Showing 1 - 10 of 1,843
Persistent link: https://www.econbiz.de/10008552392
Persistent link: https://www.econbiz.de/10012237002
methods Our results suggest that model averaging does not dominate other well designed prediction model specification methods … using recursive estimation windows, which dominate other windowing" approaches in our experiments, prediction models …-spread variables in nonlinear prediction specification. …
Persistent link: https://www.econbiz.de/10009372767
prediction model specification methods, and that using “hybrid” combination factor/shrinkage methods often yields superior …-spread variables in nonlinear prediction model specification. …
Persistent link: https://www.econbiz.de/10011052271
methods Our results suggest that model averaging does not dominate other well designed prediction model specification methods … using recursive estimation windows, which dominate other windowing approaches in our experiments, prediction models …-spread variables in nonlinear prediction specification. …
Persistent link: https://www.econbiz.de/10010282841
Persistent link: https://www.econbiz.de/10012030940
Persistent link: https://www.econbiz.de/10011959151
Persistent link: https://www.econbiz.de/10010256842
In this paper, the cross-validation methods namely the <InlineEquation ID="IEq1"> <EquationSource Format="TEX">$$C_{p}$$</EquationSource> <EquationSource Format="MATHML"> <math xmlns:xlink="http://www.w3.org/1999/xlink"> <msub> <mi>C</mi> <mi>p</mi> </msub> </math> </EquationSource> </InlineEquation>, PRESS and GCV are presented under the multiple linear regression model when multicollinearity exists and additional information imposes restrictions among the parameters that should hold in exact terms. The selection...</equationsource></equationsource></inlineequation>
Persistent link: https://www.econbiz.de/10011241324
Large-n studies of conflict have produced a large number of statistically significant results but little accurate guidance in terms of anticipating the onset of conflict. The authors argue that too much attention has been paid to finding statistically significant relationships, while too little...
Persistent link: https://www.econbiz.de/10008855383