An application of the minimum discrimination information estimate to compute log-likelihood ratios

1973 ◽  
Vol 10 (2) ◽  
pp. 469-474
Author(s):  
E. L. Melnick ◽  
S. Kullback

In this paper the minimum discrimination information estimate is used to compute the log-likelihood ratio or logarithm of the Radon-Nikodym derivative In (dP1/dP2) when the stochastic process {x(t), t∈T) has either the probability measure P1 or P2. One example tests the mean value function of Gaussian processes. The other tests the mean value function of a continuous time Poisson process.

1973 ◽  
Vol 10 (02) ◽  
pp. 469-474
Author(s):  
E. L. Melnick ◽  
S. Kullback

In this paper the minimum discrimination information estimate is used to compute the log-likelihood ratio or logarithm of the Radon-Nikodym derivative In (dP 1/dP 2) when the stochastic process {x(t), t∈T) has either the probability measure P 1 or P 2. One example tests the mean value function of Gaussian processes. The other tests the mean value function of a continuous time Poisson process.


1973 ◽  
Vol 9 (22) ◽  
pp. 528
Author(s):  
E. Ball
Keyword(s):  

2001 ◽  
Vol 56 (6) ◽  
pp. 521-525 ◽  
Author(s):  
Maciej Bujak ◽  
Jacek Zaleski

AbstractN ,N-Dimethylethylenediammonium pentachloroantimonate(III) crystallizes in the monoclinic system, in space group P21/c (a = 12.460(2), b = 10.252(2), c = 10.330(2) Å, β = 97.75(3)°, V = 1307.5(4) Å3, Z = 4, dc = 1.997, dm = 1.99(2) g/cm3). The crystal structure of [(CH3)2NH(CH2)2NH3][SbCl5] consists of isolated [SbCl5]2- anions and [(CH3)2NH(CH2)2NH3]2+ cations. The [SbCl5]2- anion has a distorted square pyramidal geometry, presenting one short axial and four long equatorial Sb-Cl bonds. The square pyramids are characteristically stacked one close to the other, parallel to the c axis. The voids between the anionic sublattice are filled by [(CH3)2NH(CH2)2NH3]2+ cations. The five non-equivalent Sb-Cl bond distances within the [SbCl5]2- square pyramid are significantly different. The equatorial Sb-Cl bonds are in the range 2.427(2)-2.968(2) Å, whereas the axial one is 2.384(1) Å long. The study reveals that N-H...C1 hydrogen bonds are responsible for the deformation of equatorial Sb-Cl bonds from the mean value of 2.654(7) Å. Analysis of intermolecular interactions between the [SbCl5]2- pyramids in the structure, reflected in changes of Sb-Cl bond lengths from the values characteristic of non-interacting pyramids, leads to the conclusion that the van der Waals radius of Sb is significantly smaller than that estimated by Pauling.


2018 ◽  
Author(s):  
Sigit Haryadi ◽  
Salma Huda California

In this paper, we proposed a modification of the measurement of the personality consistency level of the Pauli & Kraepelin Test in the field of psychology, using the formula made in April 2016, by Sigit Haryadi, and named "the Harmony in Gradation" or “the Haryadi Index”. The purpose of this proposal is because the existing formula uses only the mean value of the deviation, which leads to the possibility that the result of consistency measurement on people whose facts are different levels of consistency will be considered to have the same consistency level, on the other hand, the proposed method will be more accurate and precise in terms of providing an assessment of the level of personality consistency of a person.


2013 ◽  
Vol 433-435 ◽  
pp. 595-598
Author(s):  
Yu Nian Ru ◽  
Jian Ping Li

This paper proposes a novel stopping criterion based on the HDA stopping criterion. To devise the criterion, we consider both the HDA criterion and the mean of the absolute values of the log-likelihood ratios (LLR) at the output of the component decoders over each frame together. The new criterion saves more than 0.5 iteration ,in the low signal-to-noise ratios (SNR) situation,with a negligible degradation of the error performance.


1977 ◽  
Vol 9 (1-2) ◽  
pp. 84-104 ◽  
Author(s):  
Maria Amélia Cabral ◽  
Jorge Afonso Garcia

The study and analysis of the various factors influencing insurance risks constitutes an intricate and usually quite extensive problem. We have to consider on the one hand the nature and heterogeneity of the elements we have been able to measure, and on the other the problem of deciding—without knowing exactly what results to expect—on the types of analysis to carry out and the form in which to present the results.These difficulties, essentially stemming from the fact that we cannot easily define “a priori” a measure of influence, can be overcome only by using highly sophisticated mathematical models. The researcher must define his objectives clearly if he is to avoid spending too much of his time in exploring such models.Either for these reasons or for lack of our experience in this field we were led to the study of three models, presenting entirely different characteristics though based on the analysis and behaviour of mean value fluctuations, measured by their variances or by the least-squares method.Our first model, described in II. 1, associates the notion of influence with the notion of variance. It analyses in detail the alteration of the mean values variance, when what we refer to as a “margination” is executed in the parameter space, taking each of the parameters in turn. We start off by having n distinct parameters, reducing them by one with each step.


1974 ◽  
Vol 11 (02) ◽  
pp. 382-387 ◽  
Author(s):  
Jan-Erik Karlsson

We assume that the number of claims occur according to a renewal process and treat the number of claims that occur and are reported in a certain time interval as a renewal process with random displacements. We obtain a renewal equation for the mean value function and an integral equation for the Laplace transform of the distribution of the claims that are reported. We also give asymptotic expressions for the mean value function and calculate the generating function in the case where the renewal process is a Poisson process. This matter is a part of the IBNR-problem in insurance mathematics.


Author(s):  
JOONG-YANG PARK ◽  
YANG-SOOK HWANG ◽  
TAKAJI FUJIWARA

Recently the general testing-domain dependent NHPP SRGM is developed to reflect repeated execution of constructs and location of detected faults. It assumes that debugging is perfect. Since realistic models need to reflect imperfect debugging, this paper integrates imperfect debugging in the general testing-domain dependent NHPP SRGM. Differential equations representing the mean value function are first derived for general testing strategy and then realized for the uniform testing. Specific mean value functions are obtained for some selected fault detection rate functions and constant fault reduction rate. Finally empirical performance evaluation is fulfilled.


Sign in / Sign up

Export Citation Format

Share Document