Obtener la data

Analisis de divorsio

if(!require(RColorBrewer)) install.packages('RColorBrewer')

## Loading required package: RColorBrewer

require(RColorBrewer)

if(!require(dplyr)) install.packages('dplyr')

## Loading required package: dplyr

## Warning: package 'dplyr' was built under R version 4.2.3

## 
## 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

require(dplyr)

if(!require(ggplot2)) install.packages('ggplot2')

## Loading required package: ggplot2

## Warning: package 'ggplot2' was built under R version 4.2.3

require(ggplot2)

## lectura de datos
d <- read.csv("https://www.dropbox.com/s/a77erydd1ip6lnr/divorce.csv?dl=1", 
                header = TRUE, sep = ',')

Tabla de datos

#knitr::kable(d)

1. Individuos participaron en el estudio y cuántos se divorciaron.

total_participants <- nrow(d)

divorced_cases <- d %>% filter(class == 1)

total_divorced <- nrow(divorced_cases)

# Imprimir los resultados
cat("Total de participantes en el estudio:", total_participants, "\n")

## Total de participantes en el estudio: 170

cat("Total de individuos que se divorciaron:", total_divorced, "\n")

## Total de individuos que se divorciaron: 84

2. Determinar patrón dif entre quienes se divorcia y no

2.1 Calculo de frecuencia

preguntas <- paste0("x", 1:54)

frecuencias <- d %>%
  group_by(class) %>%
  summarise(across(all_of(preguntas), ~ mean(.))) %>%
  mutate(across(all_of(preguntas), ~ . / sum(.)))

2.1.1 Tabla de frecuencias

knitr::kable(frecuencias)

class	x1	x2	x3	x4	x5	x6	x7	x8	x9	x10	x11	x12	x13	x14	x15	x16	x17	x18	x19	x20	x21	x22	x23	x24	x25	x26	x27	x28	x29	x30	x31	x32	x33	x34	x35	x36	x37	x38	x39	x40	x41	x42	x43	x44	x45	x46	x47	x48	x49	x50	x51	x52	x53	x54
0	0.1102532	0.1395001	0.1798365	0.0893369	0.0335791	0.2475594	0.0116311	0.0435438	0.0197017	0.1279485	0.0579357	0.1185161	0.1634241	0.091655	0.073292	0.0545505	0.0522042	0.0303085	0.0420526	0.0236442	0.0538727	0.0276619	0.0285077	0.0875952	0.102508	0.0657338	0.0534194	0.0308208	0.0307861	0.0654746	0.1957155	0.176553	0.0796903	0.1456542	0.030976	0.0107362	0.1491026	0.0929341	0.1352524	0.0553603	0.1184645	0.2328278	0.3597797	0.136595	0.3344549	0.3815291	0.2725123	0.372168	0.2669749	0.2833333	0.3249833	0.3103618	0.2631288	0.1691814
1	0.8897468	0.8604999	0.8201635	0.9106631	0.9664209	0.7524406	0.9883689	0.9564562	0.9802983	0.8720515	0.9420643	0.8814839	0.8365759	0.908345	0.926708	0.9454495	0.9477958	0.9696915	0.9579474	0.9763558	0.9461273	0.9723381	0.9714923	0.9124048	0.897492	0.9342662	0.9465806	0.9691792	0.9692139	0.9345254	0.8042845	0.823447	0.9203097	0.8543458	0.969024	0.9892638	0.8508974	0.9070659	0.8647476	0.9446397	0.8815355	0.7671722	0.6402203	0.863405	0.6655451	0.6184709	0.7274877	0.627832	0.7330251	0.7166667	0.6750167	0.6896382	0.7368712	0.8308186

2.2 Grafico de frecuencias por Class

ggplot(data = frecuencias) +
  geom_bar(aes(x = "", y = x1, fill = factor(class)), stat = "identity", position = "fill") +
  geom_bar(aes(x = "", y = x2, fill = factor(class)), stat = "identity", position = "fill") +
  # Repetir la línea anterior para todas las columnas x3, x4, ... x54 ...
  scale_fill_manual(values = c("#66A61E", "#7570B3")) +
  labs(x = NULL, y = "Frecuencia Relativa", fill = "Estado") +
  ggtitle("Frecuencia de Respuestas por Grupo (Divorciados vs. No Divorciados)") +
  theme_minimal() +
  theme(legend.position = "bottom") +
  theme(axis.text.x = element_blank())

