arxiv: 2604.17490 · v1 · submitted 2026-04-19 · 🧮 math.ST · q-fin.RM· stat.TH

Recognition: unknown

Joint Exclusivity

Nawaf Mohammed

Authors on Pith no claims yet

Pith reviewed 2026-05-10 05:07 UTC · model grok-4.3

classification 🧮 math.ST q-fin.RMstat.TH

keywords joint exclusivitynegative dependencerandom vectormarginal distributionscopulasupport structurejoint mixability

0 comments

The pith

Joint exclusivity random vectors with prescribed marginals exist if and only if the sum of the marginal survival functions at zero is at most n minus one.

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

The paper defines joint exclusivity as an extremal negative dependence structure in which a random vector places no probability mass inside the open positive orthant. It proves that vectors with this property exist for any given set of marginal distributions precisely when the sum of each marginal's survival probability at zero does not exceed n minus one. The proof is completed by an explicit construction that puts all mass on the lower-dimensional faces of the orthant while matching the marginals exactly and allowing any copula dependence inside those faces. The same framework is enlarged by allowing distortions of the marginals and is shown to have a support correspondence with joint mixability.

Core claim

Joint exclusivity (JE) is defined by the exclusion of the interior of the non-negative orthant. A sharp necessary and sufficient condition for the existence of a JE random vector with prescribed marginals is the inequality sum over i in N of bar F_i(0) less than or equal to n minus 1. A canonical construction distributes probability mass on the lower-dimensional faces of the support while allowing flexible copula specifications within each face. The framework is extended to a generalized class via marginal distortion functions, and a correspondence is identified between the support structures of JE and joint mixability.

What carries the argument

The support restriction to the union of the faces of the non-negative orthant, which enforces joint exclusivity while permitting exact marginal matching and arbitrary copulas on each face.

If this is right

A JE random vector exists exactly when the sum of the marginal survival probabilities at zero is at most n-1.
Mass can be placed only on the faces while still matching all marginal distributions.
Any copula may be chosen independently on each face without disturbing the marginals.
Marginal distortion functions extend the construction to cases where the basic sum condition is violated.
The boundary support of JE vectors mirrors the support structure of jointly mixable vectors.

Where Pith is reading between the lines

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

The sum condition supplies an immediate numerical test for whether this form of extremal negative dependence is feasible under given marginals.
The modular face-wise construction separates marginal constraints from the choice of dependence structure inside each face.
The identified support correspondence with joint mixability points to a symmetric treatment of extremal positive and negative dependence.

Load-bearing premise

That probability mass can always be allocated to the lower-dimensional faces of the orthant while exactly reproducing the given marginal distributions and allowing arbitrary copula dependence within each face.

What would settle it

For n=2 and two continuous marginals each with survival probability 1 at zero, check whether any random vector with those marginals can have zero probability that both components are positive; if such a vector exists, the necessity of the sum condition fails.

Figures

Figures reproduced from arXiv: 2604.17490 by Nawaf Mohammed.

**Figure 2.** Figure 2: Support of the canonical JE random vector [PITH_FULL_IMAGE:figures/full_fig_p018_2.png] view at source ↗

**Figure 3.** Figure 3: Support of the G-JE random vector XN with Gi as linear truncations at 0.75. takes values in (bi − ε, bi) for some ε > 0, then G∗ i = (bi − ai)/γ. Setting ai = 0 and bi = Fi(0), condition (3.18) becomes X i∈N Fi(0) ≤ min γ(n − 1) γ(n − 1) − (n − 2), γ − maxi∈N Fi(0) γ − 1 . One can verify that the right-hand side does not exceed n−1, consistent with the restriction imposed by non-linear distortions. Mor… view at source ↗

**Figure 4.** Figure 4: The sets WJE and WJM as supports of JE and JM random vectors (n = 3). 29 [PITH_FULL_IMAGE:figures/full_fig_p029_4.png] view at source ↗

read the original abstract

We introduce joint exclusivity (JE), a form of extremal negative dependence that extends the classical notion of mutual exclusivity. The JE structure is analytically tractable and is defined by the exclusion of the interior of the non-negative orthant. We establish a sharp necessary and sufficient condition for the existence of a JE random vector with prescribed marginals, namely $\sum_{i\in N} \overline{F}_i(0) \leq n - 1$. We propose a canonical construction that distributes probability mass on lower-dimensional faces of the support, while allowing flexible copula specifications within each face. The framework is further extended to a generalized class (G-JE) via marginal distortion functions. Finally, we identify a correspondence between the support structures of JE and joint mixability, revealing a structural link between the two concepts.

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.

