Thank you very much for your help Matt.
Indeed, it works well when the multiply imputed dataset comes from the amelia function:

library(Rmixmod)
data(titanic);
library(missForest)
set.seed(0)
titanicna<-prodNA(titanic,.2)
summary(titanicna)

 Class       Age         Sex       Survived
 0   :733   0   :  85   0   : 388   0   :1183
 1   :256   1   :1662   1   :1393   1   : 566
 2   :225   NA's: 454   NA's: 420   NA's: 452
 3   :553
 NA's:434


res.amelia<-amelia(titanicna,noms = 1:4)
z5 <- zlogit$new()
z5$zelig(Survived~ Class+Age, data = res.amelia)
z5

Model: Combined Imputations
            Estimate Std.Error  z value  Pr(>|z|)
(Intercept) -0.50632    0.2047 -2.47350 1.338e-02   .
Class1       1.40721    0.1776  7.92321 2.220e-15 ***
Class2       0.66160    0.1602  4.12910 3.642e-05 ***
Class3      -0.00529    0.1374 -0.03852 9.693e-01
Age1        -0.53445    0.1947 -2.74473 6.056e-03   *
---
Signif. codes:  '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1

For results from individual imputed datasets, use summary(x, subset = i:j)
Next step: Use 'setx' method


However, now I would like to use another function than amelia to perform MI.
My output is a list of dataframes. Can I use Zelig to achieve this goal?

Thank you very much for your help,

AUDIGIER Vincent
Applied Mathematic Department, Agrocampus Ouest
65 rue de Saint-Brieuc, 35042 Rennes Cedex, France
Tel: (+33)2 23 48 54 76
Website: http://vincentaudigier.weebly.com/
  
Le 08/12/2015 15:12, Matt Blackwell a écrit :
Hi Vincent, 

We just released an update to Amelia and now the vignette shows how to use the latest version of Zelig. See Section 4.10 here: https://cran.r-project.org/web/packages/Amelia/vignettes/amelia.pdf

Or see the Zelig documentation here: http://docs.zeligproject.org/en/latest/using-Zelig-with-Amelia.html

Cheers,
Matt

~~~~~~~~~~~
Matthew Blackwell
Assistant Professor of Government
Harvard University
url: http://www.mattblackwell.org

On Tue, Dec 8, 2015 at 8:22 AM, Vincent Audigier <vincent.audigier@agrocampus-ouest.fr> wrote:
Dear list members,

I would like to analyse a multiply imputed data set with zelig,
but I don't know how to do with the last version of the Zelig package.
For instance, the following code, which runs well using a previous version
of the package (4.2.1 for instance), produces an error with the version 5.0.9:

library("Amelia")
data(freetrade)
amelia.out <- amelia(freetrade, m = 15, ts = "year", cs = "country")

is.list(amelia.out$imputations)
#TRUE
is.data.frame(amelia.out$imputations[[1]])
#TRUE

library("Zelig")
zelig.fit <- zelig(tariff ~ pop + gdp.pc + year + polity, data = amelia.out$imputations, model = "ls", cite = FALSE)

#Error: data is not a data frame

Could you give me an example to show me how to use the last version
of Zelig?

Thank you very much for your help,

Best,

--
AUDIGIER Vincent
 Applied Mathematic Department, Agrocampus Ouest
65 rue de Saint-Brieuc, 35042 Rennes Cedex, France
Tel: (+33)2 23 48 54 76
Website: http://vincentaudigier.weebly.com/

--
Amelia mailing list served by HUIT
[Un]Subscribe/View Archive: http://lists.gking.harvard.edu/?info=amelia
More info about Amelia: http://gking.harvard.edu/amelia
Amelia mailing list
Amelia@lists.gking.harvard.edu

To unsubscribe from this list or get other information:

https://lists.gking.harvard.edu/mailman/listinfo/amelia