Home About us Contact
|
Home About us Contact | ||
|
|
||
Fitted Model (fitted + model)
Selected AbstractsINAR(1) modeling of overdispersed count series with an environmental applicationENVIRONMETRICS, Issue 4 2008Harry Pavlopoulos Abstract This paper is concerned with a novel version of the INAR(1) model, a non-linear auto-regressive Markov chain on ,, with innovations following a finite mixture distribution of Poisson laws. For , the stationary marginal probability distribution of the chain is overdispersed relative to a Poisson, thus making INAR(1) suitable for modeling time series of counts with arbitrary overdispersion. The one-step transition probability function of the chain is also a finite mixture, of m Poisson-Binomial laws, facilitating likelihood-based inference for model parameters. An explicit EM-algorithm is devised for inference by maximization of a conditional likelihood. Alternative options for inference are discussed along with criteria for selecting m. Integer-valued prediction (IP) is developed by a parametric bootstrap approach to ,coherent' forecasting, and a certain test statistic based on predictions is introduced for assessing performance of the fitted model. The proposed model is fitted to time series of counts of pixels where spatially averaged rain rate exceeds a given threshold level, illustrating its capabilities in challenging cases of highly overdispersed count data. Copyright © 2007 John Wiley & Sons, Ltd. [source] Classification of protein crystallization images using Fourier descriptorsJOURNAL OF APPLIED CRYSTALLOGRAPHY, Issue 3 2007James Foadi The two-dimensional Fourier transform (2D-FT) is well suited to the extraction of features to differentiate image texture, and the classification of images based on information acquired from the frequency domain provides a complementary method to approaches based within the spatial domain. The intensity, I, of the Fourier-transformed images can be modelled by an equation of power law form, I = Ar,, where A and , are constants and r is the radial spatial frequency. The power law is fitted over annuli, centred at zero spatial frequency, and the parameters, A and ,, determined for each spatial frequency range. The variation of the fitted parameters across wedges of fixed polar angle provides a measure of directionality and the deviation from the fitted model can be exploited for classification. The classification results are combined with an existing method to classify individual objects within the crystallization drop to obtain an improved overall classification rate. [source] MODELING VARIETAL EFFECT ON THE WATER UPTAKE BEHAVIOR OF MILLED RICE (ORYZA SATIVA L.) DURING SOAKINGJOURNAL OF FOOD PROCESS ENGINEERING, Issue 6 2007B.K. YADAV ABSTRACT Milled rice is soaked until saturation before cooking and other processing. The soaking behavior of the milled rice is affected by varietal factor as well as initial moisture content (M0) of the samples. In the present study, tests were performed for milled whole kernels of 10 rice varieties ranging from low to high amylose content (16,29% d.b.) with three initial moisture levels (approximately 8, 12 and 16% d.b.) for monitoring water uptake in rice kernels during soaking at room temperature (25 ± 1C), in relation to the varietal differences manifested by the physicochemical properties. The water uptake by milled rice kernels took place at a faster rate in the beginning and was followed by a diminishing rate finally leading to a saturated value during soaking. The water uptake of the kernels during soaking could be best expressed by a modified exponential relationship with R2 values ranging from 0.971 to 0.998 for all varieties. The slope of the fitted straight line between actual and estimated moisture contents of milled rice during soaking using a modified exponential relationship was about unity (0.998) with a high R2 value of 0.989 and a root mean square error of 1.2% d.b. The parameters of the fitted model were the function of the M0 and the physicochemical properties of the milled rice. Using developed relationship, the water uptake of the milled rice during soaking could be estimated from its M0 and the physicochemical properties within±10% of the actual values. PRACTICAL APPLICATIONS This information would be useful for the scientific world working on the soaking characteristics of various varieties of rice, mainly for the modeling of the soaking process. It could also be used as a tool in selecting the rice varieties to meet their desired water uptake properties in relation to their psychochemical properties by rice breeder scientists. [source] Cluster Dynamics: New Evidence and Projections for Computing Services in Great Britain,JOURNAL OF REGIONAL SCIENCE, Issue 2 2005Bernard Fingleton In the main section of the paper, spatial econometric models are estimated controlling for supply- and demand-side conditions to isolate the effect of initial cluster intensity. The paper then projects cluster development using the fitted model, showing how clusters are likely to emerge and intensify. One aspect of the paper is the existence of a de-clustering mechanism due to congestion effects. [source] Robust sequential designs for nonlinear regressionTHE CANADIAN JOURNAL OF STATISTICS, Issue 4 2002Sanjoy Sinha Abstract The authors introduce the formal notion of an approximately specified nonlinear regression model and investigate sequential design methodologies when the fitted model is possibly of an incorrect parametric form. They present small-sample simulation studies which indicate that their new designs can be very successful, relative to some common competitors, in reducing mean squared error due to model misspecifi-cation and to heteroscedastic variation. Their simulations also suggest that standard normal-theory inference procedures remain approximately valid under the sequential sampling schemes. The methods are illustrated both by simulation and in an example using data from an experiment described in the chemical engineering literature. Les auteurs définissent formellement le concept de modéle de régression non linéaire approxima-tif et proposentdes plans d'expérience séquentiels pour les situations o4uG la forme paramétrique du modéle ajusté est inexacte. Ils présentent une étude de simulation qui montre que, pour de petits échantillons, leurs nouveaux plans sont largement préférables aux plans usuels en terme de réduction de I'erreur quadratique moyenne associée à rinadéquation du modéle et à l'hétéroscédasticité. Leurs simulations montrent aussi que les procédures d'inférence classiques associées au paradigme normal restent valables, à peu de choses prés, pour ces plans expéimentaux se'quentiels. La methodologie proposde est illustrée par voie de simulation et au moyen d'une application concréte tirée de la pratique du génie chimique. [source] | |||||||||||||