Amelia

amelia@lists.gking.harvard.edu

669 discussions

by Gary King

Hi Amelia, I attach your signed form, and also include here a photo of the gas meter. Can you let us know about the upgrade? Thanks Gary King, 9 Beecher Road, Brookline MA 02445 [image: 20220602_102803.jpeg] -- *Gary King* - Albert J. Weatherhead III University Professor - Director, IQSS <http://iq.harvard.edu/> - Harvard University GaryKing.org <http://garyking.org/> - King(a)Harvard.edu - @KingGary <https://twitter.com/kinggary> - 617-500-7570 - Assistant <king-assist(a)iq.harvard.edu>: 617-495-9271

1 year, 11 months

Changes to Amelia mailing list

by Mukerjee, Zagreb

Hello users of Amelia, We are moving the discussion of this mailing list to our Github. For discussing Amelia, asking questions, or suggesting features, please use our Github discussions, found at https://github.com/IQSS/Amelia/discussions. To report any bugs, please fill out this form: https://github.com/IQSS/Amelia/issues/new. Thank you, Zagreb Mukerjee Research Data Scientist IQSS

2 years, 11 months

Imputation using amelia-message error-perfectly collinear

by Antonio Rodriguez Andres

Hello Amelia users I have tried to use the amelia package, and I got the following error. I am dealing with a macro panel dataset for 126 countries and 16 years. I want to impute using the entire dataset, the values of time to export, time to import (measured in hours), and cost of exports and imports in USD. The proportion of missingness is quite large around 45 and 65 % for the variables. For that purpose, I use the option empri, read Amelia manual on page 31. am = amelia(final_datos1, m = 5, intercs = TRUE, empri = .01*nrow(final_datos1), cs = "country", ts = "year") After running this, it gives me the error Warning message: In amcheck(x = x, m = m, idvars = numopts$idvars, priors = priors, : The variable year is perfectly collinear with another variable in the data. It seems to me that this is due to the fact that for the combination of country and year, there are missing values for all variables Any help is appreciated -- Member, Editorial Committee, *The Economic and Labour Relations Review* (a SAGE journal) http://elr.sagepub.com/ Member, Editorial Committee, African Journal of Economic and Management Studies http://emeraldgrouppublishing.com/products/journals/editorial_team.htm?id=a… https://www.researchgate.net/profile/Antonio_Andres (Research Gate profile)

3 years

How can I make a function to run several regression models using imputed data with Amelia?

by j.baldwin＠ucl.ac.uk

I have a multiply imputed dataset (imputed using Amelia) and would like to derive a function which runs several regressions (with the same outcome, and different predictor variables) in one go. The reason is that I need to run several regressions (with the same predictors) on different outcome variables. I have defined the function but when I run it, I get an error message: Error in model.frame.default(formula = outcome ~ country, data = as.data.frame(.), : variable lengths differ (found for 'country') I think it is because the imputed datasets are an "amelia" object and not a typical data frame, so it is hard to index the variable "country". But I'm not sure how to do this. A reproducible example is below. I would really appreciate any advice. library(Amelia) library(Zelig) # Use africa dataset data(africa) # Impute data imp.out <- amelia(x = africa, cs = "country", ts = "year", logs = "gdp_pc", m=5) summary(imp.out) # Define function to run regression predicting an outcome from country, gdp_pc, civlib, and population reg_function <- function(outcome, data) { # Run regressions using the zelig function country <- zelig(outcome ~ country, model = "normal", data=data, cite=FALSE) gdp_pc <- zelig(outcome ~ gdp_pc, model = "normal", data=data, cite=FALSE) population <- zelig(outcome ~ population, model = "normal", data=data, cite=FALSE) # Put results into a vector results <- ( c(combine_coef_se(country)[2,1], combine_coef_se(country)[2,2], combine_coef_se(gdp_pc)[2,1], combine_coef_se(gdp_pc)[2,2], combine_coef_se(population)[2,1], combine_coef_se(population)[2,2])) # Return results in a matrix return(matrix(results, nrow=1, ncol=6, dimnames=list(c(""), c("Est_country", "SE_country", "Est_gdp_pc", "SE_gdp_pc", "Est_population", "SE_population")))) } # Run regression for outcome variables "year", "infl", and "trade" # This is where I get the error messages that the variable lengths differ for 'country' year <- reg_function(year, imp.out$imputations) year <- reg_function(infl, imp.out$imputations) year <- reg_function(trade, imp.out$imputations)

