REVIEW 1 major objections 5 minor 68 references
Characterizing Bias in Post-Bandit Inference under Index Algorithms
T0 review · 1 major / 5 minor · reviewed 2026-08-15 · deepseek-v4-flash
Pith's one-line read Stable index bandit algorithms such as UCB1 carry a precisely quantified bias in post-hoc sample means: for every arm that is not uniquely optimal, the standardized bias decays at the slow rate $1/\sqrt{\log T}$, with the constant set by…
desk verdict Sharp new bias formula with a nice fluid tool, but the multiple-optima proof has a gap that needs fixing before the headline claim is credible. read the letter →
The pith
A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.
The reading
What carries the argument
The load-bearing object is the effective exploration rate $$\Gamma_t(x,n):=-2\,$n^{{3/2}}$\,\frac{\partial_n I_t(x,n)}{\partial_x I_t(x,n)},$$ which the paper interprets as how many additional pulls of an arm offset a one-standard-error perturbation of its sample mean while keeping the index unchanged; large $\Gamma$ means the algorithm barely reacts to noise, hence less bias. The second engine is the empirical fluid approximation $\tilde n_t$, defined by solving the index-equalization equations with the population means replaced by sample means evaluated at the deterministic fluid counts $n_t$; unlike the deterministic fluid $n_t$, it retains the coupling between pull counts and reward fluctuations, and Lemma 3 shows that the covariance $(\tilde n_{a,T}-n_{a,T})(\bar X_a(n_{a,T})-\mu_a)$ supplies exactly the leading term of the bias. Around the two approximations, the proof uses the covariance identity of Lemma 2, $\mathbb{E}[\bar X_a(N_{a,T})-\mu_a]=-q^{-1}\mathbb{E}[(N_{a,T}-q)(\bar X_a(N_{a,T})-\mu_a)]$ for any deterministic $q$, and Lemma 4's residual bounds to kill everything not of leading order.
What would settle it
Simulate a three-arm bandit with two optimal arms (mean 0) and one suboptimal arm, all with variance $\sigma^2=1$, under UCB1 at $T=10^6$; the paper predicts $f_T\,\mathbb{E}[Z_{a,T}]\to -1/2$ for each optimal arm and $-1$ for the suboptimal arm, and $\frac{f_T}{\sqrt{n_{a,T}}}\mathbb{E}[\bar X_a(N_a(T))-\mu_a]\to-1$ for the suboptimal arm. If the products converge instead to zero, or to constants that depend on the exploration constant $\rho$, the leading-order covariance claim in Lemma 3 is wrong; equivalently, verifying that $\mathbb{E}[Z_{a,T}]\sqrt{\mathrm{Reg}_T}$ takes the same constant under $f_t=\sqrt{2\log t}$ and $f_t=t^{1/4}$ would confirm the regret-bias trade-off.
Extended reading notes
Core claim
The paper's central result, Theorem 1, states that under its regularity and stability conditions, for every arm $a$, the standardized sample-mean bias and the expected $Z$-statistic obey $$\frac{\Gamma_{a,T}}{\sqrt{n_{a,T}}}\,\mathbb{E}\big[\bar X_a(N_a(T))-\mu_a\big]\;\to\;-2\left(1-\frac{\mathbf 1_{a\in O}}{|O|}\right)\$sigma_a^{2}$,\qquad \Gamma_{a,T}\,\mathbb{E}[Z_{a,T}]\;\to\;-\left(1-\frac{\mathbf 1_{a\in O}}{|O|}\right)\sigma_a,$$ where $O$ is the set of optimal arms and $\Gamma_{a,T}$ is the effective exploration rate of the index function. For generalized UCB indices $I_t(x,n)=x+f_t/\sqrt n$, $\Gamma_{a,T}=f_T$, so the expected $Z$-statistic of every arm that is not the unique optimal arm is of order $-1/f_T$; with $f_T=\sqrt{\rho\log T}$ this is the slow $1/\sqrt{\log T}$ decay, while the unique optimal arm's bias is only $O(f_T/T)$ or smaller. The negative sign reproduces the known downward bias of adaptively collected means, and the prefactor $(1-\mathbf 1_{a\in O}/|O|)$ is zero for the unique optimal arm, full for every suboptimal arm, and intermediate when several arms tie for the top, reflecting the extra selection bias caused by the algorithm oscillating among indistinguishable optimal arms.
