top-width: 2px;
##   border-top-color: #A8A8A8;
##   border-right-style: none;
##   border-right-width: 2px;
##   border-right-color: #D3D3D3;
##   border-bottom-style: solid;
##   border-bottom-width: 2px;
##   border-bottom-color: #A8A8A8;
##   border-left-style: none;
##   border-left-width: 2px;
##   border-left-color: #D3D3D3;
## }
## 
## #parkyipszx .gt_caption {
##   padding-top: 4px;
##   padding-bottom: 4px;
## }
## 
## #parkyipszx .gt_title {
##   color: #333333;
##   font-size: 125%;
##   font-weight: initial;
##   padding-top: 4px;
##   padding-bottom: 4px;
##   padding-left: 5px;
##   padding-right: 5px;
##   border-bottom-color: #FFFFFF;
##   border-bottom-width: 0;
## }
## 
## #parkyipszx .gt_subtitle {
##   color: #333333;
##   font-size: 85%;
##   font-weight: initial;
##   padding-top: 3px;
##   padding-bottom: 5px;
##   padding-left: 5px;
##   padding-right: 5px;
##   border-top-color: #FFFFFF;
##   border-top-width: 0;
## }
## 
## #parkyipszx .gt_heading {
##   background-color: #FFFFFF;
##   text-align: center;
##   border-bottom-color: #FFFFFF;
##   border-left-style: none;
##   border-left-width: 1px;
##   border-left-color: #D3D3D3;
##   border-right-style: none;
##   border-right-width: 1px;
##   border-right-color: #D3D3D3;
## }
## 
## #parkyipszx .gt_bottom_border {
##   border-bottom-style: solid;
##   border-bottom-width: 2px;
##   border-bottom-color: #D3D3D3;
## }
## 
## #parkyipszx .gt_col_headings {
##   border-top-style: solid;
##   border-top-width: 2px;
##   border-top-color: #D3D3D3;
##   border-bottom-style: solid;
##   border-bottom-width: 2px;
##   border-bottom-color: #D3D3D3;
##   border-left-style: none;
##   border-left-width: 1px;
##   border-left-color: #D3D3D3;
##   border-right-style: none;
##   border-right-width: 1px;
##   border-right-color: #D3D3D3;
## }
## 
## #parkyipszx .gt_col_heading {
##   color: #333333;
##   background-color: #FFFFFF;
##   font-size: 100%;
##   font-weight: normal;
##   text-transform: inherit;
##   border-left-style: none;
##   border-left-width: 1px;
##   border-left-color: #D3D3D3;
##   border-right-style: none;
##   border-right-width: 1px;
##   border-right-color: #D3D3D3;
##   vertical-align: bottom;
##   padding-top: 5px;
##   padding-bottom: 6px;
##   padding-left: 5px;
##   padding-right: 5px;
##   overflow-x: hidden;
## }
## 
## #parkyipszx .gt_column_spanner_outer {
##   color: #333333;
##   background-color: #FFFFFF;
##   font-size: 100%;
##   font-weight: normal;
##   text-transform: inherit;
##   padding-top: 0;
##   padding-bottom: 0;
##   padding-left: 4px;
##   padding-right: 4px;
## }
## 
## #parkyipszx .gt_column_spanner_outer:first-child {
##   padding-left: 0;
## }
## 
## #parkyipszx .gt_column_spanner_outer:last-child {
##   padding-right: 0;
## }
## 
## #parkyipszx .gt_column_spanner {
##   border-bottom-style: solid;
##   border-bottom-width: 2px;
##   border-bottom-color: #D3D3D3;
##   vertical-align: bottom;
##   padding-top: 5px;
##   padding-bottom: 5px;
##   overflow-x: hidden;
##   display: inline-block;
##   width: 100%;
## }
## 
## #parkyipszx .gt_spanner_row {
##   border-bottom-style: hidden;
## }
## 
## #parkyipszx .gt_group_heading {
##   padding-top: 8px;
##   padding-bottom: 8px;
##   padding-left: 5px;
##   padding-right: 5px;
##   color: #333333;
##   background-color: #FFFFFF;
##   font-size: 100%;
##   font-weight: initial;
##   text-transform: inherit;
##   border-top-style: solid;
##   border-top-width: 2px;
##   border-top-color: #D3D3D3;
##   border-bottom-style: solid;
##   border-bottom-width: 2px;
##   border-bottom-color: #D3D3D3;
##   border-left-style: none;
##   border-left-width: 1px;
##   border-left-color: #D3D3D3;
##   border-right-style: none;
##   border-right-width: 1px;
##   border-right-color: #D3D3D3;
##   vertical-align: middle;
##   text-align: left;
## }
## 
## #parkyipszx .gt_empty_group_heading {
##   padding: 