• The Journal of the Acoustical Society of Korea
• /
• v.39 no.1
• /
• pp.32-37
• /
• 2020

This paper proposes a new l₁-norm-Recursive Least Squares (RLS) algorithm which is numerically more robust than the conventional l₁-norm-RLS. The l₁-norm-RLS was proposed by Eksioglu and Tanc in order to estimate the sparse acoustic channel. However the algorithm has numerical instability in the inverse matrix calculation. In this paper, we propose a new algorithm which is robust against the numerical instability. We show that the proposed method improves stability under several numerically erroneous situations.

• Economic and Environmental Geology
• /
• v.28 no.4
• /
• pp.433-438
• /
• 1995

The most popular minimization method is based on the least-squares criterion, which uses the $L_2$ norm to quantify the misfit between observed and synthetic data. The solution of the least-squares problem is the maximum likelihood point of a probability density containing data with Gaussian uncertainties. The distribution of errors in the geophysical data is, however, seldom Gaussian. Using the $L_2$ norm, large and sparsely distributed errors adversely affect the solution, and the estimated model parameters may even be completely unphysical. On the other hand, the least-absolute-deviation optimization, which is based on the $L_1$ norm, has much more robust statistical properties in the presence of noise. The solution of the $L_1$ problem is the maximum likelihood point of a probability density containing data with longer-tailed errors than the Gaussian distribution. Thus, the $L_1$ norm gives more reliable estimates when a small number of large errors contaminate the data. The effect of outliers is further reduced by M-fitting method with Cauchy error criterion, which can be performed by iteratively reweighted least-squares method.

• The Journal of the Acoustical Society of Korea
• /
• v.29 no.6
• /
• pp.374-380
• /
• 2010

It is known that the problem of FIR filtering with noisy input and output data can be solved by a total least squares (TLS) estimation. It is also known that the performance of the TLS estimation is very sensitive to the ratio between the variances of the input and output noises. In this paper, we propose a convex combination algorithm between the ordinary recursive LS based TLS (RTLS) and the ordinary recursive LS (RLS). This combined algorithm is robust to the noise variance ratio and has almost the same complexity as the RTLS. Simulation results show that the proposed algorithm performs near TLS in noise variance ratio ${\gamma}{\approx}1$ and that it outperforms TLS and LS in the rage of 2 < $\gamma$ < 20. Consequently, the practical workability of the TLS method applied to noisy data has been significantly broadened.

• The Korean Journal of Applied Statistics
• /
• v.17 no.3
• /
• pp.519-533
• /
• 2004

In this paper, we suggest quasi-likelihood estimation (QLE) method and its robust version in estimating spatial dependence modelled through variogram used for spatial data modelling. We compare the statistical characteristics of the estimators with other popular least squares estimators of parameters for variogram model by simulation study. The QLE method for estimating spatial dependence has the advantages that it does not need the concept of lags commonly required for least squares estimation methods as well as its statistical superiority. The QLE method also shows the statistical superiority to the other methods for the tested Gaussian and non-Gaussian spatial processes.

• Proceedings of the KSRS Conference
• /
• 2005.10a
• /
• pp.47-51
• /
• 2005

Using satellite images, an optimal solution to water motion has been presented in this study. Since temperature patterns are suitable tracers in water motion, Sea Surface Temperature (SST) images of Caspian Sea taken by MODIS sensor on board Terra satellite have been used in this study. Two daily SST images with 24 hours time interval are used as input data. Computation of templates correspondence between pairs of images is crucial within motion algorithms using non-rigid body objects. Image matching methods have been applied to estimate water body motion within the two SST images. The least squares matching technique, as a flexible technique for most data matching problems, offers an optimal spatial solution for the motion estimation. The algorithm allows for simultaneous local radiometric correction and local geometrical image orientation estimation. Actually, the correspondence between the two image templates is modeled both geometrically and radiometrically. Geometric component of the model includes six geometric transformation parameters and radiometric component of the model includes two radiometric transformation parameters. Using the algorithm, the parameters are automatically corrected, optimized and assessed iteratively by the least squares algorithm. The method used in this study, has presented more efficient and robust solution compared to the traditional motion estimation schemes.

