Advances in antithetic time series analysis: separating fact from artifact

Journal Title: Operations Research and Decisions - Year 2016, Vol 26, Issue 3

Abstract

The problem of biased time series mathematical model parameter estimates is well known to be insurmountable. When used to predict future values by extrapolation, even a de minimis bias will even-tually grow into a large bias, with misleading results. This paper elucidates how combining antithetic time series’ solves this baffling problem of bias in the fitted and forecast values by dynamic bias can-cellation. Instead of growing to infinity, the average error can converge to a constant.

Authors and Affiliations

Dennis RIDLEY

Keywords

Related Articles

On the core of a cost allocation problem under asymmetric information

We study a cost allocation problem under asymmetric information, and show that the ex ante incentive compatible core is non-empty. We also obtain a non-emptiness result for the incentive compatible coarse core, which is...

Probabilities on streams and reflexive games

Probability measures on streams (e.g. on hypernumbers and p-adic numbers) have been defined. It was shown that these probabilities can be used for simulations of reflexive games. In particular, it can be proved that Auma...

The optimal portfolio under VaR and ES

An analysis of the dependence structure among certain European indices (FTSE100, CAC40, DAX30, ATX20, PX, BUX and BIST) has been conducted. The main features of the financial data were studied: asymmetry, fat-tailedness...

The role of normal logical form in decision-making and knowledge management

The normal form in logic has been considered. Any propositional function, i.e. any finite logical expression can be written in such a form. This indicates the possibility of an unequivocal logical representation of many...

Using a multicriteria interactive approach in scheduling non-critical activities

A typical project consists of many activities. Logical dependencies cause some of them to be critical and some non-critical. While critical activities have a strict start time, in some projects the problem of selecting t...

Download PDF file
  • EP ID EP323622
  • DOI -
  • Views 42
  • Downloads 0

How To Cite

Dennis RIDLEY (2016). Advances in antithetic time series analysis: separating fact from artifact. Operations Research and Decisions, 26(3), 57-68. https://europub.co.uk/articles/-A-323622