Load-bearing premise
The headline formula rests on Condition 3's concentration-rate assumptions, that the scaled gap $\Gamma_{a,T}(N_a(T)-\tilde n_{a,T})/n_{a,T}$ tends to zero in $L^p$ and that the sample mean evaluated at the random stop is within $o(1/\sqrt{n_{a,T}})$ of its fluid-time value, which the paper verifies for UCB1 and Poly-UCB but simply posits for the general index-algorithm statement of Theorem 1; the paper also states without proof (Lemma 1) that the fluid and empirical-fluid allocations exist and are unique.
Editorial extensions
If this is right
- Under UCB1, the standardized bias of any arm that is not the unique optimal arm decays only as $1/\sqrt{\log T}$, so at any realistic horizon the distortion remains comparable to the standard error and shifts naive hypothesis tests built from bandit-collected data.
- Bias and regret obey a fixed trade-off: within the generalized UCB family, $\mathbb{E}[Z_{a,T}]\cdot\sqrt{\mathrm{Reg}_T}\to\kappa_a$ with $\kappa_a$ independent of the algorithm, so an algorithm cannot reduce its bias without paying more regret, and vice versa.
- The unique optimal arm is qualitatively different: its expected $Z$-statistic bias is $O(f_T/T)$, polynomially small, whereas any arm sharing the top with another optimal arm carries the full $-1/f_T$ bias because the algorithm's oscillation among optimal arms amplifies selection bias.
- For arms with the same mean, the higher-variance arm gets the larger bias and more distorted $Z$-statistic, since the formula's strength is proportional to $\sigma_a$ (and $\sigma_a^2$ for the sample mean), a concrete prediction of Theorem 2.
Reading between the lines
- (Editorial inference) The prefactor $(1-\mathbf 1_{a\in O}/|O|)$ predicts a numerically testable symmetry: simulating an $m$-arm bandit with all arms tied at the same mean should reproduce the factor $1-1/m$ on every arm, and the same simulation could check whether one arm's bias in a tie equals the bias it would carry as the unique suboptimal arm in a two-arm problem.
- (Editorial inference) Because $\Gamma$ is a local derivative of the index function, the same definition could assign an effective exploration rate to non-index policies by measuring how many pulls a one-standard-error reward shift displaces; if the logic carries, Thompson sampling and $\epsilon$-greedy would get concrete bias orders instead of only stability-or-instability labels.
- (Editorial inference) The formula suggests a plug-in debiasing recipe, subtracting $(1-\mathbf 1_{a\in O}/|O|)\sigma_a/f_T$ from the $Z$-statistic with estimated $\sigma_a$, whose residual error should be $o(1/f_T)$; a finite-sample experiment comparing coverage before and after this correction would test both the leading constant and the rate.
Signed reviews
Editorial analysis
A structured set of objections, weighed in public.
Referee Report
Summary. This paper studies the bias of post-bandit sample means and Z-statistics under index-based bandit algorithms. It introduces the effective exploration rate Γ and a two-stage (fluid and empirical-fluid) approximation of pull counts. The main theorem states that under Conditions 1–3, Γ_{a,T}/√n_{a,T} E[\bar X_a(N_a(T))−μ_a] → −2(1 − 1_{a∈O}/|O|)σ_a² and Γ_{a,T}E[Z_{a,T}] → −(1 − 1_{a∈O}/|O|)σ_a. For generalized UCB, Γ=f_T, so for UCB1 the standardized bias of every non-unique-optimal arm decays as 1/√log T. The paper also derives a regret-bias trade-off from these rates.
Significance. If the proof of the UCB verification were complete, this would be a substantial contribution: it gives the first sharp leading-order bias formula for a canonical stable algorithm, identifies an interpretable algorithm-dependent quantity (effective exploration rate), and makes a concrete falsifiable prediction (1/√log T bias decay for UCB1). The empirical fluid approximation is a promising technique. The paper is also honest in presenting Condition 3 as a verification condition rather than as a derived property. However, the current manuscript does not fully support the multiple-optima case, and the conditional nature of Theorem 1 limits the generality of the 'stable index algorithms' claim to families for which Condition 3 can actually be verified.
