An official website of the United States government
This study examines the effect of attrition of the housing sample on the price-change variance and index estimates of the housing component of the Consumer Price Index. Attrition rates from 1999 to 2004 were calculated for different variables and applied to the housing sample as it existed in the six-month period of March through August 2004 to model the size and makeup of the housing sample through the next 10 years. Simulated price relative calculations were run on these reduced samples to obtain estimates of the price-change variance and index estimates. Then, they were compared with full sample estimates.