pith. sign in

arxiv: 2606.22035 · v1 · pith:YMOFYQUQnew · submitted 2026-06-20 · 💰 econ.EM · stat.ME

Inference methods for unit-specific coefficients in panel data models with latent group structure

Mikihito Nishi , Ryo Okui This is my paper

Pith reviewed 2026-06-26 10:57 UTC · model grok-4.3

classification 💰 econ.EM stat.ME
keywords panel datalatent group structureinferencegroup membership uncertaintyunit-specific coefficientsminimum wage
0
0 comments X

The pith

Panel data inference for unit-specific coefficients gains efficiency by clustering into latent groups while integrating over uncertainty in those assignments.

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

This paper develops statistical procedures for estimating and inferring unit-specific coefficients in panel data models that have an unobserved group structure. The methods cluster units into a few groups to borrow strength but integrate inference with confidence sets for the group assignments, so that uncertainty about which group a unit belongs to is not ignored. Two variants are given: one minimizes the test statistic over the confidence set for membership, the other applies a bias correction. Both produce valid confidence intervals that are narrower than those from separate time-series estimation for each unit, especially when error variances are large. The paper also supplies standard errors that remain valid even when the number of time periods is small.

Core claim

The core discovery is a pair of inference procedures that combine standard t- and Wald-tests with confidence sets for latent group membership. The first takes the infimum of the test statistic over the set; the second bias-corrects for possible misclassification. Adjusted standard errors are derived that account for group uncertainty and remain valid with short panels.

What carries the argument

Integrating t-tests and Wald tests over confidence sets for group membership, either by minimization or by bias correction, while constructing group-uncertainty-adjusted standard errors.

If this is right

  • Monte Carlo evidence shows narrower confidence sets than unit-by-unit methods when error variances differ across units.
  • Ignoring group assignment uncertainty produces incorrect size and coverage.
  • The minimization method can yield shorter but possibly disconnected intervals; the bias-correction method yields connected intervals.
  • The adjusted standard errors are valid even with short time periods and may be used independently of the group inference procedures.

Where Pith is reading between the lines

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

  • The integration technique could be adapted to other panel models that involve estimated classifications or cluster assignments, such as regional or industry groupings.
  • Because the methods explicitly handle misassignment, they may reduce the risk of overconfident policy conclusions when units are assigned to groups for efficiency.
  • The approach suggests testable checks for whether group uncertainty is material in any given application by comparing coverage with and without the adjustment.

Load-bearing premise

Valid confidence sets for group membership can be constructed such that integrating the test statistics or applying the bias correction over those sets yields correct coverage and size even in short panels.

What would settle it

A simulation experiment in which the true group structure is known, group assignment is estimated with error, and coverage rates of the proposed intervals are compared to nominal levels when time periods are few.

Figures

Figures reproduced from arXiv: 2606.22035 by Mikihito Nishi, Ryo Okui.

Figure 1
Figure 1. Figure 1: 90% naive confidence intervals 22 [PITH_FULL_IMAGE:figures/full_fig_p022_1.png] view at source ↗
Figure 2
Figure 2. Figure 2: 90% minimum-t-based confidence intervals [PITH_FULL_IMAGE:figures/full_fig_p023_2.png] view at source ↗
Figure 3
Figure 3. Figure 3: 90% bias-corrected confidence intervals 23 [PITH_FULL_IMAGE:figures/full_fig_p023_3.png] view at source ↗
Figure 4
Figure 4. Figure 4: Unit-wise coverage rates of confidence intervals, [PITH_FULL_IMAGE:figures/full_fig_p026_4.png] view at source ↗
Figure 5
Figure 5. Figure 5: Unit-wise mean lengths of confidence intervals, [PITH_FULL_IMAGE:figures/full_fig_p027_5.png] view at source ↗
Figure 6
Figure 6. Figure 6: Unit-wise coverage rates of confidence sets, [PITH_FULL_IMAGE:figures/full_fig_p029_6.png] view at source ↗
Figure 7
Figure 7. Figure 7: Unit-wise coverage rates of confidence intervals, [PITH_FULL_IMAGE:figures/full_fig_p045_7.png] view at source ↗
Figure 8
Figure 8. Figure 8: Unit-wise coverage rates of confidence sets, [PITH_FULL_IMAGE:figures/full_fig_p046_8.png] view at source ↗
Figure 9
Figure 9. Figure 9: Unit-wise mean lengths of confidence intervals, [PITH_FULL_IMAGE:figures/full_fig_p047_9.png] view at source ↗
read the original abstract

