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: problems with levpet command


From   Nick Cox <[email protected]>
To   "[email protected]" <[email protected]>
Subject   Re: st: problems with levpet command
Date   Wed, 29 Jan 2014 09:40:21 +0000

<>

Thanks for closing the thread here.

Nick
[email protected]


On 29 January 2014 08:10, Skrinjaric Bruno <[email protected]> wrote:
> OK. I think I got it. Apparently, the problem was that I have panel data
> with gaps in time variable, i.e. I have data for years 2008, 2010 and
> 2012.
> I -recode-d variable year to be without gaps, and then -levpet- works.
>
> -----Original Message-----
> From: [email protected]
> [mailto:[email protected]] On Behalf Of Nick Cox
> Sent: Tuesday, January 28, 2014 12:27 PM
> To: [email protected]
> Subject: Re: st: problems with levpet command
>
> OK. I think now that your problem must be something specific to
> -levpet-. I am out of advice because I've never used it and don't know
> anything about its precise assumptions, but
>
> . set trace on
>
> before -levpet- would show where the program fails. If you show the
> results, someone may be able to give advice.
>
>
> Nick
> [email protected]
>
>
> On 28 January 2014 11:19, Skrinjaric Bruno <[email protected]> wrote:
>> Here it is...
>>
>> . summarize lnrva lnl lnrm lnrk id year
>>
>>     Variable |       Obs        Mean    Std. Dev.       Min        Max
>> -------------+--------------------------------------------------------
>>        lnrva |      1047    17,20429    2,074527   8,822554   23,24413
>>          lnl |      1047    4,766175    1,732232          0   9,194313
>>         lnrm |      1047    17,24891    2,236354   8,082948    23,6598
>>         lnrk |      1047     16,8549    2,405058   7,859804   23,52634
>>           id |      1047     2549185     1011692     154288    3964248
>> -------------+--------------------------------------------------------
>>         year |      1047    2009,975    1,627722       2008       2012
>>
>>
>> -----Original Message-----
>> From: [email protected]
>> [mailto:[email protected]] On Behalf Of Nick Cox
>> Sent: Tuesday, January 28, 2014 11:52 AM
>> To: [email protected]
>> Subject: Re: st: problems with levpet command
>>
>> You should only remove zeros with good reason, and you have not given
>> one.
>>
>> On this evidence, you really do have missings, despite your denial.
>> Show us the results of
>>
>> . summarize lnrva lnl lnrm lnrk id year
>>
>> Nick
>> [email protected]
>>
>>
>> On 28 January 2014 10:40, Skrinjaric Bruno <[email protected]>
> wrote:
>>> . d id year
>>>
>>> variable storage   display    value
>>> name          type    format     label      variable label
>>> ---------------------------------------------------------------------
>>> -
>>> --
>>> --------
>>> id                 long    %10.0g                     id of the firm
>>> year              int     %9.0g                        year
>>>
>>>
>>> . destring id year,replace
>>>
>>> id already numeric; no replace
>>> year already numeric; no replace
>>>
>>> No, that's still not it. I have removed zero values in hope of
>>> resolving this problem, but it didn't work.
>>>
>>> -----Original Message-----
>>> From: [email protected]
>>> [mailto:[email protected]] On Behalf Of Nick Cox
>>> Sent: Tuesday, January 28, 2014 11:21 AM
>>> To: [email protected]
>>> Subject: Re: st: problems with levpet command
>>>
>>> You've not told us about -id- and -year-. -levpet- requires a numeric
>
>>> panel identifier.
>>>
>>> If -id- is string, then use -encode-.
>>>
>>> (Removing zero values: why did you do that?)
>>>
>>> Nick
>>> [email protected]
>>>
>>>
>>> On 28 January 2014 09:59, Skrinjaric Bruno <[email protected]>
>> wrote:
>>>> Thanks for quick reply. When I do -describe- this is what I get...
>>>>
>>>> . describe lnrva lnl lnrm lnrk
>>>>
>>>> variable storage   display    value
>>>>    name     type       format     label      variable label
>>>> --------------------------------------------------------------------
>>>> -
>>>> -
>>>> --
>>>> --------
>>>> lnrva           float      %9.0g                               Ln of
>>>> Real VA, deflated by
>>>>
>>>> sectoral deflator
>>>> lnl                 float      %9.0g                            Ln
> of
>>>> labour
>>>> lnrm            float      %9.0g                                Ln
> of
>>>> Real material costs,
>>>>
>>>> deflated by GDP deflator
>>>> lnrk              float      %9.0g                              Ln
> of
>>>> Real capital stock, deflated
>>>>                                                                  by
>>>> GDP deflator
>>>>
>>>>
>>>> Even if I try to destring it, it says they are already numeric...
>>>>
>>>> . destring lnrva lnl lnrm lnrk, replace force lnrva already numeric;
>
>>>> no replace lnl already numeric; no replace lnrm already numeric; no
>>>> replace lnrk already numeric; no replace
>>>>
>>>> I still do not know what to do.
>>>>
>>>>
>>>> -----Original Message-----
>>>> From: [email protected]
>>>> [mailto:[email protected]] On Behalf Of Nick Cox
>>>> Sent: Tuesday, January 28, 2014 10:38 AM
>>>> To: [email protected]
>>>> Subject: Re: st: problems with levpet command
>>>>
>>>> This often means that some variable that should be numeric is really
>
>>>> string. Look carefully at the results of -describe- on the variables
>
>>>> you are using and try using -destring-.
>>>>
>>>> Nick
>>>> [email protected]
>>>>
>>>>
>>>> On 28 January 2014 09:31, Skrinjaric Bruno <[email protected]>
>>> wrote:
>>>>
>>>>> I have only recently started using Stata and I came across a
>>>>> project
>>
>>>>> where I have to use levpet command. I have downloaded st060
>>>>> (SJ-4-2)
>>
>>>>> and installed it.
>>>>>
>>>>> I want to use the following command:
>>>>>
>>>>> . levpet lnrva, free(lnl) proxy(lnrm) capital(lnrk) i(id) t(year)
>>>>> valueadded
>>>>>
>>>>> However I always get to following error:
>>>>>
>>>>> no observations
>>>>> r(2000);
>>>>>
>>>>> I am very sure I have all the observations for the variables I am
>>>> using.
>>>>> I am doing this for every sector according to NACE 1-digit
>>>>> classification and the number of observations ranges from 25 - 1125
>
>>>>> across different sectors.
>>>>> But I removed all missing values, and also all zero values. All
>>>>> variables are in float format.
>>>>>
>>>>> I have also read the help file, but I cannot find the solution to
>>>>> my
>>
>>>>> problem.
>>> *
>>> *   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/
>
> *
> *   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