This course introduces SAS programming, SAS GUI applications and common statistical methods used in data processing and analysis across all major industries (Banking, Health-Care Insurance, Telecom, Retail, etc). It attempts not only to provide an understanding of statistical techniques and guidance on the appropriate use of data analysis methodologies, but also to help students gain hands-on experience, practical skills and working process knowledge in the real world. Moreover, students can build most required skills and confidence in data analysis and result interpretation through this course study.

 A substantial part of the time is spent on analysing local datasets and producing reports using the techniques learnt in the course. The course will be conducted in a workshop type atmosphere with the instructor advising participants in the analysis of the datasets and preparation of analysis reports. The data analysis topics vary to meet different needs. It would be useful not only for getting a job but also for keeping the job. The course consists of four modules. It is a whole package of data analysis training courses that can help students to develop quantitative analysis career. The learning path is graphed as follows:

·         It is suitable for both job seekers and jobholders who want to be competitive in the job market

·         It assumes neither prior knowledge of SAS language nor statistical background

·         It introduces how to do data manipulation and statistical analysis based on both of SAS coding and GUI applications

·         It covers a broad range of statistical analysis techniques which are employed frequently in the Data Analysts’ routine work from junior to senior levels.

·         It focuses not only on gaining skills in practical problem solving across the major industries but also on mastering necessary theories to assist to select appropriate analysis approach and to interpret analysis results correctly

·         It is case-driven based introduction, which would make a complex process of data analysis in industries easy for the students to understand

This module offers extensive coverage of major basic statistical concepts and methods, concentrating on SAS coding, GUI application using, and features step-by-step instructions to help the non-statistician not only to understand fully the methodology but also to be able to use it correctly and independently. Its emphasis is on data manipulation, inspection, sampling, statistic calculation, parameter estimation, correlation detection and many means comparison

·         SAS Functions, Procedures and Syntax

·         Elementary Concepts in Statistics

·         Basic Statistics (Statistical Measure, Population Parameter, Sample Statistic, Error and Residuals, Probability Distributions, Confidence Levels, Degrees of Freedom)

·         Hypothesis Tests

·         Nonparametric Statistics and Hypothesis Tests

·         Sampling

·         Power Analysis

·         Analysis of Variance (Multiple Comparisons and Interaction Effects)

·         Correlation, Partial Correlation and Canonical Correlation

·         Contigency Table and Chi-square tests

·         Discrimination Analysis

This module covers the topics of Regression, Time Series and Clustering, which are widely used in prediction, forecasting and segmentation. It will be shown that how to do prediction, forecasting and how to organize observed data into meaningful structures through finding the relationship between several independent or predictor variables and a dependent or criterion variable.

·         Simple Linear Regression (including diagnostics)

·         Multiple Regression (including diagnostics and variable selection)

·         Generalized Linear Models

·         Logistic Regression

·         Cluster Analysis.

·         Time Series

In the Coop portion of the course, students will be using SAS and the analytical skills learned in the previous modules to work on real analytical projects. Using real data which presents real data issues and analytical challenges, following common work flow, students will earn real work experience and possess the competitive advantage in the job market.

·         Financial industry project

·         Retail industry project

·         Telecom industry project

This course attempts to make a very complex process of data mining in marketing easy for the novice to understand. In a step-by -step process, it will tell students how we can benefit from modeling, and how to go about it. It provides an introduction and hands-on skills to data mining technologies as they apply to marketing. The substance of the course will be organized around Customer Relationship Management (CRM), the development of marketing programs that target the most profitable consumer segments. Students will learn the details of data mining techniques such as logistic regression, decision tree, artificial neural networks, and clustering methods using SAS/Stat and Enterprise Miner, and how they can be used to obtain information necessary to implement CRM. In short, the course will focus on the uses of data mining in marketing (including customer segmentation, profiling segments, penetration analysis, credit risk management, predictive and descriptive modeling, model validation and reporting) rather than data mining study. In addition, students will learn how marketing science concepts such as consideration sets, multi-attribute utility theory and customer segmentation can be used to direct and interpret data mining studies. Database Marketing process, model reporting and format of model log recommendation will also be introduced.

·         Data Mining Methodology and Process

·         Modeling Business Cases Through SAS Programming

·         Modeling Business Cases Using SAS Enterprise Miner

·         Applications of Data Mining to Industries

·         Model Monitoring and Management