Order Selection Criteria Research Articles

The Quality of Lagged Products and Autoregressive Yule–Walker Models as Autocorrelation Estimates

The sample autocorrelation function is defined by the mean lagged products (LPs) of random observations. It is the inverse Fourier transform of the raw periodogram. Both contain the same information, and the quality of the full-length sample autocorrelation to represent random data is as poor as that of a raw periodogram. The autoregressive (AR) Yule-Walker method uses LP autocorrelation estimates to compute AR parameters as a parametric model for the autocorrelation. The order of the AR model can be taken as the full LP length, or it can be determined with an order selection criterion. However, the autocorrelation function can more accurately be estimated with a general parametric time-series method. This parametric estimate of the autocorrelation function always has better accuracy than the LP estimates. The LP autocorrelation function is as long as the observation window, but parametric estimates will eventually die out. They allow an objective answer to the question of how long the autocorrelation function really is.

Factors affecting false-negative rates on ex vivo sentinel lymph node mapping in colorectal cancer

Purpose Despite the increasing use of sentinel lymph node (SLN) mapping after colorectal cancer resection, reported node identification and false-negative rates vary considerably. The main aim of this prospective study was to quantify the false-negative rates on SLN mapping after resection and to evaluate factors influencing them. Methods Sixty-nine patients with biopsy-proven cancer of the colon and rectum underwent SLN mapping according to a protocol involving the ex vivo submucosal and peritumoral injection of 2–4 ml of Patent Blue V dye. All lymph nodes visualized were marked as SLN and totally embedded, then two 4 μm sections were cut for hematoxylin and eosin staining, and cytokeratin (AE1/AE3) immunostaining. A standard examination of the whole specimen and of the regional non-sentinel lymph nodes was also performed. Results SLNs were identified in 97.3% of the evaluable cases. A mean of 5.0 SLNs were removed per patient (SD ± 4.2). Nine false negatives were identified. Rectal cancer, tumor size > 60 mm, number of metastatic non-sentinel lymph nodes, and mucinous tumors were associated with false-negative SLNs. At multivariate analysis, a rectal location and mucinous differentiation were independently associated with false-negative SLNs. Conclusions Ex vivo SLN mapping after colorectal cancer surgery is technically feasible with a high identification rate. Tumor size and stage, rectal involvement and a mucinous histology seem to interfere with the reliability of SLN staging. It is mandatory to standardize the procedure and selection criteria in order to deal with the question of the reliability of SLN mapping in colorectal cancer.

Sow behaviour towards humans during standard management procedures and their relationship to piglet survival

Piglet crushing remains a major problem in pig production and is partly related to sow behavioural traits. The sows’ responses to the presence of humans around farrowing could partly contribute to piglet crushing through increased reactivity and getting up and lying down behaviour. The aim of the study was to determine if the sows’ behaviour observed during standard management procedures during gestation and after farrowing can be related with their reproductive performance including crushing levels. One hundred sows originating from a selection unit were observed before expected farrowing on their fear (withdrawal) response to human presence at feeding and their ease of transfer to the farrowing unit. After farrowing, their reaction was observed (latency to change position, number of postural changes) during a 5 min period of piglet handling (tattooing, tail cutting) and through the number of postural changes for the next 3 h. Parity influenced most of the behaviour observed during gestation, but not after farrowing. A high withdrawal response of sows tended to be correlated with higher transfer speed to the farrowing unit ( P = 0.10), was correlated with a shorter latency to change position and with more postural changes during piglet handling ( P < 0.05), and was correlated with higher crushing levels ( P < 0.05). Little effort needed for transfer and high transfer speed were to some extent associated with higher crushing levels ( P = 0.10 and P < 0.01). Latency to change posture during piglet handling was negatively correlated with the frequency of postural changes during piglet handling and the number of behavioural acts shown during this handling ( P < 0.01). No significant correlation was found between the number of postural changes after farrowing and crushing levels. No clear significant correlations were found between the different behavioural observations and the number of live-born and stillborn piglets. Although overall significant correlations are low, these results suggest that behavioural responses observed during standard management procedures can be related to piglet survival. Therefore, some of the behavioural observations could be used as selection criteria in order to improve sows’ reproductive performance.