major comments (1)
- [Appendix C.1, Lemma 15 (with Lemma 14)] The verification of Condition 3(5) for optimal arms when |O|≥2 is not established. In Lemma 15 the L_p norm of N_i(T)−\tilde n_{i,T} is split using the event Υ_i^c, and on Υ_i^c the proof asserts that the desired bound |N_i(T)−\tilde n_{i,T}|=o(T/f_T) holds directly. This is true only if the threshold d defining Υ_i satisfies d=o(T/f_T). But Lemma 14, as invoked in the same proof with g=T/√f_T, is stated only for d ≥ √n_{i,T}g/f_T + T/(2f_T²). Since n_{i,T}≍T for i∈O and f_T=√(ρ log T) for UCB1, this lower bound is ≍ T^{3/2}/f_T^{3/2} + T/(2f_T²), which is ω(T/f_T) and in fact ω(T) for large T. Thus no threshold can simultaneously be o(T/f_T) and satisfy Lemma 14's hypothesis; the 'middle range' of deviations, where T/f_T < |N_i(T)−\tilde n_{i,T}| ≪ T^{3/2}/f_T^{3/2}, is not controlled by any argument in the manuscript. Consequently Condition 3(5) is not demonstrated for optimal arms in the multiple-optima case, and the proofs of Theorem 2 for |O|≥2 and of Theorem 1 as applied to optimal arms with |O|≥2 are incomplete as written.
minor comments (5)
- [Section 3.1, Lemma 1] The proof of Lemma 1 is omitted. Since the fluid and empirical-fluid approximations are the foundation of the main theorem, the authors should supply the existence/uniqueness argument or a precise reference.
- [Proof of Lemma 2] In the proof of Lemma 2, the function is written as Γ_q(k) in one place but defined as Λ_q(k) in the lemma statement; please correct the notation.
- [Appendix C.1, Lemma 14 statement] The statement of Lemma 14 is typeset ambiguously: the conditions on d and g run together with the event {|N_i(T)−\tilde n_{i,T}|>d}. Please reformat so that the quantifiers and constraints are unambiguous.
- [Proof of Theorem 2, |O|=1 case] The sharper bound for the Z-statistic of the unique optimal arm is stated without proof ('the proof for the Z-statistic bias is similar and we omit'). Since this is a claimed sharper result, the argument should be included or at least sketched.
- [Section 1.2, related work] The in-text citation '(Halder et al., Sengupta et al. (2026))' is malformed and does not match the reference list; please fix it.
Circularity Check
No significant circularity: the bias formula is derived from a Taylor expansion of the index equations and independent concentration estimates, not assumed or fitted.
full rationale
The paper's central claim is a conditional theorem (Theorem 1) whose proof does not rely on the quantity it predicts. The effective exploration rate Γ is defined from the index function's derivatives (Definition 2), not from observed bias, and the leading covariance term in Lemma 3 is obtained by linearizing the index-equalization equations; the constant (1 − 1_{a∈O}/|O|)σ_a^2 is derived rather than imposed. Condition 3 is a concentration/stability assumption on N_a(T) around the empirical fluid count, not a restatement of the bias, and it is verified for generalized UCB through extensive tail bounds (Lemmas 8–15) that are independent of the bias formula. No parameter is fitted to data and then renamed as a prediction, no self-citation carries a load-bearing step, and no uniqueness theorem by the authors is invoked to force the choice. The reviewer-flagged difficulty in Lemma 15 concerns whether Condition 3 is actually proved for optimal arms when |O|≥2; that would be a correctness or proof gap, not a circular dependency, and therefore does not affect the circularity score.
Assumptions & free parameters
assumptions (4)
- domain assumption Reward distributions are sub-Gaussian (centered, nu-sub-Gaussian) for all arms
- domain assumption Condition 1: index function I_t(x,n) is differentiable, increasing in x, decreasing in n, with boundary limits and local derivative stability
- domain assumption Condition 2: fluid scaling n_{b,T}=omega(1), n_{b,T}/n_{a,T}=o(1), and the derivative ratio condition for optimal versus suboptimal arms
- ad hoc to paper Condition 3: concentration rates Gamma_{a,T} ||(tilde n_a - n_a)/n_a||_s = O(1), Gamma_{a,T} ||(N_a - tilde n_a)/n_a||_p = o(1), and sqrt(n_a)||Xbar_a(N_a)-Xbar_a(n_a)||_r = o(1)
Cite this review
Pith. "Pith review of Characterizing Bias in Post-Bandit Inference under Index Algorithms." pith.science (2026). https://pith.science/paper/5NSFAF7D
@misc{pith2026260801069,
author = {Pith},
title = {Pith review of: Characterizing Bias in Post-Bandit Inference under Index Algorithms},
year = {2026},
howpublished = {\url{https://pith.science/paper/5NSFAF7D}},
note = {Machine review of arXiv:2608.01069}
}
abstract
Bandit algorithms generate data for downstream inference, but adaptive sampling biases post-bandit sample means. We analyze this bias for stable index algorithms, including UCB1 and its generalizations, and derive sharp leading-order expressions for the sample-mean bias and expected $Z$-statistic. Our characterization reveals the algorithmic origin of bias through a key index-function-dependent quantity, which we term effective exploration rate. For example, under UCB1, the effective exploration rate is of order $\sqrt{\log T}$, and the standardized bias of any arm (that is not uniquely optimal) decays at the extremely slow rate $1/\sqrt{\log T}$. We also show how the choice of the index function affects both regret and bias, which reveals a regret-bias trade-off: more exploratory algorithm reduces bias but increases regret. Our sharp characterization for bias uses a novel empirical fluid approximation of the algorithm's sampling dynamics, which may be of independent interest.
