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: tsset for panel data with many variables
From
Nick Cox <[email protected]>
To
"[email protected]" <[email protected]>
Subject
Re: st: tsset for panel data with many variables
Date
Mon, 4 Nov 2013 21:09:35 +0000
It's really not clear what you are doing. Which command produces that
error message?
If you are telling Stata that you have monthly dates which are
integers like 200610, to Stata they are several thousand years into
the future. For Stata month 0 was January 1960 and this is month 646:
. di %tm 0
1960m1
. di %tm 646
2013m11
Conversely, if you are telling Stata something else, what is it?
It is futile deciding on your own date convention and hoping that
Stata will understand it. There is only one rule: follow Stata's date
conventions, or invent your own completely separate system.
In the long run it is a waste of time _not_ to read -help dates and
times- until what you need to know is clearly understood.
Please show us the results of
. describe case_id monthly_var
. list case_id monthly_var in 1/20
The request that you read
http://www.stata.com/support/faqs/resources/statalist-faq/#spell still
stands.
Nick
[email protected]
On 4 November 2013 20:43, Tetsuji Tanaka <[email protected]> wrote:
> Dear all, and thank you for the response, Nick.
>
> I am trying that the STATA recognise my panel data as a panel data.
> I made an id variable "case_id" to identify individual data (to avoid data duplication).
> My monthly data variable is written like "200601" "200612" meaning January and December in 2006, respectively.
>
> format monthly_var %tm
> tsset case_id monthly_var
>
> And I got an error message
>
> =exp required
> r(100);
>
> I don't understand what is wrong.
> Please give me ideas to overcome these problems.
Nick Cox <[email protected]> wrote
>> You don't give your exact command. Presumably you tried something of the form
>>
>> tsset panelid time
>>
>> If you omitted a panel identifier variable, that will be problem: such
>> a variable is essential. Otherwise see
>>
>> http://www.stata.com/support/faqs/data-management/repeated-time-values/
>>
>> http://www.stata.com/support/faqs/resources/statalist-faq/#spell
On 3 November 2013 10:52, Tetsuji Tanaka <[email protected]> wrote:
>> > I am an economist and am trying to make the STATA recognise my panel
>> > data of prices as a panel data using the tsset.
>> > However, the dataset has many variables and the STATA gave me an error
>> > message "repeated time values within panel".
>> >
>> > My data has monthly time variable, price, region, shop type, shop size
>> > etc.
>> >
>> > Please let me know about how to deal with the problem if you had similar
>> > experiences.
*
* 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/