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]

st: RE: RE: How should I treat my dataset???Paneldata/cross section/clustering


From   Jan Bryla <[email protected]>
To   "[email protected]" <[email protected]>
Subject   st: RE: RE: How should I treat my dataset???Paneldata/cross section/clustering
Date   Thu, 17 Mar 2011 10:55:47 +0100

Now that I think about it, neither number of schools or crime are necessarily time-invariant - the attitude towards crime might be, however. Especially over a longer period of time. But I am sure there are time-invariant examples. 

/Jan

-----Original Message-----
From: [email protected] [mailto:[email protected]] On Behalf Of Jan Bryla
Sent: 17. marts 2011 10:22
To: [email protected]
Subject: st: RE: How should I treat my dataset???Paneldata/cross section/clustering

Hello,
It is not easy to give you a specific answer to your query. That would depend on what would make economic sense. It you believe there are some sort of (unobserved) fixed/random effects then, yes, you should treat your data as multipli-cross section to clear out these effects. But I would assume that there are time-invariant characteristics of a community that affect the prices of housing (e.g. number of schools, crime etc.) that would make sense to control for, other than flood zone. So yes, without having more detail for your setting, I would advocate a form of panel-estimation.

Hope this helps.

Jan Bryla
The Danish Bankers Association




-----Original Message-----
From: [email protected] [mailto:[email protected]] On Behalf Of ajita
Sent: 17. marts 2011 02:07
To: [email protected]
Subject: st: How should I treat my dataset???Paneldata/cross section/clustering

Hi,
  I am trying to determine the effect of flood zone on housing prices. I
have data set that looks like the following:

County  community     saleyear  saleprice flood zone
A           5160            2002      80,000       A
A           5157            2002      ----        AE
A           5157            2001       ---         X
A           5157            2001       ----        ---

My confusion is how should I treat this data in order to get the effect of
independent var on dependent variable. Should I simply use reg command in
stata or is there anything I can do with this kind of data where I have same
county, different communities and different salesyear within community.

Thank you in advance
Ajita

--
View this message in context: http://statalist.1588530.n2.nabble.com/How-should-I-treat-my-dataset-Paneldata-cross-section-clustering-tp6179394p6179394.html
Sent from the Statalist mailing list archive at Nabble.com.
*
*   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/

*
*   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/

*
*   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/


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