[prev in list] [next in list] [prev in thread] [next in thread] 

List:       r-help
Subject:    [R] Extracting coefficients values with bootstrap
From:       baconbeach <baconbeach () gmail ! com>
Date:       2012-04-30 20:58:29
Message-ID: 1335819509002-4599356.post () n4 ! nabble ! com
[Download RAW message or body]

Hello fellow R users,

I am trying to extract the coefficient values during a bootstrap operation.

Here is the list of my variables that I would like to extract the
coefficient values from:

(Intercept)                              
LogRds_25k                                   
GeoRockbimodal volcanic rocks                 
GeoRockgranodiorite, quartz diorite         
GeoRockintermediate volcanic rocks           
GeoRockmafic intrusive rocks-diorite, gabbro 
GeoRockmafic volcanic rocks                  
GeoRocknonmarine sedimentary rocks   
GeoRockoffshelf miogeoclinal rocks   
GeoRocksedimentary and mafic volcanic rocks
GeoRockundivided sedimentary rocks  
GeoRockundivided volcanic rocks 

There is basically 1 variable (LogRds_25k) and 1 categorical variable
(GeoRock) with 10 categories.

Here is my script:

N = length (data_As[,1])
B = 10000
stor.r2 = rep(0,B)
stor.inter = rep(0,B)
stor.Rds = rep(0,B)
stor.Bimod  = rep(0,B)
stor.grano = rep(0,B)
stor.mafic_intru = rep(0,B)
stor.mafic_vol  = rep(0,B)
stor.nonmarine = rep(0,B)
stor.iffshelf = rep(0,B)
stor.sedi = rep(0,B)
stor.vol = rep(0,B)

for (i in 1:B){
idx = sample(1:N, replace=T)
newdata = data_As[idx,]

LogRds <- log(newdata$Rds_25k+1)
GeoRock <- factor(newdata$GeoRock)

data_As.boot = lm(newdata$Log_Level ~   
  
    LogRds + GeoRock )

stor.r2[i] = summary(data_As.boot)$r.squared
stor.inter[i] = summary(data_As.boot)$coefficients[1,1]
stor.Rds[i] = summary(data_As.boot)$coefficients[2,1]
stor.Bimod [i] = summary(data_As.boot)$coefficients[3,1]
stor.grano[i] = summary(data_As.boot)$coefficients[4,1]
stor.inter[i] = summary(data_As.boot)$coefficients[5,1]
stor.mafic_vol [i] = summary(data_As.boot)$coefficients[6,1]
stor.nonmarine[i] = summary(data_As.boot)$coefficients[7,1]
stor.iffshelf[i] = summary(data_As.boot)$coefficients[8,1]
stor.sedi[i] = summary(data_As.boot)$coefficients[9,1]
stor.vol[i] = summary(data_As.boot)$coefficients[10,1]
}

My problem is during the bootstrap operation with replacements, some samples
do not include all the categorical variables. The way my script is written,
I get an error message because I don't specify the coefficient names.

I don't know how to arrange my script, so it knows how to deal with missing
variables.

Can somebody help me with this issue?

Thank you very much

Steeve


--
View this message in context: \
http://r.789695.n4.nabble.com/Extracting-coefficients-values-with-bootstrap-tp4599356.html
 Sent from the R help mailing list archive at Nabble.com.

______________________________________________
R-help@r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.


[prev in list] [next in list] [prev in thread] [next in thread]