pith. sign in

arxiv: 2605.03406 · v2 · pith:TDN3ASGWnew · submitted 2026-05-05 · 📊 stat.ME

A General Framework for Optimal Group Sequential Testing via Mixed-Integer Linear Programming

Dae Woong Ham , Stefanus Jasin , Xuejun Zhao This is my paper

Pith reviewed 2026-05-19 18:12 UTC · model grok-4.3

classification 📊 stat.ME
keywords group sequential testingmixed-integer linear programmingoptimal boundariesalpha spendingtype I errorsequential analysisclinical trial design
0
0 comments X

The pith

Mixed-integer linear programming finds optimal rejection boundaries for group sequential tests that allow earlier stopping than standard methods.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper presents a framework for optimizing the boundaries used in group sequential hypothesis testing. By combining sample average approximation with mixed-integer linear programming, the method minimizes the expected sample size subject to constraints on type-1 and type-2 error rates. This optimized approach is shown to dominate classical procedures including Lan-DeMets, Pocock, and O'Brien-Fleming. The resulting boundaries typically allocate more of the alpha spending in the initial groups. In an application to acute kidney injury data, the method reaches a significant result sooner than the original study.

Core claim

We use a sample average approximation combined with mixed integer linear programming to directly optimize the rejection criterion in the GST setting under type-1 and type-2 error constraints, and show that this S-MILP approach dominates classical GST procedures such as Lan-DeMets, Pocock, and O'Brien-Fleming methods while often spending alpha more aggressively early.

What carries the argument

The S-MILP approach: a sample average approximation of the error probabilities paired with mixed-integer linear programming to choose the optimal rejection thresholds at each of the K analysis times.

If this is right

  • The optimal boundaries spend the alpha budget more heavily in early interim analyses than do standard methods.
  • Expected number of observations needed to reach a decision is reduced while preserving error control.
  • The framework can be applied to any specified number of groups and target error rates.
  • In medical studies, it can lead to the same conclusion with fewer participants enrolled.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • The insight on early alpha spending may guide design of more responsive sequential monitoring in other areas such as online experiments.
  • Similar optimization techniques could incorporate additional practical constraints like recruitment costs or ethical stopping rules.
  • Validation on more diverse simulation settings would strengthen confidence in the method's robustness across distributions.

Load-bearing premise

The sample average approximation provides a sufficiently accurate representation of the true type-1 and type-2 error probabilities for the optimized boundaries to maintain the desired error control in practice.

What would settle it

Generate a large number of data sets under the null hypothesis, apply the S-MILP boundaries, and check if the fraction of rejections stays at or below the nominal type-1 error level; a large excess would disprove the approximation's adequacy.

Figures

Figures reproduced from arXiv: 2605.03406 by Dae Woong Ham, Stefanus Jasin, Xuejun Zhao.

Figure 1
Figure 1. Figure 1: Plot of alpha-spending budgets for all methods. The simulation setting is the same as that view at source ↗
Figure 1
Figure 1. Figure 1: Plot of alpha-spending budgets for all methods. The simulation setting is the same as [PITH_FULL_IMAGE:figures/full_fig_p024_1.png] view at source ↗
read the original abstract

Sequential hypothesis tests are widely adopted as a principled way to perform multiple tests on data that arrives over time. In particular, researchers frequently utilize group sequential hypothesis tests (GST) to test the same hypotheses at K times or "groups" while data arrives sequentially. In this setting, many methods have been proposed to allow researchers to uniformly control type-1 error across K checks (often known as various alpha-spending budgets). Although these methods are all successfully valid in controlling uniform type-1 error, it is not clear which of these methods are optimal when trying to reject the null as soon as possible. In this paper, we directly optimize the rejection criterion in the GST setting under the same constraints of controlling type-1 and type-2 errors. We use a sample average approximation combined with mixed integer linear programming (S-MILP) approach for this problem and show how our S-MILP approach dominates classical GST procedures such as Lan-DeMets, Pocock, and O'Brien-Fleming methods. We also find that the optimal solution typically aggressively spends the alpha-budget early, shedding insight to the long-standing debate of which alpha-spending budgets are more efficient. We finally apply our optimal S-MILP approach to a recent study on acute kidney injury interventions and find our optimal S-MILP approach can reach the same statistically significant conclusion faster than the original study and other GST methods.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

2 major / 2 minor

Summary. The paper proposes a sample-average approximation combined with mixed-integer linear programming (S-MILP) framework to directly optimize group-sequential testing boundaries under explicit type-I and type-II error constraints. It claims that the resulting boundaries dominate classical spending-function methods (Lan-DeMets, Pocock, O’Brien-Fleming) by permitting earlier rejection on average, provides insight that optimal solutions spend alpha aggressively early, and illustrates the approach on an acute-kidney-injury trial.