0.5px;
##   color: #333333;
##   background-color: #FFFFFF;
##   font-size: 100%;
##   font-weight: initial;
##   border-top-style: solid;
##   border-top-width: 2px;
##   border-top-color: #D3D3D3;
##   border-bottom-style: solid;
##   border-bottom-width: 2px;
##   border-bottom-color: #D3D3D3;
##   vertical-align: middle;
## }
## 
## #parkyipszx .gt_from_md > :first-child {
##   margin-top: 0;
## }
## 
## #parkyipszx .gt_from_md > :last-child {
##   margin-bottom: 0;
## }
## 
## #parkyipszx .gt_row {
##   padding-top: 8px;
##   padding-bottom: 8px;
##   padding-left: 5px;
##   padding-right: 5px;
##   margin: 10px;
##   border-top-style: solid;
##   border-top-width: 1px;
##   border-top-color: #D3D3D3;
##   border-left-style: none;
##   border-left-width: 1px;
##   border-left-color: #D3D3D3;
##   border-right-style: none;
##   border-right-width: 1px;
##   border-right-color: #D3D3D3;
##   vertical-align: middle;
##   overflow-x: hidden;
## }
## 
## #parkyipszx .gt_stub {
##   color: #333333;
##   background-color: #FFFFFF;
##   font-size: 100%;
##   font-weight: initial;
##   text-transform: inherit;
##   border-right-style: solid;
##   border-right-width: 2px;
##   border-right-color: #D3D3D3;
##   padding-left: 5px;
##   padding-right: 5px;
## }
## 
## #parkyipszx .gt_stub_row_group {
##   color: #333333;
##   background-color: #FFFFFF;
##   font-size: 100%;
##   font-weight: initial;
##   text-transform: inherit;
##   border-right-style: solid;
##   border-right-width: 2px;
##   border-right-color: #D3D3D3;
##   padding-left: 5px;
##   padding-right: 5px;
##   vertical-align: top;
## }
## 
## #parkyipszx .gt_row_group_first td {
##   border-top-width: 2px;
## }
## 
## #parkyipszx .gt_row_group_first th {
##   border-top-width: 2px;
## }
## 
## #parkyipszx .gt_summary_row {
##   color: #333333;
##   background-color: #FFFFFF;
##   text-transform: inherit;
##   padding-top: 8px;
##   padding-bottom: 8px;
##   padding-left: 5px;
##   padding-right: 5px;
## }
## 
## #parkyipszx .gt_first_summary_row {
##   border-top-style: solid;
##   border-top-color: #D3D3D3;
## }
## 
## #parkyipszx .gt_first_summary_row.thick {
##   border-top-width: 2px;
## }
## 
## #parkyipszx .gt_last_summary_row {
##   padding-top: 8px;
##   padding-bottom: 8px;
##   padding-left: 5px;
##   padding-right: 5px;
##   border-bottom-style: solid;
##   border-bottom-width: 2px;
##   border-bottom-color: #D3D3D3;
## }
## 
## #parkyipszx .gt_grand_summary_row {
##   color: #333333;
##   background-color: #FFFFFF;
##   text-transform: inherit;
##   padding-top: 8px;
##   padding-bottom: 8px;
##   padding-left: 5px;
##   padding-right: 5px;
## }
## 
## #parkyipszx .gt_first_grand_summary_row {
##   padding-top: 8px;
##   padding-bottom: 8px;
##   padding-left: 5px;
##   padding-right: 5px;
##   border-top-style: double;
##   border-top-width: 6px;
##   border-top-color: #D3D3D3;
## }
## 
## #parkyipszx .gt_last_grand_summary_row_top {
##   padding-top: 8px;
##   padding-bottom: 8px;
##   padding-left: 5px;
##   padding-right: 5px;
##   border-bottom-style: double;
##   border-bottom-width: 6px;
##   border-bottom-color: #D3D3D3;
## }
## 
## #parkyipszx .gt_striped {
##   background-color: rgba(128, 128, 128, 0.05);
## }
## 
## #parkyipszx .gt_table_body {
##   border-top-style: solid;
##   border-top-width: 2px;
##   border-top-color: #D3D3D3;
##   border-bottom-style: solid;
##   border-bottom-width: 2px;
##   border-bottom-color: #D3D3D3;
## }
## 
## #parkyipszx .gt_footnotes {
##   color: #333333;
##   background-color: #FFFFFF;
##   border-bottom-style: none;
##   border-bottom-width: 2px;
##   border-bottom-color: #D3D3D3;
##   border-left-style: none;
##   border-left-width: 2px;
##   border-left-color: #D3D3D3;
##   border-right-style: none;
##   border-right-width: 2px;
##   border-right-color: #D3D3D3;
## }
## 
## #parkyipszx .gt_footnote {
##   margin: 0px;
##   font-size: 