This paper introduces statistical inference procedures for unit-specific coefficients in panel data models, where the coefficients exhibit a latent group structure. The proposed methods achieve efficiency gains by clustering units into a small number of groups, while explicitly accounting for the statistical uncertainty of group assignments. The core idea is to integrate standard inference procedures, such as the $t$-test and Wald tests, with confidence sets for group membership. Two methods are proposed: the first takes the minimum of the test statistics over the confidence set for group membership, and the second corrects for bias caused by possible group misassignment. The former can produce shorter but possibly disconnected sets, while the latter guarantees connected, interpretable intervals at some cost in length. We also develop standard errors that are adjusted for possible group misassignment and valid even with short time periods, which may be of independent interest. Monte Carlo simulations demonstrate that our approach yields narrower confidence sets for units with relatively large error variances than unit-by-unit time-series methods. In contrast, ignoring statistical uncertainty in the group membership estimation leads to distortions in size and coverage. We illustrate the method with an empirical example that estimates the effect of the minimum wage in each U.S. state.

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 introduces inference procedures for unit-specific coefficients in panel data models with latent group structure. It proposes integrating standard t- and Wald tests with confidence sets for group membership, via either taking the minimum test statistic over the set or applying a bias correction for possible misassignment. It also develops standard errors adjusted for group misassignment that are claimed to be valid even for short time periods. Monte Carlo simulations are reported to show narrower confidence sets than unit-by-unit time-series methods when error variances are large, while ignoring group uncertainty distorts size and coverage. An empirical illustration estimates minimum-wage effects across U.S. states.

Significance. If the procedures maintain correct coverage while delivering efficiency gains, they would be useful for applied work on heterogeneous panel models that exploit latent grouping. The short-T adjusted standard errors could have independent value. Monte Carlo evidence is presented as support, which is a positive feature when the theoretical arguments for the integrated statistics are sound.

major comments (2)
  1. [integrated inference procedures (as described in abstract and methods)] The central claim requires that valid (1-α) confidence sets for each unit's group label can be formed and that the min-test or bias-correction integration over those sets preserves correct asymptotic size and coverage. The abstract asserts this but the derivation must be supplied (particularly the handling of dependence between the label estimator and the coefficient estimator) to confirm the claim does not rely on large-T approximations that fail for small T.
  2. [adjusted standard errors section] The adjusted standard errors are stated to remain valid with short time periods; this is load-bearing for the short-T applicability of the whole approach. The paper must show explicitly that the adjustment does not break down when the group estimator itself is only approximately consistent.
minor comments (2)
  1. Clarify in the abstract or introduction whether the group-membership confidence sets are constructed from the same data used for the coefficient inference or from an independent source.
  2. [Monte Carlo simulations] The Monte Carlo section should report the exact data-generating processes, the values of T and N used, and the coverage frequencies for both proposed methods versus the naive approach.

Simulated Author's Rebuttal

2 responses · 0 unresolved

We thank the referee for the careful and constructive comments. We address the two major comments point by point below and will revise the manuscript accordingly to strengthen the theoretical support for our procedures.

read point-by-point responses

  1. Referee: [integrated inference procedures (as described in abstract and methods)] The central claim requires that valid (1-α) confidence sets for each unit's group label can be formed and that the min-test or bias-correction integration over those sets preserves correct asymptotic size and coverage. The abstract asserts this but the derivation must be supplied (particularly the handling of dependence between the label estimator and the coefficient estimator) to confirm the claim does not rely on large-T approximations that fail for small T.

    Authors: We agree that an explicit derivation is required. In the revision we will add a dedicated appendix section that derives the asymptotic size and coverage of both the min-test and bias-correction procedures. The argument will explicitly account for the dependence between the group-label estimator and the unit-specific coefficient estimator and will be stated under conditions that hold for fixed T (with N → ∞), without invoking large-T approximations. revision: yes

  2. Referee: [adjusted standard errors section] The adjusted standard errors are stated to remain valid with short time periods; this is load-bearing for the short-T applicability of the whole approach. The paper must show explicitly that the adjustment does not break down when the group estimator itself is only approximately consistent.

