EI

ei@lists.gking.harvard.edu

88 discussions

by Mukerjee, Zagreb

Hello users of EI in Gauss and R, We are moving the discussion on this mailing list to Github. For discussing EI, asking questions, or suggesting features, please use our Github discussions: Gauss at https://github.com/iqss-research/ei/discussions R at https://github.com/iqss-research/eir/discussions To report any bugs, please fill out these forms: Gauss at https://github.com/iqss-research/ei/issues/new R at https://github.com/iqss-research/eir/issues/new Thank you, Zagreb Mukerjee Research Data Scientist Institute for Quantitative Social Science, Harvard University

2 years, 11 months

Installing on Windows 10

by Christopher Low

I am trying to install eiR on Windows 10 and am using the built-in Administrator account to avoid permissions issues. I have installed R fine and was able to install the prerequisite packages from a CRAN mirror fine as well ("msm", "tmvtnorm", "ellipse", "plotrix", "ucminf", "cubature", "mnormt", "foreach", "sp", "rgl", "lattice") However when I run the command: install.packages("ei", type="source", repos="http://r.iq.harvard.edu") I get the following error: Warning: unable to access index for repository http://r.iq.harvard.edu/src/contrib Warning message: package ‘ei’ is not available (for R version 2.15.1) If I point a web browser at the address it looks like an empty directory So I downloaded the ei package (ei_1.1.tar_.gz) to a local file, but can't seem to get the syntax right to load it. I've tried all kinds of combinations and get errors on all of them. For example: > install.packages("C:/packages/ei_1.1.tar_.gz", repos = NULL, type="source") Error in rawToChar(block[seq_len(ns)]) : embedded nul in string: '\037‹\b\0Oô/O\0\003ìZ\vt\033Õ™\016íYˆµ-\033\036¥=§4ÜÈ\n²\035[OËŽã\a‘-9\026Ø²‘ä<° 2Ò\\I“ŒfÄÌÈŽ\023Â£)ïmYÎ†¥P8[\b,»Ð„7Ka³t)P^á\025–m\022ž\033\bKÛP\036' Warning messages: 1: running command 'C:/PROGRA~1/R/R-215~1.1/bin/x64/R CMD INSTALL -l "C:/Program Files/R/R-2.15.1/library" "C:/packages/ei_1.1.tar_.gz"' had status 1 2: In install.packages("C:/packages/ei_1.1.tar_.gz", repos = NULL, : installation of package ‘C:/packages/ei_1.1.tar_.gz’ had non-zero exit status and: > install.packages("file:///c:/packages/ei_1.1.tar_.gz", type="source", repos=NULL) Warning: invalid package 'file:///c:/packages/ei_1.1.tar_.gz' Error: ERROR: no packages specified Warning messages: 1: running command 'C:/PROGRA~1/R/R-215~1.1/bin/x64/R CMD INSTALL -l "C:/Program Files/R/R-2.15.1/library" "file:///c:/packages/ei_1.1.tar_.gz"' had status 1 2: In install.packages("file:///c:/packages/ei_1.1.tar_.gz", type = "source", : installation of package ‘file:///c:/packages/ei_1.1.tar_.gz’ had non-zero exit status I've installed it many times before from the http://r.iq.harvard.edu repository with no problems, even on other Windows 10 computers. Please help, thanks! ___________________________________________________________________ *Chris Low* *Empowering faculty to use technology effectively for teaching and research.* Team Lead, Technology Liaisons Faculty Technology Support, Religion & Social Science Divisions Pepperdine University (310) 506-6512 [image: Courses Upgrade Email Signature Image] http://bitly.com/coursesupgrade

6 years, 8 months

EI for R Vector Type Error

by wvanderbok＠gmail.com

Using a small sample data set displayed at the bottom, I get the following error: > dbuf <- ei(cbind(Choice.1, Choice.2, Choice.3, Choice.4) ~ cbind (Hi.Ed, Lo.Ed), total = "Pop", data = Big10, erho = 1) [1] "Running eiRxC" Warning messages: 1: In BayesMDei(formula, data, total = total, lambda1 = lambda1, lambda2 = lambda2, : column marginals are proportions - multiplying by unit size 2: In BayesMDei(formula, data, total = total, lambda1 = lambda1, lambda2 = lambda2, : row margnials are proportions - multiplying by unit size > summary(dbuf) Error in array(x, c(length(x), 1L), if (!is.null(names(x))) list(names(x), : 'data' must be of a vector type, was 'NULL' Choice.1 through Lo.Ed are of type “double.” Pop is “integer.” Any clue what the problem is? Thanks in advance, Bill Choice.1 Choice.2 Choice.3 Choice.4 Hi.Ed Lo.Ed Pop 1 0.3960557 0.12370783 0.03217493 0.4480615 0.8442948 0.1557052 6222266 2 0.3356513 0.21803941 0.04251478 0.4037946 0.7541880 0.2458120 2191191 3 0.3035858 0.25241441 0.04002214 0.4039776 0.7643341 0.2356659 2009188 4 0.2598502 0.23172176 0.03091056 0.4775175 0.7086558 0.2913442 1438117 5 0.2604717 0.20728731 0.03202850 0.5002125 0.6786428 0.3213572 1308522 6 0.4288244 0.12137359 0.03955583 0.4102462 0.7334543 0.2665457 1193225 7 0.4811792 0.08965016 0.04065763 0.3885130 0.8305589 0.1694411 1069959 8 0.3296191 0.19188244 0.04399802 0.4345004 0.7813900 0.2186100 989090 9 0.4292554 0.15589339 0.04158555 0.3732657 0.8167544 0.1832456 743816 10 0.5334055 0.05825534 0.03558262 0.3727566 0.7925295 0.2074705 646945 Sent from Mail for Windows 10

