,4bstme—A pmeedurefor sequentiaffy eatirnating the parameters and orders of mixed autoregmsive moving-average signaf modefs from tirneserfes data is presented. Iderrtfffftion ia performed by first fderstffying a purely asrtoregmwive aignaf model. Tire parametem and orders of tbe mixed autoregmsaive moving-average proeeaa are then gfven from tbe solutton of sfmple sdgebraic equations involving t...

When outputs of computational models are time series or functions of other continuous variables like distance, angle, etc., it can be that primary interest is in the general pattern or structure of the curve. In these cases, model sensitivity and uncertainty analysis focuses on the effect of model input choices and uncertainties in the overall shapes of such curves. We explore methods for chara...

identifications andanalysis of time series are time consuming, based on trial and error and highlydependent on expert judgments. this is mainly due to the presence of variousmodels for forecasting time series, as well as introducing new techniques foranalysis and predictions. in this paper, expert system structure is used toreplace traditional methods of model identifications for time series. f...

This paper investigates the use of dynamic linear modeling and maximum likelihood estimator for water quality model structure identi cation. In addition to the posterior trajectories of model's parameters, the proposed method also examines the trajectory of the estimated prediction error variance. The premise is that the model predictability should be improved as we move down in a time series. ...

Often an analyst has time series data available from performance monitors and needs to make statistical sense of it for capacity planning purposes. For example, a twenty-four hour column chart produced by averaging multiple days of time interval samples yields a statistically stable view of a resource’s usage characteristics across the day and clearly identifies its busy period. Since monitorin...

In this paper we build a Markov-Switching Autoregressive model to describe a long time series of wind speed measurement. It is shown that the proposed model is able to describe the main characteristics of this time series, and in particular the various time scales which can be observed in the dynamics, from daily to interannual fluctuations.

A method for an evaluation of the error between an unknown parameter and its estimator is developed. Its application enables us to preserve the asymptotic power of a constructed test. Testing problems in AR(1) and ARCH models are studied with a derivation of the asymptotic power function. Also the results are extended to AR(m) time series model.