• Journal of Sensor Science and Technology
• /
• v.26 no.6
• /
• pp.371-378
• /
• 2017

An accurate and robust estimation of center of rotation (CoR) using optical marker trajectory is crucial in human biomechanics. In this regard, the performances of the two prevailing least-squares methods, the Gamage and Lasenby (GL) method, and the Chang and Pollard (CP) method, are verified in this paper. While both methods are sphere-fitting approaches in closed form and require no tuning parameters, they have not been thoroughly verified by comparison of their estimation accuracies. Furthermore, while for both methods, results for stationary CoR locations are presented, cases for perturbed CoR locations have not been investigated for any of them. In this paper, the estimation performances of the GL method and CP method are investigated by varying the range of motion (RoM) and noise amount, for both stationary and perturbed CoR locations. The difference in the estimation performance according to the variation in the amount of noise and RoM was clearly shown for both methods. However, the CP method outperformed the GL method, as seen in results from both the simulated and the experimental data. Particularly, when the RoM is small, the GL method failed to estimate the appropriate CoR while the CP method reasonably maintained the accuracy. In addition, the CP method showed a considerably better predictability in CoR estimation for the perturbed CoR location data than the GL method. Accordingly, it may be concluded that the CP method is more suitable than the GL method for CoR estimation when RoM is limited and CoR location is perturbed.

• Communications for Statistical Applications and Methods
• /
• v.18 no.6
• /
• pp.761-770
• /
• 2011

Robust principal components regression is suggested to deal with both the multicollinearity and outlier problem. A main aspect of the robust principal components regression is the selection of an optimal set of principal components. Instead of the eigenvalue of the sample covariance matrix, a selection criterion is developed based on the condition index of the minimum volume ellipsoid estimator which is highly robust against leverage points. In addition, the least trimmed squares estimation is employed to cope with regression outliers. Monte Carlo simulation results indicate that the proposed criterion is superior to existing ones.

• The Korean Journal of Applied Statistics
• /
• v.19 no.1
• /
• pp.97-110
• /
• 2006

Since it is well-established that even high quality data tend to contain outliers, one would expect fat? greater reliance on robust regression techniques than is actually observed. But most of all robust regression estimators suffers from the computational difficulties and the lower efficiency than the least squares under the normal error model. The weighted self-tuning estimator (WSTE) recently suggested by Lee (2004) has no more computational difficulty and it has the asymptotic normality and the high break-down point simultaneously. Although it has better properties than the other robust estimators, WSTE does not have full efficiency under the normal error model through the weighted least squares which is widely used. This paper introduces a new approach as called the reweighted WSTE (RWSTE), whose scale estimator is adaptively estimated by the self-tuning constant. A Monte Carlo study shows that new approach has better behavior than the general weighted least squares method under the normal model and the large data.

• The Journal of Asian Finance, Economics and Business
• /
• v.7 no.10
• /
• pp.543-553
• /
• 2020

This paper examines the effect of COVID-19 pandemic on the Philippine stock exchange, peso-dollar rate and retail price of diesel using robust least squares regression and vector autoregression (VAR). The robust least squares regression using MM-estimation method concluded that COVID-19 daily infection has negative and statistically significant effect on the Philippine stock exchange index, peso-dollar exchange rate and retail pump price of diesel. This is consistent with the results of correlation diagnostics. As for the VAR model, the lag values of the independent variable disclose significance in explaining the Philippine stock exchange index, peso-dollar exchange rate and retail pump price of diesel. Moreover, in the short run, the impulse response function confirmed relative effect of COVID-19 daily infections and the variance decomposition divulge that COVID-19 daily infections have accounted for only minor portion in explaining fluctuations of the Philippine stock exchange index, peso-dollar exchange and retail pump price of diesel. In the long term, the influence levels off. The Granger causality test suggests that COVID-19 daily infections cause changes in the Philippine stock exchange index and peso-dollar exchange rate in the short run. However, COVID-19 infection has no causal link with retail pump price of diesel.

• Communications for Statistical Applications and Methods
• /
• v.1 no.1
• /
• pp.33-40
• /
• 1994

The conditional expectation of a random variable in a multivariate normal random vector is a multiple linear regression on its predecessors. Using this fact, the least median of squares estimation method developed in a multiple linear regression is adapted to a multivariate data to identify influential observations. The resulting method clearly detect outliers and it avoids the masking effect.