本研究採用 1987 年 7 月至 2025 年 6 月台灣上市櫃公司為樣本，探討資產成長效應（Asset Growth Effect）在台灣股市長期不顯著之謎。相較於美國市場顯著的負向線性關係（Cooper et al.， 2008），本研究主張此一台灣悖論根源於傳統模型忽略了台灣企業在全球供應鏈中的地位異質性。據此，本研究創新引入財報中的合約負債比率作為關係專屬性投資（RSI）程度與供應鏈訂單保障能力的核心代理變數，並結合 Hou， Xue， and Zhang (2015) 的 q 理論框架，推導出資產擴張由受罰轉為溢酬的定價反轉機制。 實證結果顯示，全樣本 Fama-MacBeth 迴歸中資產成長率（AG）無顯著線性預測能力。然而，依合約負債比率進行 50%／40%／10% 的非對稱子樣本分組後，隱藏的定價結構完整浮現：缺乏訂單保障的弱勢供應商（Low RSI）其 AG 係數顯著為負，呈現理性擴張受罰；而具備高額預付款保障的優勢供應商（High RSI）其 AG 係數則明顯反轉為正，形成實質的擴張溢酬。此一正負兩股定價力量的平均化抵銷，正是傳統線性模型失效的底層原因。 進一步分析顯示，擴張溢酬現象高度集中於電子科技業（High RSI 群體市值佔比達 75.1%），顯示該機制根植於台灣電子代工供應鏈的特殊結構。切分點穩健性測試亦證實，正向擴張溢酬僅在極端前 10%～5% 的門檻下顯著，與合約負債極端右偏的分佈特徵高度吻合。本研究為 Goo and Wang (2024) 所觀察到的非線性 U 型特徵提供了完整的微觀解釋，並確立合約負債比率為解構台灣股市資產成長效應非線性動態的關鍵調節變數。;This study investigates the "Taiwan Paradox"—the long-standing statistical insignificance of the asset growth (AG) effect in the Taiwanese stock market—using a sample of listed and OTC companies from July 1987 to June 2025. In contrast to the significant negative linear relationship documented in the U.S. market (Cooper et al.， 2008)， we contend that this paradox stems from conventional models neglecting supply chain heterogeneity. Accordingly， this study introduces the contract liability ratio as a novel proxy variable for the degree of relationship-specific investment (RSI) and supply chain order security. Integrating this proxy into the investment-based asset pricing framework (q-theory) of Hou， Xue， and Zhang (2015)， we derive a pricing reversal mechanism where asset expansion shifts from a valuation penalty to a premium. The empirical results show that while full-sample Fama-MacBeth regressions yield no significant linear predictive power for AG， an asymmetric 50%/40%/10% sorting based on the contract liability ratio reveals a hidden pricing bifurcation. Weak suppliers lacking order security (Low RSI) exhibit a significantly negative AG coefficient (-0.0095， t = -2.04)， indicating a rational expansion penalty. Conversely， dominant suppliers backed by high prepayment guarantees (High RSI) display an AG coefficient that strongly reverses to positive (0.0138， t = 2.65)， forming a substantial expansion premium. The mutual cancellation of these opposing cross-sectional forces causes standard pooled linear models to fail. Further analysis demonstrates that this expansion premium is highly concentrated in the electronic technology sector， where the High RSI group commands a 75.1% market value share， indicating that this mechanism is rooted in the unique structure of Taiwan′s electronics supply chain. Breakpoint robustness tests verify that the positive premium is confined to the extreme top 10% to 5% thresholds， matching the highly right-skewed distribution characteristic of contract liabilities. In conclusion， this study resolves the puzzle of Taiwan′s invalid AG effect， providing a comprehensive supply-chain and q-theoretic foundation for the distinctive non-linear U-shaped pattern observed by Goo and Wang (2024).
