Skip to content
Free planNo credit card requiredStart writing
AI for Research home
AI for Research home
Dashboard
Sign inGet started

Search 250 million research papers

Read the abstract, see who wrote it and who cites it, and get the citation in APA, MLA, Chicago or Harvard.

About 10,000 papers for “Likelihood function”

Likelihood Function

Tim Gebbie, Diane Wilcox, Bongani Mbambiso et al. · 2016

Wilcox, Gebbie & Mbambiso Spin, stochastic factor models, and a genetic algorithm A non-parametric clustering technique

Cited by 0

A Likelihood Function

Pk A · 2016

Here we shall derive the likelihood function P(D|M) of the model described in Section 2 of the manuscript. In short, it gives the probability that a set of data points is produced by a particular model. For the sake of generality, the model is defined in a two dimensional space (X-Y). The formalism that is developed here can be directly applied to the analysis of the T-L data by relabeling X as time and Y as length. Let us start by considering one data point and one line segment. Assuming that measurements of both coordinates are independently affected by some noise with a Gaussian distribution, we can write the probability that a data point xk,yk is represented by an infinitesimal part of a line segment in the following form: dPk ∼ exp

Cited by 0

The likelihood function of

Ori Sargsyan (161734) · Figshare · 2015

<p><b> for two values of </b><b>.</b> For a sample of 15 DNA sequences with 25 polymorphic sites at a locus, the likelihood function of the elapsed time is plotted for the values of and in red and blue, respectively.</p>

Cited by 0Open access

Seroincidence by Likelihood Function.

Jo Walker (22404069), Paula Russell (11831692), Leanne Kermack (22404072) et al. · Figshare · 2025

Each panel corresponds to the specific antigen target which was used to classify participants’ infection status when calculating seroincidence. Seroincidence estimates for the Bangladesh, Malawi, and Nepal study sites appear in the top, middle, and bottom row of panels, respectively. Solid lines denote the median seroincidence (y-axis) in each age group (x-axis). Vertical lines represent the 95% credible intervals of the seroincidence estimates. Black lines correspond to the primary analysis, while red lines correspond to a sensitivity analysis in which the likelihood function for seroincidence directly incorporates participants’ mixture model-derived probability of infection. (PNG)

Cited by 0Open access

Marginalized QCD likelihood function

Komoltsev, Oleg, Gorda, Tyler, Kurkela, Aleksi · Zenodo (CERN European Organization for Nuclear Research) · 2025

A Python implementation of a marginalized QCD likelihood function in a form that can be conveniently interfaced with Bayesian equation-of-state inference setups. The likelihood uses the partial N3LO pQCD EOS (PhysRevLett.127.162003) at high-density muH that is extrapolated to lower densities using a Gaussian Process regression conditioned with pQCD calculations of the sound speed in the range [25,40]n_sat. Based on arXiv:2312.14127 V3: fixed a major bug affecting results. The update is required for correct functionality.

Cited by 0Open access

Factoring the likelihood function

J. K. Lindsey · 1996

Abstract The likelihood function provides an overall assessment of the relative merits of different members of a given family of statistical models, although this must be balanced against their relative complexity. However, as we saw in Section 3.6.3, we often require measures of precision of the estimates of individual parameters in the model. This is most often the case in a decision context (Part IV), where, for example, one might wish to decide which of two or more treatments provides the most positive effect, while controlling for various other influential factors. As in Section 3.6.3, the techniques to be discussed in this chapter should not be used for model selection, such as determining if a parameter could be set to zero. They are appropriate for interval estimation of individual parameters once an appropriate model has been selected. When the parameter vector is of low dimension, the precision of a parameter can be determined by inspecting a plot of the (profile) likelihood function. However, when many parameters are present in a statistical model, the profile likelihood will give a poor measure of the uncertainty in any one parameter component, unless it is orthogonal to the others, because it effectively assumes that the other parameter components are known to be equal to their maximum likelihood estimates (for fixed value of the parameter ofinterest). Thus, in Section 3.6.3, we introduced a modified profile likelihood to meet this problem, with a further application in Section 4.2.2. In this chapter, we shall explore in more detail the validity of such approximations.

Cited by 0

New Log Likelihood Estimation Function

Louangrath, P. · Zenodo (CERN European Organization for Nuclear Research) · 2015

This paper provides a New Log-Likelihood Estimator (NLLE) function as a tool for value approximation. We improved the accuracy of the log MLE in two steps (i) determine the log likelihood of a random variable <em>X</em>, and (ii) adjust the estimate by a factor of . In-Sample testing was accomplished by using daily SET100 indices over a period of 60 days. Out-of-sample data were used for confirmatory verification; out-of-sample data came from 5 major stock markets: NASDAQ, DOW, SP500, DAX, and CAC40. Relevant tests used to compare the results of the proposed NLLE include Cramer-Rao Lower Bound (CRLB), Likelihood Ratio Test, Wald statistic, and Lagrange Multiplier (Score Statistic). It was found that NLLE is more efficient than the conventional MLE. It gives practitioners a better tool for value estimation in many fields of natural and social sciences.

