2 項進行中

115-1 選課時程

進行中

  • 初選第一階段 6/15 – 6/18
  • 初選第二階段 6/22 – 6/25
  • 校際選修 進行中 8/24 – 9/18
  • 初選第三階段 8/31 – 9/3
  • 開學後加退選 進行中 9/7 – 9/21
  • 逾期加退選 9/21 – 9/24
選課資源

加入行事曆

選擇訂閱 Google Calendar,或下載通用的 ICS 檔案。

使用 Google Calendar 時,Google 會收到這份課表的公開連結。

傳播數據分析

Communication Data Analysis

學期
115-1
學分
3 學分
當期課號
330102
永久課號
HKCT30005
開課單位
傳播與科技學系
授課教師
陶振超、許珊
校區
六家
類別
選修
上課時間表
週三
2
09:00–09:50
傳播數據分析
HK206(六家)
3 節連堂
3
10:10–11:00
4
11:10–12:00

* 根據陽明交大上課時間表所列

概述

Course Description: Meta-analysis is a quantitative research synthesis method that integrates findings across studies addressing the same or closely related research questions. In contemporary social science, the growing volume of research and increased emphasis on evidence-based decision making make rigorous research synthesis essential. This course trains graduate students to conduct a rigorous, transparent, and reproducible meta-analysis from start to finish, using a staged framework: (1) formulate the problem; (2) search the literature; (3) gather information from studies; (4) evaluate study quality; (5) analyze and integrate outcomes; (6) interpret evidence; and (7) present results. Goals and Objectives: By the end of the course, students will be able to: 1. Formulate a meta-analytic research problem with clear conceptual definitions and operational boundaries. 2. Conduct a transparent and replicable literature search using multiple strategies and appropriately defined search terms. 3. Design coding materials (coding sheet + codebook), extract data reliably, and establish inter-coder reliability. 4. Evaluate study quality and categorize studies by design/implementation characteristics. 5. Compute and interpret effect sizes, select appropriate meta-analytic models, and assess heterogeneity and moderators in R, using AI assistance for coding when appropriate.. 6. Conduct sensitivity analyses and examine missing data/publication bias to interpret cumulative evidence appropriately. 7. Present meta-analytic results in a scholarly format, including a manuscript and oral presentation.

先修科目

教師未提供此項資料

備註

無備註

教學方式

Course structure: Hybrid seminar-lab format (lecture + workshop). Students bring laptops for in-class demonstrations and project work. Course policies: Participation and professional practice • Students are expected to attend prepared (readings completed) and contribute to workshop discussion and feedback. • The course relies on iterative progress; late deliverables disrupt downstream steps and reduce learning value. Academic misconduct Plagiarism (including self-plagiarism), cheating on exams, copying of exercises Late work All assignments must be submitted electronically (and in hard copy if noticed) on time. Assignments submitted after the due day will be subtracted 10 points (one full grade) for each day late. Food You may not eat during class. Citation style APA 7 AI policy: Red Light: Not Permitted • Using AI to write assignments or replace your own analysis and interpretation. • Using AI summaries instead of reading the original studies. • Submitting unverified AI-generated citations, data, coding, effect sizes, or results. • Allowing AI to make final screening or coding decisions or serve as an intercoder. • Fabricating or filling in missing information with AI. Yellow Light: Permitted with Caution and Disclosure • Brainstorming topics, research questions, moderators, search terms, or coding variables. • Identifying studies or summarizing articles, provided all information is verified against the original sources. • Assisting with coding, effect-size calculations, statistical code, or interpretation, provided all outputs are independently reviewed and verified. • Developing outlines or suggesting tables and visualizations. Green Light: Permitted and Encouraged • Correcting grammar, spelling, and formatting. • Improving the clarity and flow of student-written text. • Assisting with R coding and debugging. • Organizing notes, timelines, and project tasks. All AI use must be disclosed. AI may support the research process, but it cannot replace students’ reading, judgment, analysis, or responsibility for the final work.

評分方式

1. Problem Definition (5%, Week 2) • Meta-analysis topic, conceptual definitions, inclusion/exclusion boundaries. 2. Literature Search Plan and Log (10%, Week 3) • Sources searched, search strings, dates, screening process documentation. 3. Coding Sheet + Coding Guide (10%, Week 4) • Variables, definitions, coding rules, decision tree for ambiguous cases. 4. Inter-Coder Reliability Report (15%, Week 5) • Pilot-coded subset + reliability statistics + revised codebook. 5. Meta-Analytic Results for 10% of the Papers (25%, Week 8) • Effect sizes, model selection rationale, heterogeneity assessment, preliminary moderators. 6. Presentation (15%, Last Week) • Conference-style presentation with figures/tables and clear interpretation. 7. Manuscript + Documentation (20%, Last Week) • Manuscript + appendices (search log, screening record, coding guide, dataset, and analysis outputs).

課程大綱

教師未提供此項資料

週次計畫
週次主題
第 1 週

Class 1 9:00-12:00—Course Overview + Why Research Synthesis Matters Goals: Introduce research synthesis as scientific inquiry; define meta-analysis; explain the staged workflow; discuss how synthesis differs from narrative review. In-class: Topic brainstorming; examples of strong and weak syntheses; mapping student interests to feasible research questions.

