A recursive approach to parameter estimation in regression and time series models

In this paper we discuss the recursive (or on line) estimation in (i) regression and (ii) autoregressive integrated moving average (ARIMA) time series models. The adopted approach uses Kalman filtering techniques to calculate estimates recursively. This approach is used for the estimation of constant as well as time varying parameters. In the first section of the paper we consider the linear regression model. We discuss recursive estimation both for constant and time varying parameters. For constant parameters, Kalman filtering specializes to recursive least squares. In general, we allow the parameters to vary according to an autoregressive integrated moving average process and update the parameter estimates recursively. Since the stochastic model for the parameter changes will "be rarely known, simplifying assumptions have to be made. In particular we assume a random walk model for the time varying parameters and show how to determine whether the parameters are changing over time. This is illustrated with an example.     

Improvement over bayes prediction in small samples in the presence of model uncertainty

In an online prediction context, the authors introduce a new class of mongrel criteria that allow for the weighing of candidate models and the combination of their predictions based both on model‐based and empirical measures of their performance. They present simulation results which show that model averaging using the mongrel‐derived weights leads, in small samples, to predictions that are more accurate than that obtained by Bayesian weight updating, provided that none of the candidate models is too distant from the data generator.     

Least squares adaptive polynomials

A concept of adaptive least squares polynomials is introduced for modelling time series data. A recursion algorithm for updating coefficients of the adaptive polynomial (of a fixed degree) is derived. This concept assumes that the weights w are such that i) the importance of the data values, in terms of their weights, relative to each other stays fixed, and that ii) they satisfy the update property, i.e., the polynomial does not change if a new data value is a polynomial extrapolate. Closed form results are provided for exponential weights as a special case as they are shown to possess the update property when used with polynomials.

The concept of adaptive polynomials is similar to the linear adaptive prediction provided by the Kalman filter or the Least Mean Square algorithm of Widrow and Hoff. They can be useful in interpolating, tracking and analyzing nonstationary data.     

RECURSIVE ESTIMATION OF THE GENERAL LINEAR MODEL WITH DEPENDENT ERRORS AND MULTIPLE ADDITIONAL OBSERVATIONS1

The techniques for recursive estimation of the general linear model with dependent errors and known second order properties, is generalised to allow for simultaneous addition of an arbitrary number of additional observations. Computational formulae for recursive updating of parameter estimates are derived, together with a sequence of univariate recursive residuals for testing the constancy of the regression relation over time.     

A recursive approach for estimating missing observations in an univariate time series

A linear recursive technique that does not use the Kalman filter approach is proposed to estimate missing observations in an univariate time series. It is assumed that the series follows an invertible ARIMA model. The procedure is based on the restricted forecasting approach, and the recursive linear estimators are optimal in terms of minimum mean-square error.     

The ensemble Kalman filter is an ABC algorithm

The ensemble Kalman filter is the method of choice for many difficult high-dimensional filtering problems in meteorology, oceanography, hydrology and other fields. In this note we show that a common variant of the ensemble Kalman filter is an approximate Bayesian computation (ABC) algorithm. This is of interest for a number of reasons. First, the ensemble Kalman filter is an example of an ABC algorithm that predates the development of ABC algorithms. Second, the ensemble Kalman filter is used for very high-dimensional problems, whereas ABC methods are normally applied only in very low-dimensional problems. Third, recent state of the art extensions of the ensemble Kalman filter can also be understood within the ABC framework.     

Identifiability and estimation of recursive max‐linear models

We address the identifiability and estimation of recursive max‐linear structural equation models represented by an edge‐weighted directed acyclic graph (DAG). Such models are generally unidentifiable and we identify the whole class of DAG s and edge weights corresponding to a given observational distribution. For estimation, standard likelihood theory cannot be applied because the corresponding families of distributions are not dominated. Given the underlying DAG, we present an estimator for the class of edge weights and show that it can be considered a generalized maximum likelihood estimator. In addition, we develop a simple method for identifying the structure of the DAG. With probability tending to one at an exponential rate with the number of observations, this method correctly identifies the class of DAGs and, similarly, exactly identifies the possible edge weights.     

