Across-Design Uncertainty in Short Pricing Panels: Evidence from Simulated Price Trajectories
2026-08-21 • Machine Learning
Machine Learning
AI summaryⓘ
The authors study how having many price observations but only a few actual price changes affects estimating models that use price data. They show that most of the estimation error comes from differences between possible price change patterns rather than randomness within one observed pattern. Their simulations reveal that adding more units with the same price path reduces noise less than adding units with truly independent price changes. Using a special method to estimate variance across independently priced units improves the accuracy of confidence intervals. Overall, the authors suggest designing experiments or data collection to include more independent price changes to get better estimates.
observational pricing panelprice trajectoryestimation errorgradient boostingresamplingvariance componentPaule-Mandel estimatoridentifying variationempirical coveragesynthetic data-generating process
Authors
Pedro Cadahia Delgado
Abstract
Short observational pricing panels can contain many observations while offering only a small number of distinct price movements. This paper studies the inferential consequences of that distinction in a synthetic data-generating process calibrated to a sparse pricing regime. We separate uncertainty conditional on a realised price trajectory from variation in estimation error across alternative trajectories generated by the same pricing process. In the baseline simulations, the latter component accounts for 97.6% of the variance of estimation error for the gradient-boosted specification. Within-panel resampling procedures use the information of one realised trajectory and do not identify this across-design component. Three results organise the analysis. First, across-design dispersion is well described by the empirical relation sigma_hat approx 0.182 V^(-0.271), where V equals moves times magnitude squared. Second, adding regions sharing a common price path reduces outcome noise but does not create independent price trajectories; conversely, averaging across units with independent design-specific errors reduces dispersion at the standard square root rate. Third, a Paule-Mandel variance component estimated across independently priced units substantially increases empirical coverage in homogeneous simulations, from 0.469 to 0.931. The broader implication is a shift toward designing data-generating processes that create independent identifying variation rather than relying solely on fixed passive panels.