3. Prueba de independencia de chi-cuadrado

results <- lapply(paste0("x", 1:54), function(variable) {
  contingency_table <- table(d$class, d[[variable]])
  chi_squared_test <- chisq.test(contingency_table)
  
  data.frame(
    variable = variable,
    statistic = chi_squared_test$statistic,
    p_value = chi_squared_test$p.value
  )
})

# Combinar los resultados en un data frame
results_df <- do.call(rbind, results)

# Ordenar los resultados por valor p
results_df <- results_df %>% arrange(p_value)

Resultados Chi cuadrado

knitr::kable(results_df)

	variable	statistic	p_value
X-squared17	x18	159.64920	0e+00
X-squared19	x20	156.44751	0e+00
X-squared39	x40	156.36136	0e+00
X-squared16	x17	155.78616	0e+00
X-squared18	x19	155.36940	0e+00
X-squared10	x11	155.06539	0e+00
X-squared8	x9	152.71189	0e+00
X-squared15	x16	151.50748	0e+00
X-squared25	x26	148.29700	0e+00
X-squared14	x15	146.48549	0e+00
X-squared28	x29	146.13345	0e+00
X-squared29	x30	145.76120	0e+00
X-squared38	x39	145.42385	0e+00
X-squared11	x12	145.32969	0e+00
X-squared24	x25	144.05990	0e+00
X-squared13	x14	143.99941	0e+00
X-squared35	x36	143.13264	0e+00
X-squared4	x5	142.43521	0e+00
X-squared40	x41	140.95076	0e+00
X-squared26	x27	140.38263	0e+00
X-squared27	x28	139.28987	0e+00
X-squared7	x8	139.14776	0e+00
X-squared3	x4	139.05667	0e+00
X-squared20	x21	139.04247	0e+00
X-squared37	x38	138.22477	0e+00
X-squared36	x37	135.40063	0e+00
X-squared	x1	133.63965	0e+00
X-squared43	x44	133.47049	0e+00
X-squared12	x13	132.90903	0e+00
X-squared21	x22	131.32444	0e+00
X-squared34	x35	131.03231	0e+00
X-squared9	x10	131.00120	0e+00
X-squared23	x24	128.97937	0e+00
X-squared32	x33	128.67471	0e+00
X-squared1	x2	127.47975	0e+00
X-squared30	x31	124.86215	0e+00
X-squared22	x23	124.73659	0e+00
X-squared33	x34	124.44454	0e+00
X-squared31	x32	122.64678	0e+00
X-squared53	x54	118.27635	0e+00
X-squared2	x3	116.20221	0e+00
X-squared49	x50	108.99300	0e+00
X-squared41	x42	100.92593	0e+00
X-squared50	x51	97.04007	0e+00
X-squared48	x49	95.47681	0e+00
X-squared52	x53	88.93651	0e+00
X-squared6	x7	79.59150	0e+00
X-squared47	x48	76.43169	0e+00
X-squared46	x47	74.97654	0e+00
X-squared51	x52	74.86155	0e+00
X-squared42	x43	64.37419	0e+00
X-squared44	x45	55.12227	0e+00
X-squared5	x6	41.25243	0e+00
X-squared45	x46	37.22272	2e-07

Variable mas asociada

chi cuadrado o valor P mas bajo

variable_mas_asociada <- results_df$variable[1]
print("Variable más asociada:")

## [1] "Variable más asociada:"

print(variable_mas_asociada)

## [1] "x18"

4. Grafico prueba de independencia de chi-cuadrado

ggplot(results_df, aes(x = reorder(variable, p_value), y = p_value)) +
  geom_bar(stat = "identity", fill = "#1B9E77", width = 0.5) +
  labs(x = "Variable", y = "Valor p", title = "Asociacion entre Variables y Clase") +
  theme_minimal() +
  theme(axis.text.x = element_text(angle = 45, hjust = 1, size = 8),
        axis.text.y = element_text(size = 8),
        axis.title = element_text(size = 10),
        plot.title = element_text(size = 12, face = "bold"),
        legend.position = "none")

Homework #1

Jose_Montalvo

8/9/2023

Obtener la data

Tabla de datos

1. Individuos participaron en el estudio y cuántos se divorciaron.

2. Determinar patrón dif entre quienes se divorcia y no

2.1 Calculo de frecuencia

2.1.1 Tabla de frecuencias

2.2 Grafico de frecuencias por Class

3. Prueba de independencia de chi-cuadrado

Resultados Chi cuadrado

Variable mas asociada

4. Grafico prueba de independencia de chi-cuadrado