90%;
##   padding-top: 4px;
##   padding-bottom: 4px;
##   padding-left: 5px;
##   padding-right: 5px;
## }
## 
## #parkyipszx .gt_sourcenotes {
##   color: #333333;
##   background-color: #FFFFFF;
##   border-bottom-style: none;
##   border-bottom-width: 2px;
##   border-bottom-color: #D3D3D3;
##   border-left-style: none;
##   border-left-width: 2px;
##   border-left-color: #D3D3D3;
##   border-right-style: none;
##   border-right-width: 2px;
##   border-right-color: #D3D3D3;
## }
## 
## #parkyipszx .gt_sourcenote {
##   font-size: 90%;
##   padding-top: 4px;
##   padding-bottom: 4px;
##   padding-left: 5px;
##   padding-right: 5px;
## }
## 
## #parkyipszx .gt_left {
##   text-align: left;
## }
## 
## #parkyipszx .gt_center {
##   text-align: center;
## }
## 
## #parkyipszx .gt_right {
##   text-align: right;
##   font-variant-numeric: tabular-nums;
## }
## 
## #parkyipszx .gt_font_normal {
##   font-weight: normal;
## }
## 
## #parkyipszx .gt_font_bold {
##   font-weight: bold;
## }
## 
## #parkyipszx .gt_font_italic {
##   font-style: italic;
## }
## 
## #parkyipszx .gt_super {
##   font-size: 65%;
## }
## 
## #parkyipszx .gt_footnote_marks {
##   font-size: 75%;
##   vertical-align: 0.4em;
##   position: initial;
## }
## 
## #parkyipszx .gt_asterisk {
##   font-size: 100%;
##   vertical-align: 0;
## }
## 
## #parkyipszx .gt_indent_1 {
##   text-indent: 5px;
## }
## 
## #parkyipszx .gt_indent_2 {
##   text-indent: 10px;
## }
## 
## #parkyipszx .gt_indent_3 {
##   text-indent: 15px;
## }
## 
## #parkyipszx .gt_indent_4 {
##   text-indent: 20px;
## }
## 
## #parkyipszx .gt_indent_5 {
##   text-indent: 25px;
## }
## 
## #parkyipszx .katex-display {
##   display: inline-flex !important;
##   margin-bottom: 0.75em !important;
## }
## 
## #parkyipszx div.Reactable > div.rt-table > div.rt-thead > div.rt-tr.rt-tr-group-header > div.rt-th-group:after {
##   height: 0px !important;
## }
## </style>
##   <table class="gt_table" data-quarto-disable-processing="false" data-quarto-bootstrap="false">
##   <thead>
##     <tr class="gt_col_headings gt_spanner_row">
##       <th class="gt_col_heading gt_columns_bottom_border gt_left" rowspan="2" colspan="1" scope="col" id="label"><span class='gt_from_md'><strong>Variable</strong></span></th>
##       <th class="gt_center gt_columns_top_border gt_column_spanner_outer" rowspan="1" colspan="5" scope="colgroup" id="level 1; stat_1_1">
##         <div class="gt_column_spanner"><span class='gt_from_md'><strong>0</strong></span></div>
##       </th>
##       <th class="gt_center gt_columns_top_border gt_column_spanner_outer" rowspan="1" colspan="5" scope="colgroup" id="level 1; stat_1_2">
##         <div class="gt_column_spanner"><span class='gt_from_md'><strong>1</strong></span></div>
##       </th>
##     </tr>
##     <tr class="gt_col_headings">
##       <th class="gt_col_heading gt_columns_bottom_border gt_center" rowspan="1" colspan="1" scope="col" id="stat_1_1"><span class='gt_from_md'><strong>Clinician - Choco</strong><br />
## N = 6</span><span class="gt_footnote_marks" style="white-space:nowrap;font-style:italic;font-weight:normal;line-height:0;"><sup>1</sup></span></th>
##       <th class="gt_col_heading gt_columns_bottom_border gt_center" rowspan="1" colspan="1" scope="col" id="stat_2_1"><span class='gt_from_md'><strong>Clinician - Putumayo</strong><br />
## N = 5</span><span class="gt_footnote_marks" style="white-space:nowrap;font-style:italic;font-weight:normal;line-height:0;"><sup>1</sup></span></th>
##       <th class="gt_col_heading gt_columns_bottom_border gt_center" rowspan="1" colspan="1" scope="col" id="stat_3_1"><span class='gt_from_md'><strong>Self-collected - Choco</strong><br />
## N = 7</span><span class="gt_footnote_marks" style="white-space:nowrap;font-style:italic;font-weight:normal;line-height:0;"><sup>1</sup></span></th>
##       <th class="gt_col_heading gt_columns_bottom_border