---
title: 'E-Scores: Statistical, Decision & Predictive Methods'
url: https://www.emergentmind.com/topics/e-scores-d774eaee-d876-47e6-9ba6-fa3d7b7e7961
type: topic
---

# E-Scores: Statistical, Decision & Predictive Methods

An E-score is a general term encompassing a suite of rigorous, theoretically motivated scoring functions arising in diverse settings, including statistical evidence assessment, uncertainty quantification, educational forecasting, multi-criteria decision making, and generative model evaluation. The defining property shared by contemporary E-score frameworks is a statistical or algorithmic construction grounded in e-values—quantities with controlled expectation under a null or reference model—or robust interval assignment based on formal outranking relations.

## 1. E-Values and Statistical E-Scores

E-values, central to modern E-score methodologies, are nonnegative random variables $E$ satisfying $\mathbb{E}_0[E] \le 1$ under a null hypothesis $H_0$ [2009.02824]. Key examples include likelihood ratios, Bayes factors for simple nulls, and stopped betting martingales. The realized value $e$ can be directly interpreted as the multiplicative betting gain under $H_0$.

E-scores constructed from e-values exhibit several crucial properties:
- **Evidence Scaling**: Larger e-scores indicate stronger statistical evidence against the null.
- **Robustness to Optional Stopping**: Type I error is not inflated by data-driven or sequential stopping, in contrast to $p$-values.
- **Multiplicativity and Adaptivity**: Independent e-values multiply, supporting evidence accumulation across datasets or hypotheses.
- **Dependence Robustness**: Validity holds under arbitrary dependence as expectation control is the only required condition.

These properties provide the backbone for e-score–based approaches in multiple testing (e.g., in the e-Benjamini–Hochberg (e-BH) procedure) and uncertainty quantification in predictive modeling [2009.02824, 2512.06945].

## 2. E-Scores in Multiple Hypotheses Testing

The e-BH procedure generalizes classical multiple testing frameworks by replacing $p$-values with e-scores [2009.02824]. For $K$ hypotheses with e-values $e_1,\ldots,e_K$ and FDR target $\alpha$, hypotheses are sorted and rejected up to the largest $k$ with $k\,e_{[k]}/K \ge 1/\alpha$. This thresholding is self-consistent and provides FDR control at level $\alpha$ under no assumptions on the joint dependency structure of the e-scores.

Compared to $p$-value–based methods, e-score procedures:
- Eliminate the need for independence or positive dependence assumptions.
- Permit post-selection and structured inference, as arbitrary monotone rejection sets based on e-scores preserve error control.
- Enable sequential and adaptive testing, including applications to multi-armed bandits, where per-arm e-scores are combined at arbitrary stopping times without correction.

Furthermore, p-values can be calibrated into e-values via functions $f:[0,1]\to [0,\infty)$ with controlled expectation, unifying the $p$- and $e$-score frameworks.

## 3. E-Scores for Conformal Prediction and Uncertainty Aggregation

In conformal prediction and ensemble model aggregation, e-scores arise by transformation of nonconformity or anomaly scores into normalized e-values [2512.06945]. The Symmetric Aggregated Conformal Prediction (SACP) framework demonstrates this approach for combining uncertainty across predictors:
- Each model's nonconformity scores are converted to e-values through a normalization exploiting exchangeability.
- Symmetric aggregation functions (arithmetic, geometric, harmonic mean, product, $p$-sum) combine per-model e-values into an ensemble e-score for each candidate prediction.
- The resulting aggregated e-scores enable construction of prediction sets with guaranteed marginal coverage, achieved by empirical quantile thresholding.
- Experimental benchmarks show that symmetric e-score aggregation yields tighter and more efficient uncertainty sets compared to alternative conformal aggregation strategies, with maintained coverage rates across diverse datasets.

This approach leverages the closure properties of e-values and the symmetric exchangeability in model selection, extending to both regression and classification.

## 4. E-Scores for Output (In)Correctness in Generative Models

Recent advances address the evaluation of output correctness in generative models, especially LLMs, using e-scores computed from e-value constructions [2510.25770]. The methodology targets major limitations of $p$-score–based conformal set filtering, notably the lack of post-hoc validity when users adapt the significance threshold after inspecting the scores ("p-hacking").