Significance. If the optimized boundaries can be shown to control the nominal error rates exactly (rather than only under the SAA) and the reported dominance holds under independent verification, the framework would supply a flexible, computationally tractable alternative to traditional GST design. The empirical observation on early alpha spending would also inform the long-standing debate on spending-function efficiency.

major comments (2)
  1. [Abstract] Abstract and § on SAA formulation: the claim that S-MILP “dominates” Lan-DeMets, Pocock and O’Brien-Fleming is presented without quantitative evidence (e.g., expected stopping-time differences or power curves) or confirmation that the final boundaries satisfy the nominal α under the exact (non-approximated) null distribution.
  2. [SAA and MILP formulation] SAA error-control section (likely §3–4): because both the objective and the type-I/type-II constraints are replaced by Monte-Carlo averages, any systematic under-estimation of tail probabilities can produce boundaries that violate the nominal error rates when evaluated exactly. No analytic error bound on the SAA nor an independent high-fidelity Monte-Carlo audit of the selected boundaries is reported.
minor comments (2)
  1. [Notation and formulation] Clarify the precise MILP encoding of the boundary variables and the chosen objective (expected sample size, expected stopping time, etc.).
  2. [Numerical results] Simulation figures should report variability (standard errors or quantiles) across SAA replications so that dominance claims can be assessed for statistical significance.

Simulated Author's Rebuttal

2 responses · 1 unresolved

We thank the referee for their constructive comments, which highlight important aspects of our S-MILP framework for group sequential testing. We respond to each major comment below and describe the changes we will make in revision.

read point-by-point responses

  1. Referee: [Abstract] Abstract and § on SAA formulation: the claim that S-MILP “dominates” Lan-DeMets, Pocock and O’Brien-Fleming is presented without quantitative evidence (e.g., expected stopping-time differences or power curves) or confirmation that the final boundaries satisfy the nominal α under the exact (non-approximated) null distribution.

    Authors: We agree that more explicit quantitative support for dominance would strengthen the presentation. In the revised manuscript we will add a table of expected stopping times under the alternative hypothesis for the S-MILP solution versus Lan-DeMets, Pocock, and O’Brien-Fleming boundaries, together with power curves at several effect sizes. We will also report an independent Monte-Carlo verification (10^6 replications) confirming that the final boundaries attain the nominal type-I error under the exact (non-SAA) null distribution. revision: yes

  2. Referee: [SAA and MILP formulation] SAA error-control section (likely §3–4): because both the objective and the type-I/type-II constraints are replaced by Monte-Carlo averages, any systematic under-estimation of tail probabilities can produce boundaries that violate the nominal error rates when evaluated exactly. No analytic error bound on the SAA nor an independent high-fidelity Monte-Carlo audit of the selected boundaries is reported.

    Authors: The referee correctly notes the risk inherent in replacing the exact error constraints by SAA averages. While a rigorous analytic error bound for the SAA-MILP formulation is not derived in the paper and would require substantial additional theoretical work, we will add a high-fidelity Monte-Carlo audit (using an order of magnitude more replications than the SAA sample size) of the optimized boundaries to empirically verify control of the nominal α and β under the exact distributions. revision: partial

standing simulated objections not resolved
  • Deriving a closed-form analytic error bound for the sample-average approximation within the mixed-integer linear program.