Desk Editor's Note private letter to a colleague

This paper defines joint exclusivity as an extreme negative dependence structure and claims a sharp existence condition plus a flexible construction, though the marginal-matching details in the construction could use extra scrutiny.

read the letter

The main thing here is that the paper defines joint exclusivity, a support-restricted form of negative dependence that rules out mass in the interior of the non-negative orthant, and states a necessary and sufficient condition for a random vector with this property to exist given its marginals: the sum of the survival functions at zero is at most n-1. It also supplies a canonical construction that places all mass on the lower-dimensional faces and lets you pick copulas inside each face, plus a generalization via marginal distortions and a noted link to joint mixability. Necessity is immediate from the union bound, since the events where each coordinate hits zero must cover probability one. The construction is the part that makes the result usable for modeling. The paper does a clean job of making the definition and the existence claim explicit without unnecessary machinery. The connection to mixability is a useful observation that ties two support-restriction ideas together. The soft spot is in the sufficiency argument. The construction has to solve for the masses on each face so that the induced marginals match the targets exactly, while leaving enough freedom for arbitrary copulas on the faces. When the inequality is strict there is slack, but it is not obvious from the abstract whether non-negative solutions always exist for arbitrary marginals or whether the remaining freedom really permits independent copula choice. The stress-test note flags this correctly. If the full proofs work through the equations and show solvability without hidden restrictions, the claim stands; otherwise the result only holds for a narrower class of marginals than stated. This is a technical piece for people working on multivariate dependence, copulas, or risk models that need strong negative dependence. A reader already in that subfield will find the condition and construction concrete enough to try out. I would send it to peer review because the core claim is new and specific enough that referees can check the construction details directly.

Referee Report

2 major / 2 minor

Summary. The manuscript introduces joint exclusivity (JE) as an extremal negative dependence structure for non-negative random vectors, defined by the exclusion of the interior of the non-negative orthant from the support. It derives a sharp necessary and sufficient condition for the existence of a JE vector with prescribed marginals: ∑_{i∈N} F̄_i(0) ≤ n-1. A canonical construction is proposed that places all probability mass on the coordinate hyperplanes (lower-dimensional faces) and permits arbitrary copula specifications within each face. The work extends the framework to generalized joint exclusivity (G-JE) via marginal distortion functions and identifies a structural correspondence between the support of JE vectors and jointly mixable distributions.

Significance. If the canonical construction is rigorously shown to recover arbitrary prescribed marginals while confining support to the boundary, the result supplies an analytically tractable model for strong negative dependence with clear existence conditions. The link to joint mixability is a useful structural observation. The framework could find applications in multivariate risk modeling and copula theory where extremal negative dependence is relevant.

major comments (2)

[§3] §3 (Canonical construction and proof of sufficiency): the necessity of ∑ F̄_i(0) ≤ n-1 follows immediately from the union bound on P(∪{X_i=0})=1. However, the sufficiency argument via face-wise mass placement does not explicitly exhibit the system of equations that determines the face probabilities and the conditional distributions so that every marginal F_j is exactly reproduced. It remains unclear whether a non-negative solution to this (under-determined) system always exists for general continuous marginals when the inequality is strict, and whether the residual degrees of freedom truly allow independent copula choice on each face without disturbing the marginal constraints.
[Theorem 3.1] Theorem 3.1 (existence result): while the abstract asserts a 'sharp' nec-and-suff condition and a 'flexible' construction, the manuscript provides no numerical verification or low-dimensional example (e.g., n=3 with non-uniform marginals) that confirms the induced marginals match the targets after the face distributions are chosen. Such a check would directly address whether the construction is marginal-preserving for arbitrary inputs.

minor comments (2)

[Introduction] The notation F̄_i(0) is used without an explicit reminder that it denotes the survival function evaluated at zero; a brief definition in the introduction would aid readability.
[§4] The extension to G-JE is mentioned only briefly; a short remark on how the distortion functions interact with the face construction would clarify the generalization.

Simulated Author's Rebuttal

2 responses · 0 unresolved

We thank the referee for their insightful comments, which have helped us improve the clarity and rigor of the manuscript. We address each major comment below.

read point-by-point responses

Referee: [§3] §3 (Canonical construction and proof of sufficiency): the necessity of ∑ F̄_i(0) ≤ n-1 follows immediately from the union bound on P(∪{X_i=0})=1. However, the sufficiency argument via face-wise mass placement does not explicitly exhibit the system of equations that determines the face probabilities and the conditional distributions so that every marginal F_j is exactly reproduced. It remains unclear whether a non-negative solution to this (under-determined) system always exists for general continuous marginals when the inequality is strict, and whether the residual degrees of freedom truly allow independent copula choice on each face without disturbing the marginal constraints.

