Search results for " Penalized likelihood"

showing 6 items of 6 documents

Inferential tools in penalized logistic regression for small and sparse data: A comparative study.

2016

This paper focuses on inferential tools in the logistic regression model fitted by the Firth penalized likelihood. In this context, the Likelihood Ratio statistic is often reported to be the preferred choice as compared to the ‘traditional’ Wald statistic. In this work, we consider and discuss a wider range of test statistics, including the robust Wald, the Score, and the recently proposed Gradient statistic. We compare all these asymptotically equivalent statistics in terms of interval estimation and hypothesis testing via simulation experiments and analyses of two real datasets. We find out that the Likelihood Ratio statistic does not appear the best inferential device in the Firth penal…

Statistics and ProbabilityScore testPRESS statisticEpidemiologyStatistics as TopicScoreWald testLogistic regression01 natural sciences010104 statistics & probability03 medical and health sciences0302 clinical medicineHealth Information ManagementStatisticsEconometricsHumans030212 general & internal medicine0101 mathematicsStatisticMathematicsLikelihood FunctionsModels StatisticalLogistic regression firth penalized likelihood sandwich formula score statistic gradient statisticLogistic ModelsLikelihood-ratio testData Interpretation StatisticalSample SizeAncillary statisticSettore SECS-S/01 - StatisticaStatistical methods in medical research
researchProduct

Dynamic factorial graphical models for dynamic networks

2014

Dynamic networks models describe a growing number of important scientific processes, from cell biology and epidemiology to sociology and finance. Estimating dynamic networks from noisy time series data is a difficult task since the number of components involved in the system is very large. As a result, the number of parameters to be estimated is typically larger than the number of observations. However, a characteristic of many real life networks is that they are sparse. For example, the molec- ular structure of genes make interactions with other components a highly-structured and, therefore, a sparse process. Penalized Gaussian graphical models have been used to estimate sparse networks. H…

Constraint optimization Dynamic networks Gaussian graphical models Penalized likelihood Symmetry models Time-course dataSettore SECS-S/01 - Statistica
researchProduct

Bivariate logistic models for the analysis of the students' University "success"

2012

We analyze the students’ success at University by considering their performance in terms of both “qualitative performance”, measured by their grade average, and “quantitative performance”, measured by University Credits accumulated. To jointly model both marginal and association relationships with covariates, the analysis has been carried out by fitting a bivariate ordered logistic model (BOLM), in a nonparametric fashion, by penalized maximum likelihood estimation. The advantages of such model are in terms of parsimony and parameters interpretation, while preserving goodness-of-fit. The application regards an engineering student (ES) cohort from the University of Palermo.

bivariate ordered logistic models penalized likelihoodSettore SECS-S/05 - Statistica SocialeSettore SECS-S/01 - Statistica
researchProduct

A new tuning parameter selector in lasso regression

2019

Penalized regression models are popularly used in high-dimensional data analysis to carry out variable selction and model fitting simultaneously. Whereas success has been widely reported in literature, their performance largely depend on the tuning parameter that balances the trade-off between model fitting and sparsity. In this work we introduce a new tuning parameter selction criterion based on the maximization of the signal-to-noise ratio. To prove its effectiveness we applied it to a real data on prostate cancer disease.

Least absolute shrinkage and selection operator (lasso) Model selection Variable selection Penalized likelihood Signal-to-noise ratio Clinical data
researchProduct

An association model for bivariate data with application to the anlysis of university students' success.

2015

The academic success of students is a priority for all universities. We analyze the students' success at university by considering their performance in terms of both ‘qualitative performance’, measured by their mean grade, and ‘quantitative performance’, measured by university credits accumulated. These data come from an Italian University and concern a cohort of students enrolled at the Faculty of Economics. To jointly model both the marginal relationships and the association structure with covariates, we fit a bivariate ordered logistic model by penalized maximum likelihood estimation. The penalty term we use allows us to smooth the association structure and enlarge the range of possible …

Statistics and Probability05 social sciencesBivariate analysisLogistic regression01 natural sciencesTerm (time)010104 statistics & probabilityGoodness of fitBivariate data0502 economics and businessStatisticsCovariateEconometricsRange (statistics)Settore SECS-S/05 - Statistica Sociale050207 economics0101 mathematicsStatistics Probability and UncertaintyAssociation (psychology)Mathematicsmodels for association students' performance bivariate ordinal response Dale's model maximum penalized likelihood estimation
researchProduct

Penalized inference in multivariate ordered logistic models: theory and applications

2011

Multivariate Logistic Model Penalized LikelihoodSettore SECS-S/01 - Statistica
researchProduct