    Authors: We acknowledge the need for a more explicit demonstration. The revision will include an expanded appendix subsection that proves the adjusted standard errors remain valid when the group estimator is only approximately consistent (i.e., when the misassignment probability vanishes at a suitable rate). The argument will be tailored to short-T panels and will be accompanied by additional Monte Carlo evidence under approximate consistency. revision: yes

Circularity Check

0 steps flagged

No significant circularity; methods are constructed from standard inference adjusted for estimated groups

full rationale

The paper develops two new inference procedures (min-test over group-membership confidence sets and bias-correction for misassignment) plus adjusted standard errors valid for short T. These are derived from the latent-group panel model and standard asymptotic arguments rather than by re-using fitted quantities as predictions. No equation reduces a claimed result to an input by definition, no self-citation supplies a uniqueness theorem that forces the method, and the Monte Carlo evidence is external to the derivation. The central claims therefore remain independent of the paper's own fitted objects.

Axiom & Free-Parameter Ledger

0 free parameters · 0 axioms · 0 invented entities

Abstract-only review provides no concrete information on free parameters, axioms, or invented entities beyond standard panel data assumptions.

pith-pipeline@v0.9.1-grok · 5740 in / 1026 out tokens · 23042 ms · 2026-06-26T10:57:30.279379+00:00 · methodology

discussion (0)

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

Reference graph

Works this paper leans on

211 extracted references · 15 canonical work pages

  1. [1]

    2025 , note =

    Tetsuya Kaji and Hyungjune Kang , title =. 2025 , note =

    2025

  2. [2]

    , title =

    Hansen, Bruce E. , title =. Econometrica , year =

  3. [3]

    , title =

    Hansen, Bruce E. , title =. Journal of Business & Economic Statistics , year =

  4. [4]

    2024 , note =

    Inference after Discretizing Time-Varying Unobserved Heterogeneity , author =. 2024 , note =

    2024

  5. [5]

    and Boos, Dennis D

    Berger, Roger L. and Boos, Dennis D. , title =. Journal of the American Statistical Association , year =

  6. [6]

    Econometrica , year =

    Dufour, Jean-Marie , title =. Econometrica , year =

  7. [7]

    and Weidner, Martin and Zeleneev, Andrei , title =

    Armstrong, Timothy B. and Weidner, Martin and Zeleneev, Andrei , title =. 2025 , note =

    2025

  8. [8]

    , title =

    Silvapulle, Mervyn J. , title =. Journal of the American Statistical Association , year =

  9. [9]

    , title =

    DiTraglia, Francis J. , title =. Journal of Econometrics , year =

  10. [10]

    Quantitative Economics , volume =

    Inference in a stationary/nonstationary autoregressive time-varying-parameter model , author =. Quantitative Economics , volume =. 2025 , publisher =

    2025

  11. [11]

    Asymptotic properties of

    Shimizu, Kenichi , journal =. Asymptotic properties of. 2023 , publisher =

    2023

  12. [12]

    Econometrica , volume =

    Risk and rationality: Uncovering heterogeneity in probability distortion , author =. Econometrica , volume =. 2010 , publisher =

    2010

  13. [13]

    Journal of Econometrics , volume =

    Mixture models of choice under risk , author =. Journal of Econometrics , volume =. 2011 , publisher =

    2011

  14. [14]

    2024 , eprint=

    Latent group structure in linear panel data models with endogenous regressors , author=. 2024 , eprint=

    2024

  15. [15]

    2025 , eprint=

    Robust Inference Methods for Latent Group Panel Models under Possible Group Non-Separation , author=. 2025 , eprint=

    2025

  16. [16]

    2025 , eprint=

    Conditional Selective Inference for the Selected Groups in Panel Data , author=. 2025 , eprint=

    2025

  17. [17]

    2025 , note=

    Latent grouped structures in panel data: A review , author=. 2025 , note=

    2025

  18. [18]

    Journal of Econometrics , volume=

    Spectral clustering with variance information for group structure estimation in panel data , author=. Journal of Econometrics , volume=. 2024 , publisher=

    2024

  19. [19]

    Journal of Econometrics , volume=

    A simple and computationally trivial estimator for grouped fixed effects models , author=. Journal of Econometrics , volume=. 2025 , publisher=

    2025

  20. [20]

    A partially heterogeneous framework for analyzing panel data , volume =

    Sarafidis, Vasilis and Weber, Neville , journal =. A partially heterogeneous framework for analyzing panel data , volume =