6 years, 11 months

[R] Problem installing cem package

by Santiago

Hi R users, I need your help to install the "cem" package. I tried severla time to install the package but I get the followinf error message: > install.packages("cem",repos="http://r.iq.harvard.edu", type="source") Installing package into ‘/Users/gucho/Library/R/3.1/library’ (as ‘lib’ is unspecified) trying URL 'http://r.iq.harvard.edu/src/contrib/cem_1.1.14.tar.gz' Content type 'application/x-gzip' length 2000723 bytes (1.9 MB) opened URL ================================================== downloaded 1.9 MB * installing *source* package ‘cem’ ... ** R ** data ** inst ** preparing package for lazy loading Error : .onLoad failed in loadNamespace() for 'tcltk', details: call: dyn.load(file, DLLpath = DLLpath, ...) error: unable to load shared object '/Library/Frameworks/R.framework/Versions/3.1/Resources/library/tcltk/libs/tcltk.so': dlopen(/Library/Frameworks/R.framework/Versions/3.1/Resources/library/tcltk/libs/tcltk.so, 10): Library not loaded: /usr/X11/lib/libXft.2.dylib Referenced from: /usr/local/lib/libtk8.6.dylib Reason: image not found Error : package ‘tcltk’ could not be loaded ERROR: lazy loading failed for package ‘cem’ * removing ‘/Users/gucho/Library/R/3.1/library/cem’ Warning in install.packages : installation of package ‘cem’ had non-zero exit status I have a iMac with OS Yosemite. Thanks for your help.

9 years, 1 month

betaB, betaW cross-district average in EI for R with R x C

by Fetzer, Joel

The examples online seem to illustrate how to obtain parameters for a particular district when using a multinomial-Dirichlet R x C model of EI for R. Most likely I somehow missed the information in the documentation, but how would one obtain the, say, betaB averaged across all districts at once, not just for district 1 or district 2, etc. Many thanks, Joel Fetzer Pepperdine University

9 years, 8 months

dumping EI output into pretty tables

by Megan Gall

Hello, I am running a lot of models and want a way to dump the EI results (I am interested in ) into a pretty table. This automation would free up a significant portion of my time. I have looked high and low for such a package or how-to and have found nothing. Any suggestions? megan Megan A. Gall, MSGIS, PhD Social Science Analyst, Voting Rights Project Lawyers' Committee for Civil Rights Under Law 1401 New York Avenue, NW Suite 400 Washington, DC 20005 Office: 202-662-8322 General Fax: 202-783-0857 www.lawyerscommittee.org [LClogo_661_cmyk]

9 years, 11 months

EI Diagnostic - Estimating Crossover Voting in California Top 2 Primary

by Woo Chang KANG

Hello, I am using EI to estimate crossover voting in the Top 2 Primary in California in 2012. The unit of analysis is at the precinct level and I match the turnout record of partisan voters with election return data. For simulation, I use the following formula. formula <- cbind(dem.return, rep.return, oth.return) ~ cbind(dem.show, rep.show, oth.show) dem.return : Vote Share of a Democratic Candidates at the precinct level rep.return : Vote Share of a Republican Candidates oth.return : Vote Share of a Non-Two Party Candidate dem.show : Ratio of Democratic Registered Voters among who casted ballot for the primary rep.show : Ratio of Republic Registered Voters among who casted ballot for the primary oth.show : Ratio of Non-two Party Voters among who casted ballot for the primary My quantity of interests are the ratio of democratic registered voters who voted for the republican candidates (Democratic Crossover to Republican Party) and the ratio of republican registered voters who voted for the democratic candidates (Republican Crossover to Democratic Party). Using precinct level data, I am trying to estimate population weighted average of crossover voting at the State Assembly District. In some districts, the estimate looks reasonable. However, in other districts, my estimates suggest that more than half of each partisan voters crossover to other parties. I wonder what would be the best way to examine how reasonable my EI estimates are. Thank you for your help. Best, Woo Chang KANG -- Woo Chang KANG Ph.D. Candidate Department of Politics New York University 19 West 4th St. 2nd Fl., New York, NY 10012.

10 years, 4 months

Question about EzI

by Germán Rosati

Hello again. I have a question regarding EzI software. I have a dataset with electoral data desaggregated up to county level. I have run the model with presidential vote in one year as "t" and legislative vote in a previous year as "x". Since the dataset contains data up to county level, I want to export the estimates results in order to make a georeferentiation. When I export those estimates there is not an indicator (ID), so I can´t know to which county correspond each estimate. Is the order in which those estimates are exported the same as in the original database? If not, how can I know which estimate correspond to which county? Sorry for troubling you again. Thank you very much, Bests regards, Germán Rosati PS: I´m sorry for my (not very elegant) english

10 years, 4 months

training on using EI

by Douglas Johnson

Is there anyone on this list, preferably in the LA area, that would be interested in providing some consulting / training on EI in Jan or Feb? I'm looking to get up to speed quickly on the mechanics of using the software (I've read the books & articles and understand the ideas, now just need to learn the technical details of running the program). Thanks! - Doug Douglas Johnson, Fellow Rose Institute of State and Local Government at Claremont McKenna College douglas.johnson(a)cmc.edu 310-200-2058

10 years, 4 months

(no subject)

by Barry Ames

I'm trying to use ei within R, but I've been unable to extract the ei files from the tar package. I get an "error/warning" message. I've enlisted my computer help desk; the same thing happens when they try to extract the files. Any suggestions? Barry

10 years, 4 months

2024

2023

2022

2021

2020

2019

2018

2017

2016

2015

2014

2013

2012

2011

2010

2009

2008

2007

2006

2005

2004

2003

2002

EI