Using Frame Information to Enhance the Quality of a Price Index

The Consumer Price Index (CPI) calculation proceeds in stages. In the first stage, price indices are estimated for the elementary aggregates of a CPI, which consist of small and homogeneous sets of products defined within the consumption classification used in the CPI. These elementary indices are aggregated to obtain higher-level indices using the elementary expenditure aggregates as weights (ILO, 2004). In order to better represent the market shares of various types of stores selling the same types of products, it is possible to stratify by outlet type. This raises questions as to which level would be more appropriate to define as the elementary aggregate. Using information available on the survey frame or from administrative data to derive market shares to represent the strata contributions, this paper aims to assess the impact on the index of the switch from the Jevons to the Laspeyres index at a given level of aggregation. In this study we compare, using a Jevons index at a lower level, followed by combining all “type of outlets” strata using a Laspeyres index to using a Jevons index at the current level with weights to reflect market shares. The use of weights under the typical elementary level is also studied