Re: [R] NA confusion (length question)
Hi Jeffrey, As a bit of a side note, data copied in html emails tends to show up poorly (since emails to the list are converted to plain text). Anyways, note the difference between: length(mylm$residuals) length(residuals(mylm)) Accessing the residuals value from mylm is *not* quite the same as calling the residuals() function on mylm. So, if you use: cbind(residuals(mylm), mydata) you should be good. Hope that helps, Josh On Tue, Sep 14, 2010 at 6:20 AM, Stratford, Jeffrey jeffrey.stratf...@wilkes.edu wrote: Hi folks, I am running a very simple regression using mylm - lm(mass ~ tarsus, na.action=na.exclude) I would like the use the residuals from this analysis for more regression but I'm running into a snag when I try cbind(mylm$residuals, mydata) # where my data is the original data set The error tells me that it cannot use cbind because the length of mylm$residuals is 50 and mydata is 52. This makes sense except I thought that na.exclude preserves length by inserting NA in residuals where there were NA's in the orginal data ( i = 3, 20). When I ask to see the residuals( mylm$residuals) I see 52 numbers. How can this be? I am just looking to see how I can produce a third vector with length = 52 and NA's for i=3,20. I'm using R 2.11.1 on Windows XP and the data are below Many thanks, Jeff tarsus mass 21.5 23.2 21.8 22.6 20.9 NA 21.6 20.8 21.5 21.5 22 23.2 21.6 23 22.1 21 21.1 21 20.6 22.9 20.1 21.8 22.2 20.4 21.9 21.5 21.1 21.3 21.5 20.1 19.9 21.4 22.1 27.3 20.1 19.7 19.6 16.7 20.9 NA 20.1 21.7 21.8 22.3 20.9 21.1 21.6 20.8 22.4 20.5 21.4 20.4 21.4 21 21.6 21 21.2 23.3 21.1 21.9 22 21 22.2 21.5 20.6 20.6 21.3 20.5 20.6 20.5 21.4 20.8 21.8 21.4 21.6 19.6 22.4 24.3 21.7 20.3 21.4 21.3 20.7 18.2 21.3 20.9 21.7 20.7 22.6 20 22 23 18.4 20 20.1 20.6 19.8 19.1 21.1 26.3 19.8 22.3 21.2 22.2 19.5 20.6 19.7 22.7 Jeffrey A. Stratford Department of Health and Biological Sciences 84 W. South Street Wilkes University, PA 18766 jeffrey.stratf...@wilkes.edu 570-408-4761 (office) 570-332-2942 (cell) http://web.wilkes.edu/jeffrey.stratford/ [[alternative HTML version deleted]] __ R-help@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. -- Joshua Wiley Ph.D. Student, Health Psychology University of California, Los Angeles http://www.joshuawiley.com/ __ R-help@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.
Re: [R] NA confusion (length question)
Josh, I am raising my cup of coffee to you - that worked perfectly. Cheers and thanks again! -Original Message- From: Joshua Wiley [mailto:jwiley.ps...@gmail.com] Sent: Tuesday, September 14, 2010 9:29 AM To: Stratford, Jeffrey Cc: r-help@r-project.org Subject: Re: [R] NA confusion (length question) Hi Jeffrey, As a bit of a side note, data copied in html emails tends to show up poorly (since emails to the list are converted to plain text). Anyways, note the difference between: length(mylm$residuals) length(residuals(mylm)) Accessing the residuals value from mylm is *not* quite the same as calling the residuals() function on mylm. So, if you use: cbind(residuals(mylm), mydata) you should be good. Hope that helps, Josh On Tue, Sep 14, 2010 at 6:20 AM, Stratford, Jeffrey jeffrey.stratf...@wilkes.edu wrote: Hi folks, I am running a very simple regression using mylm - lm(mass ~ tarsus, na.action=na.exclude) I would like the use the residuals from this analysis for more regression but I'm running into a snag when I try cbind(mylm$residuals, mydata) # where my data is the original data set The error tells me that it cannot use cbind because the length of mylm$residuals is 50 and mydata is 52. This makes sense except I thought that na.exclude preserves length by inserting NA in residuals where there were NA's in the orginal data ( i = 3, 20). When I ask to see the residuals( mylm$residuals) I see 52 numbers. How can this be? I am just looking to see how I can produce a third vector with length = 52 and NA's for i=3,20. I'm using R 2.11.1 on Windows XP and the data are below Many thanks, Jeff tarsus mass 21.5 23.2 21.8 22.6 20.9 NA 21.6 20.8 21.5 21.5 22 23.2 21.6 23 22.1 21 21.1 21 20.6 22.9 20.1 21.8 22.2 20.4 21.9 21.5 21.1 21.3 21.5 20.1 19.9 21.4 22.1 27.3 20.1 19.7 19.6 16.7 20.9 NA 20.1 21.7 21.8 22.3 20.9 21.1 21.6 20.8 22.4 20.5 21.4 20.4 21.4 21 21.6 21 21.2 23.3 21.1 21.9 22 21 22.2 21.5 20.6 20.6 21.3 20.5 20.6 20.5 21.4 20.8 21.8 21.4 21.6 19.6 22.4 24.3 21.7 20.3 21.4 21.3 20.7 18.2 21.3 20.9 21.7 20.7 22.6 20 22 23 18.4 20 20.1 20.6 19.8 19.1 21.1 26.3 19.8 22.3 21.2 22.2 19.5 20.6 19.7 22.7 Jeffrey A. Stratford Department of Health and Biological Sciences 84 W. South Street Wilkes University, PA 18766 jeffrey.stratf...@wilkes.edu 570-408-4761 (office) 570-332-2942 (cell) http://web.wilkes.edu/jeffrey.stratford/ [[alternative HTML version deleted]] __ R-help@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. -- Joshua Wiley Ph.D. Student, Health Psychology University of California, Los Angeles http://www.joshuawiley.com/ __ R-help@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.
