search for: resid2

Hi R-users, My question is more methodological one, rather than technical. I have to samples representing residuals based on two measurements techniques (resid1,resid2; n=69). I need to compare two samples, to reject one technique (the worse one), and to keep the one which gave lower residuals (better one). What to look for? What should I analyse? Means, variance, std. deviations? Based on preliminary EDA: mean_resid1 < mean_resid2 #I would reject resid2...

...ngth of my initial values is not the same as the parameter. Can somebody guide me where my mistake is. Thanks, Elisa. ################################# #### OLS ESTIMATION fit1 <- lm(Y1 ~ Xi) fit2 <- lm(Y2 ~ Xi) fit3 <- lm(Y3~ Xi) resid1 <- Y1-as.matrix(cbind( 1,Xi))%*%fit1$coef resid2 <- Y2-as.matrix(cbind( 1,Xi))%*%fit2$coef resid3 <- Y3-as.matrix(cbind( 1,Xi))%*%fit3$coef sigma1<-sum(resid1*resid1)/nrow(Xi) sigma2<-sum(resid2*resid2)/nrow(Xi) sigma3<-sum(resid3*resid3)/nrow(Xi) rho12<- cor(resid1, resid2) rho13<- cor(resid1, resid3) rho23<- cor(resid2,...

...to the R-help mailing list; many people that read this list are interested in nonlinear regression problems, and will be eager to offer their insights. Regarding combination of two residual functions: using finite difference derivatives, it is straightforward. You define a new residual function, resid2, that evaluates both old residual functions, and returns their scaled sums. So if you had foo1(par1, ...) and foo2(par2, ...) you define resid2 <- function(c(par1,par2), ...) { sse1 <- foo1(par1, ...) sse2 <- foo2(par2, ...) return(sse1 * w1 + sse2 * w2) } w1 and w2 are we...