Circularity Check

0 steps flagged

No circularity: direct MILP optimization of boundaries under explicit error constraints

full rationale

The paper formulates the GST boundary optimization as a mixed-integer linear program whose objective and constraints are defined directly from the desired type-1 and type-2 error tolerances. The S-MILP procedure solves this program using Monte-Carlo averages; the resulting boundaries are outputs of the solver, not redefinitions or statistical fits of the same quantities. Classical-method comparisons are performed by evaluating the obtained boundaries on independent simulation draws or by direct numerical reporting, none of which reduce to the optimization inputs by construction. No self-citations are invoked as load-bearing uniqueness theorems, and no ansatz or renaming of known results is smuggled in. The derivation chain therefore remains self-contained against external benchmarks.

Axiom & Free-Parameter Ledger

1 free parameters · 1 axioms · 0 invented entities

The paper's approach depends on the accuracy of the sample average approximation for enforcing error constraints and the ability to solve the resulting MILP to optimality. Specific free parameters include the number of samples used in the approximation and the discretization of the decision space.

free parameters (1)
  • SAA sample size
    The sample average approximation requires selecting a number of samples to approximate the expectations in the constraints.
axioms (1)
  • domain assumption The group sequential testing problem can be formulated as a mixed-integer linear program with accurate error control via approximation.
    This is the core modeling assumption enabling the optimization.

pith-pipeline@v0.9.0 · 5785 in / 1152 out tokens · 52997 ms · 2026-05-19T18:12:45.296775+00:00 · methodology

Review history (3 revisions) →

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Lean theorems connected to this paper

Citations machine-checked in the Pith Canon. Every link opens the source theorem in the public Lean library.

What do these tags mean?
matches
The paper's claim is directly supported by a theorem in the formal canon.
supports
The theorem supports part of the paper's argument, but the paper may add assumptions or extra steps.
extends
The paper goes beyond the formal theorem; the theorem is a base layer rather than the whole result.
uses
The paper appears to rely on the theorem as machinery.
contradicts
The paper's claim conflicts with a theorem or certificate in the canon.
unclear
Pith found a possible connection, but the passage is too broad, indirect, or ambiguous to say the theorem truly supports the claim.

Reference graph

Works this paper leans on

179 extracted references · 179 canonical work pages · 1 internal anchor

  1. [1]

    Eales, J. D. and Jennison, C. , title =. Biometrika , volume =. 1992 , doi =

    work page 1992

  2. [2]

    Hampson, L. V. and Jennison, C. , title =. Journal of the Royal Statistical Society, Series B , volume =. 2013 , doi =

    work page 2013

  3. [3]

    2021 , publisher=

    Lectures on stochastic programming: modeling and theory , author=. 2021 , publisher=

    work page 2021

  4. [4]

    , author=

    Introduction to sample size determination and power analysis for clinical trials. , author=. Controlled clinical trials , year=

    work page

  5. [5]

    , biburl =

    Cohen, J. , biburl =

    work page

  6. [6]

    arXiv preprint arXiv:1909.06406 , year=

    Order statistics on the spacings between order statistics for the uniform distribution , author=. arXiv preprint arXiv:1909.06406 , year=

    work page arXiv 1909

  7. [7]

    Operations Research Letters , volume=

    Sample average approximation of expected value constrained stochastic programs , author=. Operations Research Letters , volume=. 2008 , publisher=

    work page 2008

  8. [8]

    Optimization Online , pages=

    Lectures on parametric optimization: An introduction , author=. Optimization Online , pages=

    work page

  9. [9]

    The Zero Set of a Real Analytic Function

    The zero set of a real analytic function , author=. arXiv preprint arXiv:1512.07276 , year=

    work page internal anchor Pith review Pith/arXiv arXiv

  10. [10]

    Journal of optimization theory and applications , volume=

    Sample average approximation method for chance constrained programming: theory and applications , author=. Journal of optimization theory and applications , volume=. 2009 , publisher=

    work page 2009

  11. [11]

    Electronic Journal of Probability , number =

    Xiequan Fan and Ion Grama and Quansheng Liu , title =. Electronic Journal of Probability , number =. 2015 , doi =

    work page 2015

  12. [12]

    2022 , month=

    Aurelien Bibaut and Nathan Kallus and Michael Lindon , title=. 2022 , month=. doi:None , url=

    work page 2022

  13. [13]

