• Communications for Statistical Applications and Methods
• /
• 제26권4호
• /
• pp.371-383
• /
• 2019

Panel data sets have been developed in various areas, and many recent studies have analyzed panel, or longitudinal data sets. Maximum likelihood (ML) may be the most common statistical method for analyzing panel data models; however, the inference based on the ML estimate will have an inflated Type I error because the ML method tends to give a downwardly biased estimate of variance components when the sample size is small. The under estimation could be severe when data is incomplete. This paper proposes the restricted maximum likelihood (REML) method for a random effects panel data model with a censored dependent variable. Note that the likelihood function of the model is complex in that it includes a multidimensional integral. Many authors proposed to use integral approximation methods for the computation of likelihood function; however, it is well known that integral approximation methods are inadequate for high dimensional integrals in practice. This paper introduces to use the moments of truncated multivariate normal random vector for the calculation of multidimensional integral. In addition, a proper asymptotic standard error of REML estimate is given.

• 대한원격탐사학회지
• /
• 제39권6_1호
• /
• pp.1491-1495
• /
• 2023

본 연구는 북극의 해빙표면온도(ice surface temperature, IST)를 자동화된 기계 학습(automated machine learning, AutoML) 기반으로 산출하였다. AutoML 기반 IST는 상관관계(correlation coefficient, R) 0.97, 평균 제곱근 오차(root mean squared error, RMSE) 2.51K로 산출되었다. 심층신경망(deep neural network, DNN) 모델과 비교하여 AutoML IST는 Moderate Resolution Imaging Spectroradiometer (MODIS) IST 및 ice mass balance (IMB) buoy IST와의 검증 결과에서 좋은 정확도를 보인다. 이는 어려운 극지방 조건에서 IST 추정 정확도를 향상시키는 AutoML의 효과를 강조한다.

• Communications for Statistical Applications and Methods
• /
• 제14권3호
• /
• pp.561-576
• /
• 2007

Five plotting positions are applied to the computation of probability weighted moments (PWM) on the parameters of the generalized logistic distribution. Over a range of parameter values with some finite sample sizes, the effects of five plotting positions are investigated via Monte Carlo simulation studies. Our simulation results indicate that the Landwehr plotting position frequently tends to document smaller biases than others in the location and scale parameter estimations. On the other hand, the Weibull plotting position often tends to cause larger biases than others. The plotting position (i - 0.35)/n seems to report smaller root mean square errors (RMSE) than other plotting positions in the negative shape parameter estimation under small samples. In comparison to the maximum likelihood (ML) method under the small sample, the PWM do not seem to be better than the ML estimators in the location and scale parameter estimations documenting larger RMSE. However, the PWM outperform the ML estimators in the shape parameter estimation when its magnitude is near zero. Sensitivity of right tail quantile estimation regarding five plotting positions is also examined, but superiority or inferiority of any plotting position is not observed.

• Structural Engineering and Mechanics
• /
• 제89권3호
• /
• pp.283-300
• /
• 2024

Machine learning (ML) models based on artificial neural network (ANN) and decision tree (DT) were developed for estimation of axial capacity of concrete columns reinforced with fiber reinforced polymer (FRP) bars. Between the design codes, the Canadian code provides better formulation compared to the Australian or American code. For empirical models based on elastic modulus of FRP, Hadhood et al. (2017) model performed best. Whereas for empirical models based on tensile strength of FRP, as well as all empirical models, Raza et al. (2021) was adjudged superior. However, compared to the empirical models, all ML models exhibited superior performance according to all five performance metrics considered. The performance of ANN and DT models were comparable in general. Under the present setup, inclusion of the transverse reinforcement information did not improve the accuracy of estimation with either ANN or DT. With selective use of inputs, and a much simpler ANN architecture (4-3-1) compared to that reported in literature (Raza et al. 2020: 6-11-11-1), marginal improvement in correlation could be achieved. The metrics for the best model from the study was a correlation of 0.94, absolute errors between 420 kN to 530 kN, and the range being 0.39 to 0.51 for relative errors. Though much superior performance could be obtained using ANN/DT models over empirical models, further work towards improving accuracy of the estimation is indicated before design of FRP reinforced concrete columns using ML may be considered for design codes.