gt_center" rowspan="1" colspan="1" scope="col" id="stat_4_1"><span class='gt_from_md'><strong>Self-collected - Putumayo</strong><br />
## N = 20</span><span class="gt_footnote_marks" style="white-space:nowrap;font-style:italic;font-weight:normal;line-height:0;"><sup>1</sup></span></th>
##       <th class="gt_col_heading gt_columns_bottom_border gt_center" rowspan="1" colspan="1" scope="col" id="stat_0_1"><span class='gt_from_md'><strong>Total</strong></span><span class="gt_footnote_marks" style="white-space:nowrap;font-style:italic;font-weight:normal;line-height:0;"><sup>1</sup></span></th>
##       <th class="gt_col_heading gt_columns_bottom_border gt_center" rowspan="1" colspan="1" scope="col" id="stat_1_2"><span class='gt_from_md'><strong>Clinician - Choco</strong><br />
## N = 8</span><span class="gt_footnote_marks" style="white-space:nowrap;font-style:italic;font-weight:normal;line-height:0;"><sup>1</sup></span></th>
##       <th class="gt_col_heading gt_columns_bottom_border gt_center" rowspan="1" colspan="1" scope="col" id="stat_2_2"><span class='gt_from_md'><strong>Clinician - Putumayo</strong><br />
## N = 17</span><span class="gt_footnote_marks" style="white-space:nowrap;font-style:italic;font-weight:normal;line-height:0;"><sup>1</sup></span></th>
##       <th class="gt_col_heading gt_columns_bottom_border gt_center" rowspan="1" colspan="1" scope="col" id="stat_3_2"><span class='gt_from_md'><strong>Self-collected - Choco</strong><br />
## N = 28</span><span class="gt_footnote_marks" style="white-space:nowrap;font-style:italic;font-weight:normal;line-height:0;"><sup>1</sup></span></th>
##       <th class="gt_col_heading gt_columns_bottom_border gt_center" rowspan="1" colspan="1" scope="col" id="stat_4_2"><span class='gt_from_md'><strong>Self-collected - Putumayo</strong><br />
## N = 42</span><span class="gt_footnote_marks" style="white-space:nowrap;font-style:italic;font-weight:normal;line-height:0;"><sup>1</sup></span></th>
##       <th class="gt_col_heading gt_columns_bottom_border gt_center" rowspan="1" colspan="1" scope="col" id="stat_0_2"><span class='gt_from_md'><strong>Total</strong></span><span class="gt_footnote_marks" style="white-space:nowrap;font-style:italic;font-weight:normal;line-height:0;"><sup>1</sup></span></th>
##     </tr>
##   </thead>
##   <tbody class="gt_table_body">
##     <tr><td headers="label" class="gt_row gt_left" style="font-weight: bold;">estrategia_toma_cat</td>
## <td headers="stat_1_1" class="gt_row gt_center"><br /></td>
## <td headers="stat_2_1" class="gt_row gt_center"><br /></td>
## <td headers="stat_3_1" class="gt_row gt_center"><br /></td>
## <td headers="stat_4_1" class="gt_row gt_center"><br /></td>
## <td headers="stat_0_1" class="gt_row gt_center"><br /></td>
## <td headers="stat_1_2" class="gt_row gt_center"><br /></td>
## <td headers="stat_2_2" class="gt_row gt_center"><br /></td>
## <td headers="stat_3_2" class="gt_row gt_center"><br /></td>
## <td headers="stat_4_2" class="gt_row gt_center"><br /></td>
## <td headers="stat_0_2" class="gt_row gt_center"><br /></td></tr>
##     <tr><td headers="label" class="gt_row gt_left">    Campaña</td>
## <td headers="stat_1_1" class="gt_row gt_center">6 (100.0%)</td>
## <td headers="stat_2_1" class="gt_row gt_center">5 (100.0%)</td>
## <td headers="stat_3_1" class="gt_row gt_center">7 (100.0%)</td>
## <td headers="stat_4_1" class="gt_row gt_center">7 (35.0%)</td>
## <td headers="stat_0_1" class="gt_row gt_center">25 (65.8%)</td>
## <td headers="stat_1_2" class="gt_row gt_center">8 (100.0%)</td>
## <td headers="stat_2_2" class="gt_row gt_center">16 (94.1%)</td>
## <td headers="stat_3_2" class="gt_row gt_center">24 (85.7%)</td>
## <td headers="stat_4_2" class="gt_row gt_center">24 (57.1%)</td>
## <td headers="stat_0_2" class="gt_row gt_center">72 (75.8%)</td></tr>
##     <tr><td headers="label" class="gt_row gt_left">    Tamizaje rutinario</td>
## <td