Search Results - subject:"Expectation–maximization"

Marked point process hotspot maps for homicide and gun crime prediction in Chicago

Mohler, George - In: International Journal of Forecasting 30 (2014) 3, pp. 491-497

Crime hotspot maps are a widely used and successful method of displaying spatial crime patterns and allocating police resources. However, hotspot maps are often created over a single timescale using only one crime type. In the case of short-term hotspot maps that utilize several weeks of crime...

Persistent link: https://www.econbiz.de/10010786461

Parameter estimation of two-level nonlinear mixed effects models using first order conditional linearization and the EM algorithm

Fu, Liyong; Wang, Mingliang; Lei, Yuancai; Tang, Shouzheng - In: Computational Statistics & Data Analysis 69 (2014) C, pp. 173-183

, using first order conditional expansion (FOCE) and the expectation–maximization (EM) algorithm. The FOCE–EM algorithm was …

Persistent link: https://www.econbiz.de/10010871365

Mixtures of equispaced normal distributions and their use for testing symmetry with univariate data

Bacci, Silvia; Bartolucci, Francesco - In: Computational Statistics & Data Analysis 71 (2014) C, pp. 262-272

constrained and unconstrained log-likelihoods, by means of the Expectation–Maximization algorithm, symmetry is tested against …

Persistent link: https://www.econbiz.de/10010871403

Lower confidence limit for reliability based on grouped data using a quantile-filling algorithm

Zhang, Mimi; Hu, Qingpei; Xie, Min; Yu, Dan - In: Computational Statistics & Data Analysis 75 (2014) C, pp. 96-111

The aim of this paper is to propose an approach to constructing lower confidence limits for a reliability function and investigate the effect of a sampling scheme on the performance of the proposed approach. This is accomplished by using a data-completion algorithm and certain Monte Carlo...

Persistent link: https://www.econbiz.de/10010871428

Factor analysis parameter estimation from incomplete data

Roberts, W.J.J. - In: Computational Statistics & Data Analysis 70 (2014) C, pp. 61-66

An expectation–maximization (EM) algorithm for factor analysis parameter estimation when observations are missing is …

Persistent link: https://www.econbiz.de/10011056502

Conditional Markov regime switching model applied to economic modelling

Goutte, Stéphane - In: Economic Modelling 38 (2014) C, pp. 258-269

, we extend the classical Expectation–Maximization (EM) algorithm to be applied to our regime switching model. We apply it …

Persistent link: https://www.econbiz.de/10010753344

Conditional Markov regime switching model applied to economic modelling

Goutte, Stéphane - In: Economic modelling 38 (2014), pp. 258-269

Persistent link: https://www.econbiz.de/10010419115

Marked point process hotspot maps for homicide and gun crime prediction in Chicago

Mohler, George - In: International journal of forecasting 30 (2014) 3, pp. 491-497

Persistent link: https://www.econbiz.de/10010512295

Quantile Forecasting for Credit Risk Management using possibly Mis-specified Hidden Markov Models

Banachewicz, Konrad; Lucas, André - 2007

Recent models for credit risk management make use of Hidden Markov Models (HMMs). The HMMs are used to forecast quantiles of corporate default rates. Little research has been done on the quality of such forecasts if the underlying HMM is potentially mis-specified. In this paper, we focus on...

Persistent link: https://www.econbiz.de/10010325238

Quantile Forecasting for Credit Risk Management using possibly Mis-specified Hidden Markov Models

Banachewicz, Konrad; Lucas, André - Tinbergen Institute - 2007

Persistent link: https://www.econbiz.de/10005136969