  21. [21]

    Panel data models with grouped factor structure under unknown group membership , volume =

    Ando, Tomohiro and Bai, Jushan , journal =. Panel data models with grouped factor structure under unknown group membership , volume =

  22. [22]

    Econometrica , year=

    Optimal shrinkage estimation of fixed effects in linear panel data models , author=. Econometrica , year=

  23. [23]

    Panel forecasts of country-level

    Liu, Laura and Moon, Hyungsik Roger and Schorfheide, Frank , journal=. Panel forecasts of country-level. 2021 , publisher=

    2021

  24. [24]

    Forecasting with a panel

    Liu, Laura and Moon, Hyungsik Roger and Schorfheide, Frank , journal=. Forecasting with a panel. 2023 , publisher=

    2023

  25. [25]

    Econometrica , volume=

    Forecasting with dynamic panel data models , author=. Econometrica , volume=. 2020 , publisher=

    2020

  26. [26]

    Merlev. A. Probability Theory and Related Fields , pages =

  27. [27]

    A central limit theorem for k -means clustering , volume =

    Pollard, David , date-added =. A central limit theorem for k -means clustering , volume =. The Annals of Probability , number =

  28. [28]

    A consistent procedure for determining the number of clusters in regression clustering , volume =

    Shao, Qing and Wu, Yuehua , date-added =. A consistent procedure for determining the number of clusters in regression clustering , volume =. Journal of Statistical Planning and Inference , number =

  29. [29]

    A multivariate analogue of the one-sided test , volume =

    Kudo, Akio , date-added =. A multivariate analogue of the one-sided test , volume =. Biometrika , number =

  30. [30]

    A Practical Two-Step Method for Testing Moment Inequalities , volume =

    Romano, Joseph P and Shaikh, Azeem M and Wolf, Michael , date-added =. A Practical Two-Step Method for Testing Moment Inequalities , volume =. Econometrica , number =

  31. [31]

    Newey and Kenneth D

    Whitney K. Newey and Kenneth D. West , date-added =. A Simple Positive Semi-Definite, Heteroskedasticity and Autocorrelation Consistent Covariance Matrix , volume =. Econometrica , number =

  32. [32]

    Adaptive estimation of a quadratic functional by model selection , year =

    Laurent, Beatrice and Massart, Pascal , date-added =. Adaptive estimation of a quadratic functional by model selection , year =. Annals of Statistics , pages =

  33. [33]

    An asymptotic expansion for the tail area of the t-distribution , volume =

    Soms, Andrew P , date-added =. An asymptotic expansion for the tail area of the t-distribution , volume =. Journal of the American Statistical Association , number =

  34. [34]

    An exact test for multiple inequality and equality constraints in the linear regression model , volume =

    Wolak, Frank A , date-added =. An exact test for multiple inequality and equality constraints in the linear regression model , volume =. Journal of the American Statistical Association , number =

  35. [35]

    An introduction to probability theory and its applications: volume I , year =

    Feller, William , date-added =. An introduction to probability theory and its applications: volume I , year =

  36. [36]

    Approximations for the quantiles of Student's t and F distributions and their error bounds , volume =

    Fujikoshi, Yasunori and Mukaihata, Satoru , date-added =. Approximations for the quantiles of Student's t and F distributions and their error bounds , volume =. Hiroshima mathematical journal , number =

  37. [37]

    Asymptotic theory of weakly dependent random processes , year =

    Rio, Emmanuel , date-added =. Asymptotic theory of weakly dependent random processes , year =

  38. [38]

    Asymptotically unbiased inference for a dynamic panel model with fixed effects when both n and T are large , volume =

    Hahn, Jinyong and Kuersteiner, Guido , date-added =. Asymptotically unbiased inference for a dynamic panel model with fixed effects when both n and T are large , volume =. Econometrica , number =

  39. [39]

    Silveira , date-added =

    Bernardo S. Silveira , date-added =. Bargaining with asymmetric information: An empirical study of plea negotiations , volume =. Econometrica , number =

  40. [40]

    Bootstrap inference in partially identified models defined by moment inequalities: Coverage of the identified set , volume =

    Bugni, Federico A , date-added =. Bootstrap inference in partially identified models defined by moment inequalities: Coverage of the identified set , volume =. Econometrica , number =

  41. [41]