headers="stat_1_1" class="gt_row gt_center">0 (0.0%)</td>
## <td headers="stat_2_1" class="gt_row gt_center">0 (0.0%)</td>
## <td headers="stat_3_1" class="gt_row gt_center">0 (0.0%)</td>
## <td headers="stat_4_1" class="gt_row gt_center">13 (65.0%)</td>
## <td headers="stat_0_1" class="gt_row gt_center">13 (34.2%)</td>
## <td headers="stat_1_2" class="gt_row gt_center">0 (0.0%)</td>
## <td headers="stat_2_2" class="gt_row gt_center">1 (5.9%)</td>
## <td headers="stat_3_2" class="gt_row gt_center">4 (14.3%)</td>
## <td headers="stat_4_2" class="gt_row gt_center">18 (42.9%)</td>
## <td headers="stat_0_2" class="gt_row gt_center">23 (24.2%)</td></tr>
##     <tr><td headers="label" class="gt_row gt_left" style="font-weight: bold;">etnia_cat</td>
## <td headers="stat_1_1" class="gt_row gt_center"><br /></td>
## <td headers="stat_2_1" class="gt_row gt_center"><br /></td>
## <td headers="stat_3_1" class="gt_row gt_center"><br /></td>
## <td headers="stat_4_1" class="gt_row gt_center"><br /></td>
## <td headers="stat_0_1" class="gt_row gt_center"><br /></td>
## <td headers="stat_1_2" class="gt_row gt_center"><br /></td>
## <td headers="stat_2_2" class="gt_row gt_center"><br /></td>
## <td headers="stat_3_2" class="gt_row gt_center"><br /></td>
## <td headers="stat_4_2" class="gt_row gt_center"><br /></td>
## <td headers="stat_0_2" class="gt_row gt_center"><br /></td></tr>
##     <tr><td headers="label" class="gt_row gt_left">    Indigena</td>
## <td headers="stat_1_1" class="gt_row gt_center">0 (0.0%)</td>
## <td headers="stat_2_1" class="gt_row gt_center">0 (0.0%)</td>
## <td headers="stat_3_1" class="gt_row gt_center">1 (14.3%)</td>
## <td headers="stat_4_1" class="gt_row gt_center">9 (45.0%)</td>
## <td headers="stat_0_1" class="gt_row gt_center">10 (26.3%)</td>
## <td headers="stat_1_2" class="gt_row gt_center">0 (0.0%)</td>
## <td headers="stat_2_2" class="gt_row gt_center">5 (29.4%)</td>
## <td headers="stat_3_2" class="gt_row gt_center">0 (0.0%)</td>
## <td headers="stat_4_2" class="gt_row gt_center">15 (35.7%)</td>
## <td headers="stat_0_2" class="gt_row gt_center">20 (21.1%)</td></tr>
##     <tr><td headers="label" class="gt_row gt_left">    Afrocolombiano</td>
## <td headers="stat_1_1" class="gt_row gt_center">6 (100.0%)</td>
## <td headers="stat_2_1" class="gt_row gt_center">0 (0.0%)</td>
## <td headers="stat_3_1" class="gt_row gt_center">6 (85.7%)</td>
## <td headers="stat_4_1" class="gt_row gt_center">0 (0.0%)</td>
## <td headers="stat_0_1" class="gt_row gt_center">12 (31.6%)</td>
## <td headers="stat_1_2" class="gt_row gt_center">8 (100.0%)</td>
## <td headers="stat_2_2" class="gt_row gt_center">0 (0.0%)</td>
## <td headers="stat_3_2" class="gt_row gt_center">25 (89.3%)</td>
## <td headers="stat_4_2" class="gt_row gt_center">2 (4.8%)</td>
## <td headers="stat_0_2" class="gt_row gt_center">35 (36.8%)</td></tr>
##     <tr><td headers="label" class="gt_row gt_left">    Otro</td>
## <td headers="stat_1_1" class="gt_row gt_center">0 (0.0%)</td>
## <td headers="stat_2_1" class="gt_row gt_center">5 (100.0%)</td>
## <td headers="stat_3_1" class="gt_row gt_center">0 (0.0%)</td>
## <td headers="stat_4_1" class="gt_row gt_center">11 (55.0%)</td>
## <td headers="stat_0_1" class="gt_row gt_center">16 (42.1%)</td>
## <td headers="stat_1_2" class="gt_row gt_center">0 (0.0%)</td>
## <td headers="stat_2_2" class="gt_row gt_center">12 (70.6%)</td>
## <td headers="stat_3_2" class="gt_row gt_center">3 (10.7%)</td>
## <td headers="stat_4_2" class="gt_row gt_center">25 (59.5%)</td>
## <td headers="stat_0_2" class="gt_row gt_center">40 (42.1%)</td></tr>
##   </tbody>
##   
##   <tfoot class="gt_footnotes">
##     <tr>
##       <td class="gt_footnote" colspan="11"><span class="gt_footnote_marks" style="white-space:nowrap;font-style:italic;font-weight:normal;line-height:0;"><sup>1</sup></span> <span class='gt_from_md'>n (%)</span></td>
##     </tr>
##   </tfoot>
## </table>
## </div>

