Abstract: Smoothing and prognosis belong to the main problems, which we deal with when process various time series. Unlike the typical approaches related with lineal regression on polynomial and trigonometric functions we consider local procedures. We describe algorithms that resolve these problems and present results of experiments using data of the Russian State Statistical Committee. All procedures are realized in the Excel-VBA.

Keywords: econometrics, local regression, time series, seasonality

ACM Classification Keywords: I.2.m Miscellaneous

Link:

SMOOTHING AND PROGNOSIS OF MULTI-FACTOR TIME SERIES OF ECONOMICAL DATA BY MEANS OF LOCAL PROCEDURES (REGRESSION AND CURVATURE EVALUATION)

Alexander Kovaldji, Vladimir Averkiev, Marina Sarkissyan

http://foibg.com/ibs_isc/ibs-27/ibs-27-p05.pdf