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: cell names for results generated from user-written package 'markov'
From
Nick Cox <[email protected]>
To
"[email protected]" <[email protected]>
Subject
Re: st: cell names for results generated from user-written package 'markov'
Date
Thu, 22 Aug 2013 18:08:53 +0100
1. -markov-.
Sometimes, people just don't read documentation!
. ssc desc markov
-------------------------------------------------------------------------------------
package markov from http://fmwww.bc.edu/repec/bocode/m
-------------------------------------------------------------------------------------
TITLE
'MARKOV': module to generate Markov probabilities
DESCRIPTION/AUTHOR(S)
markov examines varname, treated as a sequence or series, to
produce basic summaries relevant to discrete-time, discrete-state
Markov chains. markov tabulates one-step transition frequencies
from one state to another, carries out a chi-square test for
independence, and tabulates a transition probability matrix. The
frequency matrix and the probability matrix are saved as F and P,
or as whatever names are specified. Matrices with these names are
overwritten. It is the user's responsibility to ensure that data
are in the appropriate sort order when markov is called. tabchi
must be installed first. Note added 2011: This is a small and
limited program from 1998 that just does what it says, and no
more. For example, it does not support panel data, or modelling
with predictor variables, or do almost anything else you might
want to do with Markov chain models.
Author: Nicholas J. Cox, University of Durham
Support: email [email protected]
Distribution-Date: 19980228
2. What to do
Reduce your dataset to averages with -collapse-, then apply -xtset.
The problem sounds too messy to contemplate otherwise.
Nick
[email protected]
On 22 August 2013 17:52, Milena Przheska
<[email protected]> wrote:
> - Nick,
>
> Thank you for your reply.
>
> Sometimes less is more.
>
> The problem with the -xttrans- I'm facing is that it requires that
> panel data be declared with -xtset-
>
> What is particular with my data set is that it records choices by
> different subjects and sometimes dates are the same. I have large
> number of subjects, so -by- command will not be useful. I am
> interested in the changes between choices on average, so I added
> missing values to break between subjects.
>
> This is little unconventional, and I cannot find a way to tweak
> -xtset- for this particular case.
>
> Thanks,
> Milena
>
> On Thu, Aug 22, 2013 at 6:26 PM, Nick Cox <[email protected]> wrote:
>> That is an ancient program that does very little.
>>
>> See -xttrans- or http://www.stata.com/statalist/archive/2013-04/msg01043.html
>> Nick
>> [email protected]
>>
>>
>> On 22 August 2013 16:53, Milena Przheska
>> <[email protected]> wrote:
>>> Dear Statalist members,
>>>
>>> I am using the following package
>>>
>>> package markov from http://fmwww.bc.edu/RePEc/bocode/m
>>> Author: Nicholas J. Cox, University of Durham
>>>
>>>
>>> I export the results from the matrices F and P to excel, but the row
>>> and column names are simply r1, r2...c1, c2...
>>>
>>>
>>> I am exploring the transition from one choice to another for
>>> categorical variable with many levels and I do not know upfront which
>>> choices appear and which do not, so it is important for me to save the
>>> names of the rows and columns in a way that will enable me to identify
>>> which levels of the variable they refer to.
>>>
>>> Is there a way to do this within the package I am using or some other
>>> package/command?
>>>
>>>
>>> Thanks for all your help, I appreciate it.
>>>
>>>
>>> Kindest regards,
>>> Milena Przheska
>>> *
>>> * 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/