● 課程說明(Course Description)
Statistics and Data Science play vital roles in scientific research and their
goal is to make such an iterative learning process as efficient as possible.
To achieve this goal, we may encounter the analysis of and make inference on
data from 3-dimensional perspectives (observation, variable and time horizon).
From a static (cross-sectional) viewpoint with prefixed time horizon, one
could investigate the inter-dependence structures (or associations) among all
collected variables as well as cluster observational units into homogeneous or
heterogeneous subgroups and make further analysis. Furthermore, to account for
temporal evolution, time series analysis may provide a proactive tool to
address the dynamic structures of all variables. Topics to be covered in this
course, therefore, include: DOE/robust design, sampling methods, data
visualization, low-dimensional summary for big data, reliability analysis,
regression and time series analysis, classification and clustering, prediction
and feature selection.

● 指定用書(Text Books)
自編講義

● 教學方式(Teaching Method)
課堂觀念講授、軟體操作說明、案例練習

● 教學進度(Syllabus)
(Tseng) Weak 1. Introduction
(Tseng) Weak 2. Design of experiments & robust design
(Tseng) Weak 3. Design of experiments & robust design
(All) Weak 4. Project proposal
(Tseng) Weak 5. Quality and reliability inference
(Tseng) Weak 6. Quality and reliability inference
(Tseng) Weak 7. Fault detection and classification (個案分析)
(Hsu) Weak 8. Data description and collection (sampling methods)
(Hsu) Weak 9 Multivariate analysis
(Hsu) Weak 10.Prediction: regression analysis
(Hsu) Weak 11.Classification and clustering
(Hsu) Weak 12.個案分析
(Ing) Weak 13.General modeling procedure
(Ing) Weak 14.Time series: analysis of serially correlated data
(Ing) Weak 15.Model selection: explanation vs. prediction
(Ing) Weak 16.Feature selection for high-dimensional data
(Ing) Weak17.個案分析
(All) Weak 18.Student Project Presentation

● 成績考核(Evaluation)
期中、末報告