Working Paper: CEPR ID: DP15663
Authors: Sarah Lein; Rahel Braun
Abstract: Official statistics measuring the cost of living are known to suffer from several biases. This paper shows that the size of the biases can vary with economic conditions. Using homescan data, it is first confirmed that official price indexes can be tracked using such granular datasets. While the often-acknowledged substitution bias is shown to be relatively small, neglected preference adjustment and product entry/exit results in a 2.6 percentage point bias in the annual inflation rate on average. Furthermore, the bias is particularly large in the aftermath of a shock to relative prices, increasing to 3.7 percentage points.
Keywords: Homescan data; Inflation measurement; Bias in inflation indexes
JEL Codes: E31; E4; E5; C3; C23
Edges that are evidenced by causal inference methods are in orange, and the rest are in light blue.
| Cause | Effect |
|---|---|
| traditional price indexes (C43) | overestimate inflation (E31) |
| substitution bias (D11) | overestimate inflation (E31) |
| preference adjustment bias (D91) | overestimate inflation (E31) |
| product entry-exit bias (L11) | overestimate inflation (E31) |
| relative price shocks (P22) | increase bias size (C46) |
| preference adjustment bias after relative price shocks (D11) | overall inflation measurement bias (E31) |
| CUPI inflation rate (E31) | decline after exchange rate shock (F31) |
| traditional index (C43) | decline after exchange rate shock (F31) |