Affiliations: [a] Istat and University of Padova, Padova, Italy | [b] Statistics Department, International Monetary Fund,
Washington, D.C., USA
Correspondence:
[*]
Corresponding author: 700 19th Street NW,
Washington, D.C., 20431, USA. Tel.: +1 202 623 7028; E-mail:
[email protected]
Abstract: We present a new technique for temporally benchmarking a time series according to
a Growth Rates Preservation (GRP) principle. This procedure basically looks for
the solution to a non linear program, according to which a smooth, non-convex
function of the unknown values of the target time series has to be minimized
subject to linear equality constraints which link the more frequent series to a
given, less frequent benchmark series. We develop a Newton's method with Hessian
modification applied to a suitably reduced-unconstrained problem. This method
exploits the analytic Hessian of the GRP objective function, making full use of
all the derivative information at disposal. We show that the proposed technique
is easy to implement, computationally robust and efficient, all features which
make it a plausible competitor of other benchmarking procedures currently used
by statistical agencies.
