Course image Survey Sample Methods AY 2020
Semester 1
The module aims at introducing a set of principles of survey design that are the basis of standard practices in the field. It presents statistical concepts and techniques in sample design, execution, and estimation, and models of behavior describing errors in responding to survey questions.
•Introduction to survey methodology: need for survey sampling, terminology, notation, estimation strategy, survey errors, probability sampling and non-probability sampling;
•Inference and error in surveys; Â
•Target populations, sampling frames and coverage error; Â
•Sampling techniques: simple random sampling, systematic sampling, stratified sampling, cluster sampling, multi-stage sampling, unequal probability sampling;
•Basic inference for survey data: bias of estimators, inclusion probabilities, standard errors, finite population correction, variance estimation, confidence intervals, proportions, domains, ratio estimation, Horvitz-Thompson estimator, design-based inference,
•Specific topics in survey sampling: double sampling procedures, randomized response models, small area estimation, resampling methods,
•Analysis of survey data and illustration with statistical software.
At the end of the module, the students should be able:
•To know and understand the Principles of survey design;
•To know and understand the Methods of survey sampling;
•To know and understand the Data collection methods;
•To know and understand the Design of the questionnaire;
•To know and understand the Survey measurement;
•To know and understand the Randomized and non-randomized research design.
Course image DSC6232: Numerical linear algebra
Semester 1
Welcome to the module of Numerical Linear algebra.
The main aim of this module is to equip the students with a common basis for linear algebra tools which are fundamental to the development of statistical models and implementation of machine learning algorithms. Moreover, the module treats main classes of large scale problems covering both dense and sparse matrices with numerical implementation on practical problems arising in areas such as data mining.