Formula Bias and Within-stratum Substitution Bias in the U.S. CPI

In 1978 BLS adopted an estimator for U.S. CPI component indexes that incorporates scientific samples of outlets and varieties and that allows the calculation of reliable standard errors. Consumer substitution of outlets and varieties offering better values could cause bias in these indexes. A more important source of bias is, however, a tendency to give excessive weight to items whose initial price is temporarily low. The empirical evidence is striking. Average price series and matched food CPIs grew at almost the same rate before 1978, but between 1980 and 1992 the CPIs average about 1.4% per year more growth. For unleaded gasoline, the discrepancy averages 0.8% per year. © 1998 by the President and Fellows of Harvard College and the Massachusetts Institute of Technology