r - predict.lm() in a loop. warning: prediction from a rank-deficient fit may be misleading -



r - predict.lm() in a loop. warning: prediction from a rank-deficient fit may be misleading -

#r code # fit regression model each cluster y <- list() length(y) <- k vars <- list() length(vars) <- k f <- list() length(f) <- k (i in 1:k) { vars[[i]] <- names(corc[[i]][corc[[i]]!= "1"]) f[[i]] <- as.formula(paste("death ~", paste(vars[[i]], collapse= "+"))) y[[i]] <- lm(f[[i]], data=c1[[i]]) #training set c1[[i]] <- cbind(c1[[i]], fitted(y[[i]])) c2[[i]] <- cbind(c2[[i]], predict(y[[i]], c2[[i]])) #test set }

hello,

i have training info set (c1) , test info set (c2). each 1 has 129 variables. did k means cluster analysis on c1 , split info set based on cluster membership , created list of different clusters (c1[[1]], c1[[2]], ..., c1[[k]]). assigned cluster membership each case in c2 , created c2[[1]],..., c2[[k]]. fit linear regression each cluster in c1. dependant variable "death". predictors different in each cluster , vars[[i]] (i=1,...,k) shows list of predictors' name. want predict death each case in test info set (c2[[1]],..., c2[[k]). when run next code, of clusters got error: in predict.lm(y[[i]], c2[[i]]) : prediction rank-deficient fit may misleading

i read alot warning couldn't figure out issue is. appreciate if perchance assist me this.

thanks, mahsa

you can inspect predict function body(predict.lm). there see line:

if (p < ncol(x) && !(missing(newdata) || is.null(newdata))) warning("prediction rank-deficient fit may misleading")

this warning checks if rank of info matrix @ to the lowest degree equal number of parameters want fit. 1 way invoke having collinear covariates:

data <- data.frame(y=c(1,2,3,4), x1=c(1,1,2,3), x2=c(3,4,5,2), x3=c(4,2,6,0), x4=c(2,1,3,0)) data2 <- data.frame(x1=c(3,2,1,3), x2=c(3,2,1,4), x3=c(3,4,5,1), x4=c(0,0,2,3)) fit <- lm(y ~ ., data=data) predict(fit, data2) 1 2 3 4 4.076087 2.826087 1.576087 4.065217 warning message: in predict.lm(fit, data2) : prediction rank-deficient fit may misleading

notice x3 , x4 have same direction in data. 1 multiple of other. can checked length(fit$coefficients) > fit$rank

another way having more parameters available variables:

fit2 <- lm(y ~ x1*x2*x3*x4, data=data) predict(fit2, data2) warning message: in predict.lm(fit2, data2) : prediction rank-deficient fit may misleading

r

Comments

Post a Comment

Popular posts from this blog

c - Compilation of a code: unkown type name string -

c - Compilation of a code: unkown type name string - i have next lines of code compiler says following: "unknown type name 'string'" both in declaration , definition of function. can tell me what's wrong? thanks. #include <stdio.h> #include <stdlib.h> #include <string.h> void frecognizeclient(string *actualclient) there no string type in c. need utilize array so: char array[10]; then can pass in function: void frecognizeclient(char *actualclient); c arrays string compilation
Read more

java - Bypassing "final local variable defined in an enclosing type" -

java - Bypassing "final local variable defined in an enclosing type" - i'm writing programme , i'm getting "the final local variable asd cannot assigned, since it's defined in enclosing type". i provide illustration not code produces error aswell. have arraylist utilize later (if define within button can't utilize later on), outside of button, pressing button should give values arraylist. in illustration "create new arraylist" cause same problem. button btn = new button("asd"); final arraylist asd = new arraylist(); btn.setonaction(new eventhandler<actionevent>() { public void handle(final actionevent event) { asd = new arraylist(); //here's error.. } }); clear arraylist , add together values. java javafx
Read more

json - Hibernate and Jackson (java.lang.IllegalStateException: Cannot call sendError() after the response has been committed) -

json - Hibernate and Jackson (java.lang.IllegalStateException: Cannot call sendError() after the response has been committed) - hello have problem hibernate , jackson. have 2 pojos @entity @table(name = "users") public class user implements serializable { static final long serialversionuid = 4235637833262722256l; @id @generatedvalue private int id; @column(name = "creation_date") private date creationdate; @column(name = "first_name") private string firstname; @column(name = "last_name") private string lastname; @version @column(name = "version") private int version; @column(name = "e_mail") private string email; @column(name = "enabled") private boolean enabled; @column(name = "login") private string login; @column(name = "password") private string password; @jsonmanagedreference("role") @onetomany(mappedby = "user", cascade = cascadetype.all,fetch = fetchtyp...
Read more