Statistical Computing and Lab. |

PrerequisiteThis course introduces basic concepts of computer programming and computer-assisted statistical data anslysis. We begin with learning how to write a program using general-purpose programming languages such as C and Fortran, and then study languages specialized for statistical data analysis, such as R. We will examine various statistical analysis methods using these programming languages. Optionally, we will study the elementary concepts of database. |

Probability Concept and Applications |

PrerequisiteThis course is designed to introduce basic probability concepts, theories and their applications to related fields such as natural science, engineering, and social science. |

Sampling Design and Survey Practice |

ElectiveThis course treats the theory and practice of sampling. It focuses on sampling and surveying of finite populations from various points including the simple random sample, stratified, cluster, and double sampling, properties of various estimators including ratio and regression, sampling with unequal probabilities, and error estimation for complex samples. Students will be required to perform survey practices and participate in group discusssions. |

Mathematical Statistics 1 |

PrerequisiteThis course focuses on conditional probability, stochastic independence and the distributions of random variables such as Normal, Binomial, Multinomial, Gamma, Chi-square, Poisson, and Multivariate Normal variables. |

Mathematical Statistics 2 |

PrerequisiteThis advanced course provides a deeper understanding of limit distributions,including the central limit theorem, statistical estimation, testing statistical hypotheses, nonparametric tests, sufficient statistics, statistical inferences and normal theory. This course has a prerequiste of Mathematical statistics 1. |

Regression Analysis and Lab. |

PrerequisiteThis course deals with both the theory and application of regression analysis covering simple, multiple, and nonlinear regression analysis, dummy variables, response surface analysis, selection of variables and diagnostics. Students will be required to perform statistical analysis using SAS. |

Discrete Data Analysis and Lab. |

ElectiveThis course introduces categorical data analysis based on log-linear model, selection of models, goodness-of-fit test, maximum likelihood estimation of expected frequencies in the contingency table, analysis of incomplete contingency tables, logit models, and linear logistic regression models. |

Experimental Design and Lab. |

ElectiveThis course introduces Latin and Graeco-Latin square, factorial and block design, mixed models, fractional replication and complete randomization of one factor. Regression analysis and Lab are prerequisites to this course. |

Multivariate Data Analysis and Lab. |

ElectiveThe focal point of this course is on multivariate data and its analysis. The class will estimate and test the means of multivariate data, perform principal component analysis along with factor analysis and cluster as well as discriminant analysis. The course has prerequistes of Mathematical statistics 1, 2, and Linear algebra. |

Bayesian Statistics and Lab. |

ElectiveThis course deals with subjective probability, preferences quantification, Bayesian decision theory, conjugate prior distribution, limit posterior distribution, Bayesian estimation and test, and secondary decision theor. |

Survival Data Analysis and Lab. |

ElectiveIn this course, students will study the estimation and testing of survival time and be introduced to the life table method and Kaplan-Meyer estimation to model survival functions. Topics will include various test methods for the comparison of three or more groups as well as regression models such as Cox proportional hazard models and accelerated regression models for the selection of risk factors that affect survival time. |

Datamining Methods and Lab. |

ElectiveThis course covers basic concepts and methodologies of data mining on various real problems. Preprocessing procedures including categorization, sampling etc are taught and various data mining methods including linear regression, logistic regression, decision trees, neural networks, clustering and association are covered. also, evaluation methods such as lift and prediction errors are taught. Finally, as a term project, students are participated in one real project. In this course, various statistical packages such as R, SPSS, SAS are extensively used. |

Nonparametric Statistics and Lab. |

ElectiveThis elementary course introduces basic nonparametric methods and distribution-free statistics. It also deals with distributions of order and rank statistics. Some of the specific issues that are dealt with include nonparametric estimation of point and confidence intervals with comparison of parametric methods, location parameter estimation of one sample, location and scale parameter estimation of two samples, and nonparametric testing problem of distribution functions. |

Time Series Analysis and Lab. |

ElectiveThis course introduces the different laws and uses of various statistical packages. Topics include the moving average, exponential smoothing, the ARIMA models and the basic concepts of seasonal effects. |

Statistical Quality Control and Lab. |

ElectiveThis course deals with theory of statistical quality control, covering normal plot, control chart, sampling inspection, probability theory, and single sampling of measurement. The courses Statistics and Laboratory, Mathematical Statistics 1, 2, and Sampling Design and Survey Practice are prerequisite. |

Applications of Function Estimation and Lab. |

ElectiveThis course deals with nonparametric estimation methods for functions in various statistical models and is mainly focused on methodologies and applications rather than on theories. Topics that we will examine in this course include the following: nonparametric estimation methods such as Kernel estimation, local polynomial method, wavelet estimation and spline estimation; estimation methods of density function, regression function, survival function and quantile function. We will also observe the ways in which these methods can be applied to classification and discriminant analysis, generalized linear model, censored regression model, and proportional hazard model. |

Stochastic Processes |

ElectiveIn this course, discrete and continuous Markov chain and renewal process are covered. In the Markov chain, recurrence, Ergodic theorem, reversibility, and their applications are main subject. In the renewal process, several renewal theorem and their applications are covered. |

Computational Statistics |

ElectiveThis course offers basics of statistical computing methods for parametric and Bayesian statistics. For parametric statistics, we study optimization methods such as the Newton-Raphson method, for maximizing likelihood functions. For Bayesian statistics, we study Markov-chain Monte Carlo methods such as Gibbs Sampling and the Metropolis algorithm. Besides theory, we also perform real data analysis using these methods. We also introduce data structures and matrix algorithms useful for computational statistics. |