### Cochran-Mantel-Haenszel

# 2. Test MH para estrategia_toma_cat
tabla_3d_estrategia2 <- table(
  BASE_AUTOTOMA_clean$estrategia_toma_cat,  # Variable de resultado
  BASE_AUTOTOMA_clean$asiste_seguimiento,    # Variable de comparación
  BASE_AUTOTOMA_clean$estrato_mh             # Estratos
)

mh_estrategia2 <- mantelhaen.test(tabla_3d_estrategia2)
# 3. Test MH para etnia_cat
tabla_3d_etnia2 <- table(
  BASE_AUTOTOMA_clean$etnia_cat,
  BASE_AUTOTOMA_clean$asiste_seguimiento,
  BASE_AUTOTOMA_clean$estrato_mh
)

mh_etnia2 <- mantelhaen.test(tabla_3d_etnia2)
print(mh_estrategia2)

## 
##  Mantel-Haenszel chi-squared test with continuity correction
## 
## data:  tabla_3d_estrategia2
## Mantel-Haenszel X-squared = 0.51619, df = 1, p-value = 0.4725
## alternative hypothesis: true common odds ratio is not equal to 1
## 95 percent confidence interval:
##  0.2289625 1.6144307
## sample estimates:
## common odds ratio 
##         0.6079837

print(mh_etnia2)

## 
##  Cochran-Mantel-Haenszel test
## 
## data:  tabla_3d_etnia2
## Cochran-Mantel-Haenszel M^2 = 0.81162, df = 2, p-value = 0.6664

Filtrando la base de datos

Asistencia al tratamiento

###FILTRANDO LA BASE 
BASE_AUTOTOMA_filt2 <- BASE_AUTOTOMA_clean %>%  filter(asistio_tratamiento == 1)
BASE_AUTOTOMA_filt3 <- BASE_AUTOTOMA_clean %>%  filter(asiste_seguimiento == 1)


##Solo asistentes 
# Tabla estratificada (recomendada)
BASE_AUTOTOMA_filt2 %>%
  select(metodo_int_treat_cat, departamento_cat, 
         estrategia_toma_cat, etnia_cat) %>%
  tbl_strata(
    strata = metodo_int_treat_cat,
    .tbl_fun = ~ .x %>%
      tbl_summary(
        by = departamento_cat,
        statistic = all_categorical() ~ "{n} ({p}%)"
      ) %>%
      add_overall()
  )

Characteristic	Clinician			Self-collected
Characteristic	Overall N = 34¹	Putumayo N = 22¹	Choco N = 12¹	Overall N = 85¹	Putumayo N = 54¹	Choco N = 31¹
estrategia_toma_cat
Campaña	33 (97%)	21 (95%)	12 (100%)	53 (62%)	25 (46%)	28 (90%)
Tamizaje rutinario	1 (2.9%)	1 (4.5%)	0 (0%)	32 (38%)	29 (54%)	3 (9.7%)
etnia_cat
Indigena	5 (15%)	5 (23%)	0 (0%)	20 (24%)	19 (35%)	1 (3.2%)
Afrocolombiano	12 (35%)	0 (0%)	12 (100%)	29 (34%)	2 (3.7%)	27 (87%)
Otro	17 (50%)	17 (77%)	0 (0%)	36 (42%)	33 (61%)	3 (9.7%)
¹ n (%)

Cochran-Mantel-Haenszel

# 1. Crear la tabla visual (con chi-cuadrado por ahora)
tabla_visual3 <- BASE_AUTOTOMA_filt2 %>%
  select(metodo_int_treat_cat, departamento_cat, 
         estrategia_toma_cat, etnia_cat) %>%
  tbl_strata(
    strata = metodo_int_treat_cat,
    .tbl_fun = ~ .x %>%
      tbl_summary(by = departamento_cat) %>%
      add_overall() %>%
      bold_labels()
  )

# 2. Calcular Mantel-Haenszel manualmente para cada variable
# Para estrategia_toma_cat
tabla_3d_estrategia3 <- table(
  BASE_AUTOTOMA_filt2$estrategia_toma_cat,
  BASE_AUTOTOMA_filt2$departamento_cat,
  BASE_AUTOTOMA_filt2$metodo_int_treat_cat
)
mh_estrategia3 <- mantelhaen.test(tabla_3d_estrategia3)

# Para etnia_cat
tabla_3d_etnia3 <- table(
  BASE_AUTOTOMA_filt2$etnia_cat,
  BASE_AUTOTOMA_filt2$departamento_cat,
  BASE_AUTOTOMA_filt2$metodo_int_treat_cat
)
mh_etnia3 <- mantelhaen.test(tabla_3d_etnia3)

# 3. Ver resultados
print(mh_estrategia3)

## 
##  Mantel-Haenszel chi-squared test with continuity correction
## 
## data:  tabla_3d_estrategia3
## Mantel-Haenszel X-squared = 14.807, df = 1, p-value = 0.0001191
## alternative hypothesis: true common odds ratio is not equal to 1
## 95 percent confidence interval:
##  0.02404799 0.32992832
## sample estimates:
## common odds ratio 
##        0.08907363

print(mh_etnia3)

## 
##  Cochran-Mantel-Haenszel test
## 
## data:  tabla_3d_etnia3
## Cochran-Mantel-Haenszel M^2 = 92.801, df = 2, p-value < 2.2e-16

Asistencia al seguimiento

BASE_AUTOTOMA_filt3 %>%
  select(metodo_int_treat_cat, departamento_cat, 
         estrategia_toma_cat, etnia_cat) %>%
  tbl_strata(
    strata = metodo_int_treat_cat,
    .tbl_fun = ~ .x %>%
      tbl_summary(
        by = departamento_cat,
        statistic = all_categorical() ~ "{n} ({p}%)"
      ) %>%
      add_overall()
  )

