R語言是怎么做方差分解的

datatotal<-read.table("datasetmultifunctionality.txt", header=T, sep="\t")
colnames(datatotal)

有的是常規(guī)的標準化

有的是log轉化

常規(guī)的標準化開頭提到的推文里介紹了方差分解必須用標準化后的數(shù)據(jù)，但是有的log轉化是什么意思呢？

#####logtransformation moments
datatotal[,c(12,13,16,17)]<-log(datatotal[,c(12,13,16,17)])
datatotal[,14]<-log(datatotal[,14]-min(datatotal[,14])+1)
datatotal[,15]<-log(datatotal[,15]-min(datatotal[,15])+1)
datatotal[,18]<-log(datatotal[,18]-min(datatotal[,18])+1)
datatotal[,19]<-log(datatotal[,19]-min(datatotal[,19])+1)

#####Zscorring environmental variables
datatotal$ELEVATION<-(datatotal$ELEVATION-mean(datatotal$ELEVATION))/sd(datatotal$ELEVATION)
datatotal$LAT<-(datatotal$LAT-mean(datatotal$LAT))/sd(datatotal$LAT)
datatotal$SINLONG<-(datatotal$SINLONG-mean(datatotal$SINLONG))/sd(datatotal$SINLONG)
datatotal$COSLONG<-(datatotal$COSLONG-mean(datatotal$COSLONG))/sd(datatotal$COSLONG)
datatotal$SLO<-(datatotal$SLO-mean(datatotal$SLO))/sd(datatotal$SLO)
datatotal$ARIDITY<-(datatotal$ARIDITY-mean(datatotal$ARIDITY))/sd(datatotal$ARIDITY)
datatotal$SAND<-(datatotal$SAND-mean(datatotal$SAND))/sd(datatotal$SAND)
datatotal$PH<-(datatotal$PH-mean(datatotal$PH))/sd(datatotal$PH)
datatotal$SR<-(datatotal$SR-mean(datatotal$SR))/sd(datatotal$SR)

#####Zscorring moments
datatotal$CWM_logH<-(datatotal$CWM_logH-mean(datatotal$CWM_logH))/sd(datatotal$CWM_logH)
datatotal$CWV_logH<-(datatotal$CWV_logH-mean(datatotal$CWV_logH))/sd(datatotal$CWV_logH)
datatotal$CWS_logH<-(datatotal$CWS_logH-mean(datatotal$CWS_logH))/sd(datatotal$CWS_logH)
datatotal$CWK_logH<-(datatotal$CWK_logH-mean(datatotal$CWK_logH))/sd(datatotal$CWK_logH)
datatotal$CWM_logSLA<-(datatotal$CWM_logSLA-mean(datatotal$CWM_logSLA))/sd(datatotal$CWM_logSLA)
datatotal$CWV_logSLA<-(datatotal$CWV_logSLA-mean(datatotal$CWV_logSLA))/sd(datatotal$CWV_logSLA)
datatotal$CWS_logSLA<-(datatotal$CWS_logSLA-mean(datatotal$CWS_logSLA))/sd(datatotal$CWS_logSLA)
datatotal$CWK_logSLA<-(datatotal$CWK_logSLA-mean(datatotal$CWK_logSLA))/sd(datatotal$CWK_logSLA)

#####Zscorring ecosystem functions

datatotal$BGL<-(datatotal$BGL-mean(datatotal$BGL))/sd(datatotal$BGL)
datatotal$FOS<-(datatotal$FOS-mean(datatotal$FOS))/sd(datatotal$FOS)
datatotal$AMP<-(datatotal$AMP-mean(datatotal$AMP))/sd(datatotal$AMP)
datatotal$NTR<-(datatotal$NTR-mean(datatotal$NTR))/sd(datatotal$NTR)
datatotal$I.NDVI<-(datatotal$I.NDVI-mean(datatotal$I.NDVI))/sd(datatotal$I.NDVI)


#####Calculating indices of multifunctionality (M5: 5 functions)
colnames(datatotal)
M5<-rowMeans(datatotal[,c(20,21,22,23,24)])
datatotal<-cbind(datatotal,M5)


#####Log-transfromation of multifunctionality
logM5<-log(datatotal$M5-min(datatotal$M5)+1)
datatotal<-cbind(datatotal,logM5)

代碼是

library(MuMIn)
mod12<-lm(logM5 ~ LAT + SINLONG + COSLONG +   
            ARIDITY + SLO + SAND + PH + I(PH^2) + ELEVATION+
            CWM_logSLA + I(CWM_logSLA^2)+ CWV_logSLA + I(CWV_logSLA^2) +  CWS_logSLA + CWK_logSLA + I(CWK_logSLA^2) +
            CWM_logH + I(CWM_logH^2)+ CWV_logH + I(CWV_logH^2) +  CWS_logH + CWK_logH + I(CWK_logH^2) +
            SR
          , data=datatotal)
# 這一步要好長時間
dd12<-dredge(mod12, subset = ~ LAT & SINLONG & COSLONG & ARIDITY & SLO & SAND & PH &SR & ELEVATION &   
               dc(CWM_logSLA,I(CWM_logSLA^2)) & dc(CWV_logSLA,I(CWV_logSLA^2)) & dc(CWK_logSLA,I(CWK_logSLA^2)) 
             & dc(CWM_logH,I(CWM_logH^2)) & dc(CWV_logH,I(CWV_logH^2)) & dc(CWK_logH,I(CWK_logH^2)), 
             options(na.action = "na.fail"))

subset(dd12,delta<2)
de12<-model.avg(dd12, subset = delta < 2)
summary(de12)

這一步得到的數(shù)據(jù)就是論文中 的figure4a

 

下期推文介紹如何利用得到的數(shù)據(jù)畫圖

這里遇到的問題是：

• 1、 模型里有的變量會用     I()函數(shù)包起來，這個函數(shù)起到什么作用呢？
• 2、模型選擇那一步用到了     dc()函數(shù)，這個函數(shù)又起到什么作用呢？