Vai ai contenuti. | Spostati sulla navigazione | Spostati sulla ricerca | Vai al menu | Contatti | Accessibilità

| Crea un account

Di Fonzo, Tommaso - Marini, Marco (2012) New Procedures for the Reconciliation of Time Series. [Working Paper] WORKING PAPER SERIES, 6/2012 . , PADOVA (Inedito)

Full text disponibile come:

[img]
Anteprima
Documento PDF
569Kb

Abstract (inglese)

We propose new simultaneous and two-step procedures for reconciling systems of time series subject to temporal and contemporaneous constraints according to a Growth Rates Preservation (GRP) principle. Two nonlinear optimization algorithms are used: an interior-point method applied to the constrained problem and a Newton’s method with Hessian modification applied to a suitably reduced-unconstrained problem. Both techniques exploit the analytic gradient and Hessian of the GRP objective function, making full use of all the derivative information at disposal. We apply the proposed GRP procedures to two large systems of economic series, and compare the results with those of other reconciliation procedures based on the Proportional First Differences (PFD) principle, a linear approximation of the GRP principle widely
used by data-producing agencies. Our experiments show that (i) an optimal solution to the nonlinear GRP problem can be efficiently achieved through the proposed Newton’s optimization algorithms, and (ii) GRP-based procedures preserve better the growth rates in the system than linear PFD solutions, especially for series with high temporal discrepancy and high volatility.


Statistiche Download - Aggiungi a RefWorks
Tipo di EPrint:Working Paper
Anno di Pubblicazione:27 Agosto 2012
Parole chiave (italiano / inglese):Benchmarking, Reconciliation, Movement preservation, Constrained nonlinear optimization, Newton’s method, Interior-point. JEL classification codes: C22, C61, C82.
Settori scientifico-disciplinari MIUR:Area 13 - Scienze economiche e statistiche > SECS-S/01 Statistica
Struttura di riferimento:Dipartimenti > Dipartimento di Scienze Statistiche
Codice ID:7183
Depositato il:10 Set 2014 14:38
Simple Metadata
Full Metadata
EndNote Format

Download statistics

Solo per lo Staff dell Archivio: Modifica questo record