Conjugate-Prior-Penalized Learning of Gaussian Mixture Models for Multifunction Myoelectric Hand Control

This paper presents a new learning method for Gaussian mixture models (GMMs) to improve their generalization ability. A traditional maximum a posterior (MAP) parameter estimate is used to achieve regularization based on conjugate priors. Plus, a model order selection criterion is derived from Bayesian-Laplace approaches, using the conjugate priors to measure the uncertainty of the estimated parameters. As a result, the proposed learning method avoids the possibility of convergence toward the boundary of the parameter space, and is also capable of selecting the optimal order for a GMM with more enhanced stability than conventional methods using a flat prior. When applying the proposed learning method to construct a GMM classifier for electromyogram (EMG) pattern recognition, the proposed GMM classifier achieves a high generalization ability and outperforms conventional classifiers in terms of recognition accuracy.

Likelihood-Based Hypothesis Tests for Brain Activation Detection From MRI Data Disturbed by Colored Noise: A Simulation Study

Functional magnetic resonance imaging (fMRI) data that are corrupted by temporally colored noise are generally preprocessed (i.e., prewhitened or precolored) prior to functional activation detection. In this paper, we propose likelihood-based hypothesis tests that account for colored noise directly within the framework of functional activation detection. Three likelihood-based tests are proposed: the generalized likelihood ratio (GLR) test, the Wald test, and the Rao test. The fMRI time series is modeled as a linear regression model, where one regressor describes the task-related hemodynamic response, one regressor accounts for a constant baseline and one regressor describes potential drift. The temporal correlation structure of the noise is modeled as an autoregressive (AR) model. The order of the AR model is determined from practical null data sets using Akaike's information criterion (with penalty factor 3) as order selection criterion. The tests proposed are based on exact expressions for the likelihood function of the data. Using Monte Carlo simulation experiments, the performance of the proposed tests is evaluated in terms of detection rate and false alarm rate properties and compared to the current general linear model (GLM) test, which estimates the coloring of the noise in a separate step. Results show that theoretical asymptotic distributions of the GLM, GLR, and Wald test statistics cannot be reliably used for computing thresholds for activation detection from finite length time series. Furthermore, it is shown that, for a fixed false alarm rate, the detection rate of the proposed GLR test statistic is slightly, but (statistically) significantly improved compared to that of the common GLM-based tests. Finally, simulations results reveal that all tests considered show seriously inferior performance if the order of the AR model is not chosen sufficiently high to give an adequate description of the correlation structure of the noise, whereas the effects of (slightly) overmodeling are observed to be less harmful.

Literary Text in the Spanish as a Foreign Language Class: Proposals and Use Models

This article aims to propose the introduction of the literary text to the programs of Spanish as a foreign language (S/FL). The literary text in this frame is meant to be a communication act and a means for teaching / learning Spanish as a foreign language within an institutionalized and artificial context made suitable for an intermediate / advanced student profile. The research gives considerable importance to the literary text as an input that catalyzes a variety of both oral and written activities and as a didactical means integrating communication skills. Moreover, it establishes some selection criteria in order to target the characteristics of the texts to be used, in accordance with linguistic goals, contents and students' needs and interests, suggesting some useful didactical and methodological parameters for enhancing suitable activities for all text types. Finally, two practical proposals for transforming a literary text into a communication activity are presented.&#x0D; Received: 26-02-2008/ Accepted: 10-08-2008&#x0D; How to reference this article:&#x0D; Jouini, K. (2008). El texto literario en la clase de español como lengua extranjera: propuestas y modelos de uso. Íkala. 13(2), pp.121-159.&#x0D;

Electricity demand loads modeling using AutoRegressive Moving Average (ARMA) models

This study addresses the problem of modeling the electricity demand loads in Greece. The provided actual load data is deseasonilized and an AutoRegressive Moving Average (ARMA) model is fitted on the data off-line, using the Akaike Corrected Information Criterion (AICC). The developed model fits the data in a successful manner. Difficulties occur when the provided data includes noise or errors and also when an on-line/adaptive modeling is required. In both cases and under the assumption that the provided data can be represented by an ARMA model, simultaneous order and parameter estimation of ARMA models under the presence of noise are performed. The produced results indicate that the proposed method, which is based on the multi-model partitioning theory, tackles successfully the studied problem. For validation purposes the produced results are compared with three other established order selection criteria, namely AICC, Akaike's Information Criterion (AIC) and Schwarz's Bayesian Information Criterion (BIC). The developed model could be useful in the studies that concern electricity consumption and electricity prices forecasts.

