R Markdown

This is an R Markdown document. Markdown is a simple formatting syntax for authoring HTML, PDF, and MS Word documents. For more details on using R Markdown see http://rmarkdown.rstudio.com.

When you click the Knit button a document will be generated that includes both content as well as the output of any embedded R code chunks within the document. You can embed an R code chunk like this:

Meta analisis packages:

# install.packages("meta")
# install.packages("metafor")
# install.packages("foreign")

Libraries

library(meta);library(metafor);library(foreign)
## Loading 'meta' package (version 5.5-0).
## Type 'help(meta)' for a brief overview.
## Readers of 'Meta-Analysis with R (Use R!)' should install
## older version of 'meta' package: https://tinyurl.com/dt4y5drs
## Loading required package: Matrix
## Loading required package: metadat
## 
## Loading the 'metafor' package (version 3.4-0). For an
## introduction to the package please type: help(metafor)

Working directory

setwd("~/Dropbox/1 UNL/Tesis/Salome/")

Data

d <- read.csv("datos.1.08.2022.csv", sep=",")

Colnames

colnames(d)
##  [1] "Autor"                   "Titulo"                 
##  [3] "DOI"                     "Diseño.De.Estudio"      
##  [5] "Número.De.Participantes" "Población...años."      
##  [7] "Seroprevalencia"         "Prevalencia"            
##  [9] "Incidencia"              "Riesgo"                 
## [11] "Tasa.de.infección"       "Provincia"              
## [13] "Total"                   "Cases"                  
## [15] "Test"                    "X"                      
## [17] "País"                    "Resultado.Primario"     
## [19] "Conclusión"
d <- d[,c(1,13,14)]
d <- d[c(-5,-6,-7),]
d$Cases <- round(d$Cases,0)
d$Total <- as.numeric(d$Total)
d$Cases <- as.numeric(d$Cases)

Fist model (single Proportions)

meta_d <- metaprop(event = d$Cases,
                   n = d$Total, studlab=d$Autor)
meta_d
## Number of studies combined: k = 9
## Number of observations: o = 10338
## Number of events: e = 1908
## 
##                      proportion           95%-CI
## Common effect model      0.1846 [0.1772; 0.1922]
## Random effects model     0.1786 [0.1254; 0.2479]
## 
## Quantifying heterogeneity:
##  tau^2 = 0.3845; tau = 0.6201; I^2 = 97.8% [96.9%; 98.4%]; H = 6.67 [5.66; 7.85]
## 
## Test of heterogeneity:
##       Q d.f.  p-value             Test
##  355.61    8 < 0.0001        Wald-type
##  350.23    8 < 0.0001 Likelihood-Ratio
## 
## Details on meta-analytical method:
## - Random intercept logistic regression model
## - Maximum-likelihood estimator for tau^2
## - Logit transformation

Forest Plot

metafor::forest(meta_d,comb.random=TRUE,comb.fixed=FALSE)

summary(meta_d)
##                               proportion           95%-CI
## Ortiz-Prado et al. 2021           0.1586 [0.1033; 0.2284]
## Acurio-Páez et al 2020            0.1319 [0.1187; 0.1459]
## Ortiz-Prado et al. 2022           0.4030 [0.3438; 0.4644]
## Ortiz-Prado et al. 2021           0.2366 [0.2152; 0.2592]
## Ortiz-Prado et al. 2022           0.1227 [0.0766; 0.1831]
## Vallejo-Janeta et al. 2021        0.1265 [0.0960; 0.1626]
## Rodriguez-Paredes et al. 2021     0.1614 [0.1501; 0.1731]
## Del Brutto et al. 2020            0.0773 [0.0520; 0.1099]
## Boonsaeng et al. 2021             0.3400 [0.3114; 0.3695]
## 
## Number of studies combined: k = 9
## Number of observations: o = 10338
## Number of events: e = 1908
## 
##                      proportion           95%-CI
## Common effect model      0.1846 [0.1772; 0.1922]
## Random effects model     0.1786 [0.1254; 0.2479]
## 
## Quantifying heterogeneity:
##  tau^2 = 0.3845; tau = 0.6201; I^2 = 97.8% [96.9%; 98.4%]; H = 6.67 [5.66; 7.85]
## 
## Test of heterogeneity:
##       Q d.f.  p-value             Test
##  355.61    8 < 0.0001        Wald-type
##  350.23    8 < 0.0001 Likelihood-Ratio
## 
## Details on meta-analytical method:
## - Random intercept logistic regression model
## - Maximum-likelihood estimator for tau^2
## - Logit transformation
## - Clopper-Pearson confidence interval for individual studies
funnel(meta_d,comb.random=T,comb.fixed=F,studlab=F)

