2.1. Econometric techniques: Theory versus practice
Generate an AI Snapshot to get a quick, structured summary of this paper.
A concise AI-generated summary of the paper will appear here once you click Generate AI Snapshot.
TL;DR
The basic concepts used in econometric modeling are introduced, and five prescriptions to avoid common real-world pitfalls in that style of modeling are described, and the paper discusses model development in practice, building upon experience with PURHAPS.
Abstract
This paper introduces the basic concepts used in econometric modeling, and describes five prescriptions to avoid common real-world pitfalls in that style of modeling. The paper begins by comparing econometric modeling with other forms of modeling used in energy modeling and engineering. It describes what an econometric model is, and how to build one. It then gives a detailed explanation of many facets of the five prescriptions: pay attention to uncertainty; don't expect a free lunch when devising specifications; pay attention to prior information; don't expect to draw conclusions without adequate data; and check the historical track record of your model. The issues of generalization and robustness over time receive special attention; they are important in practice, and subtle in theory. Finally, the paper discusses model development in practice, building upon experience with PURHAPS, a model I developed for the Energy Information Administration (EIA).
