Paper: arXiv 2305.17419

Authors: Ben Moews

Abstract

Modern mainstream financial theory is underpinned by the efficient market hypothesis, which posits the rapid incorporation of relevant information into asset pricing. Limited prior studies in the operational research literature have investigated tests designed for random number generators to check for these informational efficiencies. Treating binary daily returns as a hardware random number generator analogue, tests of overlapping permutations have indicated that these time series feature idiosyncratic recurrent patterns. Contrary to prior studies, we split our analysis into two streams at the annual and company level, and investigate longer-term efficiency over a larger time frame for Nasdaq-listed public companies to diminish the effects of trading noise and allow the market to realistically digest new information. Our results demonstrate that information efficiency varies across years and reflects large-scale market impacts such as financial crises. We also show the proximity to results of a well-tested pseudo-random number generator, discuss the distinction between theoretical and practical market efficiency, and find that the statistical qualification of stock-separated returns in support of the efficient market hypothesis is dependent on the driving factor of small inefficient subsets that skew market assessments.

Complexity vs Empirical Score

  • Math Complexity: 6.5/10
  • Empirical Rigor: 7.0/10
  • Quadrant: Holy Grail — high math complexity, high empirical rigor

Why this score: The paper employs advanced statistical tests (overlapping permutations) and theoretical econometrics (martingale definitions, tautology critiques) but is grounded in heavy empirical analysis of Nasdaq data over long time frames, evaluating specific market events like financial crises.

Research Flowchart

  flowchart TD
  A["Research Goal:<br>Test Market Efficiency via RNG Tests"] --> B["Methodology:<br>Overlapping Permutation Tests"]
  B --> C["Data Input:<br>Nasdaq Binary Daily Returns<br>1990-2023"]
  C --> D["Computational Process:<br>Annual & Company-Level Analysis"]
  D --> E["Outcome 1:<br>Efficiency varies with time<br>e.g., financial crises"]
  D --> F["Outcome 2:<br>Statistical fit depends on<br>small inefficient subsets"]
  D --> G["Outcome 3:<br>Practical vs. Theoretical<br>Efficiency distinction"]

Evidence Card

What the authors claim, on what data, and who has checked it. Read from the paper's own text by a language model: every quote is verbatim, nothing was re-run. How to read this card

Proposes

The paper proposes applying overlapping permutation tests from random number generation to Nasdaq stock return data, comparing company‑level and year‑level analyses and benchmarking against a well‑tested pseudo‑random number generator.

Source sentence
In this paper, we confirm the viability of cross-disciplinary methodology transfers, from the field of random number generation to econometrics, bridging the gap through the application of operational research to the study of financial markets. For both streams, we perform comparisons to a well-tested pseudo-random number generator and find comparable measures for company-separated data once outliers are removed, while

Assumes 6

  • Successive returns are independent. statistical
    Source sentence
    Interpreting market efficiency as the independence of successive returns, an additional assumption can be made, which is their identical distribution.
  • Successive returns are identically distributed. statistical
    Source sentence
    This leads, as conditional and marginal probability distributions of independent random variables are identical, to f(ri,t+1|Φt) = f(ri,t+1), (5) for a density function f that is invariant to t.
  • Prices follow a submartingale, i.e., E(p_{i,t+1}|Φ_t) ≥ p_{i,t}. model
    Source sentence
    Under the assumption that ∀t∀Φt : E(˜pi,t+1|Φt) ≥pi,t ⇒∀t∀Φt : E(˜ri,t+1|Φt) ≥0, (4) the time series of prices {pi,t} follows a submartingale.
  • Binary daily returns can be treated as a hardware random number generator analogue. other
    Source sentence
    Treating binary daily returns as a hardware random number generator analogue, tests of overlapping permutations have indicated that these time series feature idiosyncratic recurrent patterns.
Show 2 more
  • Missing data do not affect the distribution of binary patterns under study. data
    Source sentence
    As our approach studies market efficiency regardless of contributing factors, this is not of direct concern, but our analysis shows an improvement in month-to-month efficiency for the year said act was passed, lasting until the Global Financial Crisis of 2007–2008. 2.3.
  • Outlier removal (small percentage of highest contributors) yields a sample that qualifies for randomness. statistical
    Source sentence
    We confirm this effect by dropping sufficiently small percentages of the highest contributors and reevaluating the measures for combined χ2 values. The fourth to penultimate rows in the upper part of Table 2 demonstrate how small percentages (1%, 2%, 3%) result in statistical insignificance for the combined χ2 values for different window sizes, starting with ν = 3, 5, 6 for 1%.

Data

  • Nasdaq monthly close prices · WRDS Compustat market-prices public
    2001-2019 · 4,905 Nasdaq‑listed companies
    Source sentence
    Exchange and empirical data description We retrieve monthly close prices of Nasdaq-listed stocks, spanning the years 2001–2019, from the Wharton Research Data Services (WRDS) Compustat database. This provides us with a dataset featuring 809,195 entries for 4,905 companies, with associated company identifiers and dates.

Costs

Not applicable The paper reports no trading or execution result.

Finds 5

  • Company‑separated Nasdaq stocks show average market efficiency, but this is only confirmed after omitting a small subset of outliers that otherwise drive the overall assessment toward significant inefficiency. statistical
    Source sentence
    Our results for company-separated data demonstrate that stocks of individual Nasdaq-listed public companies feature average market efficiency as measured in this study, although this efficiency is only confirmed when omitting a small subset of outliers, which skew the overall assessment towards statistically significant inefficiency for the overall exchange.
  • Information efficiency varies across years and declines during financial crisis periods. statistical
    Source sentence
    Our results demonstrate that information efficiency varies across years and reflects large-scale market impacts such as financial crises. When performing the same analysis on year-separated data instead, we find that the same effect applies, but also that assessments vary starkly in their pattern recurrence, which is further confirmed through the distribution of summed counts, and reflects cross-correlations and
  • When using daily close prices, a slightly larger number of outliers is observed, reflecting short‑term inefficiencies spanning only a few days. statistical
    Source sentence
    For daily instead of monthly close prices, the number of outliers is slightly larger, as shorter-term inefficiencies in price behaviour can contribute to the results, and this increase is driven by short patterns spanning only a few days.
  • After removing outliers, company‑level return series exhibit statistical measures comparable to those of a well‑tested pseudo‑random number generator. statistical
    Source sentence
    For both streams, we perform comparisons to a well-tested pseudo-random number generator and find comparable measures for company-separated data once outliers are removed, while annual analyses differ in their year-to-year variation.
  • Dropping very small percentages (1‑3%) of the highest contributors renders the combined χ² statistics statistically insignificant, indicating that a tiny inefficient subset drives the rejection of randomness. statistical
    Source sentence
    We confirm this effect by dropping sufficiently small percentages of the highest contributors and reevaluating the measures for combined χ2 values. The fourth to penultimate rows in the upper part of Table 2 demonstrate how small percentages (1%, 2%, 3%) result in statistical insignificance for the combined χ2 values for different window sizes, starting with ν = 3, 5, 6 for 1%.

Checked by others

No other paper in the archive has been found to support or contradict these findings. Coverage is partial, so this is neither replication nor refutation.

Cited by 1 paper in the archive (1 by independent authors): Emergence of Randomness in Temporally Aggregated Financial … (used as a baseline)

Code

No repository by the authors found in the paper.

Extracted 2026-11-14 · same card as JSON · A language model chose these items: check the source sentence before relying on one.