Cross Entropy Approximation of Structured Gaussian Covariance Matrices

We apply two variations of the principle of minimum cross entropy (the Kullback information measure) to fit parameterized probability density models to observed data densities. For an array beamforming problem with P incident narrowband point sources, sensors, and colored noise, both approaches yield eigenvector fitting methods similar to that of the MUSIC algorithm and of the oblique transformation in factor analysis. Furthermore, the corresponding cross entropies (CE) are related to the MDL model order selection criterion .

Modeling of the grounding resistance variation using ARMA models

This study addresses the problem of modeling the variation of the grounding resistance during the year. An AutoRegressive Moving Average (ARMA) model is fitted (off-line) on the provided actual data using the Corrected Akaike Information Criterion (AICC). The developed model is shown to fit the data in a successful manner. Difficulties occur when the provided data includes noise or errors and also when an on line/adaptive modeling is required. In both cases, and under the assumption that the provided data can be represented by an ARMA model, simultaneous order and parameter estimation of ARMA models under the presence of noise is necessary. In this paper, a new method based on the multi-model partitioning theory which is also applicable to on line/adaptive operation, is used for the solution of the above mentioned problem. The simulations show that the proposed method succeeds in selecting the correct ARMA model order and estimates the parameters accurately in very few steps and even with a small sample size. For validation purposes the method introduced is compared with three other established order selection criteria presenting very good results. The proposed method can be extremely useful in the studies of electrical engineer designers, since the variation of the grounding resistance during the year affects significantly power systems performance and must be definitely considered.

Recursive parametric tests for multichannel adaptive signal detection

The problem of detecting a multichannel signal in spatially and temporally coloured disturbances is considered. The parametric Rao and parametric generalised likelihood ratio test detectors, recently developed by modelling the disturbance as a multichannel autoregressive (AR) process, have been shown to perform well with limited or even no range training data. These parametric detectors, however, assume that the model order of the multichannel AR process is known a priori to the detector. In practice, the model order has to be estimated by some model order selection technique. Meanwhile, a standard non-recursive implementation of the parametric detectors is computationally intensive since the unknown parameters have to be estimated for all possible model orders before the best one is identified. To address these issues, herein the joint model order selection, parameter estimation and target detection are considered. We present recursive versions of the aforementioned parametric detectors by integrating the multichannel Levinson algorithm, which is employed for recursive and computationally efficient parameter estimation, with a generalised Akaike Information Criterion for model order selection. Numerical results show that the proposed recursive parametric detectors, assuming no knowledge of the model order, yield a detection performance nearly identical to that of their non-recursive counterparts at significantly reduced complexity.

Nonparametric Functional Mapping of Quantitative Trait Loci Underlying Programmed Cell Death

The development of an organism represents a complex dynamic process, which is controlled by a network of genes and multiple environmental factors. Programmed cell death (PCD), a physiological cell suicide process, occurs during the development of most organisms and is, typically, a complex dynamic trait. Understanding how genes control this complex developmental process has been a long-standing topic in PCD studies. In this article, we propose a nonparametric model, based on orthogonal Legendre polynomials, to map genes or quantitative trait loci (QTLs) that govern the dynamic features of the PCD process. The model is built under the maximum likelihood-based functional mapping framework and is implemented with the EM algorithm. A general information criterion is proposed for selecting the optimal Legendre order that best fits the dynamic pattern of the PCD process. The consistency of the order selection criterion is established. A nonstationary structured antedependence model (SAD) is applied to model the covariance structure among the phenotypes measured at different time points. The developed model generates a number of hypothesis tests regarding the genetic control mechanism of the PCD process. Extensive simulation studies are conducted to investigate the statistical behavior of the model. Finally, we apply the model to a rice tiller number data set in which several QTLs are identified. The developed model provides a quantitative and testable framework for assessing the interplay between genes and the developmental PCD process, and will have great implications for elucidating the genetic architecture of the PCD process.