3 years

Amelia & Imputation for Cluster-Randomized Control Trial

by Emma Gause

Hello, I am working with data from a cluster-randomized, longitudinal control trial and need to impute missingness within individuals over time. It doesn’t look like there is an option in Amelia to specify clusters. I have set the cs to be the participant ID, and currently am just including the cluster variable as a time-invariant categorical covariate. Is there a better way to specify my Amelia model to account for the clustering? Thank you, Emma -- Emma Gause, MS, MA Research Scientist Harborview Injury Prevention & Research Center Firearm Injury and Policy Research Program egause(a)uw.edu<mailto:egause@uw.edu> <mailto:egause@uw.edu> [signature_380473688]

3 years, 1 month

Applying the imputation mode to new data

by Paul Dunmore

My use case is to build a model on a training data set and then demonstrate its performance on a separate test data set; both data sets may contain missing data. Amelia seems to assume that missing values will be imputed on the same data set used to estimate the imputation model itself. Is there an interface, or a reasonably discrete section of the code in the package, which allows an imputation model developed from a training set to be used to impute missing values in a test set? -- Paul Dunmore 100 Marine Parade Paraparaumu 5032 New Zealand

3 years, 6 months

Re: [amelia] Principal Components of Amelia Datasets

by Matt Blackwell

Hi Stuart, Unfortunately, we don't have any code for implementing PCA with Amelia output. I was more providing a high-level idea for how one could implement this. If separate PCA analyses don't work, then maybe combine the data first and then run PCA on the stacked data (weighting each row by 1/64). Cheers, Matt ~~~~~~~~~~~ Matthew Blackwell Associate Professor of Government Harvard University url: http://www.mattblackwell.org On Mon, Oct 12, 2020 at 10:18 PM Dr Stuart Reece <asreece(a)bigpond.net.au> wrote: > Thanks Matt. > > > > Can you please provide code to work out the PCA in each imputed dataset??? > > Actually I went through and did this by hand in all 64 imputed datasets > (for 50% missing data) – and then the code for analyzing it would not work > at all…. > > Extremely frustrating…. > > > > I tried this with missMDA and factoMineR and PCA – but it only gave one > dataset at the end and the results were not robust…. > > > > But I really liked the Amelia framework and wanted to use it – but could > not make the code run after constructing PCA’s in each dataset as noted > earlier. > > > > Thanks for your advice, > > > > Stuart. > > > > > > > > > > > > > > > > *From:* Matt Blackwell [mailto:mblackwell@gov.harvard.edu] > *Sent:* Tuesday, 13 October 2020 11:59 AM > *To:* stuart.reece(a)bigpond.com > *Cc:* amelia(a)lists.gking.harvard.edu; Gary King; James Honaker; Stuart > Reece > *Subject:* Re: Principal Components of Amelia Datasets > > > > Hi Stuart, > > > > Probably the most straightforward way to do this would be to apply PCA to > each of the imputed data sets and then use those in whatever analysis > models you want. As an alternative, you could use the stacked dataset of > all imputation (see my earlier email) and run PCA giving each of the rows > of the stacked data (1/m) weight where m is the number of imputed datasets. > This would ensure that all of the imputed data sets use the same factor > loadings. > > > > Cheers, > Matt > > > > ~~~~~~~~~~~ > > Matthew Blackwell > > Associate Professor of Government > > Harvard University > > url: http://www.mattblackwell.org > <https://urldefense.proofpoint.com/v2/url?u=http-3A__www.mattblackwell.org&d…> > > > > > > On Fri, Oct 9, 2020 at 10:38 PM <stuart.reece(a)bigpond.com> wrote: > > Hi Amelia Users. > > > > I was wondering if anyone would advise how I can add principal components > to imputed datasets – and how to correctly combine them from all the > imputations ??? > > > > I was not able to find anything on this online…. > > > > Thanks so much, > > > > Stuart Reece. > >

3 years, 6 months

Re: [amelia] Query on Amelia::combine.output()

