To: Elroy Jetson who wrote (5379 ) 5/1/2004 7:15:06 AM From: Haim R. Branisteanu Read Replies (1) | Respond to of 116555 thanks for the information. I was under the impression that the "equivalent rent" was introduced at the same time. Do you know when did the BLS started to have an index of home prices and in which year they added hedonic adjustments to CPI?In 1997, BLS started the process of developing a new housing sample to replace the one that had been in use since 1987, and began using it starting with the index for January 1999. BLS dropped the owner sample and returned to the method that was used for the rental equivalence index when it was first introduced, that is, reweighting the renter sample to represent owner-occupied units. This decision was made for several reasons: Moving implicit rents by matching renter and owner observations is inherently a reweighting of the rent sample. A large portion of the 1987 sample was devoted to owners, to support the estimation of initial implicit rent. By dropping the owner sample, the field staff would not have to initiate, price, and maintain an owner sample. Because owner-renter matching is not needed for rental equivalence, the calculation of the index would be greatly simplified. Sample Selection for the 1999 CPI Housing Sample Geographic stratification. Research performed by BLS using 1980 and 1990 census data indicated that location is the most important variable in determining rent change. Once geography is taken into account, only rent level is significant in predicting rent change. Geographic stratification was used for several reasons: It helps ensure sample coverage for the major characteristics (geography and rent level) that are correlated with rent change. Stratification is the best way to correlate renter-occupied units with owner-occupied units in the same neighborhood, in order to produce the rental equivalence index. Housing units constructed after 1990 can be located and assigned to the existing geographic strata, as described below. Using data from the 1990 census, CPI analysts, as before, divided the CPI areas into segments (neighborhoods). These segments were then stratified by location within each CPI area. Six geographic strata were formed in each CPI area. Once geography is taken into account, only rent level is significant in predicting rent change, so the stratification boundaries were determined using information about population and median rent level. Weighting during segment sample selection. CPI analysts then selected segments in the strata to represent housing units constructed before 1990. Because the rent and rental equivalence indexes measure the change in the price of the shelter service provided by both renter-occupied and owner-occupied housing, segments were selected with probability proportional to estimated total expenditures for rent and implicit rent.bls.gov