Contributions of Professor Hirotugu Akaike in Statistical Science

Professor Hirotugu Akaike was awarded the 2006 Kyoto Prize for “his major contribution to statisticalscience and model ing with the Akaike Information Criterion (AIC)”. In 1973, he proposed the AIC as a naturalextension of the log-likelihood. The most natural way of applying the AIC is to use it as the model selection or order selection criterion. In the MAICE (minimum AIC estimation) procedure, the model with the minimum value of the AIC is selected as the best one among many possible models. This provided a versatile procedure for statistical modeling that is free from the ambiguities inherent in application of the hypothesis test procedure. However, the impact of the AIC is not limited to the realization of an automatic model selection procedure, and it eventually led to a paradigm shift in statisticalscience. In conventionalstatisticalinference, the theories of estimation and test are developed under the assumption of the presence of a true model. However, in statistical modeling, the model should be constructed based on the entire knowledge such as the established theory, empirical facts, current observations and even the objective of the analysis. Prof. Akaike gave a practical answer to the selection of the prior distribution of the Bayes model. Due to the development of information technologies, we can now access to huge amounts of data in various fields of science and social life. In this information and knowledge society, the Bayes modelis becoming a key technology. In this article, we shall look back at his research in five stages, namely, the launching period, frequency domain time series analysis, time series modeling, AIC and statistical modeling and Bayes modeling (Parzen et al. (1998)). It should be noted here that the reader will notice that his research was always performed based on the needs of researchers in the real-world.

Source Enumeration via the EEF Criterion

Recently, the exponentially embedded families (EEF) criterion for model order selection has been proposed based on the theories of exponentially embedded families and sufficient statistics. In this letter, it is proved that the EEF criterion is consistent, and then the EEF is used to determine the number of sources in array signal processing. Computer simulation results demonstrate better performance of the EEF criterion for closely spaced sources, at low SNR and/or a small number of snapshots.

Application of the multi-model partitioning theory for simultaneous order and parameter estimation of multivariate ARMA models

In this paper, a study on how to perform simultaneous order and parameter estimation of multivariate (MV) ARMA (autoregressive moving average) models under the presence of noise is addressed. The proposed method, which is computationally efficient, is an extension of a previously presented method for MV AR models and is based on the well established and widely applied multi-model partitioning theory. A series of computer simulations indicate that the method is infallible in selecting the correct model order in very few steps. The simultaneous estimation of the multivariate ARMA parameters is also another benefit of the proposed method. The results are compared with two other established order selection criteria namely Akaike's Information Criterion (AIC) and Schwarz's Bayesian Information Criterion (BIC). Finally, it is shown that the method is also successful in tracking model order changes, in real time.

Model Order Selection Criterion For Monitoring Haemoglobin Status In Dengue Patients Using Armax Model

Abstract This paper describes the development of linear autoregressive moving average with exogenous input (ARMAX) models to monitor the progression of dengue infection based on hemoglobin status. Three differents ARMAX model order selection criteria namely Final Prediction Error (FPE), Akaike’s Information Criteria (AIC) and Lipschitz number have been evaluated and analyzed. The results showed that Lipschitz number has better accuracy compared to FPE and AIC. Finally based on Lipschitz number, appropriate model orders have been selected to monitor the progression of dengue patients based on hemoglobin status. Further work is to apply this appropriate model orders to nonlinear Autoregressive (NARMAX) model.

Fundamental resolution limits of closely spaced random signals

Fundamental limitations on estimation accuracy are well known and include a variety of lower bounds including the celebrated Cramer-Rao lower bound. However, similar theoretical limitations on resolution have not yet been presented. The authors exploit results from detection theory for deriving fundamental limitations on resolution. In this correspondence the authors discuss the case of zero mean random Gaussian signals with a general and predefined covariance matrix observed with additive white Gaussian noise. The results are general and are not based on any specific resolution technique and therefore hold for any method and for any probability of successful resolution. The resolution limit is a simple expression of the observation interval, the pre-specified resolution success probability and the second derivative of the covariance matrix. As an example, the authors discuss the bearing resolution of two emitters with closely spaced direction of arrival, impinging on an array of sensors. The theoretical limits are compared with empirical performance of the model order selection criteria known as the Akaike information criterion and the minimum description length.

