Making linear prediction perform like maximum likelihood in Gaussian autoregressive model parameter estimation

2020 ◽  
Vol 166 ◽  
pp. 107256 ◽  
Author(s):  
Çağatay Candan
Keyword(s):  
Parameter Estimation ◽  
Maximum Likelihood ◽  
Autoregressive Model ◽  
Linear Prediction ◽  
Model Parameter ◽  
Model Parameter Estimation

scholarly journals Formantinių požymių išskyrimo metodai

2008 ◽  
Vol 42 (43) ◽  
pp. 201-206
Author(s):  
Antanas Leonas Lipeika
Keyword(s):  
Feature Extraction ◽  
Parameter Estimation ◽  
Prediction Model ◽  
Linear Prediction ◽  
Point Of View ◽  
Model Parameter ◽  
Model Parameter Estimation ◽  
Levinson Algorithm ◽  
Linear Prediction Model ◽  
Autocorrelation Method

Straipsnyje nagrinėjami formantinių požymių išskyrimo metodai. Formantinių požymių išskyrimas remiasi spektro pikų radimu apskaičiuotame iš tiesinės prognozės modelio parametrųų spektre. Formantini ų požymių išskyrimo patikimumas priklauso nuo tiesinės prognozės modelio parametrų vertinimo metodo. Anksčiau tiesinės prognozės modelio parametrų vertinimui naudojome autokoreliacinį metodą, kuris neužtikrindavo patikimo formantinių požymių išskyrimo. Todėl, siekiant padidinti formantini ų požymių išskyrimo patikimumų, ieškoma geresnio tiesinės prognozės modelio parametrų vertinimo metodo. Autokoreliacinis tiesinės prognozės modelio parametrų vertinimo metodas lyginamas su kovariaciniu, Burg, Marple metodais ir modifikuotu Split Levinson algoritmu. Tyrimais nustatyta, kad pagal formančių trajektorijų išskyrimą kovariacinis, Burg, Marple tiesinės prognozės modelio parametrų vertinimo metodai iš esmės nesiskiria nuo autokoreliacinio, o modifikuotu Split Levinson algoritmu gauname daug patikimesnius formančių trajektorijų įverčius.Formant feature extraction methodsAntanas Leonas Lipeika SummaryFormant feature extraction is investigated in the paper. Extraction of formant features is based on calculating frequency positions of spectral peaks. The spectrum has been calculated from parameters of linear prediction model. Reliability of formant feature extraction depends on the method used for linear prediction model parameter estimation. The autocorrelation method previously used for linear prediction model parameter estimation was not reliable enough for formant feature extraction. Therefore we were looking for more reliable method of linear prediction model parameter estimation. The previously used autocorrelation method was compared with covariance, Burg, Marple methods and the modified Split Levinson algorithm. It was concluded, that autocorrelation, covariance, Burg and Marple methods are similar from the point of view of formant feature extraction. The modified Split Levinson algorithm provides the best formant feature estimates.

l2-Penalized temporal logit-mixed models for the estimation of regional obesity prevalence over time

2021 ◽  
pp. 096228022110175
Author(s):  
Jan P Burgard ◽  
Joscha Krause ◽  
Ralf Münnich ◽  
Domingo Morales
Keyword(s):  
Parameter Estimation ◽  
Medical Treatment ◽  
Mixed Models ◽  
Generalized Linear Mixed Models ◽  
Linear Mixed Models ◽  
Obesity Prevalence ◽  
Model Parameter ◽  
Model Parameter Estimation ◽  
Public Health Reporting ◽  
Over Time

Obesity is considered to be one of the primary health risks in modern industrialized societies. Estimating the evolution of its prevalence over time is an essential element of public health reporting. This requires the application of suitable statistical methods on epidemiologic data with substantial local detail. Generalized linear-mixed models with medical treatment records as covariates mark a powerful combination for this purpose. However, the task is methodologically challenging. Disease frequencies are subject to both regional and temporal heterogeneity. Medical treatment records often show strong internal correlation due to diagnosis-related grouping. This frequently causes excessive variance in model parameter estimation due to rank-deficiency problems. Further, generalized linear-mixed models are often estimated via approximate inference methods as their likelihood functions do not have closed forms. These problems combined lead to unacceptable uncertainty in prevalence estimates over time. We propose an l2-penalized temporal logit-mixed model to solve these issues. We derive empirical best predictors and present a parametric bootstrap to estimate their mean-squared errors. A novel penalized maximum approximate likelihood algorithm for model parameter estimation is stated. With this new methodology, the regional obesity prevalence in Germany from 2009 to 2012 is estimated. We find that the national prevalence ranges between 15 and 16%, with significant regional clustering in eastern Germany.

scholarly journals Joint Vehicle Trajectory and Model Parameter Estimation Using Road Side Sensors

2015 ◽  
Vol 15 (9) ◽  
pp. 5075-5086 ◽  
Author(s):  
Roland Hostettler ◽  
Wolfgang Birk ◽  
Magnus Lundberg Nordenvaad
Keyword(s):  
Parameter Estimation ◽  
Model Parameter ◽  
Model Parameter Estimation ◽  
Vehicle Trajectory
Sign in / Sign up

Export Citation Format

Share Document