Authors: We agree that a more explicit presentation of the underlying equations would strengthen the sufficiency proof. In the revised manuscript, we now include the full system of equations for the face probabilities. For each subset S of coordinates, the probability mass on the corresponding face is determined by solving the linear system where, for each j, the sum of masses on faces that include the j-th coordinate equals F̄_j(0). This system is underdetermined when the inequality is strict, but we prove existence of a non-negative solution by noting that the condition ∑ F̄_i(0) ≤ n-1 ensures feasibility (by the properties of the incidence matrix of faces). For the conditional distributions on each face, the marginals are matched by construction through the choice of the copula on that face, which is independent across faces because the faces are disjoint in their interior supports. The residual freedom does not disturb the marginals at zero, as those are fixed by the face masses. We have added this detailed exposition to §3. revision: yes
Referee: [Theorem 3.1] Theorem 3.1 (existence result): while the abstract asserts a 'sharp' nec-and-suff condition and a 'flexible' construction, the manuscript provides no numerical verification or low-dimensional example (e.g., n=3 with non-uniform marginals) that confirms the induced marginals match the targets after the face distributions are chosen. Such a check would directly address whether the construction is marginal-preserving for arbitrary inputs.

Authors: We appreciate the suggestion for empirical verification. We have added a new subsection with a numerical example for n=3 using exponential marginals with different rates (non-uniform). We explicitly compute the face probabilities, specify the conditional distributions on each face (using independence copulas for simplicity), and verify numerically that the empirical marginal survival functions at zero and the overall marginals match the targets within simulation error. This example confirms the marginal-preserving property and is included in the revised version of the paper. revision: yes

Circularity Check

0 steps flagged

No circularity; JE existence condition derived directly from definition and explicit construction

full rationale

The necessity of ∑ F̄_i(0) ≤ n-1 follows immediately from the JE definition (P(all X_i > 0) = 0) by observing that ∑ 1_{X_i > 0} ≤ n-1 a.s. and taking expectations; this is a standard first-principles inequality, not a self-referential loop. Sufficiency is asserted via an explicit canonical construction that places mass on the coordinate hyperplanes and specifies copulas on the faces to match the given marginals. The paper cites prior work on mutual exclusivity and mixability for context and for the structural correspondence, but these citations are not load-bearing for the main theorem, which is self-contained with no fitted parameters, ansatzes smuggled via self-citation, or renaming of known results as new derivations. The central claims therefore do not reduce to their inputs by construction.

Axiom & Free-Parameter Ledger

0 free parameters · 1 axioms · 1 invented entities

The framework rests on standard axioms of probability measures, the definition of copulas, and the geometry of the non-negative orthant; no free parameters or new invented entities with independent evidence are introduced beyond the new definition itself.

axioms (1)

standard math Standard axioms of probability measures and the existence of copulas on lower-dimensional faces
Invoked to guarantee that marginals can be preserved when mass is placed on faces.

invented entities (1)

Joint exclusivity (JE) structure no independent evidence
purpose: To formalize extreme negative dependence via exclusion of the open non-negative orthant
Newly defined concept whose properties are derived in the paper; no independent empirical or falsifiable handle is provided.

pith-pipeline@v0.9.0 · 5423 in / 1330 out tokens · 43615 ms · 2026-05-10T05:07:37.462013+00:00 · methodology

discussion (0)

Reference graph

Works this paper leans on

299 extracted references · 93 canonical work pages

[1]

2010 , isbn =

Nelsen, Roger B , publisher =. 2010 , isbn =

2010
[2]

Economic Notes , number =

Acerbi, Carlo and Tasche, Dirk , doi =. Economic Notes , number =
[3]

Review of Financial Studies , month =

Acharya, Viral V and Pedersen, Lasse H and Philippon, Thomas and Richardson, Matthew , doi =. Review of Financial Studies , month =
[4]

Adalsteinsson, Gudni , doi =
[5]

American Economic Review , month =

Agnew, Julie R and Anderson, Lisa R and Gerlach, Jeffrey R and Szykman, Lisa R , doi =. American Economic Review , month =
[6]

Negative dependence concept in copulas and the marginal free herd behavior index , url =

Jae Youn Ahn , doi =. Negative dependence concept in copulas and the marginal free herd behavior index , url =. Journal of Computational and Applied Mathematics , keywords =
[7]

Journal of Optimization Theory and Applications , number =

Ahn, Jae Youn and Fuchs, Sebastian , doi =. Journal of Optimization Theory and Applications , number =
[8]