Second model Salomé investigar Method.bias

meta_d2 <- metaprop(event = d$Cases,
                   n = d$Total, studlab=d$Autor, method.bias = "Egger")
meta_d2
## Number of studies combined: k = 9
## Number of observations: o = 10338
## Number of events: e = 1908
## 
##                      proportion           95%-CI
## Common effect model      0.1846 [0.1772; 0.1922]
## Random effects model     0.1786 [0.1254; 0.2479]
## 
## Quantifying heterogeneity:
##  tau^2 = 0.3845; tau = 0.6201; I^2 = 97.8% [96.9%; 98.4%]; H = 6.67 [5.66; 7.85]
## 
## Test of heterogeneity:
##       Q d.f.  p-value             Test
##  355.61    8 < 0.0001        Wald-type
##  350.23    8 < 0.0001 Likelihood-Ratio
## 
## Details on meta-analytical method:
## - Random intercept logistic regression model
## - Maximum-likelihood estimator for tau^2
## - Logit transformation

Forest Plot

forest(meta_d2,comb.random=TRUE,comb.fixed=FALSE)

summary(meta_d2)
##                               proportion           95%-CI
## Ortiz-Prado et al. 2021           0.1586 [0.1033; 0.2284]
## Acurio-Páez et al 2020            0.1319 [0.1187; 0.1459]
## Ortiz-Prado et al. 2022           0.4030 [0.3438; 0.4644]
## Ortiz-Prado et al. 2021           0.2366 [0.2152; 0.2592]
## Ortiz-Prado et al. 2022           0.1227 [0.0766; 0.1831]
## Vallejo-Janeta et al. 2021        0.1265 [0.0960; 0.1626]
## Rodriguez-Paredes et al. 2021     0.1614 [0.1501; 0.1731]
## Del Brutto et al. 2020            0.0773 [0.0520; 0.1099]
## Boonsaeng et al. 2021             0.3400 [0.3114; 0.3695]
## 
## Number of studies combined: k = 9
## Number of observations: o = 10338
## Number of events: e = 1908
## 
##                      proportion           95%-CI
## Common effect model      0.1846 [0.1772; 0.1922]
## Random effects model     0.1786 [0.1254; 0.2479]
## 
## Quantifying heterogeneity:
##  tau^2 = 0.3845; tau = 0.6201; I^2 = 97.8% [96.9%; 98.4%]; H = 6.67 [5.66; 7.85]
## 
## Test of heterogeneity:
##       Q d.f.  p-value             Test
##  355.61    8 < 0.0001        Wald-type
##  350.23    8 < 0.0001 Likelihood-Ratio
## 
## Details on meta-analytical method:
## - Random intercept logistic regression model
## - Maximum-likelihood estimator for tau^2
## - Logit transformation
## - Clopper-Pearson confidence interval for individual studies
funnel(meta_d2,comb.random=T,comb.fixed=F,studlab=F)

Revisar capitulo 5 de este libro efecto de pequeños estudios (Libro del paquete meta) https://link.springer.com/book/10.1007/978-3-319-21416-0