O-40 An automated breast cancer grading demonstrator – Pathscore

Despite the increasing use of sentinel lymph node (SLN) mapping after colorectal cancer resection, reported node identification and false-negative rates vary considerably. The main aim of this prospective study was to quantify the false-negative rates on SLN mapping after resection and to evaluate factors influencing them.Sixty-nine patients with biopsy-proven cancer of the colon and rectum underwent SLN mapping according to a protocol involving the ex vivo submucosal and peritumoral injection of 2–4 ml of Patent Blue V dye. All lymph nodes visualized were marked as SLN and totally embedded, then two 4 μm sections were cut for hematoxylin and eosin staining, and cytokeratin (AE1/AE3) immunostaining. A standard examination of the whole specimen and of the regional non-sentinel lymph nodes was also performed.SLNs were identified in 97.3% of the evaluable cases. A mean of 5.0 SLNs were removed per patient (SD ± 4.2). Nine false negatives were identified. Rectal cancer, tumor size > 60 mm, number of metastatic non-sentinel lymph nodes, and mucinous tumors were associated with false-negative SLNs. At multivariate analysis, a rectal location and mucinous differentiation were independently associated with false-negative SLNs.Ex vivo SLN mapping after colorectal cancer surgery is technically feasible with a high identification rate. Tumor size and stage, rectal involvement and a mucinous histology seem to interfere with the reliability of SLN staging. It is mandatory to standardize the procedure and selection criteria in order to deal with the question of the reliability of SLN mapping in colorectal cancer.

O-41 Improved methods of detection of lymphovascular invasion demonstrate that it is the predominant method of vascular invasion in breast cancer and has important clinical consequences

Despite the increasing use of sentinel lymph node (SLN) mapping after colorectal cancer resection, reported node identification and false-negative rates vary considerably. The main aim of this prospective study was to quantify the false-negative rates on SLN mapping after resection and to evaluate factors influencing them.Sixty-nine patients with biopsy-proven cancer of the colon and rectum underwent SLN mapping according to a protocol involving the ex vivo submucosal and peritumoral injection of 2–4 ml of Patent Blue V dye. All lymph nodes visualized were marked as SLN and totally embedded, then two 4 μm sections were cut for hematoxylin and eosin staining, and cytokeratin (AE1/AE3) immunostaining. A standard examination of the whole specimen and of the regional non-sentinel lymph nodes was also performed.SLNs were identified in 97.3% of the evaluable cases. A mean of 5.0 SLNs were removed per patient (SD ± 4.2). Nine false negatives were identified. Rectal cancer, tumor size > 60 mm, number of metastatic non-sentinel lymph nodes, and mucinous tumors were associated with false-negative SLNs. At multivariate analysis, a rectal location and mucinous differentiation were independently associated with false-negative SLNs.Ex vivo SLN mapping after colorectal cancer surgery is technically feasible with a high identification rate. Tumor size and stage, rectal involvement and a mucinous histology seem to interfere with the reliability of SLN staging. It is mandatory to standardize the procedure and selection criteria in order to deal with the question of the reliability of SLN mapping in colorectal cancer.

Bias Correction in Dynamic Panels under Time Series Misspecification

This paper considers higher-order autoregressive (AR(p)) panel models with fixed effects, where the lag order p is unknown and possibly misspecified. A pooled least squares estimator is considered and its asymptotic biases are studied. Specifically, we first extend the N-asymptotic bias formula in Nickell (1981) to the case where the dynamics follow a general autoregressive form. Second, √(NT)-normalized limit distribution for the pooled estimators is developed that allows for lag order misspecification, when both N and T are large. Third, a higher order approximation for the bias up to order N^(-1)T^(-2) is explored. Besides the well-known endogeneity bias incurred by the within-transformation in dynamic fixed-effects models, additional bias under misspecification is analytically derived, which argues that model specification should precede any bias correction in dynamic panel modeling. We suggest a general form for bias correction, which specifically incorporates the lag order selection. A consistent lag order selection criterion is also proposed, which is more suitable for large panel system with fixed effects. Some extensions of the bias correction are also considered under exogenous variable, and the bias corrected short-run and long-run coefficients are discussed. Lastly, as an empirical application, a study on habit formation in consumption preferences is presented using U.S. state-level data.

Robust Bayesian general linear models

We describe a Bayesian learning algorithm for Robust General Linear Models (RGLMs). The noise is modeled as a Mixture of Gaussians rather than the usual single Gaussian. This allows different data points to be associated with different noise levels and effectively provides a robust estimation of regression coefficients. A variational inference framework is used to prevent overfitting and provides a model order selection criterion for noise model order. This allows the RGLM to default to the usual GLM when robustness is not required. The method is compared to other robust regression methods and applied to synthetic data and fMRI.