
In this paper, a Marshal-Olkin bivariate model based on Burr III distribution is considered under random left censoring.The maximum likelihood estimator of the unknown parameters is obtained using the direct method and Expectation Conditional Maximization algorithm.We also obtained the Fisher information matrices.To discuss the properties of the estimators obtained iteratively, a simulation study is carried out.A real data set is used to illustrate the theoretical results.
The main aim of this paper is to investigate the identifiability of Bayesian Gaussian regression model.The model is extensively implemented in the various Bayesian modeling concepts such as model fitting and model selection approaches.In accordance with the outcomes, the Bayesian Gaussian model is identifiable when the model's design matrix is full rank.
An objective of analyzing survival data via regression is to develop a predictive model given predictors.However, due to the censoring in response variables and the high dimensionality of predictors, information needed for an appropriate model specification is often inadequate.We propose a method for an integrated study of survival time and predictors.At first, variable selection methods are employed for finding the correct subset of predictors with significantly higher probability.This is based on the Lasso approach.Then, the dimension of the predictors is further reduced using sufficient dimension reduction methods.This is based on the Sliced inverse regression for censored data (DSIRII) .In particular we use the popular Cox proportional hazards model to build a predictive model for survival data.An application to Coronary heart disease (CHD) data from the Tehran Lipid and Glucose (TGLS) study further illustrates the usefulness of the work.
One of the challenges at National Statistical Organizations is conducting a survey with a long questionnaire and a large amount of items.Filling out a lengthly questionnaire is time consuming and leads to problems such as increased unresponsiveness rate.Especially during critical situations such as pandemic Covid_19, this would be more challenging.A solution to encounter this difficulty is using a split questionnaire design that is more flexible and taking less time for collecting data.In this paper, we propose a split questionnaire design for Household Expenditure and Income Survey(HEIS) which is one of the most important surveys conducted annually by Statistical Center of Iran and its questionnaire is really long and time consuming to complete.
We present a new joint model with random effects for the correlated count with extra zero and continuous responses.In this model, we assume a Zero-Inflated Beta-Binomial distribution for the analysis of overdispersed binomial variable and a normal distribution for the analysis of continuous response.Furthermore, a full model likelihood function approach is used to obtain maximum likelihood estimates of the model parameters.We also evaluate the proposed model using the Monte Carlo simulation method.Finally, we fit the model to real data to find effective factors on mixed responses.