    URL https://doi.org/10.1080/ 01621459.2017.1307116

    Audrey Boruvka, Daniel Almirall, Katie Witkiewitz and Susan A. Murphy , title =. Journal of the American Statistical Association , volume =. 2018 , publisher =. doi:10.1080/01621459.2017.1305274 , note =

    work page doi:10.1080/01621459.2017.1305274 2018

  14. [14]

    2024 , eprint=

    Clustered Switchback Experiments: Near-Optimal Rates Under Spatiotemporal Interference , author=. 2024 , eprint=

    work page 2024

  15. [15]

    Proceedings of The KDD'23 Workshop on Causal Discovery, Prediction and Decision , pages =

    Bias-Variance Tradeoffs for Designing Simultaneous Temporal Experiments , author =. Proceedings of The KDD'23 Workshop on Causal Discovery, Prediction and Decision , pages =. 2023 , editor =

    work page 2023

  16. [16]

    2024 , eprint=

    Switchback Experiments under Geometric Mixing , author=. 2024 , eprint=

    work page 2024

  17. [17]

    arXiv: Methodology , year=

    Adaptive Experimental Design with Temporal Interference: A Maximum Likelihood Approach , author=. arXiv: Methodology , year=

    work page

  18. [18]

    Design of Panel Experiments with Spatial and Temporal Interference , journal =

    Ni, Tu and Bojinov, Iavor and Zhao, Jinglong , year =. Design of Panel Experiments with Spatial and Temporal Interference , journal =

    work page

  19. [19]

    Management Science , volume =

    Zhan, Ruohan and Ren, Zhimei and Athey, Susan and Zhou, Zhengyuan , title =. Management Science , volume =. 0 , doi =

    work page

  20. [20]

    Panning for Gold: Model-

    Cand\`es, Emmanuel and Fan, Yingying and Janson, Lucas and Lv, Jinchi , journal=. Panning for Gold: Model-

    work page

  21. [21]

    arXiv preprint arXiv:2111.02334 , year=

    Quantifying the Value of Iterative Experimentation , author=. arXiv preprint arXiv:2111.02334 , year=

    work page arXiv

  22. [22]

    2020 , publisher=

    Experimentation works: The surprising power of business experiments , author=. 2020 , publisher=

    work page 2020

  23. [23]

    Biometrika , volume =

    Thompson, William R , title = ". Biometrika , volume =. 1933 , month =. doi:10.1093/biomet/25.3-4.285 , url =

    work page doi:10.1093/biomet/25.3-4.285 1933

  24. [24]

    Bojinov, Iavor and Gupta, Somit , journal =. Online. 2022 , month =

    work page 2022

  25. [25]

    arXiv: Methodology , year=

    The phase transition for the existence of the maximum likelihood estimate in high-dimensional logistic regression , author=. arXiv: Methodology , year=

    work page

  26. [26]

    2020 , publisher=

    Trustworthy online controlled experiments: A practical guide to a/b testing , author=. 2020 , publisher=

    work page 2020

  27. [27]

    Reinforcement learning: an introduction

    Sutton, Richard and Barto, Andrew , year=. Reinforcement learning: an introduction. Adaptive Computation and Machine Learning , publisher=

    work page

  28. [28]

    Econometrica , volume=

    Sampling-Based versus Design-Based Uncertainty in Regression Analysis , author=. Econometrica , volume=. 2020 , publisher=

    work page 2020

  29. [29]

    2013 , isbn =

    Kohavi, Ron and Deng, Alex and Frasca, Brian and Walker, Toby and Xu, Ya and Pohlmann, Nils , title =. 2013 , isbn =. doi:10.1145/2487575.2488217 , booktitle =

    work page doi:10.1145/2487575.2488217 2013

  30. [30]

    arXiv e-prints , keywords =

    Estimating means of bounded random variables by betting. arXiv e-prints , keywords =

    work page

  31. [31]

    Bernoulli , year=

    Sequential estimation of quantiles with applications to A/B testing and best-arm identification , author=. Bernoulli , year=

    work page

  32. [32]

    2017 , isbn =

    Johari, Ramesh and Koomen, Pete and Pekelis, Leonid and Walsh, David , title =. 2017 , isbn =. doi:10.1145/3097983.3097992 , booktitle =

    work page doi:10.1145/3097983.3097992 2017

  33. [33]