Characteristic	Clinician			Self-collected
Characteristic	Overall N = 25¹	Putumayo N = 17¹	Choco N = 8¹	Overall N = 70¹	Putumayo N = 42¹	Choco N = 28¹
estrategia_toma_cat
Campaña	24 (96%)	16 (94%)	8 (100%)	48 (69%)	24 (57%)	24 (86%)
Tamizaje rutinario	1 (4.0%)	1 (5.9%)	0 (0%)	22 (31%)	18 (43%)	4 (14%)
etnia_cat
Indigena	5 (20%)	5 (29%)	0 (0%)	15 (21%)	15 (36%)	0 (0%)
Afrocolombiano	8 (32%)	0 (0%)	8 (100%)	27 (39%)	2 (4.8%)	25 (89%)
Otro	12 (48%)	12 (71%)	0 (0%)	28 (40%)	25 (60%)	3 (11%)
¹ n (%)

Mantel-Haenszel

# 1. Crear la tabla visual (con chi-cuadrado por ahora)
tabla_visual4 <- BASE_AUTOTOMA_filt3 %>%
  select(metodo_int_treat_cat, departamento_cat, 
         estrategia_toma_cat, etnia_cat) %>%
  tbl_strata(
    strata = metodo_int_treat_cat,
    .tbl_fun = ~ .x %>%
      tbl_summary(by = departamento_cat) %>%
      add_overall() %>%
      bold_labels()
  )

# 2. Calcular Mantel-Haenszel manualmente para cada variable
# Para estrategia_toma_cat
tabla_3d_estrategia4 <- table(
  BASE_AUTOTOMA_filt3$estrategia_toma_cat,
  BASE_AUTOTOMA_filt3$departamento_cat,
  BASE_AUTOTOMA_filt3$metodo_int_treat_cat
)
mh_estrategia4 <- mantelhaen.test(tabla_3d_estrategia4)

# Para etnia_cat
tabla_3d_etnia4 <- table(
  BASE_AUTOTOMA_filt3$etnia_cat,
  BASE_AUTOTOMA_filt3$departamento_cat,
  BASE_AUTOTOMA_filt3$metodo_int_treat_cat
)
mh_etnia4 <- mantelhaen.test(tabla_3d_etnia4)

# 3. Ver resultados
print(mh_estrategia4)

## 
##  Mantel-Haenszel chi-squared test with continuity correction
## 
## data:  tabla_3d_estrategia4
## Mantel-Haenszel X-squared = 5.4861, df = 1, p-value = 0.01917
## alternative hypothesis: true common odds ratio is not equal to 1
## 95 percent confidence interval:
##  0.06236851 0.71564966
## sample estimates:
## common odds ratio 
##         0.2112676

print(mh_etnia4)

## 
##  Cochran-Mantel-Haenszel test
## 
## data:  tabla_3d_etnia4
## Cochran-Mantel-Haenszel M^2 = 73.49, df = 2, p-value < 2.2e-16

Modelos multivariados

Asistencia tratamiento

m_Auto <- glm(asistio_tratamiento ~ metodo_int_treat_cat + departamento_cat + 
              etnia_cat +  estrategia_toma_cat + regimen_agr_cat +
              ult_tamizaje_agr_cat + area_residencia_cat + ngestaciones_cat, 
            binomial(link = "logit"), data = BASE_AUTOTOMA_clean)
summary(m_Auto)

## 
## Call:
## glm(formula = asistio_tratamiento ~ metodo_int_treat_cat + departamento_cat + 
##     etnia_cat + estrategia_toma_cat + regimen_agr_cat + ult_tamizaje_agr_cat + 
##     area_residencia_cat + ngestaciones_cat, family = binomial(link = "logit"), 
##     data = BASE_AUTOTOMA_clean)
## 
## Coefficients:
##                                        Estimate Std. Error z value Pr(>|z|)  
## (Intercept)                            2.806472   1.571944   1.785   0.0742 .
## metodo_int_treat_catSelf-collected    -1.351765   0.978236  -1.382   0.1670  
## departamento_catChoco                  1.223436   1.435643   0.852   0.3941  
## etnia_catAfrocolombiano               -0.723776   1.437395  -0.504   0.6146  
## etnia_catOtro                          0.573075   0.838212   0.684   0.4942  
## estrategia_toma_catTamizaje rutinario  0.983375   0.840431   1.170   0.2420  
## regimen_agr_catSubsidiado             -0.276363   0.742823  -0.372   0.7099  
## ult_tamizaje_agr_cat25-36 meses        0.686360   1.392468   0.493   0.6221  
## ult_tamizaje_agr_cat>36 meses         -0.003414   1.455407  -0.002   0.9981  
## area_residencia_catRural              -0.839792   0.735430  -1.142   0.2535  
## ngestaciones_cat>3                    -0.992279   0.684724  -1.449   0.1473  
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## (Dispersion parameter for binomial family taken to be 1)
## 
##     Null deviance: 89.059  on 130  degrees of freedom
## Residual deviance: 79.363  on 120  degrees of freedom
##   (2 observations deleted due to missingness)
## AIC: 101.36
## 
## Number of Fisher Scoring iterations: 6

library(sjPlot)
library(sjmisc)
library(sjlabelled)
tbl_regression(m_Auto, exponentiate = TRUE, add_estimate_to_reference_rows=TRUE)  %>% add_global_p()

