R^2 Spectrum

April 21, 2012
By

(This article was first published on NIR-Quimiometría, and kindly contributed to R-bloggers)

We have seen in the previous post, how to calculate the correlation spectrum, but other simple way to show  how the bands correlate to the constituent of interest is to calculate R^2. This way we remove the negative part of the correlation spectrum.
Xmsc<-NIR_msc
Ymoi<-demo_raw\$Moisture
cor_spec<-cor(Ymoi,Xmsc[,1:700])
rsq_spec<-(cor(Ymoi,Xmsc[,1:700]))^2
cov_spec<-cov(Ymoi,Xmsc[,1:700])*50
matplot(wave_nir,t(cor_spec),lty=1,pch=”*”,xlab=”nm”,ylab=”log(1/R)”)
matplot(wave_nir,t(rsq_spec),lty=1,pch=”*”,xlab=”nm”,ylab=”log(1/R)”)
matplot(wave_nir,t(cov_spec),lty=1,pch=”*”,xlab=”nm”,ylab=”log(1/R)”)
#We merge the R /R^2/Cov spectrum with the sample spectra treated with MSC.
cor_spec<-rbind(cor_spec,NIR_msc)
rsq_spec<-rbind(rsq_spec,NIR_msc)
cov_spec<-rbind(cov_spec,NIR_msc)
matplot(wave_nir,t(cor_spec),lty=1,pch=”*”,xlab=”nm”,ylab=”log(1/R)”)
matplot(wave_nir,t(rsq_spec),lty=1,pch=”*”,xlab=”nm”,ylab=”log(1/R)”)
matplot(wave_nir,t(cov_spec),lty=1,pch=”*”,xlab=”nm”,ylab=”log(1/R)”)
In order to see better the Covariance Spectrum, I multiplied by a factor,We can see how the covariance spectrum gives sharp bands an gives us a better idea where the variation due to moisture is.

R-bloggers.com offers daily e-mail updates about R news and tutorials on topics such as: Data science, Big Data, R jobs, visualization (ggplot2, Boxplots, maps, animation), programming (RStudio, Sweave, LaTeX, SQL, Eclipse, git, hadoop, Web Scraping) statistics (regression, PCA, time series, trading) and more...

Tags: