Why Lagged Predictors Can Help Explain Recession Outcomes
Summary
The note gives an econometric rationale for adding lagged versions of predictors to a recession classification model. Its example is the yield curve: an inversion may precede a downturn by many months, so the curve observed earlier can be relevant to whether the economy is entering recession now. The curve’s current level may tell a different story if it has already begun to steepen as the downturn starts.
It connects this timing pattern to partial adjustment and adaptive expectations models. These approaches have different theoretical explanations: one separates short-run from long-run effects, while the other treats observed predictors as carrying expectations that may be revised as outcomes unfold. The answer says both can lead to a regression structure containing current and lagged predictor terms. This is a conceptual justification rather than empirical evidence that lagged features improve a particular classifier; it gives no model specification, validation results, or guidance on selecting lags.
Key ideas
- Earlier predictor values can matter when their effects on outcomes unfold over time.
- A yield curve inversion may precede recession, making its past values useful for current prediction.
- Partial adjustment and adaptive expectations offer distinct explanations for including lags.
- Both explanations can yield models with current and lagged predictor terms.
- The discussion motivates lagged features but does not demonstrate predictive performance for a specific model.
Tags
Full text
# Predictive power of lagged features # Predictive power of lagged features I have to build a classification model to predict recessions. I have selected a set of features (some are economic and some are financial). I have noticed that it is good pratice often to add to the original features also their lagged versions. So basically the features are lagged/shifted forward in the "future" of 1 or more samples. It seems that shifting in the future features samples have some predictive power. See picture below as an example Can anybody please provide me with an econometric justification of this? Thanks Luigi ## Answer by demully (score 3, accepted) https://quant.stackexchange.com/a/60413 In its simplest terms, imagine you were just using the yield curve as your single predictor of recessions. Suppose (horribly simplistically) that curve inversions tend to signal downturns in 12-18 months time. The curve 12-18 months ago is thus a relevant variable for whether the economy is going into recession or not today. It might also be the case that the curve today tends to have started to steepen back up at the point at which the economy starts to shrink. So it might even be the case that the current value of the curve would not then itself be relevant. These kind of effects are classically represented in traditional econometrics as the "partial adjustment model", or as the "adaptive expectations model". The two are grounded in different, almost completely opposed, theoretical/philosophical assumptions. The former assume (and try to distinguish between) the longer-term versus shorter-term effect of your regressors on your response variable. The latter assume that your regressors already embed some (unknown) anticipation about the future of your response, and so the behaviour of your response also has to reflect revisions to these expectations, when the actual outcomes in your regressors play out differently to the (unknown) expected ones. As such, the two models appear very different at first. However, there is a big irony here. You end up with the same final structure modelling either via regression, namely: Y = a.X + b.laggedX + e hope this helps, DEM
Shown in full with attribution under the source's licence. Licence: CC BY-SA 4.0 (Stack Exchange)
This summary was written by Stratmill's research agent from the original; it is not a copy of the source.