[R] plotting residuals/error message
John Fox
jfox at mcmaster.ca
Sun Mar 16 14:50:30 CET 2014
Dear Jason,
Your suspicion is correct: the cases with NAs in either ft_dpc_r or pid_x
are absent from the residuals but not from pid_x.
There are several ways to deal with this problem, but one straightforward
way is to use na.exclude in place of the default na.omit in the call to lm,
as in lm(ft_dpc_r~pid_x, na.action=na.exclude). Then residuals() will pad
out the values it returns with NAs.
I hope this helps,
John
-----------------------------------------------
John Fox, Professor
McMaster University
Hamilton, Ontario, Canada
http://socserv.socsci.mcmaster.ca/jfox/
> -----Original Message-----
> From: r-help-bounces at r-project.org [mailto:r-help-bounces at r-
> project.org] On Behalf Of Gainous,Jason
> Sent: Saturday, March 15, 2014 1:42 PM
> To: r-help at r-project.org
> Subject: [R] plotting residuals/error message
>
> I am trying to plot the residuals from a linear model and I get the
> following error message: Error in xy.coords(x, y, xlabel, ylabel, log)
> : 'x' and 'y' lengths differ. The outcome is a continuous variable and
> the explanatory variable is ordinal. My immediate suspicion was that it
> had something to do with missing values. Each variable has missing
> values coded as NA. I can't figure it out. Please help. Thanks.
>
> > obama.mod = lm(ft_dpc_r~pid_x)
> > summary(obama.mod)
>
> Call:
> lm(formula = ft_dpc_r ~ pid_x)
>
> Residuals:
> Min 1Q Median 3Q Max
> -89.271 -14.783 0.729 10.729 84.193
>
> Coefficients:
> Estimate Std. Error t value Pr(>|t|)
> (Intercept) 101.5155 0.5797 175.12 <2e-16 ***
> pid_x -12.2441 0.1411 -86.76 <2e-16 ***
> ---
> Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
>
> Residual standard error: 22.85 on 5876 degrees of freedom
> (36 observations deleted due to missingness)
> Multiple R-squared: 0.5616, Adjusted R-squared: 0.5615
> F-statistic: 7528 on 1 and 5876 DF, p-value: < 2.2e-16
>
> > plot(pid_x, resid(obama.mod), ylab = "Model Residuals")
> Error in xy.coords(x, y, xlabel, ylabel, log) :
> 'x' and 'y' lengths differ
>
>
> Jason Gainous, Ph.D.
> Associate Professor
> Department of Political Science
> University of Louisville
> 203 Ford Hall
> Louisville, KY 40292
> (502) 852-1660
> Homepage: https://louisville.academia.edu/JasonGainous
>
>
> [[alternative HTML version deleted]]
>
> ______________________________________________
> R-help at r-project.org mailing list
> https://stat.ethz.ch/mailman/listinfo/r-help
> PLEASE do read the posting guide http://www.R-project.org/posting-
> guide.html
> and provide commented, minimal, self-contained, reproducible code.
More information about the R-help
mailing list