Course Calender

Course Calender

SAYT1016 Data Science: Inference, Prediction and Learning 數據科學:推理、預測和學習
Course Outline:
(Click Icon to download !!)
(Last update on: 25 April 2022)

pdf

 

Key facts for Summer 2022:

Date:   17, 18, 19, 22, 23, 24* August 2022 (30 hours)
Time:   9:30am – 12:30pm, 2:30pm – 5:30pm
Teaching Platform:   Face to Face  (The Chinese University of Hong Kong) #
Enrollment:   50
Expected applicants:   Students who are promoting to S4-S5 with good knowledge in mathematics
and with strong interest in solving real problems
Tuition Fee:   HKD 3,900.00
(Students who have attended all sessions will be granted a HKD 1,000 scholarship)
Lecturer:   Prof. CHAN Kin Wai
* This date is reserved for make-up classes in case there is any cancellation of classes due to unexpected circumstances.
# This course is offered face-to-face lessons at CUHK campus. It may switch to online teaching in accordance with the pandemic development and the policy of the university.



Introduction:

Uncertainty exists in many real-life problems, ranging from stock returns to sport results to medication effects to election outcomes. Statistics offers methods to handle uncertainty with a higher precision. This course introduces ways to define, model and forecast uncertainty through real-life examples and counterintuitive phenomena. Topics include exchange paradox, Simpson’s paradox, linear regression model, non-parametric regression model, historical simulation, and k-mean clustering.

不確定性存在於許多現實生活中的問題,例子涵蓋股票回報、運動結果、藥物效果、選舉結果等。統計科學提供了具更高準定性的方法,以處理不確定性的問題。本課程以實際示例和違反直覺的現象引導,來定義、模型和預測不確定性。主題包括替換悖論,辛普森悖論,線性迴歸模型,非參數迴歸模型,歷史模擬法,k 平均演算法。

 

Organising units:
  • Department of Statistics, CUHK
  • Centre for Promoting Science Education, CUHK
Category:   Category I – University Credit-Bearing
Learning outcomes:   Upon completion of this course, students should be able to:
  1. properly define and write down probabilistic statements, appropriately use conditional statements, and correctly use expected values;
  2. sensibly build simple statistical models for continuous, binary, dependent variables, and construct simple nonparametric models; and
  3. produce reasonable predictions for supervised and unsupervised problems by various methods.
   
Learning Activities:
  1. Lectures
  2. Lab
  3. Case Discussion
  4. Projects
Medium of Instruction:   Cantonese supplemented with English
Assessment:
  1. Short answer test or exam
  2. Presentation
Recognition:   No. of University unit(s) awarded: 1
* Certificate or letter of completion will be awarded to students who attain at least 75% attendance and pass the assessment (if applicable)
 
Expected applicants:   Students who are promoting to S4-S5 with good knowledge in mathematics and with strong interest in solving real problems
Organising period:   Summer 2021; Summer 2022
Application method:   SAYT Online application