Tarea clinic Trat
Instrucciones
Con los datos que se importan a continuación, concluir si es el tipo tratamiento médico (T: A,B), o la clínica (Clinic: uno,dos) lo que explica el pronóstico (positivo, negativo).
packages
if(!require(googlesheets4)){install.packages("googlesheets4")}
if(!require(googledrive)){install.packages("googledrive")}
if(!require(ggplot2)){install.packages("ggplot2")}
if(!require(DescTools)){install.packages("DescTools")}
if(!require(MASS)){install.packages("MASS")}
if(!require(binom)){install.packages("binom")}
if(!require(scales)){install.packages("scales")}
##
library(googlesheets4)
library(googledrive)
library(ggplot2)
library(DescTools)
library(MASS)
library(binom)
library(scales)Table Treatment & Clinics
ss= "https://docs.google.com/spreadsheets/d/1RFCYi7rjRPcbzcB01Nq3jgtc_o21LaDU8yFU41gjQKs/edit?usp=sharing"
hoja= "clinicTrat"
rango = "B4:E8"
#
gs4_deauth()
trat <- read_sheet(ss,
sheet=hoja,
range=rango,
col_names=TRUE
)## Reading from "ClinicaxTratamiento"## Range "'clinicTrat'!B4:E8"trat$Clinic <- as.factor(trat$Clinic)
trat$T <- as.factor(trat$T)
#
trat$pr.exito <- trat$Posit /
(trat$Posit+trat$Negat) # Proporción de éxito (resultado positivo al tratamiento)
trat## # A tibble: 4 x 5
## Clinic T Posit Negat pr.exito
## <fct> <fct> <dbl> <dbl> <dbl>
## 1 dos A 4 16 0.2
## 2 dos B 22 32 0.407
## 3 uno A 8 32 0.2
## 4 uno B 12 8 0.6ggplot
ggplot( aes( x= T, y= pr.exito, fill = T), data= trat) +
geom_bar(stat="identity", position= "dodge")
ggplot( aes( x= Clinic, y= pr.exito), data= trat) +
geom_bar(stat="identity", position= "dodge")
p <- ggplot( aes( x= Clinic, y= pr.exito, fill = T), data= trat) +
geom_bar(stat="identity", position= "dodge")
p
Odds
trat$Odds.exito <- trat$Posit / trat$Negat
trat## # A tibble: 4 x 6
## Clinic T Posit Negat pr.exito Odds.exito
## <fct> <fct> <dbl> <dbl> <dbl> <dbl>
## 1 dos A 4 16 0.2 0.25
## 2 dos B 22 32 0.407 0.688
## 3 uno A 8 32 0.2 0.25
## 4 uno B 12 8 0.6 1.5glm
# Variable respuesta es binaria (dos columnas)
Y.trat <- cbind(trat$Posit, trat$Negat)
Y.trat## [,1] [,2]
## [1,] 4 16
## [2,] 22 32
## [3,] 8 32
## [4,] 12 8Modelo comparando clínicas
glm.clinic <- glm( Y.trat ~ trat$Clinic, family=binomial)
summary(glm.clinic)##
## Call:
## glm(formula = Y.trat ~ trat$Clinic, family = binomial)
##
## Deviance Residuals:
## 1 2 3 4
## -1.4844 0.8536 -1.8696 2.4359
##
## Coefficients:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) -0.61310 0.24351 -2.518 0.0118 *
## trat$Clinicuno -0.08004 0.36646 -0.218 0.8271
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for binomial family taken to be 1)
##
## Null deviance: 12.409 on 3 degrees of freedom
## Residual deviance: 12.361 on 2 degrees of freedom
## AIC: 30.97
##
## Number of Fisher Scoring iterations: 4Modelo comparando tratamientos médicos
glm.trat <- glm( Y.trat ~ trat$T, family=binomial)
summary(glm.trat)##
## Call:
## glm(formula = Y.trat ~ trat$T, family = binomial)
##
## Deviance Residuals:
## 1 2 3 4
## 0.0000 -0.7704 0.0000 1.2599
##
## Coefficients:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) -1.3863 0.3227 -4.295 1.74e-05 ***
## trat$TB 1.2238 0.3982 3.073 0.00212 **
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for binomial family taken to be 1)
##
## Null deviance: 12.409 on 3 degrees of freedom
## Residual deviance: 2.181 on 2 degrees of freedom
## AIC: 20.79
##
## Number of Fisher Scoring iterations: 3Modelo en busca de interacción: Clinic * T
glm <- glm( Y.trat ~ trat$T * trat$Clinic, family=binomial)
summary(glm)##
## Call:
## glm(formula = Y.trat ~ trat$T * trat$Clinic, family = binomial)
##
## Deviance Residuals:
## [1] 0 0 0 0
##
## Coefficients:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) -1.386e+00 5.590e-01 -2.480 0.0131 *
## trat$TB 1.012e+00 6.239e-01 1.622 0.1049
## trat$Clinicuno -5.861e-13 6.847e-01 0.000 1.0000
## trat$TB:trat$Clinicuno 7.802e-01 8.682e-01 0.899 0.3689
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for binomial family taken to be 1)
##
## Null deviance: 1.2409e+01 on 3 degrees of freedom
## Residual deviance: 8.8818e-15 on 0 degrees of freedom
## AIC: 22.609
##
## Number of Fisher Scoring iterations: 3Modelo aditivo: Clinic + T
##
## Call:
## glm(formula = Y.trat ~ trat$T + trat$Clinic, family = binomial)
##
## Deviance Residuals:
## 1 2 3 4
## 0.6023 -0.2762 -0.3845 0.4521
##
## Coefficients:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) -1.7352 0.4507 -3.850 0.000118 ***
## trat$TB 1.4369 0.4458 3.223 0.001268 **
## trat$Clinicuno 0.4987 0.4277 1.166 0.243581
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for binomial family taken to be 1)
##
## Null deviance: 12.40871 on 3 degrees of freedom
## Residual deviance: 0.79129 on 1 degrees of freedom
## AIC: 21.4
##
## Number of Fisher Scoring iterations: 4Refeencias
Agresti, A., & Coull, B. A. (1998). Approximate is better than “exact” for interval estimation of binomial proportions. The American Statistician, 52(2), 119–126.