Meta-Analysis Example

# load data from google spreadsheet
library(RCurl)
library(bitops)
library(metafor)
library(Formula)
my_data <- read.csv("~/Desktop/Dropbox/DrSc UABC/Colaborations/Juan Quispe/Basilar Artery/basilarArteryDataCollector/R_meta_analysis_example_data - Sheet1.csv", dec=",")
my_data

Calculating effect sizes

my_data <- escalc(n1i = n_controls, n2i = n_patients, m1i = mean_controls, m2i = mean_patients, 
    sd1i = sd_controls, sd2i = sd_patients, data = my_data, measure = "SMD", 
    append = TRUE)

Calculating random-effects meta-analysis

ma_model_1 <- rma(yi, vi, data = my_data)
summary(ma_model_1)

Random-Effects Model (k = 12; tau^2 estimator: REML)

  logLik  deviance       AIC       BIC      AICc 
-24.4650   48.9300   52.9300   53.7258   54.4300   

tau^2 (estimated amount of total heterogeneity): 4.8657 (SE = 2.1341)
tau (square root of estimated tau^2 value):      2.2058
I^2 (total heterogeneity / total variability):   98.76%
H^2 (total variability / sampling variability):  80.64

Test for Heterogeneity:
Q(df = 11) = 604.6327, p-val < .0001

Model Results:

estimate      se    zval    pval   ci.lb   ci.ub 
  1.4446  0.6459  2.2366  0.0253  0.1787  2.7105  * 

---
Signif. codes:  0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1

A summary effect size of **1.4446 represents de differences between patients and controls. With it being statistically significant with p = 0.0253.

Forest-plot of results

forest(ma_model_1, slab = paste(my_data$study, as.character(my_data$year), sep = ", "))

Examples of Forest-Plot Visualizations

Using databases available in the R package ‘metaviz’.

Database Mozart:

metaviz::mozart

Variation I

library(metaviz)
viz_forest(x = mozart[1:10, c("d", "se")], study_labels = mozart[1:10, c("study_name")],
           summary_label = "Summary effect", xlab = "Cohen d")

Variation II

viz_forest(x = mozart[1:10, c("d", "se")], study_labels = mozart[1:10, c("study_name")],
           summary_label = "Summary effect", xlab = "Cohen d", variant = "thick", method = "FE")

Subgroup Analysis

viz_forest(x = mozart[1:10, c("d", "se")], 
           group = mozart[1:10, "rr_lab"], 
           study_labels = mozart[1:10, "study_name"], 
           summary_label = c("Summary (rr_lab = no)", "Summary (rr_lab = yes)"), 
           xlab = "Cohen d",
           col = "Darkblue")

           #variant = "thick")

Tables and Subgroups in one Visualization

study_table <- data.frame(
  name = exrehab[, "study_name"],
  eventsT = paste(exrehab$ai, "/", exrehab$ai + exrehab$bi, sep = ""),
  eventsC = paste(exrehab$ci, "/", exrehab$ci + exrehab$di, sep = ""))
summary_table <- data.frame(
    name = "Summary",
    eventsT = paste(sum(exrehab$ai), "/", sum(exrehab$ai + exrehab$bi), sep = ""),
    eventsC = paste(sum(exrehab$ci), "/", sum(exrehab$ci + exrehab$di), sep = ""))
viz_forest(x = exrehab[, c("logrr", "logrr_se")], variant = "classic",
           col = "Greys", xlab = "logRR", annotate_CI = T,
           study_table = study_table,
           summary_table = summary_table,
           table_headers = c("ID", "Events (T)", "Events (C)"))