    Central limit theorems for high dimensional dependent data , volume =

    Chang, Jinyuan and Chen, Xiaohui and Wu, Mingcong , date-added =. Central limit theorems for high dimensional dependent data , volume =. Bernoulli , number =

  42. [42]

    Classification of nonparametric regression functions in heterogeneous panels , volume =

    Vogt, Michael and Linton, Oliver , date-added =. Classification of nonparametric regression functions in heterogeneous panels , volume =. Journal of the Royal Statistical Society: Series B , pages =

  43. [43]

    Comparison and anti-concentration bounds for maxima of Gaussian random vectors , volume =

    Chernozhukov, Victor and Chetverikov, Denis and Kato, Kengo , date-added =. Comparison and anti-concentration bounds for maxima of Gaussian random vectors , volume =. Probability Theory and Related Fields , number =

  44. [44]

    arXiv , author =:1801.00332v3 , title =

    arXiv

  45. [45]

    Consistent estimation with many moment inequalities , volume =

    Menzel, Konrad , date-added =. Consistent estimation with many moment inequalities , volume =. Journal of Econometrics , number =

  46. [46]

    Y. A. Davidov , date-added =. Convergence of Distributions Generated by Stationary Stochastic Processes , volume =. Theory of Probability and Its Applications , pages =

  47. [47]

    Convergence rate of estimators of clustered panel models with misclassification , volume =

    Andreas Dzemski and Ryo Okui , date-added =. Convergence rate of estimators of clustered panel models with misclassification , volume =. Economics Letters , pages =

  48. [48]

    Empirical and multiplier bootstraps for suprema of empirical processes of increasing complexity, and related Gaussian couplings , volume =

    Chernozhukov, Victor and Chetverikov, Denis and Kato, Kengo , date-added =. Empirical and multiplier bootstraps for suprema of empirical processes of increasing complexity, and related Gaussian couplings , volume =. Stochastic Processes and their Applications , number =

  49. [49]

    Estimation and identification of latent group structures in panel data , volume =

    Mehrabani, Ali , date-added =. Estimation and identification of latent group structures in panel data , volume =. Journal of Econometrics , number =

  50. [50]

    Galvao and Kengo Kato , date-added =

    Antonio F. Galvao and Kengo Kato , date-added =. Estimation and Inference for Linear Panel Data Models Under Misspecification When Both. Journal of Business

  51. [51]

    Yixiao Sun , date-added =

  52. [52]

    Wilke and Kristina Zapp , date-added =

    Enno Mammen and Ralf A. Wilke and Kristina Zapp , date-added =. Estimation of Group Structures in Panel Models with Individual Fixed Effects , year =

  53. [53]

    Estimation of panel group structure models with structural breaks in group memberships and coefficients , volume =

    Lumsdaine, Robin L and Okui, Ryo and Wang, Wendun , date-added =. Estimation of panel group structure models with structural breaks in group memberships and coefficients , volume =. Journal of Econometrics , number =

  54. [54]

    Finite mixture models , year =

    McLachlan, Geoffrey and Peel, David , date-added =. Finite mixture models , year =

  55. [55]

    Gaussian approximation for high dimensional vector under physical dependence , volume =

    Zhang, Xinyang and Cheng, Guang , date-added =. Gaussian approximation for high dimensional vector under physical dependence , volume =. Bernoulli , number =

  56. [56]

    Grouped patterns of heterogeneity in panel data , volume =

    Bonhomme, St. Grouped patterns of heterogeneity in panel data , volume =. Econometrica , number =

  57. [57]

    Heterogeneous structural breaks in panel data models , year =

    Ryo Okui and Wendun Wang , date-added =. Heterogeneous structural breaks in panel data models , year =. Journal of Econometrics , note =

  58. [58]

    Donald W. K. Andrews , date-added =. Heteroskedasticity and Autocorrelation Consistent Covariance Matrix Estimation , volume =. Econometrica , number =

  59. [59]

    Wuyi Wang and Peter C. B. Phillips and Liangjun Su , date-added =. Homogeneity pursuit in panel data models: theory and applications , volume =. Journal of Applied Econometrics , pages =

  60. [60]

    Identification and estimation in panel models with overspecified number of groups , volume =

    Liu, Ruiqi and Shang, Zuofeng and Zhang, Yonghui and Zhou, Qiankun , date-added =. Identification and estimation in panel models with overspecified number of groups , volume =. Journal of Econometrics , number =

  61. [61]

