Re: [R] missing value with sign observed

From: Ben Bolker <>
Date: Sat, 05 Apr 2008 21:33:26 +0000 (UTC)

kate <yhsu6 <at>> writes:


> When I read this txt file into R and attach this data, I found the output of y
is as the follows
> [1] 8 5 3 + -1 +
> Levels: -1 + 3 5 8
> Could I get rid of Levels in the output? Because I need to use the observed y
and x run regression first and then
> assign the value to the missing y later.

  You probably want to use the argument na.strings="+" in your input command (scan or read.table) -- R is interpreting the existence of a non-numeric value in your input as evidence that you want that variable to be a factor (a categorical, non-numeric variable).

  Ben Bolker mailing list PLEASE do read the posting guide and provide commented, minimal, self-contained, reproducible code. Received on Sat 05 Apr 2008 - 21:36:02 GMT

Archive maintained by Robert King, hosted by the discipline of statistics at the University of Newcastle, Australia.
Archive generated by hypermail 2.2.0, at Sat 05 Apr 2008 - 22:30:26 GMT.

Mailing list information is available at Please read the posting guide before posting to the list.

list of date sections of archive