search for: tempslope

Displaying 2 results from an estimated 2 matches for "tempslope".

Did you mean: tempscop
2012 May 31
1
fitting allometric equation using a for a power model
...ooks worse. Data and code below: temppow<-lm(log(y)~log(x)) plot(log(y)~log(x)) plot(residuals(temppow), main="pow") abline(temppow) plot(y~x, main="pow") tempsum<-summary(temppow)$adj.r.squared tempint<-summary(temppow)$coefficients[1,1] #intercept of power function tempslope<-summary(temppow)$coefficients[2,1] #slope of power function tempmin<-min(x) tempmax<-max(x) lngth<-c(tempmin:tempmax) # vector from the minimum to the maximum values of independent variable prediction<-exp(tempint)*((lngth)^tempslope)*exp((summary(temppow)$sigma^2)/2) # exp((summar...
2012 Jun 01
1
trouble with append() in a for loop
...y cross.val.error.temp<-numeric(0) b<-c(1:length(x)) for(i in b){ frame.val.temp<-data.frame(x,y) frame.val<-frame.val.temp[-i,] yt<-frame.val$y xt<-frame.val$x temppow.val<-lm(log(yt)~log(xt)) tempint.val<-summary(temppow.val)$coefficients[1,1] #intercept of power function tempslope.val<-summary(temppow.val)$coefficients[2,1] nls.model.val<-nls(yt~exp(intercept)*((xt)^slope), start=list(intercept=tempint.val, slope=tempslope.val)) prediction.cross.val<-((exp(intercept.nls))*((x[i])^slope.nls)) value.temp<-(prediction.cross.val-y[i])/y[i] cross.val.error<-append(...