Cited by 0Open access

LR likelihood ratio function diagram.

Wei Wei (21173), Yu Ma (111665) · Figshare · 2024

&lt;div&gt;&lt;p&gt;Dual carbon targets is the key to sustainable development in China and even the world, so how to achieve green low-carbon economy is a general trend. As an important guarantee for carbon emission reduction, green technology innovation is essential for promoting the development of green economy. The analysis of the internal mechanism of green technology innovation affecting carbon emission reduction will help provide the development direction for green technology innovation, help China’s carbon neutrality and carbon peak goals as soon as possible, and contribute Chinese wisdom to the sustainable development of the world. This study innovatively adds the carbon market vitality in measuring carbon reduction capacity, and the study extends the previous carbon reduction capacity to expand the influence of green technology innovation and is more practical, and explores the relationship between green technology innovation and carbon reduction capacity. Based on 30 provinces in China from 2006 to 2021, SDM and panel threshold model are constructed to analyze the spatial spillover effect of green technology innovation and carbon emission reduction ability, the threshold characteristics of green technology innovation on carbon emission reduction ability. The results show the carbon emission reduction capacity of Chinese provinces and cities has been increasing year by year, showing the situation of “leading in eastern China, rising of central China, and catching up with western China”. Green technology innovation and carbon emission reduction capacity show positive spatial correlation, which is manifested in the fact that green technology innovation not only reduces the carbon emission reduction capacity of the region effectively but also has significant spatial spillover characteristics on promoting the carbon emission reduction capacity of the neighboring regions. Also, green technology innovation have a double threshold effect on carbon emission reduction capacity, which means its influence on carbon emission reduction capacity is obviously strengthened. Based on such study conclusions, it is recommended to build a new pattern of “great synergy”, strengthen the in-depth integration of green technology innovation and carbon emission reduction, and formulate green and low-carbon differentiated standards, so as to promote a comprehensive green transformation.&lt;/p&gt;&lt;/div&gt;

Cited by 0Open access

Accelerating the Phylogenetic Likelihood Function

Frederico Pratas, Pedro Trancoso, Alexandros Stamatakis et al. · 2016

All in-text\treferences\tunderlined\tin\tblue\tare\tlinked\tto\tpublications\ton\tResearchGate, letting you\taccess\tand\tread\tthem\timmediately.

Cited by 0

The modified profile likelihood function

Thomas A. Severini · 2000

Abstract In Chapter 8 it was shown that, in some cases, inference about a parameter of interest ψ may be based on a marginal or conditional likelihood function. Those methods are only available however when the model has a particular structure. Furthermore, even when a marginal or conditional likelihood function exists, calculation of the likelihood function is often difficult.In this chapter, we consider the modified profile likelihood, a pseudo-likelihood function that is available for general models. The modified profile likelihood may be derived as an approximation to either a marginal or conditional likelihood when either of those likelihoods exists. Furthermore, the calculation of the modified profile likelihood function does not require the existence of a marginal or conditional likelihood and, hence, it has been adopted for general use.

Cited by 0

An Extended Quasi-Likelihood Function

J. A. Nelder, Daryl Pregibon · Biometrika · 1987

Wedderburn's original definition of quasi-likelihood for generalized linear models is extended to allow the comparison of variance functions as well as those of linear predictors and link functions. The relationship between generalized linear models and the use of transformations of the response variable is explored, and the ideas are illustrated by three examples.

Cited by 42

Single threshold likelihood ratio function.

Chenggang Wang (597525), Fan Meng (60551), Tiansen Liu (21181911) · Figshare · 2025

<div> Developing exports of technology-intensive products is a key focus for China’s high-quality foreign trade development. The rapid growth of global digital trade brings new opportunities and challenges for China’s exports of technology-intensive products. This paper utilizes panel data from 2005 to 2022. And we construct an extended gravity model to thoroughly investigate the impact of digital trade development in importing countries on China’s exports of technology-intensive products. The research findings indicate: (1) The development of digital trade in importing countries significantly promotes China’s exports of technology-intensive products. This effect is more pronounced beyond a certain threshold. (2) The reduction of trade costs and increased foreign direct investment play intermediary roles in facilitating the impact of digital trade in importing countries on China’s exports of technology-intensive products. However, institutional distance exerts a negative inhibitory effect on this process. (3) The impact of digital trade development in importing countries on China’s exports of technology products varies due to differences in product types, national income levels, regional characteristics, economic cooperation, and market potential. The conclusions of this paper provide theoretical and empirical evidence for the Chinese government to enhance the efficiency of exporting technology-intensive products. </div>

Cited by 0Open access