[R] Ordered logit in R
Eik Vettorazzi
E.Vettorazzi at uke.uni-hamburg.de
Thu Feb 18 12:58:26 CET 2010
so, what did you expect instead as a result of an orderd logistic
regression?
See http://www.ats.ucla.edu/stat/R/dae/ologit.htm for interpretational help.
hth.
Mathew, Abraham T schrieb:
> I ran the follow code for an ordered logit, but don't know why two levels of my dependent variable are at the topic of my list of variables.
>
> I don't know why this appears, and what I'm supposed to take from them
>
> y>=0. Haven't thought much about this
> y>=1. Favor
>
>
> library(Design)
> two <- lrm(trade1 ~ age2 + education2 + personal2 + economy2 + partisan2 + employment2 + union2 + home2 + market2 + race2 + income2)
> two
> summary(two)
>
>
> #Logistic Regression Model
> #
> #lrm(formula = trade1 ~ age2 + education2 + personal2 + economy2 +
> # partisan2 + employment2 + union2 + home2 + market2 + race2 +
> # income2)
> #
> #Frequencies of Responses
> # 5. Oppose 0. Haven't thought much about this
> # 258 311
> # 1. Favor
> # 209
> #
> #Frequencies of Missing Values Due to Each Variable
> # trade1 age2 education2 personal2 economy2 partisan2
> # 210 0 3 7 16 134
> #employment2 union2 home2 market2 race2 income2
> # 678 5 59 207 10 82
> #
> # Obs Max Deriv Model L.R. d.f. P C Dxy
> # 778 1e-10 79.47 11 0 0.647 0.295
> # Gamma Tau-a R2 Brier
> # 0.296 0.194 0.11 0.191
> #
> # Coef S.E. Wald Z P
> #y>=0. Haven't thought much about this 3.045016 0.879724 3.46 0.0005
> #y>=1. Favor 1.198983 0.873244 1.37 0.1697
> #age2 0.003499 0.006006 0.58 0.5602
> #education2 -0.232741 0.048080 -4.84 0.0000
> #personal2 -0.117132 0.089053 -1.32 0.1884
> #economy2 -0.308168 0.104512 -2.95 0.0032
> #partisan2 -0.103308 0.091803 -1.13 0.2605
> #employment2 -0.097818 0.378070 -0.26 0.7958
> #union2 0.038079 0.168730 0.23 0.8215
> #home2 0.274581 0.157926 1.74 0.0821
> #market2 -0.195350 0.153563 -1.27 0.2033
> #race2 -0.057408 0.112952 -0.51 0.6113
> #income2 -0.130017 0.068048 -1.91 0.0560
>
> ______________________________________________
> 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.
>
--
Eik Vettorazzi
Institut für Medizinische Biometrie und Epidemiologie
Universitätsklinikum Hamburg-Eppendorf
Martinistr. 52
20246 Hamburg
T ++49/40/7410-58243
F ++49/40/7410-57790
More information about the R-help
mailing list