Re: st: Re: Analyzing time series data on prices by districts & markets

[Chris Parker <cparker.phd2007@london.edu>]

Hi Partho,

It looks like you want to do something like this:

> 1.      For each date, the total number of markets (over all states and
> districts) for which a price is reported, and

bysort date: gen nummarkets = _N

> 2.      The maximum number of markets for which a price is reported for any
> date in the datasets

Are you wanting a variable with a constant equal to the maximum number
of mandis open on each day? If so:

egen maxmarkets = max(nummarkets)

> In addition, to do a geographical analysis, I would like to record,
> for each date
>
> 1.      The number of reporting markets in each district versus the total
> no. of markets in that district,

egen markettag = tag(market)
bysort state district: egen marketsindistrict = total(markettag)
bysort state district date: gen marketsopen = _N
gen percentmarketsopen = marketsopen/marketsindistrict

> 2.      The number of districts in each state for which prices are
> reported, versus the total no. of districts in that state

egen districttag = tag(district)
bysort state: egen numdistricts = total(districttag)
bysort state date: egen districtswithprices = total(districttag)
gen percentdistrictswithprices = districtswithprices/numdistricts

> 3.      Similarly, the number of states for which prices are reported,
> versus the total no. of state s where a price is ever reported

egen statetag = tag(state)
bysort state: egen numstates = total(statetag)
bysort state date: egen stateswithprices = total(statetag)
gen percentstateswithprices = stateswithprices/numstates


Chris

Chris Parker

________________________________

PhD Candidate | Management Science & Operations
London Business School | Regent's Park | London NW1 4SA | United Kingdom
Direct line +44 (0)20 7000 8816 | Email cparker.phd2007@london.edu

On Mon, Jun 13, 2011 at 3:30 PM, Partho Sarkar <partho.ss@gmail.com> wrote:
>
> Dear Dr, Cox,
>
> Many thanks for the prompt reply.  I am replying to you directly
> partly because I am not sure how to post a follow-up (please excuse me
> if this is inappropriate)
>
> The data looks like this:
>
> date    state   mkt     dist    price
> 1       Asm     Ca      ach     1700
> 1       Asm     Ka      ari     1450
> 1       Jha     Du      umk     1185
> 1       Jha     Pa      aka     2400
> 2       Asm     Ka      ari     1750
> 2       Ker     Ch      hir     2000
> 2       Ker     Ch      hir     2400
>
> And the first step of the answers for this example would be
>
> #mkts= 5        #dist=6 #states=3
>
>
> Best regards,
>
> Partha S. Sarkar
> Consultant Econometrician
> Indicus Analytics Pvt. Ltd (www.indicus.net)
> New Delhi, India
>
> You wrote:
>
> From      Nick Cox <n.j.cox@durham.ac.uk>
> To        "'statalist@hsphsun2.harvard.edu'" <statalist@hsphsun2.harvard.edu>
> Subject           st: RE: Analyzing time series data on prices by districts & markets
> Date      Mon, 13 Jun 2011 14:27:55 +0100
>
> The list's guidelines preclude attachments but certainly do not
> preclude ASCII text within a posting showing part of your data.
>
> Nick
> n.j.cox@durham.ac.uk
>
> In reply to my question:
>
>
>
>
>
> On Mon, Jun 13, 2011 at 6:21 PM, Partho Sarkar <partho.ss@gmail.com> wrote:
> > Hello all,
> >
> > I am quite new to Stata (and this list), and trying hard to quickly
> > pick up the skills while on the job.  Would really appreciate some
> > help with this task, and please excuse if this seems too elementary!
> >
> > Problem:
> >
> > I have a large dataset which gives prices of a commodity at each date
> > for different markets across the country.  The markets are classified
> > by State, District & Market (names).  (The commodity is only traded in
> > some markets, in some districts, and some states).   I need to get an
> > idea of the periods/dates for which the data are “sparse”, i.e., there
> > are too few of the Markets reporting a price.
> >
> > So I need,
> >
> > 1.      For each date, the total number of markets (over all states and
> > districts) for which a price is reported, and
> > 2.      The maximum number of markets for which a price is reported for any
> > date in the dataset
> >
> > In addition, to do a geographical analysis, I would like to record,
> > for each date
> >
> > 1.      The number of reporting markets in each district versus the total
> > no. of markets in that district,
> > 2.      The number of districts in each state for which prices are
> > reported, versus the total no. of districts in that state
> > 3.      Similarly, the number of states for which prices are reported,
> > versus the total no. of state s where a price is ever reported
> >
> > I hope this is clear, as I think the List rules prevent me from
> > including a preview/sample of my data.
> >
> > Thank you
> >
> > P. Sarkar
> > Consultant Econometrician
> > India
> >
>
> *
> *   For searches and help try:
> *   http://www.stata.com/help.cgi?search
> *   http://www.stata.com/support/statalist/faq
> *   http://www.ats.ucla.edu/stat/stata/
>
> ______________________________________________________________________
>
> This email has been scanned by the MessageLabs Email Security System
> on behalf of the London Business School community.
> For more information please visit http://www.messagelabs.com/email
> ______________________________________________________________________

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