Reference graph
Works this paper leans on
-
[1]
Advances in neural information processing systems , volume=
Statistical inference with m-estimators on adaptively collected data , author=. Advances in neural information processing systems , volume=
-
[2]
NeurIPS 2022 Workshop on Causality for Real-world Impact , year=
Beyond Central Limit Theorem for Higher-Order Inference in Batched Bandits , author=. NeurIPS 2022 Workshop on Causality for Real-world Impact , year=
work page 2022
-
[3]
Annual Review of Statistics and its Application , volume=
Demystifying inference after adaptive experiments , author=. Annual Review of Statistics and its Application , volume=. 2025 , publisher=
work page 2025
-
[4]
arXiv preprint arXiv:1103.4601 , year=
Doubly robust policy evaluation and learning , author=. arXiv preprint arXiv:1103.4601 , year=
-
[5]
Proceedings of the national academy of sciences , volume=
Confidence intervals for policy evaluation in adaptive experiments , author=. Proceedings of the national academy of sciences , volume=. 2021 , publisher=
work page 2021
-
[6]
Journal of the American statistical Association , volume=
Estimation of regression coefficients when some regressors are not always observed , author=. Journal of the American statistical Association , volume=. 1994 , publisher=
1994
-
[7]
Journal of the American statistical Association , volume=
A generalization of sampling without replacement from a finite universe , author=. Journal of the American statistical Association , volume=. 1952 , publisher=
1952
-
[8]
arXiv preprint arXiv:2511.18750 , year=
On instability of minimax optimal optimism-based bandit algorithms , author=. arXiv preprint arXiv:2511.18750 , year=
Show all 68 references
-
[9]
Biometrika , pages=
Design Stability in Adaptive Experiments: Implications for Treatment Effect Estimation , author=. Biometrika , pages=. 2026 , publisher=
2026
-
[10]
International Conference on Machine Learning , pages=
Accurate inference for adaptive linear models , author=. International Conference on Machine Learning , pages=. 2018 , organization=
2018
-
[11]
Stable thompson sampling: Valid inference via variance inflation, 2025 , author=
2025
-
[12]
arXiv preprint arXiv:2512.00222 , year=
Statistical inference under adaptive sampling with linucb , author=. arXiv preprint arXiv:2512.00222 , year=
-
[13]
International Conference on Artificial Intelligence and Statistics , pages=
Multi-armed bandit experimental design: Online decision-making and adaptive inference , author=. International Conference on Artificial Intelligence and Statistics , pages=. 2023 , organization=
2023
-
[14]
Applied Stochastic Models in Business and Industry , volume=
A modern Bayesian look at the multi-armed bandit , author=. Applied Stochastic Models in Business and Industry , volume=. 2010 , publisher=
2010
-
[15]
Marketing Science , volume=
Customer acquisition via display advertising using multi-armed bandit experiments , author=. Marketing Science , volume=. 2017 , publisher=
2017
-
[16]
Some aspects of the sequential design of experiments , author=
-
[17]
Mathematical Proceedings of the Cambridge Philosophical Society , volume=
Large-sample theory of sequential estimation , author=. Mathematical Proceedings of the Cambridge Philosophical Society , volume=. 1952 , organization=
1952
-
[18]
arXiv preprint arXiv:2602.07472 , year=
Bandit Allocational Instability , author=. arXiv preprint arXiv:2602.07472 , year=
-
[19]
The american mathematical monthly , volume=
A better bound on the variance , author=. The american mathematical monthly , volume=. 2000 , publisher=
2000
-
[20]
Artificial Intelligence and Statistics , pages=
Controlling bias in adaptive data analysis using information theory , author=. Artificial Intelligence and Statistics , pages=. 2016 , organization=
2016
-
[21]
arXiv preprint arXiv:1902.00746 , year=
On the bias, risk and consistency of sample means in multi-armed bandits , author=. arXiv preprint arXiv:1902.00746 , year=
1902 arXiv
-
[22]
Advances in neural information processing systems , volume=
Inference for batched bandits , author=. Advances in neural information processing systems , volume=
-
[23]
The Annals of Statistics , pages=
