Error in Performing Forward Selection in R

Asked Oct 14 '21 at 08:53

Active Oct 14 '21 at 09:24

Viewed 86 times

I am trying to perform forward selection for my data frame which I encountered some issues which I think there may be alternatives for it.

I will first show you my code on it:

#library(tidyverse)
library(caret)
library(leaps)
library(MASS)

XBC <- read.csv("path/to/my/file/file.csv")

XBC <- XBC[ -c(1:3) ]
full.model <- lm(Treatment~., data = XBC)
# Stepwise regression model
step.model <- step(full.model, direction = "forward", scope = formula(full.model))

This is the error I kept receiving:

full.model <- lm(Treatment~., data = XBC)

Error in lm.fit(x, y, offset = offset, singular.ok = singular.ok, ...) : NA/NaN/Inf in 'y' In addition: Warning message: In storage.mode(v) <- "double" : NAs introduced by coercion

As I know the reason why this error occurs was because the data in the column Treatment are characters which are the different treatment groups that I have.

Is there any alternative for me to do a forward selection for this Treatment group that I have as they are characters.

Link to dataframe

edited Oct 14 '21 at 09:24

UseR10085

7,120
3
24
54

asked Oct 14 '21 at 08:53

Calvin Chow

Can you make your question reproducible by providing the data you are using? Visit [How to make a great R reproducible example](https://stackoverflow.com/questions/5963269/how-to-make-a-great-r-reproducible-example). – UseR10085 Oct 14 '21 at 09:10
Hi, i have added the link to the dataframe i am using – Calvin Chow Oct 14 '21 at 09:13
Are you sure you want a linear regression model for your data? `lm` needs the y to be numeric. You can see it from `?lm` in R. – UseR10085 Oct 14 '21 at 09:26
yeah i need it. is there any alternatives other than lm? – Calvin Chow Oct 14 '21 at 09:29
or could i solve it my differentiating my Treatment groups into numbers? – Calvin Chow Oct 14 '21 at 09:34
That depends on your objective – UseR10085 Oct 14 '21 at 09:39

Error in Performing Forward Selection in R

0 Answers0