2026-09-09(三)
第 2 週

Class 2 9:00-12:00—Formulating the Problem Core: Conceptual definitions; operational boundaries; inclusion/exclusion logic; associational vs causal questions. Workshop element: Students draft research question and define variables and outcomes. Discussion of the selected topics with the instructor and receipt of instructor feedback. Deliverable launched: Assignment 1 (Problem definition). Draft conceptual definitions and preliminary inclusion/exclusion criteria. Class 3 14:00-17:00—Searching the Literature (Systematic and Replicable) Core:Search terms; databases and sources; complementary search strategies; documenting the search; anticipating retrieval bias. In-class: Build database search strings; compare yield; discuss strategies for unpublished or hard-to-find studies. Deliverable launched: Discussion of the initial literature search results with the instructor and receipt of instructor feedback.

2026-09-16(三)
第 3 週

Class 4 9:00-12:00— Searching the Literature, Screening and Study Flow Documentation Core: Keep searching for literature. Translating searches into screening stages; documenting study flow; screening disagreements; avoiding post hoc decision making. In-class: Title/abstract screening practice; handling duplicates; screening decision rules. Deliverable: Assignment 2 (Literature search plan + initial search log). Class 5 14:00-17:00— Gathering Information from Studies (Coding Design) Core: What to extract; coding sheet vs codebook; selecting moderators; extracting sample and design details; extracting statistical outcomes. In-class: Students draft a coding framework for their topic and outcomes. Deliverable launched: Discussion of the draft codebook and coding sheet with the instructor.

2026-09-23(三)
第 4 週

Class 6 9:00-12:00—Inter-Coder Reliability and Coding Training Core: Reliability; coder training; resolving discrepancies; documentation for ambiguous cases. In-class: Pilot coding on a shared set of studies; compute agreement; revise codebook language. Deliverable launched: Assignment 3 (Coding sheet + coding guide/codebook). Class 7 14:00-17:00—Evaluating Study Quality, Effect Sizes, Moderator Analyses and Subgroup Comparisons Core: Criteria for inclusion/exclusion based on design and implementation; categorizing studies; role of quality in synthesis (exclusion vs moderation vs sensitivity analysis). In-class: Students develop a quality rubric appropriate to their topic; decide how quality will be incorporated analytically. Deliverable launched: Assignment 4 (Inter-coder reliability report).

2026-09-30(三)
第 5 週

Class 8 9:00-12:00— Effect Sizes, Models, Moderator Analyses and Subgroup Comparisons, and Heterogeneity Core: Effect size metrics; fixed vs random effects models; heterogeneity; independence issues; preparing an analysis-ready dataset. In-class: Effect size extraction demo; dataset structure; initial analysis workflow overview. Deliverable launched: Assignment 5 (Preliminary meta-analytic results plan).

2026-10-07(三)
第 6 週

No class.

2026-10-14(三)
第 7 週

No class.

2026-10-21(三)
第 8 週

No class.

2026-10-28(三)
第 9 週

Class 9 9:00-12:00— Analysis Lab 1: Data Cleaning + Effect Size Computation Focus: Students bring coded datasets; instructor reviews effect size calculations; troubleshoot missing statistics and coding ambiguities. Checkpoint: Confirm unit-of-analysis rules and independence decisions. Deliverable: submit project progress

2026-11-04(三)
第 10 週

Class 10 9:00-12:00— Analysis Lab 2: Model Choice + Heterogeneity Focus: Fit baseline models; interpret average effects and confidence intervals; evaluate heterogeneity diagnostics. Checkpoint: Confirm alignment between theoretical rationale and analytic plan. Deliverable: submit project progress

2026-11-11(三)
第 11 週

Class 11 9:00-12:00— Moderator Analyses and Subgroup Comparisons Focus: Test key moderators; interpret conditional effects; avoid overfitting; connect moderators to theoretical mechanisms. Deliverable: Updated results tables/figures.

2026-11-18(三)
第 12 週

Class 12 9:00-12:00— Publication Bias, Missing Data, and Sensitivity Analyses Core: Examine potential missing evidence; assess robustness to analytic assumptions; interpret bias diagnostics carefully. In-class: Run multiple checks; discuss limitations and what conclusions remain supported. Deliverable: Updated results tables/figures. Students may complete the content for Classes 9–12 remotely and meet with the instructor online to discuss any questions they may have.

2026-11-25(三)
第 13 週

Class 13 9:00-12:00—Interpreting Evidence (From Numbers to Meaning) Core: Practical vs statistical significance; generalizability; limits of causal inference; translating findings into clear claims. Deliverable launched: Presentation slides draft (Assignment 6).

2026-12-02(三)
第 14 週

Class 14 9:00-12:00—Presenting Results (Writing Workshop) Core: Manuscript structure; reporting completeness; transparent methods; clear results narrative; defensible discussion and limitations. In-class: Outline peer review; methods checklist; revision planning.

2026-12-09(三)
第 15 週

Individual advising

2026-12-16(三)
第 16 週

Class 16 9:00-12:00—Student Presentations + Peer Feedback Round 2 + Wrap-Up Activity: the class presents (10–12 minutes each). Feedback: Structured rubric: clarity of question, search documentation, coding reliability, analytic choices, interpretation, and communication. Wrap-up: What makes a synthesis trustworthy; publication planning; reflection on documentation and reproducibility. Final deliverable: Final manuscript + documentation package.

2026-12-23(三)
教科書

Research Synthesis and Meta-Analysis: A Step-by-Step Approach • Edition: Fifth Edition • By: Harris Cooper • Free online version: https://methods.sagepub.com/book/mono/research-synthesis-and-meta-analysis-5e/toc

Office Hours
地點
HK206
時間
Wednesday 09:00-12:00 and 14:00-17:00
聯絡方式
陶振超 taoc@nycu.edu.tw 許珊 shan.xu@ttu.edu