1,720,992 research outputs found
Bayesian LASSO Quantile Regression: An Application to the Modeling of Low Birth Weight
Full text linkThe modeling of low birth weight using ordinary least square is not
appropriate and inefficient. The low birth weight data violates the normality assumption
since the data is right skewed. The data usually contains outliers as well. Many
researchers used quantile regression approach to model this case but this method has
limitation. The limitation of this approach is need moderate to big sample size. This
study aims to combine the quantile regression with Bayesian LASSO approach to model
the low birth weight. Bayesian method has ability to model small sample size since it
involves the information related to data (known as likelihood function) and prior
information about the parameter tobe estimated (prior distribution). This study
demonstrated that Bayesian quantile regression and Bayesian LASSO (Least Absolute
Shrinkage Selection Operator)quantile regression could yield the acceptable model of
low birth weight case based on indicators of goodness of fit model. Bayesian LASSO
quantile regression produced better estimated parameter values since it yielded shorter
95% Bayesian credible interval than Bayesian quantile regression
The Infinitely Divisible Characteristic Function of Compound Poisson Distribution as the Sum of Variational Cauchy Distribution
Full text linkThe new particular compound Poisson distribution is introduced as the sum of
independent and identically random variables of variational Cauchy distribution with the number
of random variables has Poisson distribution. This compound Poisson distribution is
characterized by using characteristic function that is obtained by using Fourier-Stieltjes
transform. The infinite divisibility of this characteristic function is constructed by introducing
the specific function that satisfied the criteria of characteristic function. This characteristic
function is employing the properties of continuity and quadratic form in term of real and non�negative function such that its convolution has the characteristic function of compound Poisson
distribution as the sum of variational Cauchy distribution
Assessment of health and social security agency participants proportion using hierarchical Bayesian small area estimation
Full text linkData on the number of health insurance participants at the subdistrict level is crucial since it is strongly correlated
with the availability of health service centers in the areas. This study’s primary purpose is to predict the proportion of health
and social security participants of a state-owned company named Badan Penyelenggara Jaminan Sosial Kesehatan (BPJS) in
eleven subdistricts in Padang, Indonesia. The direct, ordinary least square, and hierarchical Bayesian for small area estimation
(HB-SAE) methods were employed in obtaining the best estimator for the BPJS participants in these small areas. This study
found that the HB-SAE method resulted in better estimation than two other methods since it has the smallest standard deviation
value. The auxiliary variable age (percentage of individuals more than 50 years old) and the percentage of health complaints have
a significant effect on the proportion of the number of BPJS participants based on the HB-SAE method
Simulation Study to Describe Bayesian Analysis of Nonlinear Structural Equation Modeling
Full text linkStructural equation modeling (SEM) has widely used in many disciplines, such
as economic, politic or health. Nonlinear structural equation modeling, as part of SEM,
also has been developing analytically but still limited. In this method, the parameter
models are estimated using conjugate prior in Bayesian approach. In nonlinear SEM, the
models are specified including quadratic forms and/or interactions of latent variables.
Posterior mean and posterior variance of the parameters are estimated using iteration
approach since it is difficult to estimate those parameters model using analytical
approach. The iteration approach used here is Markov Chain Monte Carlo (MCMC)
method with Gibbs sampling. The simulation study is done to illustrate the proposed
estimation methods for nonlinear model. A group of 300 data are generated to
demonstrate the implementation of the proposed method. This study resulted that the
proposed nonlinear SEM model could be accepted based on criteria of goodness of fit
model
Sample size and power calculation for univariate case in quantile regression
Full text linkThe purpose of this study is to calculate the statistical power and sample size in
simple linear regression model based on quantile approach. The statistical theoretical
framework isthen implemented to generate data using R. For any given covariate and
regression coefficient, we generate a random variable and error. There are two conditions for
error distributions here; normal and nonnormal distribution. This study resulted that for normal
error term, sample size is large if the effect size is small. Meanwhile, the level of statistical power is also affected by effect size, the more effect size the more level of power. For nonnormal error terms, it isn’t recommended using small effect size, moderate effect size
unless sample size more than 320 and large effect size unless sample size more than 160 because it resulted in lower statistical power
Validity test and its consistency in the construction of patient loyalty model
Full text linkThe main objective of this present study is to demonstrate the estimation of validity values and its consistency
based on structural equation model. The method of estimation was then implemented to an empirical data in case of the
construction the patient loyalty model. In the hypothesis model, service quality, patient satisfaction and patient loyalty
were determined simultaneously, each factor were measured by any indicator variables. The respondents involved in this
study were the patients who ever got healthcare at Puskesmas in Padang, West Sumatera. All 394 respondents who had
complete information were included in the analysis. This study found that each construct; service quality, patient
satisfaction and patient loyalty were valid. It means that all hypothesized indicator variables were significant to measure
their corresponding latent variable. Service quality is the most measured by tangible, patient satisfaction is the most
mesured by satisfied on service and patient loyalty is the most measured by good service quality. Meanwhile in structural
equation, this study found that patient loyalty was affected by patient satisfaction positively and directly. Service quality
affected patient loyalty indirectly with patient satisfaction as mediator variable between both latent variables. Both
structural equations were also valid. This study also proved that validity values which obtained here were also
consistence based on simulation study using bootstrap approach
Sample size and power calculation for univariate case in quantile regression
Full text linkThe purpose of this study is to calculate the statistical power and sample size in
simple linear regression model based on quantile approach. The statistical theoretical
framework isthen implemented to generate data using R. For any given covariate and
regression coefficient, we generate a random variable and error. There are two conditions for
error distributions here; normal and nonnormal distribution. This study resulted that for normal
error term, sample size is large if the effect size is small. Meanwhile, the level of statistical power is also affected by effect size, the more effect size the more level of power. For nonnormal error terms, it isn’t recommended using small effect size, moderate effect size
unless sample size more than 320 and large effect size unless sample size more than 160 because it resulted in lower statistical power
- …
