Zelig July 2010

zelig@lists.gking.harvard.edu

9 participants
6 discussions

summary with imputations bug ... any workarounds?

by Peter Flom

Good morning If I run <<< susan.lsmixed.out <- zelig(formula = unprot_vag_sex ~ married + age + TREATMENT.ARM*time + highest_grade + income + tag(1|id), data = susanMI.out$imputations, model = "ls.mixed") summary(susan.lsmixed.out) >>>> I get an error Error in x$coef : $ operator is invalid for atomic vectors Searching the archives, I see that others have had similar problems. Is there a workaround? summary(susan.lsmixed.out[[1]]) works fine; should I then average across the five imputed data sets? thanks! Peter Peter L. Flom, PhD Statistical Consultant Website: http://www DOT statisticalanalysisconsulting DOT com/ Writing; http://www.associatedcontent.com/user/582880/peter_flom.html Twitter: @peterflom - Zelig Mailing List, served by Harvard-MIT Data Center Send messages: zelig(a)lists.gking.harvard.edu [un]subscribe Options: http://lists.gking.harvard.edu/?info=zelig Zelig program information: http://gking.harvard.edu/zelig/

12 years, 1 month

Problem with Zelig combining ARIMA results from Amelia output

by Brad Epperly

I'm using Amelia for multiple imputation, and after the creation of the Amelia object and m data sets, I want to use Zelig to automatically combine the results of my AR models. I have no problem getting it to work for LS models, when using summary and subset I can get either the combined model outputs or the output from individual imputed data sets. Using model="arima", however, this is not working. Instead, I always get m identical summaries, and this error: Error in tmp[, 1] : incorrect number of dimensions This occurs on different imputed data sets, so I'm not quite sure what I'm doing wrong. I can write (inelegant) code to do the averaging myself, but it's not easily portable. Any help would be much appreciated. Brad Epperly PhD Candidate Department of Political Science University of Washington Box 353530 Seattle, WA 98195 epperly(a)u.washington.edu

13 years, 9 months

How to get predicted values from generalized additive logit model?

by Shige Song

Dear All, I would like to produce and plot predicted values (probability) from a generalized additive logit model ("model=logit.gam"), but am not sure how to. Here is my model: z.out <- zelig(y ~ s(year), model="logit.gam", data=d) x.out <- setx(z.out, year=1950:1980) s.out <- sim(z.out, x=x.out) I got error message "Error in coef %*% t(x) : non-conformable arguments". I remember in the "vertci" demo, there is something like this: z.out <- zelig(vote ~ race + educate + age + I(age^2) + income, model = "logit", data = turnout) x.low <- setx(z.out, educate = 12, age = 18:95) x.high <- setx(z.out, educate = 16, age = 18:95) s.out <- sim(z.out, x = x.low, x1 = x.high) So I guess the problem is that Zelig does not allow a range specified for the variable included in the "s()" term. In that case, what is the best way to get a predicted values (probability), given a range of values in the independent variable? Many thanks. Best, Shige - Zelig Mailing List, served by Harvard-MIT Data Center Send messages: zelig(a)lists.gking.harvard.edu [un]subscribe Options: http://lists.gking.harvard.edu/?info=zelig Zelig program information: http://gking.harvard.edu/zelig/

13 years, 9 months

question about graph created with plot.ci()

by JOSE A ALEMAN

Dear Zelig team, I have recently used plot.ci() to create some graphs but I would like R to use smaller intervals to increase the number of bars in the graph. Also, I have noticed that R is not plotting across the full range of the x variable "Neocorporatism". The variable "Neocorporatism" ranges from -1.6 to 1.4. As you can see in the plot below, however, it seems like R is disregarding most positive values of the variable. Why would this be the case? (Embedded image moved to file: pic13506.jpg) Thank you, Jose A. Aleman http://faculty.fordham.edu/aleman

13 years, 9 months

Dude, where's my data?