Re: [R] NA confusion (length question)
You're quite welcome. If you've a hankering to learn more you can see the documentation for ?residuals.lm (note the .lm addition, which designates the particular method that gets dispatched since your object class was lm). For even more fun: ?naresid (which residuals() calls) and to see how it knew where to add the NAs: mylm$na.action On Tue, Sep 14, 2010 at 6:36 AM, Stratford, Jeffrey jeffrey.stratf...@wilkes.edu wrote: Josh, I am raising my cup of coffee to you - that worked perfectly. Cheers and thanks again! -Original Message- From: Joshua Wiley [mailto:jwiley.ps...@gmail.com] Sent: Tuesday, September 14, 2010 9:29 AM To: Stratford, Jeffrey Cc: r-help@r-project.org Subject: Re: [R] NA confusion (length question) Hi Jeffrey, As a bit of a side note, data copied in html emails tends to show up poorly (since emails to the list are converted to plain text). Anyways, note the difference between: length(mylm$residuals) length(residuals(mylm)) Accessing the residuals value from mylm is *not* quite the same as calling the residuals() function on mylm. So, if you use: cbind(residuals(mylm), mydata) you should be good. Hope that helps, Josh On Tue, Sep 14, 2010 at 6:20 AM, Stratford, Jeffrey jeffrey.stratf...@wilkes.edu wrote: Hi folks, I am running a very simple regression using mylm - lm(mass ~ tarsus, na.action=na.exclude) I would like the use the residuals from this analysis for more regression but I'm running into a snag when I try cbind(mylm$residuals, mydata) # where my data is the original data set The error tells me that it cannot use cbind because the length of mylm$residuals is 50 and mydata is 52. This makes sense except I thought that na.exclude preserves length by inserting NA in residuals where there were NA's in the orginal data ( i = 3, 20). When I ask to see the residuals( mylm$residuals) I see 52 numbers. How can this be? I am just looking to see how I can produce a third vector with length = 52 and NA's for i=3,20. I'm using R 2.11.1 on Windows XP and the data are below Many thanks, Jeff tarsus mass 21.5 23.2 21.8 22.6 20.9 NA 21.6 20.8 21.5 21.5 22 23.2 21.6 23 22.1 21 21.1 21 20.6 22.9 20.1 21.8 22.2 20.4 21.9 21.5 21.1 21.3 21.5 20.1 19.9 21.4 22.1 27.3 20.1 19.7 19.6 16.7 20.9 NA 20.1 21.7 21.8 22.3 20.9 21.1 21.6 20.8 22.4 20.5 21.4 20.4 21.4 21 21.6 21 21.2 23.3 21.1 21.9 22 21 22.2 21.5 20.6 20.6 21.3 20.5 20.6 20.5 21.4 20.8 21.8 21.4 21.6 19.6 22.4 24.3 21.7 20.3 21.4 21.3 20.7 18.2 21.3 20.9 21.7 20.7 22.6 20 22 23 18.4 20 20.1 20.6 19.8 19.1 21.1 26.3 19.8 22.3 21.2 22.2 19.5 20.6 19.7 22.7 Jeffrey A. Stratford Department of Health and Biological Sciences 84 W. South Street Wilkes University, PA 18766 jeffrey.stratf...@wilkes.edu 570-408-4761 (office) 570-332-2942 (cell) http://web.wilkes.edu/jeffrey.stratford/ [[alternative HTML version deleted]] __ R-help@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. -- Joshua Wiley Ph.D. Student, Health Psychology University of California, Los Angeles http://www.joshuawiley.com/ __ R-help@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. __ R-help@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.