• Journal of Communications and Networks
• /
• 제15권3호
• /
• pp.245-251
• /
• 2013

This paper addresses the issue of time-difference-of-arrival (TDOA) estimation for complex noncircular signals. First, under the wide-sense stationary assumption, we derive the maximum likelihood (ML) estimator and the Cramer-Rao lower bound for Gaussian noncircular signals in Gaussian circular noise. The ML estimator uses the second-order statistics information of a noncircular signal more comprehensively when compared with the cross-correlation (CC) and the conjugate CC estimators. Further, we present a scheme to modify the traditional signal-selective TDOA methods for noncircular signals on the basis of the cyclostationarity of man-made signals. This scheme simultaneously exploits the information contained in both the cyclic cross-correlation (CCC) and the conjugate CCC of a noncircular signal.

• Communications for Statistical Applications and Methods
• /
• 제23권2호
• /
• pp.131-146
• /
• 2016

In research on behavioral studies, significant attention has been paid to the stage-sequential process for longitudinal data. Latent class profile analysis (LCPA) is an useful method to study sequential patterns of the behavioral development by the two-step identification process: identifying a small number of latent classes at each measurement occasion and two or more homogeneous subgroups in which individuals exhibit a similar sequence of latent class membership over time. Maximum likelihood (ML) estimates for LCPA are easily obtained by expectation-maximization (EM) algorithm, and Bayesian inference can be implemented via Markov chain Monte Carlo (MCMC). However, unusual properties in the likelihood of LCPA can cause difficulties in ML and Bayesian inference as well as estimation in small samples. This article describes and addresses erratic problems that involve conventional ML and Bayesian estimates for LCPA with small samples. We argue that these problems can be alleviated with a small amount of prior input. This study evaluates the performance of likelihood and MCMC-based estimates with the proposed prior in drawing inference over repeated sampling. Our simulation shows that estimates from the proposed methods perform better than those from the conventional ML and Bayesian method.

• Journal of the Korean Data and Information Science Society
• /
• 제16권3호
• /
• pp.651-656
• /
• 2005

In this paper the quasi-likelihood function was proposed and the estimators which are the solutions of the estimating equations for estimation of a class of nonlinear time series models. We compare the performances of the proposed estimators with those of the ML estimators under the heavy-railed distributions by simulation.

• 한국통신학회논문지
• /
• 제34권12C호
• /
• pp.1184-1191
• /
• 2009

본 논문에서는 IEEE 802.15.4a IR-UWB Ranging 시스템을 위한 주파수 옵셋 추정기를 제안한다. 주파수 옵셋 추정은 실내 다중경로 환경에서의 고정밀 Ranging을 위해 반드시 필요한 것으로 IEEE 802.15.4a 시스템에 적합한 주파수 옵셋 추정기의 제안이 필수이다. 먼저 IR-UWB 패킷에서 Ternary 프리앰블 코드 특징을 이용하여 ML 기반 주파수 옵셋 추정기를 제안하고, 하드웨어 구현을 위해 복잡도가 낮은 주파수 옵셋 추정기를 제안한다. 제안된 두 개의 주파수 옵셋 추정기 성능을 확인하기 위하여 이론적 분석을 수행하였고, IEEE 802.15.4a 다중 경로 채널 모델을 이용한 시뮬레이션을 통하여 다중 경로 환경에서도 주파수 옵셋 추정 성능이 우수함을 증명한다.

• The Journal of the Acoustical Society of Korea
• /
• 제20권3E호
• /
• pp.25-30
• /
• 2001

In angle of arrival estimation, the direction of a signal is usually assumed to be a point. If the direction of a signal is distributed due to some reasons in real surroundings, however, angle of arrival estimation techniques based on the point source assumption may result in poor performance. In this paper, we consider angle of arrival estimation when the signal sources are distributed. A parametric source model is proposed, and the estimation techniques based on the well-known maximum likelihood technique is considered under the model. In addition, Various statistical properties of the estimation errors were obtained.

• 한국정보통신학회논문지
• /
• 제20권1호
• /
• pp.45-51
• /
• 2016

본 논문에서는 전체 송신 안테나 중 일부 안테나만을 활성화하여 신호 송신에 사용하는 일반화 공간변조(Generalized Spatial Modulation) 시스템을 위한 최대우도 수신기를 제안한다. 제안 수신기는 신호 검출시 채널 정보 오차의 효과를 완화시키기 위하여 채널 정보 오차로 인해 생성되는 실질 잡음 신호의 순시 공분산 행렬을 추정한다. 추정된 공분산 행렬은 검출 정확도를 높이기 위해 반복수행을 통해 갱신되며, 추정 결과는 최대 우도 검출에 사용된다. 모의 실험 결과에서 기존의 채널 정보 오차를 고려하지 않는 수신기와 비교하여 높은 성능을 얻음을 확인할 수 있다.