by Jay Ulfelder

Dear Zeligists, I am trying to use Zelig to estimate mixed-effects logit models and am encountering an error message that I can't understand. Apparently, Zelig isn't "seeing" my data set, but other modeling commands in R are seeing it fine. I'm sure I'm overlooking something obvious and apologize in advance for wasting your time, but I would really appreciate it if you could help me fix the problem. Here is the workspace image in text form from the session. As you can see, R is seeing the data and estimating a GLM with no trouble. But when I use Zelig, I get the 'undefined columns selected' message. I saw a few threads in the listserv archives that covered the same message, but none of them seemed to apply to a case where the data set was already a data frame recognized by R. Thanks in advance, Jay R version 2.10.1 (2009-12-14) Copyright (C) 2009 The R Foundation for Statistical Computing ISBN 3-900051-07-0 R is free software and comes with ABSOLUTELY NO WARRANTY. You are welcome to redistribute it under certain conditions. Type 'license()' or 'licence()' for distribution details. Natural language support but running in an English locale R is a collaborative project with many contributors. Type 'contributors()' for more information and 'citation()' on how to cite R or R packages in publications. Type 'demo()' for some demos, 'help()' for on-line help, or 'help.start()' for an HTML browser interface to help. Type 'q()' to quit R. > # Analysis of Democratic Survival > # Merge 21, All Non-OECD Democratic Episodes > # Jay Ulfelder (SAIC) > # July 2010 > > # Load requisite packages > > library(foreign) > library(Zelig) Loading required package: MASS Loading required package: boot ## ## Zelig (Version 3.4-8, built: 2010-01-20) ## Please refer to http://gking.harvard.edu/zelig for full ## documentation or help.zelig() for help with commands and ## models supported by Zelig. ## ## Zelig project citations: ## Kosuke Imai, Gary King, and Olivia Lau. (2009). ## ``Zelig: Everyone's Statistical Software,'' ## http://gking.harvard.edu/zelig. ## and ## Kosuke Imai, Gary King, and Olivia Lau. (2008). ## ``Toward A Common Framework for Statistical Analysis ## and Development,'' Journal of Computational and ## Graphical Statistics, Vol. 17, No. 4 (December) ## pp. 892-913. ## To cite individual Zelig models, please use the citation format printed with ## each model run and in the documentation. ## > # Load and attach data from current directory > > demdat <- read.dta("RGJ All Non-OECD M21 Analysis File.dta") > dim(demdat) [1] 1447 78 > save(demdat, file="demdat.RData") > rm(demdat) > load("demdat.RData") > attach(demdat) > table(rgjtaut1) rgjtaut1 0 1 1390 57 > table(first) first 0 1 867 580 > rgjdurdl <- log(rgjdurd) > xxxcimrl <- log(xxxcimr) > base <- glm(rgjtaut1 ~ rgjdurdl + xxxcimrl + rgjaltp + first + postcw + fhsciv, + data = demdat, family=binomial) > summary(base) Call: glm(formula = rgjtaut1 ~ rgjdurdl + xxxcimrl + rgjaltp + first + postcw + fhsciv, family = binomial, data = demdat) Deviance Residuals: Min 1Q Median 3Q Max -1.2745 -0.2895 -0.2070 -0.1343 3.0262 Coefficients: Estimate Std. Error z value Pr(>|z|) (Intercept) -7.1637 0.9179 -7.804 5.98e-15 *** rgjdurdl 0.3788 0.1997 1.897 0.0578 . xxxcimrl 0.4293 0.2257 1.902 0.0572 . rgjaltp 0.8690 0.4082 2.129 0.0333 * first 0.2230 0.3001 0.743 0.4573 postcw -0.4540 0.3524 -1.288 0.1976 fhsciv 0.8635 0.1516 5.695 1.24e-08 *** --- Signif. codes: 0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1 (Dispersion parameter for binomial family taken to be 1) Null deviance: 464.75 on 1410 degrees of freedom Residual deviance: 396.83 on 1404 degrees of freedom (36 observations deleted due to missingness) AIC: 410.83 Number of Fisher Scoring iterations: 7 > # Adding random Intercepts for countries > > basez <- zelig(y ~ rgjdurdl + xxxcimrl + rgjaltp + first + postcw + fhsciv + tag(1 | sftgcode), + data = demdat, model="logit.mixed") Loading required package: Matrix Loading required package: lattice Attaching package: 'lattice' The following object(s) are masked from package:boot : melanoma Attaching package: 'Matrix' The following object(s) are masked from package:base : det Attaching package: 'lme4' The following object(s) are masked from package:stats : AIC Error in `[.data.frame`(d, , all.vars(as.expression(formula))) : undefined columns selected > -- Jay Ulfelder, Ph.D. Research Director Political Instability Task Force Science Applications International Corp. (SAIC) jay_ulfelder(a)stanfordalumni.org (301) 588-8478 [home office] (301) 580-8736 [mobile]

13 years, 10 months

specify more than one value in setx

by Casey Klofstad

Hey all- Can someone explain how to specify the value of more than one variable in setx? For example, I have a model with predicts y with b1 b2 and b3. In this example, how could I set b1 = 1, b2 = 0 and b3 = mean? Thanks much, -c -- Casey A. Klofstad University of Miami Department of Political Science Coral Gables, FL klofstad(a)gmail.com http://www.as.miami.edu/personal/cklofstad/ - Zelig Mailing List, served by Harvard-MIT Data Center Send messages: zelig(a)lists.gking.harvard.edu [un]subscribe Options: http://lists.gking.harvard.edu/?info=zelig Zelig program information: http://gking.harvard.edu/zelig/

13 years, 10 months

2024

2023

2022

2021

2020

2019

2018

2017

2016

2015

2014

2013

2012

2011

2010

2009

2008

2007

2006

2005

2004

2003

Zelig July 2010