    Rapid Regression Detection in Software Deployments through Sequential Testing , year =

    Lindon, Michael and Sanden, Chris and Shirikian, Vach\'. Rapid Regression Detection in Software Deployments through Sequential Testing , year =. doi:10.1145/3534678.3539099 , pages =

    work page doi:10.1145/3534678.3539099

  34. [34]

    Tibshirani , title =

    Jonathan Taylor and Robert J. Tibshirani , title =. Proceedings of the National Academy of Sciences , volume =. 2015 , doi =

    work page 2015

  35. [35]

    Nephrology Dialysis Transplantation , volume =

    Noordzij, Marlies and Tripepi, Giovanni and Dekker, Friedo W and Zoccali, Carmine and Tanck, Michael W and Jager, Kitty J , title = ". Nephrology Dialysis Transplantation , volume =. 2010 , month =. doi:10.1093/ndt/gfp732 , url =

    work page doi:10.1093/ndt/gfp732 2010

  36. [36]

    Panel experiments and dynamic causal effects: A finite population perspective , volume =

    Bojinov, Iavor and Rambachan, Ashesh and Shephard, Neil , year =. Panel experiments and dynamic causal effects: A finite population perspective , volume =. Quantitative Economics , doi =

    work page

  37. [37]

    Journal of the American Statistical Association , year=

    A Generalization of Sampling Without Replacement from a Finite Universe , author=. Journal of the American Statistical Association , year=

    work page

  38. [38]

    Limitations of Design-based Causal Inference and A/B Testing under Arbitrary and Network Interference , volume =

    Basse, Guillaume and Airoldi, Edoardo , year =. Limitations of Design-based Causal Inference and A/B Testing under Arbitrary and Network Interference , volume =. Sociological Methodology , doi =

    work page

  39. [40]

    doi:10.48550/arXiv.2201.08343 , year=

    Using Machine Learning to Test Causal Hypotheses in Conjoint Analysis , author=. doi:10.48550/arXiv.2201.08343 , year=

    work page doi:10.48550/arxiv.2201.08343

  40. [41]

    D. A. Darling and Herbert Robbins , title =. Proceedings of the National Academy of Sciences , volume =. 1967 , doi =

    work page 1967

  41. [42]

    D. R. Cox , publisher =. Planning of Experiments , year =

    work page

  42. [43]

    , journal =

    Paul W. Holland , title =. Journal of the American Statistical Association , volume =. 1986 , publisher =. doi:10.1080/01621459.1986.10478354 , URL =

    work page doi:10.1080/01621459.1986.10478354 1986

  43. [44]

    , author=

    Estimating causal effects of treatments in randomized and nonrandomized studies. , author=. Journal of Educational Psychology , year=

    work page

  44. [45]

    Catoni-style confidence sequences for heavy-tailed mean estimation , author=

    work page

  45. [46]

    L., Athanasopoulos, G., and Hyndman, R

    Iavor Bojinov and Neil Shephard , title =. Journal of the American Statistical Association , volume =. 2019 , publisher =. doi:10.1080/01621459.2018.1527225 , URL =

    work page doi:10.1080/01621459.2018.1527225 2019

  46. [47]

    Anytime-valid off-policy inference for contextual bandits , publisher =

    Waudby-Smith, Ian and Wu, Lili and Ramdas, Aaditya and Karampatziakis, Nikos and Mineiro, Paul , keywords =. Anytime-valid off-policy inference for contextual bandits , publisher =. 2022 , copyright =. doi:10.48550/ARXIV.2210.10768 , url =

    work page doi:10.48550/arxiv.2210.10768 2022

  47. [48]

    Management Science , volume =

    Bojinov, Iavor and Simchi-Levi, David and Zhao, Jinglong , title =. Management Science , volume =. 2020 , doi =

    work page 2020

  48. [49]

    A lasso for hierarchical interactions

    Bien, Jacob and Taylor, Jonathan and Tibshirani, Robert. A lasso for hierarchical interactions. Ann. Statist. 2013. doi:10.1214/13-AOS1096

    work page doi:10.1214/13-aos1096 2013

  49. [50]