Recursive estimation of bilinear time series models

In this paper we are concerned with the recursive estimation of bilinear models. Some methods from linear time invariant systems are adapted to suit bilinear time series models. The time-varying Kalman filter and associated parameter estimation algorithm is carried on the bilinear time series models. The methods are illustrated with examples.     

Borrowing strength from past data in small domain prediction by kalman filtering - a case

Point and interval estimators for small domains based exclusively on current and domain specific sample observations are generally ineffective because of inadequate sample-sizes. So, borrowing strength from sample values for analogous domains and simultaneously from all relevant past and auxiliary data is useful in deriving improved small domain statistics. Postulating for simplicity a linear regression model with a single covariate and a zero intercept but a time-specific domain-invariant slope we start with “synthetic” generalized regression predictors for the domain totals. These borrow across only domains. For further improvements a simple autoregressive model is postulated for the slope parameters. Employing Kalman filtering the previous predictors are revised to borrow supplementary strength across time. As drastic simplifying assumptions are needed in such predictions the efficacy of the procedure is examined through an empirical exercise using live data as well as simulations. The numerical findings turn out encouraging.     

The Kalman Filter from the Perspective of Goldberger—Theil Estimators

This article is designed to point out the close connection between recursive estimation procedures, such as Kalman filter theory, familiar to control engineers, and linear least squares estimators and estimators that include prior information in the form of linear restrictions, such as mixed estimators and ridge estimators, familiar to statisticians. The only difference between the two points of view seems to be a difference in terminology. To demonstrate this point, it is shown how the Kalman filter equations can be derived from an existing textbook account of linear least squares theory and the notion of combining prior information in linear models, that is, the Goldberger—Theil mixed estimators' point of view. The author advocates the inclusion of these ideas early when least squares estimation concepts are being taught.     

Ensemble Approaches to Estimating the Population Mean with Missing Response

We propose new ensemble approaches to estimate the population mean for missing response data with fully observed auxiliary variables. We first compress the working models according to their categories through a weighted average, where the weights are proportional to the square of the least‐squares coefficients of model refitting. Based on the compressed values, we develop two ensemble frameworks, under which one is to adjust weights in the inverse probability weighting procedure and the other is built upon an additive structure by reformulating the augmented inverse probability weighting function. The asymptotic normality property is established for the proposed estimators through the theory of estimating functions with plugged‐in nuisance parameter estimates. Simulation studies show that the new proposals have substantial advantages over existing ones for small sample sizes, and an acquired immune deficiency syndrome data example is used for illustration.     

Implementation of recursive nonparametric kernel estimation and a monte carlo study on its finite sample properties

The recursive estimator for the conditional mean of a nonparametric regression model with independent observations was thoroughly explored by Ahmad and Lin (1976), and Singh and Ullah (1986). Their studies are mainly concerned with the estimator's asymptotic behaviour. However, they do not include much discussion on the strategy of computing the estimates. In this paper, we provide a convenient implementation of the recursive estimator and examine its finite sample properties through simulation studies. Our study has demonstrated that for relatively short length of recursive updating, the estimates are generally equivalent to their fixed window width counterparts However, we found that substantial recursive updating can seriously lower the estimator's efficiency even though it is a consistent estimator.     

Implementation of recursive nonparametric kernel estimation and a monte carlo study on its finite sample properties

The recursive estimator for the conditional mean of a nonparametric regression model with independent observations was thoroughly explored by Ahmad and Lin (1976), and Singh and Ullah (1986). Their studies are mainly concerned with the estimator's asymptotic behaviour. However, they do not include much discussion on the strategy of computing the estimates. In this paper, we provide a convenient implementation of the recursive estimator and examine its finite sample properties through simulation studies. Our study has demonstrated that for relatively short length of recursive updating, the estimates are generally equivalent to their fixed window width counterparts However, we found that substantial recursive updating can seriously lower the estimator's efficiency even though it is a consistent estimator.     

