|
5. Sampling Methods |
2 |
|
The Sampling Methods module systematically provides knowledge of research sampling methods including non-random and random sampling methods. The main content of the module focuses on random sampling methods such as simple random sampling, system sampling, stratified sampling, cluster sampling, mixed sampling, and estimation methods such as proportion estimation, regression estimation and estimation of differences. The course also provides ways of determining the sample size in an investigation to ensure the representativeness of the sample. Introduce to students the supporting software for random sampling and survey results processing skills. |
|
6. Multivariate Data Analysis |
2 |
|
The Multivariate Data Analysis course provides a systematic approach to multivariate analysis of primary data that is commonly used in business analysis as well as academic research. This course equips learners the way to build & test contruct scales used in research and applications, using SPSS and AMOS software. Techniques for testing the effects of moderator and mediate variables in research models. In addition, learners also know how to use cluster analysis to group objects, and discriminant analysis to find features to help distinguish objects, or multidimentional scaling to draw the perceptual mapping of mind people about interested objects. |
|
7. Graduate econometrics |
3 |
|
The specialized econometrics course will cover several key models as well as identification and estimation methods used in modern econometrics. This course also provides advanced knowledge and fosters the skills in applying to real projects and empirical projects. These advanced topics include regression with panel data; autocorrelation, heteroskedasticity and endogeneity on panel data; dynamic panel data and spatial regression. You will learn the modern ways of setting up problems and doing better estimation and inference than the basis empirical practice. The course also guides the use of software to support calculations such as Eviews/Stata/R. After finishing the module, the student understands the advantages and disadvantages of the model. These knowledges are crucial in order to read and write research papers in quantitative research. More generally, the ability to understand the assumptions behind econometric methods and to interpret both statistical estimation and test results is very important for work in economics, policy, and other social science. PhD candidates will get a lot of hands-on experience with using the methods on real data sets |
|
- Elective: Select 1 out of 3 |
3 |
|
|
|
8. Time series analysis |
3 |
|
The time series analysis course provides knowledges and skills needed to do empirical research in fields operating with time series data sets. The course aims to provide students with techniques and receipts for estimation and assessment of quality of economic models with time series data. Special attention will be placed on limitations and pitfalls of different methods and their potential fixes. Topics include: - Stationary process, spurious regression problem and stationary tests - AR, MA, ARMA, ARIMA and Box-Jenskin method - ARCH/GARCH model - VAR/SVAR models - Cointegration and ECM/VECM model - Spectral analysis The course will also emphasize recent developments in Time Series Analysis and will present some open questions and areas of ongoing research. In addition, students are guided to practice on Eviews/Stata/R software and read and understand research articles related to advanced models of time series. |
|
9. Bayesian Statistics |
3 |
|
The Bayesian statistics course introduces the Bayesian approach to statistical inference for data analysis in many applications. This course will cover the theory of Bayesian inference, and data analysis using statistical software will also be emphasized. Topics include: comparison of Bayesian and frequentist methods, Bayesian model specification, prior specification, basics of decision theory, Markov chain Monte Carlo, Bayes factor, empirical Bayes, Bayesian linear regression and generalized linear models, hierarchical models. MCMC for model estimation and some necessary tests to evaluate the models. |
|
10. Statistical Learning |
3 |
|
Statistical learning is a recently developed field of Statistics, closely associated with the development of computer science and especially machine learning. This course introduces some of the important tools/models for the purpose of analyzing complex data sets. The course content includes both theoretical basis and application of these tools/models. They will not be seen as black-boxes, instead learners will understand more deeply instead of just using them. The main reason is this: there is no tool or model that will work well for all practical situations, without understanding how the tool works it is difficult to choose the most appropriate tool for a given situation. specific situation. Tools/models to be covered include: ❖ Supervised learning algorithms: linear regression, logistic regression; linear discriminant analysis; cross-validation; bootstrap; linear model selection and regularization; nonlinear models as regression splines; decision trees, support vector machine, and neural networks. ❖ Unsupervised learning algorithms: dimensionality reduction, clustering. Students will be guided to practice on the Python/R programming language. |