    Jens Hainmueller and Daniel J. Hopkins. The Hidden American Immigration Consensus: A Conjoint Analysis of Attitudes toward Immigrants. American Journal of Political Science. 2015. doi:10.1111/ajps.12138

    work page doi:10.1111/ajps.12138 2015

  50. [51]

    Political Behavior , year=

    The Contingent Effects of Candidate Sex on Voter Choice , author=. Political Behavior , year=

    work page

  51. [52]

    Is It Immigration or the Immigrants? The Emotional Influence of Groups on Public Opinion and Political Action

    Brader and Ted and Nicholas Valentino and Elizabeth Suhay. Is It Immigration or the Immigrants? The Emotional Influence of Groups on Public Opinion and Political Action. American Journal of Political Science. 2008

    work page 2008

  52. [53]

    Who Is against Immigration? A Cross-Country Investigation of Individual Attitudes toward Immigrants , volume =

    Anna Maria Mayda , journal =. Who Is against Immigration? A Cross-Country Investigation of Individual Attitudes toward Immigrants , volume =

    work page

  53. [54]

    Schildkraut, Deborah J. , year=. Americanism in the Twenty-First Century: Public Opinion in the Age of Immigration , DOI=

    work page

  54. [55]

    Gender as a Factor in the Attribution of Leadership Traits , volume =

    Deborah Alexander and Kristi Andersen , journal =. Gender as a Factor in the Attribution of Leadership Traits , volume =

    work page

  55. [56]

    Koch , journal =

    Jeffrey W. Koch , journal =. Gender Stereotypes and Citizens' Impressions of House Candidates' Ideological Orientations , volume =

    work page

  56. [57]

    Political Research Quarterly , volume =

    Leonie Huddy and Nayda Terkildsen , title =. Political Research Quarterly , volume =. 1993 , doi =

    work page 1993

  57. [58]

    and Malhotra, Neil , title =

    Newman, Benjamin J. and Malhotra, Neil , title =. The Journal of Politics , volume =. 2019 , doi =

    work page 2019

  58. [59]

    2022 , journal=

    Improving the External Validity of Conjoint Analysis: The Essential Role of Profile Distribution , author =. 2022 , journal=

    work page 2022

  59. [60]

    arXiv preprint arXiv:2006.03980 , year=

    Fast and Powerful Conditional Randomization Testing via Distillation , author=. arXiv preprint arXiv:2006.03980 , year=

    work page arXiv 2006

  60. [61]

    What Do We Learn About Voter Preferences From Conjoint Experiments? , year =

    Scott Abramson and Korhan Kocak and Asya Magazinnik , institution =. What Do We Learn About Voter Preferences From Conjoint Experiments? , year =

    work page

  61. [62]

    Improving Preference Elicitation in Conjoint Designs using Machine Learning for Heterogeneous Effects , year =

    Scott Abramson and Korhan Kocak and Asya Magazinnik and Anton Strezhnev , institution =. Improving Preference Elicitation in Conjoint Designs using Machine Learning for Heterogeneous Effects , year =

    work page

  62. [63]

    Using Conjoint Experiments to Analyze Elections: The Essential Role of the Average Marginal Component Effect (AMCE) , journal =

    Bansak, Kirk and Hainmueller, Jens and Hopkins, Daniel and Yamamoto, Teppei , year =. Using Conjoint Experiments to Analyze Elections: The Essential Role of the Average Marginal Component Effect (AMCE) , journal =

    work page

  63. [64]

    , year =

    Bodog, Simona and Florian, G.L. , year =. Conjoint Analysis in Marketing Research , volume =

    work page

  64. [65]

    Green and V

    Paul E. Green and V. Srinivasan , journal =. Conjoint Analysis in Marketing: New Developments with Implications for Research and Practice , volume =

    work page

  65. [66]

    Agricultural and resource economics review , pages =

    Campbell, Benjamin L and Mhlanga, Saneliso and Lesschaeve, Isabelle , keywords =. Agricultural and resource economics review , pages =. 2013 , title =

    work page 2013

  66. [67]

    and Yamamoto, Teppei , year=

    Hainmueller, Jens and Hopkins, Daniel J. and Yamamoto, Teppei , year=. Causal Inference in Conjoint Analysis: Understanding Multidimensional Choices via Stated Preference Experiments , volume=. Political Analysis , publisher=. doi:10.1093/pan/mpt024 , number=

    work page doi:10.1093/pan/mpt024

  67. [68]