Robust Kalman tracking and smoothing with propagating and non-propagating outliers

A common situation in filtering where classical Kalman filtering does not perform particularly well is tracking in the presence of propagating outliers. This calls for robustness understood in a distributional sense, i.e.; we enlarge the distribution assumptions made in the ideal model by suitable neighborhoods. Based on optimality results for distributional-robust Kalman filtering from Ruckdeschel (Ansätze zur Robustifizierung des Kalman-Filters, vol 64, 2001; Optimally (distributional-)robust Kalman filtering, arXiv: 1004.3393, 2010a), we propose new robust recursive filters and smoothers designed for this purpose as well as specialized versions for non-propagating outliers. We apply these procedures in the context of a GPS problem arising in the car industry. To better understand these filters, we study their behavior at stylized outlier patterns (for which they are not designed) and compare them to other approaches for the tracking problem. Finally, in a simulation study we discuss efficiency of our procedures in comparison to competitors.     

Recursive online EM estimation of mixture autoregressions

This paper develops a recursive expectation–maximization (REM) algorithm for estimating a mixture autoregression (MAR) with an independent and identically distributed regime transition process. The proposed method, which is useful for long time series as well as for data available in real time, follows a recursive predictor error-type scheme. Based on a slightly modified system to the expectation–maximization (EM) equations for an MAR model, the REM algorithm consists of two steps at each iteration: the expectation step, in which the current unobserved regime transition is estimated from new data using previous recursive estimates, and the minimization step, in which the MAR parameter estimates are recursively updated following a minimization direction. Details of implementation of the REM algorithm are given and its finite-sample performance is shown via simulation experiments. In particular, the EM and REM provide roughly similar estimates, especially for moderate and long time series.     

Multiple hypothesis test for parameter constancy based on recursive residuals

This article presents a multiple hypothesis test procedure that combines two well known tests for structural change in the linear regression model, the CUSUM test and the recursive t test. The CUSUM test is run through the sequence of recursive residuals as usual; if the CUSUM plot does not violate the critical lines, one more step is taken to perform the t test for hypothesis of zero mean based on all recursive residuals. The asymptotic size of this multiple hypothesis test is derived; power simulation results suggest that it outperforms the traditional CUSUM test and complements other tests that are currently stressed in econometrics.     

Multiple hypothesis test for parameter constancy based on recursive residuals

This article presents a multiple hypothesis test procedure that combines two well known tests for structural change in the linear regression model, the CUSUM test and the recursive t test. The CUSUM test is run through the sequence of recursive residuals as usual; if the CUSUM plot does not violate the critical lines, one more step is taken to perform the t test for hypothesis of zero mean based on all recursive residuals. The asymptotic size of this multiple hypothesis test is derived; power simulation results suggest that it outperforms the traditional CUSUM test and complements other tests that are currently stressed in econometrics.     

Prediction theory for autoregressivemoving average processes

This paper reviews statistical prediction theory for autoregressive-moving average processes wing techniques developed in control theory. It demonstrates explicitly the connectioluns between the statistical and control theory literatures. Both the forecasting problem and the Single extraction problem am considered, udng linear least squares methods. Whereas the classical Statistical theory developed by Wiener and Kolmogomv is restricted to stationary stochaotic processes, the recursive techniques known as the Kalman filter are shown to provide a satisfactory treatment of the difference-stationary care and other more general cases. Complete results for non-invertible moving averages are also obtained.     

A kind of stochastic recursive Zero-Sum differential game problem with double obstacles constraint

Abstract

This paper concerns a class of stochastic recursive zero-sum differential game problem with recursive utility related to a backward stochastic differential equation (BSDE) with double obstacles. A sufficient condition is provided to obtain the saddle-point strategy under some assumptions. In virtue of the corresponding relationship of doubly reflected BSDE and mixed game problem, a stochastic linear recursive mixed differential game problem is studied to apply our theoretical result, and here the explicit saddle-point strategy as well as the saddle-point stopping time for the mixed game problem are obtained. Besides, a numeral example is also given to demonstrate the result by virtue of partial differential equations (PDEs) computation method.     

Fourth Quarter Survey of the Economic Outlook

Written mainly for its pedagogical interest, this note deals with the computational formulas for the recursive updating of weighted least squares parameter estimates and the residual sum of squares in the general linear model under the assumption that the errors have a multivariate normal distribution. This approach simplifies considerably the derivations of Haslett (1985).