For a set of model outputs, an oracle estimator $\hat o(x, y)$ predicts correctness. Scores are computed as:
$$
e(x, y) = \frac{(n+1)\,f(x, y)}{f(x, y) + \sum_{i=1}^n f^*(x^i)}
$$
where $f$ is a monotonic transform of $\hat o$, and $f^*(x^i)$ aggregates the worst-case "incorrect" score on calibration samples. The e-score for $y$ is $s(y)=1/e(x, y)$. The key theoretical guarantee is that for any (even post-hoc chosen) threshold $\alpha$,
$$
\mathbb{E}\left[\frac{1\{\exists\; \text{incorrect } y: s(y)\le\alpha\}}{\alpha}\right] \le 1,
$$
a post-hoc size-distortion control not shared by p-scores. Applications to mathematical factuality and property-constrained LLM outputs demonstrate that e-scores preserve selectivity while closing the "p-hacking" loophole. The use of e-scores thus ensures the statistical validity of filtering procedures under adaptively chosen tolerance levels.

## 5. E-Scores in Multi-Criteria Decision Analysis

The ELECTRE-Score methodology (also referenced as "E-score") assigns interval-valued scores to alternatives based on formal outranking relations among reference sets, departing from compensatory additive models such as Multi-Attribute Value Theory (MAVT) [1905.06089]. The method proceeds as follows:
- For alternatives $a \in A$ and criteria $g_1,\ldots,g_n$ (with possible imprecision), define pairwise outranking $\succsim$ using per-criterion thresholds for indifference, strict preference, and veto.
- Reference sets of limiting profiles are constructed and ordered, each accorded a score via a deck-of-cards protocol reflecting the decision-maker's perceived gaps between reference bands.
- For each alternative, lower and upper bounds of its E-score interval are determined as the maximal reference score it outranks and the minimal one that outranks it, respectively.
- E-scores are thus robust intervals $(\underline s(a), \overline s(a))$ rather than precise cardinal values, mitigating overcompensation and enhancing robustness to parameter or data perturbations.

This non-compensatory, outranking-based E-score paradigm supports decision contexts with qualitative or uncertain data and provides theoretical guarantees including monotonicity, stability, and conformity.

## 6. E-Scores in Educational Prediction: The Embibe Score Quotient

In the Embibe Score Quotient (ESQ) framework, E-scores refer to the predicted next-test score of a learner, computed from a high-dimensional summary of academic, behavioral, effort, and test-taking features [2010.02629]:
- Feature engineering encompasses Bayesian Knowledge Tracing outputs, DeepFM concept mastery embeddings, and fine-grained behavioral signals.
- Sequential RNNs or bucketed random forests generate test score predictions, with the RNN achieving median absolute error of 4.57% and Pearson correlation of $\approx 0.93$.
- Shapley values calculated per prediction enable actionable, individualized feedback by attributing score contributions to academic, effort, behavioral, and test-taking features.
- Quantile regression provides calibrated prediction intervals, functioning as confidence gauges for decision support.
- The framework supports counterfactual what-if analyses, enabling prescriptive nudges by inversely optimizing features for a target score increment.

The Embibe Score Quotient operationalizes E-scores in a production educational platform, unifying prediction, interpretation, uncertainty quantification, and prescriptive analytics.

## 7. Interpretations, Strengths, and Theoretical Guarantees

E-scores, as instantiated in the above settings, are distinguished by the following features:
- **Expectation Control**: E-scores are designed to control first moments or produce interval bands, with rigorous guarantees against error inflation, even under complex dependence (e.g., e-BH FDR control [2009.02824], e-score post-hoc error control [2510.25770], ELECTRE interval stability [1905.06089]).
- **Non-Compensatory and Robust**: Outranking-based E-scores do not allow poor performance on one criterion to be offset by high performance elsewhere [1905.06089].
- **Adaptivity**: E-score methodologies retain their guarantees under adaptive, post-hoc thresholding, unlike conventional $p$-value or value-function approaches [2510.25770].
- **Interpretability and Prescriptiveness**: Modern applications, as in ESQ, leverage feature attribution for actionable guidance [2010.02629].
- **Unified Framework**: Both $p$-based and e-based multiple testing procedures are subsumed via calibration, illustrating the generality of the e-score principle [2009.02824].

A plausible implication is that e-value–driven E-score methodologies are likely to see further adoption across fields requiring robust, adaptive, and interpretable decision-support or uncertainty quantification.

---

**References**  
- [2009.02824] "False discovery rate control with e-values"
- [2512.06945] "Symmetric Aggregation of Conformity Scores for Efficient Uncertainty Sets"
- [2510.25770] "E-Scores for (In)Correctness Assessment of Generative Model Outputs"
- [1905.06089] "Electre-Score: A first outranking based method for scoring actions"
- [2010.02629] "A framework for predicting, interpreting, and improving Learning Outcomes"

Source: https://www.emergentmind.com/topics/e-scores-d774eaee-d876-47e6-9ba6-fa3d7b7e7961