    Brett Hauber and Juan Marcos González and Catharina G.M

    A. Brett Hauber and Juan Marcos González and Catharina G.M. Groothuis-Oudshoorn and Thomas Prior and Deborah A. Marshall and Charles Cunningham and Maarten J. IJzerman and John F.P. Bridges. Statistical Methods for the Analysis of Discrete Choice Experiments: A Report of the ISPOR Conjoint Analysis Good Research Practices Task Force. Value in Health. 2016...

    work page doi:10.1016/j.jval.2016.04.004 2016

  68. [69]

    A weighted logistic regression for conjoint analysis and Kansei engineering , volume =

    Barone, Stefano and Lombardo, Alberto and Tarantino, Pietro , year =. A weighted logistic regression for conjoint analysis and Kansei engineering , volume =. Quality and Reliability Engineering International , doi =

    work page

  69. [70]

    Voting Cues in Low-Information Elections: Candidate Gender as a Social Information Variable in Contemporary United States Elections , author=

    work page

  70. [71]

    Causal inference in genetic trio studies , volume =

    Bates, Stephen and Sesia, Matteo and Sabatti, Chiara and Cand. Causal inference in genetic trio studies , volume =. 2020 , doi =. https://www.pnas.org/content/117/39/24117.full.pdf , journal =

    work page 2020

  71. [72]

    , Title =

    Arrow, Kenneth J. , Title =. Journal of Economic Perspectives , Volume =. 1998 , Month =

    work page 1998

  72. [73]

    The Democratic Dilemma: Can Citizens Learn What They Need to Know? , volume =

    Lupia, Arthur and Mccubbins, Mathew , year =. The Democratic Dilemma: Can Citizens Learn What They Need to Know? , volume =. The American Political Science Review , doi =

    work page

  73. [74]

    R.Duncan Luce and John W. Tukey. Simultaneous conjoint measurement: A new type of fundamental measurement. Journal of Mathematical Psychology. 1964. doi:https://doi.org/10.1016/0022-2496(64)90015-X

    work page doi:10.1016/0022-2496(64)90015-x 1964

  74. [75]

    Thirty Years of Conjoint Analysis: Reflections and Prospects , volume =

    Green, Paul and Krieger, Abba and Wind, Yoram , year =. Thirty Years of Conjoint Analysis: Reflections and Prospects , volume =. Interfaces , doi =

    work page

  75. [76]

    and Wiley, J.B

    Raghavarao, D. and Wiley, J.B. and Chitturi, P. , year =. Choice-based conjoint analysis: Models and Designs , publisher =

    work page

  76. [77]

    Using Conjoint Analysis To Elicit Employers’ Preferences Toward Key Competencies For A Business Manager Position , volume =

    Popovic, Milena and Kuzmanovic, Marija and Martic, Milan , year =. Using Conjoint Analysis To Elicit Employers’ Preferences Toward Key Competencies For A Business Manager Position , volume =. Management - Journal for theory and practice of management , doi =

    work page

  77. [78]

    Journal of the American Statistical Association , volume =

    Donald B Rubin , title =. Journal of the American Statistical Association , volume =. 2005 , publisher =

    work page 2005

  78. [79]

    and Yamamoto, Teppei , year=

    Bansak, Kirk and Hainmueller, Jens and Hopkins, Daniel J. and Yamamoto, Teppei , year=. The Number of Choice Tasks and Survey Satisficing in Conjoint Experiments , volume=. Political Analysis , publisher=. doi:10.1017/pan.2017.40 , number=

    work page doi:10.1017/pan.2017.40 2017

  79. [80]

    and Yamamoto, Teppei , year=

    Bansak, Kirk and Hainmueller, Jens and Hopkins, Daniel J. and Yamamoto, Teppei , year=. Beyond the breaking point? Survey satisficing in conjoint experiments , DOI=. Political Science Research and Methods , publisher=

    work page

  80. [81]

    Regression Shrinkage and Selection via the Lasso , volume =

    Robert Tibshirani , journal =. Regression Shrinkage and Selection via the Lasso , volume =

    work page

Showing first 80 references.