Characteristic	OR	95% CI	p-value
metodo_int_treat_cat			0.12
Clinician	1.00	—
Self-collected	0.26	0.03, 1.40
departamento_cat			0.4
Putumayo	1.00	—
Choco	3.40	0.23, 64.5
etnia_cat			0.6
Indigena	1.00	—
Afrocolombiano	0.48	0.03, 8.11
Otro	1.77	0.34, 10.2
estrategia_toma_cat			0.2
Campaña	1.00	—
Tamizaje rutinario	2.67	0.55, 16.2
regimen_agr_cat			0.7
Contributivo/otro	1.00	—
Subsidiado	0.76	0.16, 3.11
ult_tamizaje_agr_cat			0.6
<= 24 meses	1.00	—
25-36 meses	1.99	0.07, 27.2
>36 meses	1.00	0.03, 15.4
area_residencia_cat			0.3
Urbano	1.00	—
Rural	0.43	0.10, 1.99
ngestaciones_cat			0.2
<=3	1.00	—
>3	0.37	0.09, 1.45
Abbreviations: CI = Confidence Interval, OR = Odds Ratio

Asistencia al seguimiento

m_Auto2 <- glm(asiste_seguimiento ~ metodo_int_treat_cat + departamento_cat + 
                etnia_cat +  estrategia_toma_cat + regimen_agr_cat +
                ult_tamizaje_agr_cat + area_residencia_cat + ngestaciones_cat, 
              binomial(link = "logit"), data = BASE_AUTOTOMA_clean)

tbl_regression(m_Auto2, exponentiate = TRUE, add_estimate_to_reference_rows=TRUE)  %>% add_global_p()

Characteristic	OR	95% CI	p-value
metodo_int_treat_cat			0.7
Clinician	1.00	—
Self-collected	1.19	0.41, 3.36
departamento_cat			>0.9
Putumayo	1.00	—
Choco	1.07	0.12, 10.2
etnia_cat			0.8
Indigena	1.00	—
Afrocolombiano	1.92	0.19, 20.8
Otro	0.99	0.33, 2.82
estrategia_toma_cat			0.6
Campaña	1.00	—
Tamizaje rutinario	0.76	0.26, 2.20
regimen_agr_cat			0.4
Contributivo/otro	1.00	—
Subsidiado	0.69	0.26, 1.74
ult_tamizaje_agr_cat			0.7
<= 24 meses	1.00	—
25-36 meses	1.44	0.21, 8.80
>36 meses	2.07	0.26, 15.6
area_residencia_cat			0.5
Urbano	1.00	—
Rural	0.69	0.26, 1.93
ngestaciones_cat			0.065
<=3	1.00	—
>3	0.38	0.14, 1.06
Abbreviations: CI = Confidence Interval, OR = Odds Ratio

Test indpendencia

#asistencia al tratamiento
independence_test(
  asistio_tratamiento ~ metodo_int_treat_cat  + departamento_cat + estrategia_toma_cat +
    lugar_de_residencia_cat,
  data = BASE_AUTOTOMA_clean,
  distribution = approximate(B = 10000)
)

## 
##  Approximative General Independence Test
## 
## data:  asistio_tratamiento by
##   metodo_int_treat_cat, departamento_cat, estrategia_toma_cat, lugar_de_residencia_cat
## maxT = 1.1658, p-value = 0.7645
## alternative hypothesis: two.sided

independence_test(
  asiste_seguimiento ~ metodo_int_treat_cat  + departamento_cat + estrategia_toma_cat +
    lugar_de_residencia_cat,
  data = BASE_AUTOTOMA_clean,
  distribution = approximate(B = 10000)
)

## 
##  Approximative General Independence Test
## 
## data:  asiste_seguimiento by
##   metodo_int_treat_cat, departamento_cat, estrategia_toma_cat, lugar_de_residencia_cat
## maxT = 1.2877, p-value = 0.5947
## alternative hypothesis: two.sided

Tazas vph

Nicolas Martínez Ramos

2026-01-23

Piloto_VPH

Test general de independencia colpo_compliance

Constraste

Test general de independencia short compliance

Contraste

PR shortcompliance

Ajustando por el resto de variables

PR colpo_compliance

Ajustando por el resto de variables

Proyecto de autotoma

Estratificaicón tabla Asistencia al tratamiento

Cochran-Mantel-Haenszel

Tabla estartificada seguimiento

### Cochran-Mantel-Haenszel

Filtrando la base de datos

Cochran-Mantel-Haenszel

Mantel-Haenszel

Modelos multivariados

Asistencia tratamiento

Asistencia al seguimiento

Test indpendencia