Al-Qadisiyah Journal of Pure Science Vol.(26) Issue (5) (2021) pp. Math. 44–57 ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- a.b Al-Qadisiyah University College of Administration and Economics Email: zainabsami670@gmail.com http://qu.edu.iq/journalsc/index.php/JOPS Bayesian Variable Selection for Semiparametric Logistic Regression 1. Introduction Regression analysis methods are fundamental in analyzing the relevant data by describing the relationship between a set of independent variables and the dependent variable (Kerlinger & Pedhazur, 1973). However, it is unable to describe and explain the relationships between the covariates and the response variable if the latter has binary value, where the nature of the response variable is required to be a continuous quantity and not a classification (Lea, 1997)[1]. This is why the need has arisen for developing new statistical methods that have the Authors Names a. Zainab Sami b. Taha Alshaybawee Article History Received on: 30/10/2021 Revised on: 19/11/2021 Accepted on: 26/11/2021 Keywords: Logistic regression Bayesian inference Single index model Lasso MCMC algorithm ABSTRACT Lasso variable selection is an attractive approach to improve the prediction accuracy. Bayesian lasso approach is suggested to estimate and select the important variables for single index logistic regression model. Laplace distribution is set as prior to the coefficients vector and prior to the unknown link function (Gaussian process). A hierarchical Bayesian lasso semiparametric logistic regression model is constructed and MCMC algorithm is adopted for posterior inference. To evaluate the performance of the proposed method BSLLR is through comparing it to three existing methods BLR, BPR and BBQR. Simulation examples and numerical data are to be considered. The results indicate that the proposed method get the smallest bias, SD, MSE and MAE in simulation and real data. The proposed method BSLLR performs better than other methods. DOI: https://doi.org/10.29350/ jops.0202.02. 5.2622