Greetings,
I am securing access to a panel data set (that is, a data set where each unit has an associated value over a fixed sample of time). The data set consists of a set of buildings, with a set of fixed characteristics, such as size, story height, age, etc. To this we will add a geo-reference attribute (a lat-long coordiante). In the absence of a spatial component, we would estimated some sort of random effects model, using the time series element of the data as our dependent variable Our goal is to test the extent to which adding a spatial component to the model "improves" the fit. I would be very interested in comments from anyone on this list about (1) whether this is an appropriate way to test the influence of location; and (2) Are there alternative approaches we should consider?
Thanks.
Best regards,
Mark
* By using the ai-geostats mailing list you agree to follow its rules ( see http://www.ai-geostats.org/help_ai-geostats.htm )
* To unsubscribe to ai-geostats, send the following in the subject or in the body (plain text format) of an email message to [EMAIL PROTECTED] Signoff ai-geostats
