Conditional Forecasting Task

From GM-RKB
(Redirected from Conditional Forecasting)
Jump to navigation Jump to search

A Conditional Forecasting Task is a multi-predictor forecasting task with a sequential mixed multi-predictor dataset.



References

2012

  • (Kunst, 2012) ⇒ Robert M. Kunst. (2012). “Econometric Forecasting - Conditional forecasting." Lecture Notes.
    • Economists are often interested in forecasts for [math]\displaystyle{ x_{t+h} }[/math] that assume [math]\displaystyle{ x_s, s \le t }[/math] as known as well as the values of other variables [math]\displaystyle{ y_s, s \le t + h }[/math]. The solution appears to be [math]\displaystyle{ E\left(x_{t+h} | x^t_{-\infty} \cup y^{t+h}_{-\infty}\right) }[/math].
      • The assumed values [math]\displaystyle{ y_{t+1},..., y_{t+h} }[/math] may be incorrect;
      • Any dynamic model that views [math]\displaystyle{ x_t }[/math] as a function of [math]\displaystyle{ x^{t-1}_{-\infty} }[/math] and [math]\displaystyle{ y^{t}_{-\infty} }[/math] may miss the reaction of y to past x (feedback problem, open loop, weak and strong exogeneity);
      • Changing the generation mechanism for [math]\displaystyle{ y }[/math] relative to the observations may affect the reaction of [math]\displaystyle{ y }[/math] (super exogeneity).

2005