近幾年台灣各大專院校相繼成立校務研究辦公室，致力於探討學生議題及 評估學校政策，透過科學化的決策支援系統輔助學校決策者改善學校經營方針與規劃未來發展，旨在促進學校和教育政策的發展，提高學校的教學品質、學生學習成果和學校整體運作效率。本校校務研究單位目前已蒐集、整理各單位的資料並進行整合，校務倉儲資料庫提供的實證資料涉及範疇極其多樣，教務、學務、總務以及人事等皆包含在內。 在大數據分析的浪潮中，各個機構將面臨數量龐大的可分析議題，然而， 對於選定何種類型資料針對特定議題進行分析仍然相當困難，有時候，分析結果可能出現錯誤或不如預期的情況，這些問題往往源於自身機構內資料面向的不完整性，由於資料種類的不足，可能導致錯誤的分析結果，因此，必須納入額外資料，重新進行分析，以獲得所期望的結果。本研究旨在探討在已有資料集中是否需要納入額外資料來進行分析，比較納入額外資料前後的準因果規則集，整理出三種情況進行評估：準因果規則強弱變化、更特定準因果規則以及更直接準因果規則，提供分析者一個以因果勝算比的角度考量是否應該納入額外資料的方法。本研究將以校務資料為例，以學生為主體，進行因果勝算比探勘，討論「給予學生經濟協助」與「學生擴大交友圈」兩大面向，在探究畢業走向相關議題時是否值得考慮進去。 ;In recent years, many universities in Taiwan have established offices of institutional research one after another, dedicated to exploring student issues and evaluating school’s policies. These offices assist school administration in improving school management and future development planning by scientific decision support systems. The goal is to promote the development of schools and educational policies, enhance teaching quality, student learning outcomes and school operational efficiency. In the era of big data, institutions would face plenty of issues. However, it still difficult to determine which types of data should be used in specific issue analysis. Occasionally, analysis results may be wrong or unexpected. This situation often happen when the dimension of data within institution itself is not widely enough. Insufficient data types can lead to inaccurate analysis results, must incorporate additional data for reanalysis to obtain expected outcomes. This research aims to explore the need for incorporating additional data into existing datasets for analysis. We compare the odds ratio before and after incorporating additional data, evaluating three scenarios: changes in the strength of quasi causal rule, more specific quasi causal rules and core direct quasi causal rules. This provide analysts with a method to consider whether additional data should be incorporated from a causal odds ratio perspective. This research takes student data as an example, implements causal odds ratio mining with student data and discusses whether “providing financial assistance to student” and “expanding student’s social network” should be considered when exploring issues related to prospects after graduation.
