Working Paper: NBER ID: w9980
Authors: C. Lanier Benkard; Patrick Bajari
Abstract: We show that hedonic price indexes may be biased when not all product characteristics are observed. We derive two primary sources of bias. The first is a classical selection problem that arises due to changes over time in the values of unobserved characteristics. The second comes from changes in the implicit prices of unobserved characteristics. Next, we show that the bias can be corrected for under fairly general assumptions using extensions of factor analysis methods. We test our methods empirically using a new comprehensive monthly data set for desktop personal computer systems. For this data we find that the standard hedonic index has a slight upward bias of approximately 1.4\\% per year. We also find that omitting an important characteristic (CPU benchmark) causes a large bias in the index with standard methods, but that this bias is essentially eliminated when the proposed correction is applied.
Keywords: No keywords provided
JEL Codes: E3; C1; D6
Edges that are evidenced by causal inference methods are in orange, and the rest are in light blue.
| Cause | Effect |
|---|---|
| unobserved characteristics improve over time (O49) | upward bias in price index estimates (C43) |
| products exit the sample (Y60) | upward bias in price index estimates (C43) |
| omitting an important characteristic (CPU benchmark) (L15) | substantial bias in price index calculations (C43) |
| including CPU benchmark (C88) | reduction in bias in price index calculations (C43) |
| bias due to selection (C24) | biased price index calculations (C43) |