Estimating Bias and Lag on Indexes Proposed to Be Moved to Less Than Bimonthly Pricing

• Activity Number: 567
• Type: Contributed
• Date/Time: Wednesday, August 1, 2012 : 2:00 PM to 3:50 PM
• Sponsor: Section on Government Statistics
• Author(s): Onimissi Sheidu*+
• Companies: Bureau of Labor Statistics
• Keywords: Consumer Price Index ; Price Relatives ; Pricing Frequency ; Bias ; Lag ; Simulation

Abstract

The CPI is a monthly measure of the average change in the prices paid by urban consumers for a market basket of consumer goods and services. It is constructed from approximately 8,000 basic indexes, which correspond to 38 geographic (87 PSUs) areas and 211 item categories. Although the prices of these items for the construction of the CPI are collected regularly, (usually on a monthly or bimonthly basis), not all these prices change at the same rate or even exhibit change. It has been suggested that some of the items with slower rate of change be moved to a less than bimonthly period of pricing. This study tries to assess and determine the existence of bias and lag for indexes with less than bimonthly pricing. The result of this study shows a very limited presence of small bias and lag on indexes of very few item strata that is not widespread either in scope or intensity for the pricing frequencies proposed and the index areas involved.