Notice: On March 31, it was **announced** that Statalist is moving from an email list to a **forum**. The old list will shut down on April 23, and its replacement, **statalist.org** is already up and running.

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

From |
"Ivica Rubil" <irubil@eizg.hr> |

To |
<statalist@hsphsun2.harvard.edu> |

Subject |
st: positive own-price effects |

Date |
Thu, 1 Dec 2011 17:55:42 +0100 |

Dear all: I have an issue not directly related to Stata, but presumably there are a number of Statalist members who are familiar with the topic of my interest. I'm estimating a complete demand system; QUAIDS, to be more specific. The problem is that I systematically positive own-price effects form most of the 13 goods in the model. I don't know what would be the reason for such counterintuitive -- indeed, contra-theory -- results, but I suspect there is sth wrong with the prices that I'm using, namely unit values (expenditure on good divided by physical quantity of good) instead of genuine prices. Even when I tired, instead of QUAIDS, a very simple specification like regress w1 lnp1 lnp2 lnp3 lnp3 ... lnp13 lntotalexp I get positive coefficient on lnp1. And similarly for all other goods. Maybe it is due to the way in which I have assigned unit values to households: 1. I have generated average unit values for year-region pairs for each good (food items) 2. Since I need food items on higher level of aggregation (e.g., meat, and not pork, beef, etc. separately) I have to aggregate somehow the average unit values generated in step (1.). To do this I computed weighted averages of these separate averages from the first step, using as weights shares of each of the goods in the appropriate group of goods (e.g., beef, pork,... in the group meat) 3. Such "prices" are then used instead of genuine prices. Does anybody have any suggestion? Thanks, ir -- Ivica Rubil Ekonomski institut / The Institute of Economics, Zagreb a. Trg J. F. Kennedyja 7, 10 000 Zagreb, Croatia t. +385-1-2362-269 f. +385-1-2335-165 e. irubil@eizg.hr www.eizg.hr * * 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/

- Prev by Date:
**Re: st: Graphing longitudinal profiles** - Next by Date:
**st: mmregress question** - Previous by thread:
**st: Re: xtmixed slope cross validation** - Next by thread:
**st: mmregress question** - Index(es):