Working Paper: NBER ID: w18181
Authors: John H. Cochrane
Abstract: I translate familiar concepts of discrete-time time-series to contnuous-time equivalent. I cover lag operators, ARMA models, the relation between levels and differences, integration and cointegration, and the Hansen-Sargent prediction formulas.
Keywords: Continuous-time models; Linear models; ARMA processes; Lag operators; Economic modeling
JEL Codes: C01; C5; C58; E17; G17
Edges that are evidenced by causal inference methods are in orange, and the rest are in light blue.
| Cause | Effect |
|---|---|
| Discrete-time models (C32) | Continuous-time models (C32) |
| Choice of model representation (C52) | Complexity of economic phenomena (D00) |
| Continuous-time models (C32) | Better understanding of underlying processes (D80) |
| Differential form (C69) | Retains predictive capacity of discrete-time models (C22) |
| Laplace transforms (C69) | Analyzing relationships between variables (C39) |
| Continuous-time models (C32) | Better capture dynamics of economic variables in response to shocks (E13) |
| Conditions for stationarity and cointegration (C22) | Understanding relationships in discrete and continuous contexts (C25) |
| Beveridge-Nelson decomposition and error correction representation (C22) | Modeling non-stationary processes (C22) |