Bookmark and Share

Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.


[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

Re: st: R: Imputation of missing data in an unbalanced panel using ICE


From   Nick Cox <njcoxstata@gmail.com>
To   "statalist@hsphsun2.harvard.edu" <statalist@hsphsun2.harvard.edu>
Subject   Re: st: R: Imputation of missing data in an unbalanced panel using ICE
Date   Fri, 25 Oct 2013 17:14:18 +0100

Indeed.

I assign a big cost to asking the wrong question or giving the wrong answer.

Nick
njcoxstata@gmail.com


On 25 October 2013 17:08, James Bernard <jamesstatalist@gmail.com> wrote:
> Thanks Nick.
>
> yes, I agree. using imputation, though tempting, raises other issues.
> So, again, lime many thing in statistics, it is a matter of
> cost-benefit analysis
>
> On Fri, Oct 25, 2013 at 11:32 PM, Nick Cox <njcoxstata@gmail.com> wrote:
>> There is a bundle of issues here.
>>
>> Carlo touches on one, which is what multiple imputation does and does
>> not purport to provide.
>>
>> Another is that the method being used here -reshape-s panel data to
>> wide, imputes and then -reshape-s back.
>>
>> This really does raise the question of precisely what assumptions are
>> needed about variations in time to make that legitimate. There's no
>> white magic independently of whether tacit assumptions match the data
>> generating process. I've not thought this through either -- I don't do
>> this stuff -- but I want to send a Hang on there... signal of caution.
>>
>> No-one seems interested any more in interpolation as a rough family of
>> methods of filling in gaps in time series. Rather, it is a smooth
>> method of filling in gaps and raises questions of its own too.
>>
>>
>> Nick
>> njcoxstata@gmail.com
>>
>>
>> On 25 October 2013 16:17, Carlo Lazzaro <carlo.lazzaro@tiscalinet.it> wrote:
>>> James asked:
>>> "Also, how wrong is to use only the first imputation (M=1) to run the model,
>>> instead of using all the imputations?".
>>>
>>> The approach James proposes would seem to rule out the between variance
>>> component (that is, the variance between different M=n datasets generated
>>> via MI), which is a qualifying features of MI.
>>>
>>> Kind regards,
>>> Carlo
>>>
>>> -----Messaggio originale-----
>>> Da: owner-statalist@hsphsun2.harvard.edu
>>> [mailto:owner-statalist@hsphsun2.harvard.edu] Per conto di James Bernard
>>> Inviato: venerdě 25 ottobre 2013 13:47
>>> A: statalist@hsphsun2.harvard.edu
>>> Oggetto: st: Imputation of missing data in an unbalanced panel using ICE
>>>
>>> Hi all,
>>>
>>> I have been using imputation techniques. Stata offers a wide range of
>>> commands to conduct imputation.
>>>
>>> I have a unbalanced panel data. Several variables have missing values.
>>> To benefit from the fact that the available observation of a variable at
>>> certain times can help estimate the missing values at other times, I changed
>>> the format of my data from long to wide and used ICE using the instruction
>>> from this site:
>>> http://www.ats.ucla.edu/stat/stata/faq/mi_longitudinal.htm
>>>
>>> These instructions work for a balanced panel data set where all firms are
>>> supposed to have values in all years.
>>>
>>> But, imagine that one firm has to have values from 2000-2003, and another
>>> from 1998-2003. And, suppose we have a variable (X) for which some
>>> observations across these two firms are missing
>>>
>>> Firm       Year        X
>>> ---------    ---------    -------
>>> A           2000       .
>>> A           2001      10
>>> A           2002       6
>>> A           2003       .
>>>
>>> B           1998       3
>>> B           1999       .
>>> B           2000        .
>>> B           2001        4
>>> B           2002        6
>>> B           2003        2
>>>
>>> Reshaping the data from long to wide would lead to: creation of 6 new
>>> varibale named "X1998", "X1999",......"X2003".... and values of X1998 and
>>> X1999 will be missing for firm A
>>>
>>> And running the ICE, it would predict values for X1998 and X1999 for both
>>> firm A and B.
>>>
>>> The next step is to get the data into long form and run the -mi- commands to
>>> make the estimation which use Rubin rules for combining the data on the m
>>> imputations made.
>>>
>>> One may argue that I can let the ICE predict the values of X1998 and
>>> X1999 for firm A. Reshape the data into long format and remove the values of
>>> X from firm A in 1998 and in 1999, because firm A is not supposed to have
>>> values in 1998 and 1999.
>>>
>>> My question is: Does asking ICE to predict values of X1998 and X1999 for
>>> firm A affect the way it predicts the value of X2000 (which is the main
>>> observation we have to impute)?
>>>
>>> Does the technique I used make sense?
>>>
>>> Also, how wrong is to use only the first imputation (M=1) to run the model,
>>> instead of using all the imputations?
>>>
>>> Thanks,
>>> James
>>> *
>>> *   For searches and help try:
>>> *   http://www.stata.com/help.cgi?search
>>> *   http://www.stata.com/support/faqs/resources/statalist-faq/
>>> *   http://www.ats.ucla.edu/stat/stata/
>>>
>>>
>>> *
>>> *   For searches and help try:
>>> *   http://www.stata.com/help.cgi?search
>>> *   http://www.stata.com/support/faqs/resources/statalist-faq/
>>> *   http://www.ats.ucla.edu/stat/stata/
>>
>> *
>> *   For searches and help try:
>> *   http://www.stata.com/help.cgi?search
>> *   http://www.stata.com/support/faqs/resources/statalist-faq/
>> *   http://www.ats.ucla.edu/stat/stata/
>
> *
> *   For searches and help try:
> *   http://www.stata.com/help.cgi?search
> *   http://www.stata.com/support/faqs/resources/statalist-faq/
> *   http://www.ats.ucla.edu/stat/stata/

*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/faqs/resources/statalist-faq/
*   http://www.ats.ucla.edu/stat/stata/


© Copyright 1996–2018 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   Site index