我们仅仅是代码的编辑者、整合者、搬运工,仅免费传授方法,下文数据和代码取自于网络和免费软件“R语言说明书”,如果您觉得我们侵犯了您的版权,请通知我们撤稿。请大家谅解,谢谢!
#第一部分 gemtc实现事件-人年数据的网状meta分析###########
#1清除环境变量并设置路径####
rm(list=ls())
getwd()
setwd("F:/HRmodels_0005binary_事件人年和事件人样本量gemtc")
#2调用软件包####
library(coda)
library(gemtc)
library(lattice)
library(rjags)
library(R2OpenBUGS)
#3Create a new network by specifying all information####
treatments <- read.table(textConnection('
id description
A "Treatment A"
B "Treatment B"
C "Treatment C"'), header=TRUE)
data <- read.table(textConnection('
study treatment responders exposure
01 A 2 150.3
01 B 5 100.4
02 B 6 115.4
02 C 1 112.7
03 A 3 60.4
03 C 4 80.3
03 B 7 80.2'), header=TRUE)
#查看一下数据
View(data)
#4构建网络治疗方案可以是A,也可以是B,也可以是C#####
network <- mtc.network(data, description="BinaryforHRExample", treatments=treatments)
#5作图--作网状证据图
#构建网络治疗方案可以是A,也可以是B,也可以是C#####
plot(network)
#6拟合一致性模型ok
model <-mtc.model(network, type="consistency", factor = 2.5, n.chain=4,likelihood="poisson",link="log",linearModel="random")
#7拟合一致性模型的结果ok
results <- mtc.run(model, n.adapt = 5000, n.iter = 20000, thin = 1,sampler ="rjags")
#8拟合一致性模型的结果的相对效应森林图
forest(relative.effect(results, "A"))
forest(relative.effect(results, "B"))
forest(relative.effect(results, "C"))
# 9相对比较联赛图
tbl <- relative.effect.table(results)
print(tbl)
# 纵坐标vs横坐标
# 10Plot effect relative to treatment "C"
forest(tbl, "C")
# 11以前与上一章雷同,请有兴趣的同学试验一下
#第二部分 gemtc实现事件-样本量数据的网状meta分析###########
# Gemtc安装包实现以HR为效应值的网络meta分析的命令(事件-样本量)
#1####
rm(list=ls())
getwd()
setwd("F:/HRmodels_0005binary_事件人年和事件人样本量gemtc")
#2####
library(coda)
library(gemtc)
library(lattice)
library(rjags)
library(R2OpenBUGS)
#3####
# Create a new network by specifying all information.
treatments <- read.table(textConnection('
id description
A "Treatment A"
B "Treatment B"
C "Treatment C"'), header=TRUE)
data <- read.table(textConnection('
study treatment responders sampleSize
01 A 2 100
01 B 5 100
02 B 6 110
02 C 1 110
03 A 3 60
03 C 4 80
03 B 7 80'), header=TRUE)
network <- mtc.network(data, description="BinaryforHRExample", treatments=treatments)
plot(network)
# 拟合二项式分布函数likelihood,连接功能式cloglog,线性模型是random
model <-mtc.model(network, type="consistency", factor = 2.5, n.chain=4,likelihood="binom",link="cloglog",linearModel="random")
results <- mtc.run(model, n.adapt = 5000, n.iter = 20000, thin = 1,sampler ="rjags")
forest(relative.effect(results, "A"))
forest(relative.effect(results, "B"))
forest(relative.effect(results, "C"))
summary(relative.effect(results, "A"))
summary(relative.effect(results, "B", c("A", "C")))
#以下请参考上一章和上一节内容哦
拓展知识:
SNPmeta
网状emta分析必备技能
网状meta分析必备技能6_R+Rstudio运用meta包做简单meta分析
网状meta分析必备技能7_使用R、GeMTC和STATA软件实现连续变量的网状Meta分析
网状meta分析stata简易教程
NMA(网状meta分析)stata简易教程(4)漏斗图的制作
NMA(网状meta分析)stata简易教程(5)排序图的制作
诊断性meta分析简单实现
其他
本文由 GCBI学院 作者:其明技术专家 发表,转载请注明来源!