Least squares estimates in stochastic regression models with applications to identification and control of dynamic systems , author=. The Annals of Statistics , pages=. 1982 , publisher=
1982
-
[24]
arXiv e-prints , pages=
Precise Asymptotics and Refined Regret of Variance-Aware UCB , author=. arXiv e-prints , pages=
-
[25]
Statistical science: a review journal of the Institute of Mathematical Statistics , volume=
Multi-armed bandit models for the optimal design of clinical trials: benefits and challenges , author=. Statistical science: a review journal of the Institute of Mathematical Statistics , volume=. 2015 , publisher=
2015
-
[26]
Biometrika , volume=
A generalized Dunnett test for multi-arm multi-stage clinical studies with treatment selection , author=. Biometrika , volume=. 2012 , publisher=
2012
-
[27]
European Journal of Cancer , volume=
Practical Bayesian adaptive randomisation in clinical trials , author=. European Journal of Cancer , volume=. 2007 , publisher=
2007
-
[28]
Advances in Neural Information Processing Systems , volume=
A closer look at the worst-case behavior of multi-armed bandit algorithms , author=. Advances in Neural Information Processing Systems , volume=
-
[29]
arXiv preprint arXiv:2210.05660 , year=
The typical behavior of bandit algorithms , author=. arXiv preprint arXiv:2210.05660 , year=
-
[30]
arXiv preprint arXiv:2304.04341 , year=
Regret distribution in stochastic bandits: Optimal trade-off between expectation and tail risk , author=. arXiv preprint arXiv:2304.04341 , year=
-
[31]
arXiv preprint arXiv:2112.06363 , year=
Risk and optimal policies in bandit experiments , author=. arXiv preprint arXiv:2112.06363 , year=
-
[32]
arXiv preprint arXiv:2109.13595 , year=
The fragility of optimized bandit algorithms , author=. arXiv preprint arXiv:2109.13595 , year=
-
[33]
International Conference on Machine Learning , pages=
Pricing experimental design: causal effect, expected revenue and tail risk , author=. International Conference on Machine Learning , pages=. 2023 , organization=
2023
-
[34]
Proceedings of the 24th annual conference on learning theory , pages=
The KL-UCB algorithm for bounded stochastic bandits and beyond , author=. Proceedings of the 24th annual conference on learning theory , pages=. 2011 , organization=
2011
-
[35]
International Conference on Machine Learning , pages=
Anytime optimal algorithms in stochastic multi-armed bandits , author=. International Conference on Machine Learning , pages=. 2016 , organization=
2016
-
[36]
arXiv preprint arXiv:2412.06126 , year=
UCB algorithms for multi-armed bandits: Precise regret and adaptive inference , author=. arXiv preprint arXiv:2412.06126 , year=
-
[37]
Management Science , volume=
Weak signal asymptotics for sequentially randomized experiments , author=. Management Science , volume=. 2024 , publisher=
2024
-
[38]
2017 , publisher=
Probability and measure , author=. 2017 , publisher=
2017
-
[39]
2020 , publisher=
Bandit algorithms , author=. 2020 , publisher=
2020
-
[40]
Advances in applied mathematics , volume=
Asymptotically efficient adaptive allocation rules , author=. Advances in applied mathematics , volume=. 1985 , publisher=
1985
-
[41]
Finite-time Analysis of the Multiarmed Bandit Problem , journal =
Peter Auer and Nicol. Finite-time Analysis of the Multiarmed Bandit Problem , journal =
-
[42]
Artificial intelligence and statistics , pages=
On Bayesian upper confidence bounds for bandit problems , author=. Artificial intelligence and statistics , pages=. 2012 , organization=
2012
-
[43]
Proceedings of the 24th annual Conference On Learning Theory , pages=
A finite-time analysis of multi-armed bandits problems with kullback-leibler divergences , author=. Proceedings of the 24th annual Conference On Learning Theory , pages=. 2011 , organization=
2011
-
[44]
Conference on learning theory , pages=
Analysis of thompson sampling for the multi-armed bandit problem , author=. Conference on learning theory , pages=. 2012 , organization=
2012
-
[45]
2011 , publisher=
Multi-armed bandit allocation indices , author=. 2011 , publisher=
2011
-
[46]
Biometrika , volume=
On the likelihood that one unknown probability exceeds another in view of the evidence of two samples , author=. Biometrika , volume=. 1933 , publisher=
