Simon Kiss
2010-Mar-26 10:32 UTC
[R] row names in regression results and saving the identification results from added variable plots
Hello all, Is there a way to take the row names from my data.frame and have them imported to the regression results? At the moment, I my original data frame looks like this: / Riding name / Turnout / Margin / Expenditures 1 / Abbotsford 2 / . 3 / . 4 / .Willow I know how to set the row names for the original data frame to be the Riding name, but when I run the regression, the residuals, dfbetas, cook's d all lose those and are listed with the original row number. This does not pose a significant problem for when I'm just looking at residuals and defbetas, because I've figured out how to match up the row names to those variables. But it is posing a bit of a problem now that I'm looking at added variable plots; the calculations are more difficult to match up the results to the row names. As a second question, I have figured out how to identify the points in added variable plots - av.plots=(model, labels=names(residuals(model_name)), identify.points=TRUE) However, when I'm finished identifying points, the results are not saved. I'm not sure if I can use the "identify" command with the av.plots command in (car) as you can with other standard plots because av.plots brings up an interactive menu that does not appear to allow for that. If any one can help, it would be appreciated! Yours, Simon Kiss ********************************* Simon J. Kiss, PhD SSHRC and DAAD Post-Doctoral Fellow John F. Kennedy Institute of North America Studies Free University of Berlin Lansstra?e 7-9 14195 Berlin, Germany Cell: +49 (0)1525-300-2812, Web: http://www.jfki.fu-berlin.de/index.html
Maybe Matching Threads
- help calculating variable based on factor level of another
- Problem with recode -Error in parse(text = range[[1]][1]) : unexpected end of input in " c(0"
- Grouping and stacking bar plot for categorical variables
- generate irregular series of dates
- R Full Screen