by Matt Blackwell

Hi Stuart, Sorry, no, ameliabind is also designed like the combine.output I described: it combines multiple runs of Amelia in one output object of class "amelia". Hope that helps! Cheers, Matt ~~~~~~~~~~~ Matthew Blackwell Associate Professor of Government Harvard University url: http://www.mattblackwell.org On Mon, Oct 12, 2020 at 10:13 PM Dr Stuart Reece <asreece(a)bigpond.net.au> wrote: > Thanks Matt. > > Yes I have used the do.call(rbind code many times. > > > > But I thought ameliabind was to do.call(rbind like dplyr’s bind_rows was > to the do.call rbind…. > > ameliabind doesn’t work that way???? > > I could not find the syntax listed anywhere online… but I don’t mind using > do.call..(rbind > > Thankyou so much, > > Stuart. > > > > > > > > > > *From:* Matt Blackwell [mailto:mblackwell@gov.harvard.edu] > *Sent:* Tuesday, 13 October 2020 11:56 AM > *To:* stuart.reece(a)bigpond.com > *Cc:* amelia(a)lists.gking.harvard.edu; Gary King; James Honaker; Stuart > Reece > *Subject:* Re: Query on Amelia::combine.output() > > > > Hi Stuart, > > > > Ah, `combine.output()` actually just takes multiple Amelia runs that were > done separately and combines them into one object, as if you didn't them > all together. This is helpful if you want to run additional imputations > after a first batch. Here is some code that will take Amelia output and > create a stacked data frame of all imputations with a column for imputation > numbers: > > > > library(Amelia) > data(africa) > imps <- 5 > a.out <- amelia(africa, cs = "country", ts = "year", m = imps) > > stacked_df <- do.call(rbind, a.out$imputations) > stacked_df$imp_number <- rep(1:imps, each = nrow(africa)) > > > > Having said all of that, you probably don't want to do this. Instead, you > probably want to apply your analysis model to each of the imputed data sets > and then combine the coefficients/model parameters using the Rubin rules > described in the various Amelia papers. > > > > Cheers, > Matt > > > > ~~~~~~~~~~~ > > Matthew Blackwell > > Associate Professor of Government > > Harvard University > > url: http://www.mattblackwell.org > <https://urldefense.proofpoint.com/v2/url?u=http-3A__www.mattblackwell.org&d…> > > > > > > On Fri, Oct 9, 2020 at 10:33 PM <stuart.reece(a)bigpond.com> wrote: > > Hi Amelia Users. > > > > I am running a Windows computer i9-9900K CPU 3.6GHz, 64MB RAM, 64-bit > system. > > > > I have the R Studio 1.3.1093 based on R 4.0.2, just re-installed today. > > > > Amelia works on my data and runs models very nicely. The parallel > routines work really well, which I very much appreciate on my 16 CPU’s. > > > > However I use complex geospatial models and would love to model the > complete imputed geospatial data in R::splm. > > > > So combining all the imputations into one df would be a fantastic > assistance. > > > > I think combine.output should do this very nicely. > > > > I think the syntax for combine.output is probably like that of ameliabind > – really simple…. Can’t find the syntax online…. > > > > But whenever I run combine.output – with whatever syntax – I always get > the same error message which reads: > > > > CombAmelia1616 <- Amelia::combine.output(a.r.CS.Raw.ETOPFA.LIR.02.16, > a.r.CS.Raw.ETOPFA.LIR.02.16e) > > Error: 'combine.output' is not an exported object from 'namespace:Amelia' > > > > I was wondering please if something is wrong?? > > > > Also – could someone please confirm that the correct syntax for > combine.output is the same as ameliabind – super simple???? > > > > Thanks so much, > > > > Stuart Reece. > > > > > > > >

3 years, 6 months

Graphing from Amelia Iterative Datasets

by stuart.reece＠bigpond.com

Hi Amelia Users, I was also wondering how one makes graphs from iterative Amelia datasets??? Or even changes a variable onto a factor across all datasets??? Or is this best done prior to running Amelia?? I mostly use ggplot2. Thanks again, Stuart Reece.

3 years, 6 months

Re: [amelia] Principal Components of Amelia Datasets

by Matt Blackwell

Hi Stuart, Probably the most straightforward way to do this would be to apply PCA to each of the imputed data sets and then use those in whatever analysis models you want. As an alternative, you could use the stacked dataset of all imputation (see my earlier email) and run PCA giving each of the rows of the stacked data (1/m) weight where m is the number of imputed datasets. This would ensure that all of the imputed data sets use the same factor loadings. Cheers, Matt ~~~~~~~~~~~ Matthew Blackwell Associate Professor of Government Harvard University url: http://www.mattblackwell.org On Fri, Oct 9, 2020 at 10:38 PM <stuart.reece(a)bigpond.com> wrote: > Hi Amelia Users. > > > > I was wondering if anyone would advise how I can add principal components > to imputed datasets – and how to correctly combine them from all the > imputations ??? > > > > I was not able to find anything on this online…. > > > > Thanks so much, > > > > Stuart Reece. >

3 years, 6 months

Jump to page:

2024

2023

2022

2021

2020

2019

2018

2017

2016

2015

2014

2013

2012

2011

2010

2009

2008

2007

2006

2005

2004

2003

2002

Amelia