1933
-
[47]
International Conference on Artificial Intelligence and Statistics , pages=
Why adaptively collected data have negative bias and how to correct for it , author=. International Conference on Artificial Intelligence and Statistics , pages=. 2018 , organization=
2018
-
[48]
arXiv preprint arXiv:2408.04595 , year=
Inference with the upper confidence bound algorithm , author=. arXiv preprint arXiv:2408.04595 , year=
-
[49]
Advances in Neural Information Processing Systems , volume=
Are sample means in multi-armed bandits positively or negatively biased? , author=. Advances in Neural Information Processing Systems , volume=
-
[50]
Advances in Neural Information Processing Systems , volume=
Estimation bias in multi-armed bandit algorithms for search advertising , author=. Advances in Neural Information Processing Systems , volume=
-
[51]
Conference on Learning Theory , pages=
lil’ucb: An optimal exploration algorithm for multi-armed bandits , author=. Conference on Learning Theory , pages=. 2014 , organization=
2014
-
[52]
Advances in Neural Information Processing Systems , volume=
Online multi-armed bandits with adaptive inference , author=. Advances in Neural Information Processing Systems , volume=
-
[53]
II , author=
An approximation of partial sums of independent RV's, and the sample DF. II , author=. Zeitschrift f. 1976 , publisher=
1976
-
[54]
Statistical methods in medical research , volume=
Unbiased estimation for response adaptive clinical trials , author=. Statistical methods in medical research , volume=. 2017 , publisher=
2017
-
[55]
, author=
Portfolio Choices with Orthogonal Bandit Learning. , author=. IJCAI , volume=
-
[56]
Annals of Mathematics and Artificial Intelligence , volume=
Algorithm portfolio selection as a bandit problem with unbounded losses , author=. Annals of Mathematics and Artificial Intelligence , volume=. 2011 , publisher=
2011
-
[57]
Proceedings of the 19th international conference on World wide web , pages=
A contextual-bandit approach to personalized news article recommendation , author=. Proceedings of the 19th international conference on World wide web , pages=
-
[58]
Royal Society open science , volume=
Risk-aware multi-armed bandit problem with application to portfolio selection , author=. Royal Society open science , volume=. 2017 , publisher=
2017
-
[59]
Proceedings of the National Academy of Sciences , volume=
Bandit solutions provide unified ethical models for randomized clinical trials and comparative effectiveness research , author=. Proceedings of the National Academy of Sciences , volume=. 2009 , publisher=
2009
-
[60]
Marketing Science , volume=
Dynamic online pricing with incomplete information using multiarmed bandit experiments , author=. Marketing Science , volume=. 2019 , publisher=
2019
-
[61]
American Economic Review , volume=
Artificial intelligence, algorithmic pricing, and collusion , author=. American Economic Review , volume=. 2020 , publisher=
2020
-
[62]
Management Science , volume=
Multimodal dynamic pricing , author=. Management Science , volume=. 2021 , publisher=
2021
-
[63]
Statistica Sinica , volume=
Estimation following sequential tests involving data-dependent treatment allocation , author=. Statistica Sinica , volume=
-
[64]
Sequential Analysis , volume=
Approximate bias calculations for sequentially designed experiments , author=. Sequential Analysis , volume=. 1998 , doi=
1998
-
[65]
Biometrika , volume=
Estimation following sequential tests , author=. Biometrika , volume=. 1978 , doi=
1978
-
[66]
Recent Developments in Nonparametric Inference and Probability , series=
Bias correction and confidence intervals following sequential tests , author=. Recent Developments in Nonparametric Inference and Probability , series=. 2006 , doi=
2006
-
[67]
Biometrika , volume=
Estimation after sequential testing: A simple approach for a truncated sequential probability ratio test , author=. Biometrika , volume=. 1992 , doi=
1992
-
[68]
The Annals of Statistics , volume=
Asymptotic expansions for the moments of a randomly stopped average , author=. The Annals of Statistics , volume=. 1993 , doi=
1993
Reviewed August 15, 2026 · model on record in the stance chip above.
Discussion (0). Continue with ORCID to comment.