課程資訊
課程名稱
生態研究法
Research Methods in Ecology 
開課學期
107-2 
授課對象
生物資源暨農學院  昆蟲學系  
授課教師
奧山利規 
課號
ENT5053 
課程識別碼
632EU1150 
班次
 
學分
3.0 
全/半年
半年 
必/選修
必修 
上課時間
星期三6,7,8(13:20~16:20) 
上課地點
 
備註
本課程以英語授課。B群組。上課教室:鄭江樓 505室。建議先修習基礎統計學。
限學士班三年級以上
總人數上限:16人 
Ceiba 課程網頁
http://ceiba.ntu.edu.tw/1072ENT5053 
課程簡介影片
 
核心能力關聯
本課程尚未建立核心能力關連
課程大綱
為確保您我的權利,請尊重智慧財產權及不得非法影印
課程概述

If you cannot register online, please come to the first class and I will give you a registration code. This course has two parts: 1) experimental design and 2) data analysis. The experimental design part of the course will use a textbook (Ruxton and Colegrave 2016; see below). The main theme of the data analysis part is the method of maximum likelihood although other approaches are also discussed. Computer simulations will be used to understand the concepts of various statistical tests, but no prior experience in programming is required. Although the course title contains the word 'ecology', this is a general course on experimental design and data analysis. Students of any fields (social science, political science, physical science, biological science, business, engineering, etc.) can take the course. No knowledge of ecology is required. The computer language R (http://www.r-project.org/) will be used. Expectations

  • Ask questions, in or out of class, when you don’t understand something. If you are confused, you are probably not the only one.
  • Assignments will be given nearly every week. Students must work on assignments on their own. Understanding a provided solution and deriving it by yourself are not the same (especially for programming). To discourage students from copying assignments (which has been very common in past years), assignments are not graded. Even if students have the perfect assignments (i.e., 100% if graded), the assignments have no influence on their grades. Nonetheless, successful completion of assignments is essential for the successful completion of the course. Students are encouraged to seek out the instructor for help when they have troubles completing assignments.
  • Students are responsible for checking their NTU email accounts regularly as some information may be sent by email. Bonus points Bonus points will be calculated based mainly on attendance and participation. Two absences or four tardies will result in 0 bonus points (being late over 20 min is regarded as an absence). Poor class participation (e.g., playing with a cell phone/computer, sleeping, etc.) is considered an absence. Even when a student has a valid reason for an absence, it is considered as an absence because attendance only affects bonus points. The maximum possible bonus points are 10% (to final % grade), but undergraduate students whose grades are less than 60% (final grade without bonus points) can get at most 60% (final grade with bonus points). Graduate students whose grades are less than 70% (final grade without bonus points) can get at most 70% (final grade with bonus points). Schedule The schedule (shown in the content section of this website) is subject to change. 

  • 課程目標
    . 
    課程要求
     
    預期每週課後學習時數
     
    Office Hours
     
    指定閱讀
     
    參考書目
     
    評量方式
    (僅供參考)
       
    課程進度
    週次
    日期
    單元主題
    Week 1
    2/20  Course overview 
    Week 2
    2/27  Statistics review</br>
    Starting with a well-defined hypothesis </br>
    Selecting the broad design for your study<br/></br>

    The section on "Controls" will be discussed in a different week. 
    Week 3
    3/06  Between-individual variation, replication and sampling<br/>
    Pseudoreplication 
    Week 4
    3/13  Hypothesis tests review 
    Week 5
    3/20  Power analysis  
    Week 6
    3/27  Review 
    Week 7
    4/03  no class 
    Week 8
    4/10  Sum of squares<br/>
    Numerical optimization<br/>
    Bootstrap  
    Week 9
    4/17  Maximum likelihood<br/>
    Likelihood ratio tests 
    Week 10
    4/24  Maximum likelihood review  
    Week 11
    5/01  Generalized Linear Models (GLMs)<br/>
    Poisson GLM<br/>
    Dummy variables 
    Week 12
    5/08  Binomial GLM<br/>
    Offset<br/>
    Gamma GLM 
    Week 13
    5/15  Overdispersion<br/>
    Quasilikelihood<br/>
    Negative binomial GLM 
    Week 14
    5/22  Customizing models 
    Week 15
    5/29  Generalized Linear Mixed Models (GLMMs) 
    Week 16
    6/05  no class 
    Week 17
    6/12  TBA