    Identifying Higher-order Rationality , volume =

    Terri Kneeland , date-added =. Identifying Higher-order Rationality , volume =. Econometrica , number =

  62. [62]

    Income and democracy , volume =

    Acemoglu, Daron and Johnson, Simon and Robinson, James A and Yared, Pierre , date-added =. Income and democracy , volume =. The American Economic Review , number =

  63. [63]

    Andrews, Donald W. K. and Barwick, Panle Jia , date-added =. Inference for parameters defined by moment inequalities: A recommended moment selection procedure , volume =. Econometrica , number =

  64. [64]

    Inference for parameters defined by moment inequalities using generalized moment selection , volume =

    Andrews, Donald WK and Soares, Gustavo , date-added =. Inference for parameters defined by moment inequalities using generalized moment selection , volume =. Econometrica , number =

  65. [65]

    Inference on causal and structural parameters using many moment inequalities , volume =

    Chernozhukov, Victor and Chetverikov, Denis and Kato, Kengo , date-added =. Inference on causal and structural parameters using many moment inequalities , volume =. Review of Economic Studies , pages =

  66. [66]

    Machine learning: a probabilistic perspective , year =

    Murphy, Kevin P , date-added =. Machine learning: a probabilistic perspective , year =

  67. [67]

    Mathematical contributions to the theory of evolution

    Pearson, Karl , date-added =. Mathematical contributions to the theory of evolution. III. Regression, heredity, and panmixia , volume =. Philosophical Transactions of the Royal Society of London. Series A, containing papers of a mathematical or physical character , pages =

  68. [68]

    Matrix analysis , year =

    Horn, Roger A and Johnson, Charles R , date-added =. Matrix analysis , year =

  69. [69]

    Moment bounds for stationary mixing sequences , volume =

    Yokoyama, Ryozo , date-added =. Moment bounds for stationary mixing sequences , volume =. Zeitschrift f

  70. [70]

    Angrist and J

    Jushua D. Angrist and J. Mostly Harmless Econometrics , year =

  71. [71]

    arXiv preprint arXiv:1804.02605 , title =

    Kuchibhotla, Arun Kumar and Chakrabortty, Abhishek , date-added =. arXiv preprint arXiv:1804.02605 , title =

    arXiv

  72. [72]

    MVTNORM: Stata module to work with the multivariate normal and multivariate t distributions , year =

    Grayling, Michael J and Mander, Adrian , date-added =. MVTNORM: Stata module to work with the multivariate normal and multivariate t distributions , year =. Statistical Software Components , publisher =

  73. [73]

    Nonparametric identification of finite mixture models of dynamic discrete choices , volume =

    Kasahara, Hiroyuki and Shimotsu, Katsumi , date-added =. Nonparametric identification of finite mixture models of dynamic discrete choices , volume =. Econometrica , number =

  74. [74]

    Nuclear Norm Regularized Estimation of Panel Regression Models , year =

    Hyungsik Roger Moon and Martin Weidner , date-added =. Nuclear Norm Regularized Estimation of Panel Regression Models , year =

  75. [75]

    Numerical computation of multivariate normal probabilities , volume =

    Genz, Alan , date-added =. Numerical computation of multivariate normal probabilities , volume =. Journal of Computational and Graphical Statistics , number =

  76. [76]

    On the problem of testing location in multivariate populations for restricted alternatives , volume =

    N. On the problem of testing location in multivariate populations for restricted alternatives , volume =. The Annals of Mathematical Statistics , number =

  77. [77]

    Panel data quantile regression with grouped fixed effects , volume =

    Gu, Jiaying and Volgushev, Stanislav , date-added =. Panel data quantile regression with grouped fixed effects , volume =. Journal of Econometrics , number =

  78. [78]

    Practical and theoretical advances in inference for partially identified models , volume =

    Canay, Ivan and Shaikh, Azeem , booktitle =. Practical and theoretical advances in inference for partially identified models , volume =

  79. [79]

    Prediction of multivariate time series by autoregressive model fitting , volume =

    Lewis, Richard and Reinsel, Gregory C , date-added =. Prediction of multivariate time series by autoregressive model fitting , volume =. Journal of multivariate analysis , number =

  80. [80]

    Self-normalized Cram

    Jing, Bing-Yi and Shao, Qi-Man and Wang, Qiying , date-added =. Self-normalized Cram. The Annals of Probability , number =

Showing first 80 references.