“Taleb actually makes a great point here and published a pretty cool paper about it.”
Election Predictions as Martingales: An Arbitrage Approach
Taleb 用套利定价论证选举预测应表现为鞅
论文把二元选举结果的估计看作鞅,并在持续更新估计时提出套利定价:估计量应按二元期权定价,因为套利估值能最小化常用于衡量概率评估者准确性的 Brier 分数。作者由标准算术布朗运动构造一个对偶鞅过程 Y 来为选举定价,并给出估计量波动率与底层变量波动率的关系:当结果高度不确定时,二元期权的套利价值接近 50%,且估计不应随民调变化而大幅波动。作者指出 2016 年美国总统选举中多个预测团队经常违反这些套利关系。
HN 上的人推荐它来说明选举概率预测必须满足无套利条件,并用它批评 538 等预测模型过于敏感,也有人坦言没有金融背景很难读懂。
HN 书评
推荐在前,同类按时间 · 每篇最多保留 20 条,统计用全部提及“read Taleb's paper, which has some actually interesting thoughts on why 538's algorithms are too eager”
“Election Predictions as Martingales: An Arbitrage Approach, Nassim Nicholas Taleb Quantitative Finance.”
“after skimming through the paper[1] (I find it hard to grasp without a solid background)”
“So any prediction that doesn't incorporate the events between making the prediction until the election actually occurs, is worthless, or to be more precise: 50/50 (arbitrage free).”
- Election Predictions as Martingales: An Arbitrage Approach ↗itronitron · 2020-11-04 · 2 分
- Election Predictions as Martingales: An Arbitrage Approach: Taleb (2017) ↗Jimmc414 · 2022-11-09 · 2 分