Insurance: Mathematics and Economics , keywords =

Ai, Jing and Brockett, Patrick L and Jacobson, Allen F , doi =. Insurance: Mathematics and Economics , keywords =
[9]

Journal of the Royal Statistical Society

Aitchison, J , doi =. Journal of the Royal Statistical Society. Series B (Methodological) , pages =
[10]

Journal of the Royal Statistical Society

Aitchison, J , doi =. Journal of the Royal Statistical Society. Series B (Methodological) , month =
[11]

, year = 1986, series =

Aitchison, J. , booktitle =. doi:10.1007/978-94-009-4109-0 , isbn =

work page doi:10.1007/978-94-009-4109-0
[12]

ASTIN Bulletin , title =

Akakpo, R and Xia, M and Polansky, A , doi =. ASTIN Bulletin , title =
[13]

Journal of the Chungcheong Mathematical Society , keywords =

Akkouchi, Mohamed , doi =. Journal of the Chungcheong Mathematical Society , keywords =
[14]

Insurance: Mathematics and Economics , keywords =

Albrecher, Hansj. Insurance: Mathematics and Economics , keywords =. doi:10.1016/j.insmatheco.2010.11.007 , issn =

work page doi:10.1016/j.insmatheco.2010.11.007 2010
[15]

doi:10.1002/9781119412540 , isbn =

Albrecher, Hansj. doi:10.1002/9781119412540 , isbn =

work page doi:10.1002/9781119412540
[16]

Asmussen, S and Albrecher, H , doi =
[17]

ANALYTIC APPROXIMATIONS FOR MULTI‐ASSET OPTION PRICING , year =

Alexander, Carol and Venkatramanan, Aanand , journal =. ANALYTIC APPROXIMATIONS FOR MULTI‐ASSET OPTION PRICING , year =. doi:10.1111/j.1467-9965.2011.00481.x , publisher =

work page doi:10.1111/j.1467-9965.2011.00481.x 2011
[18]

Goodness of Fit

T. W. Anderson and D. A. Darling , doi =. Asymptotic Theory of Certain "Goodness of Fit" Criteria Based on Stochastic Processes , volume =. The Annals of Mathematical Statistics , month =
[19]

Journal of the European Economic Association , month =

Anderson, Evan W and Hansen, Lars Peter and Sargent, Thomas J , doi =. Journal of the European Economic Association , month =
[20]

National Vital Statistics Reports , number =

Arias, Elizabeth , doi =. National Vital Statistics Reports , number =
[21]

doi:10.1016/j.econlet.2011.01.026 , journal =

work page doi:10.1016/j.econlet.2011.01.026 2011
[22]

Jensen, Arne , doi =
[23]

Arnold, Barry C , doi =
[24]

Arnold, Barry C and Castillo, Enrique and Sarabia, José-Mariá. , doi =
[25]

Probability Surveys , number =

Richard Arratia and Larry Goldstein and Fred Kochman , doi =. Probability Surveys , number =
[26]

Mathematical Finance , keywords =

Artzner, Philippe and Delbaen, Freddy and Eber, Jean-Marc and Heath, David , doi =. Mathematical Finance , keywords =
[27]

Insurance: Mathematics and Economics , keywords =

Asimit, Alexandru V and Jones, Bruce L , doi =. Insurance: Mathematics and Economics , keywords =
[28]

Insurance: Mathematics and Economics , keywords =

Asimit, Alexandru V and Furman, Edward and Vernic, Raluca , doi =. Insurance: Mathematics and Economics , keywords =
[29]

Scandinavian Actuarial Journal , keywords =

Asimit, Alexandru V and Badescu, Andrei L , doi =. Scandinavian Actuarial Journal , keywords =
[30]

Insurance: Mathematics and Economics , keywords =

Asimit, Alexandru V and Furman, Edward and Tang, Qihe and Vernic, Raluca , doi =. Insurance: Mathematics and Economics , keywords =
[31]

Communications in Statistics - Simulation and Computation , keywords =

Asimit, Alexandru V and Furman, Edward and Vernic, Raluca , doi =. Communications in Statistics - Simulation and Computation , keywords =
[32]

Methodology and Computing in Applied Probability , month =

Asimit, Alexandru V and Vernic, Raluca and Zitikis, Ricardas , doi =. Methodology and Computing in Applied Probability , month =
[33]

ASTIN Bulletin , keywords =

Asmussen, S and Binswanger, K , doi =. ASTIN Bulletin , keywords =
[34]

Insurance Mathematics and Economics , keywords =

Asmussen, S. Insurance Mathematics and Economics , keywords =. doi:10.1016/0167-6687(92)90058-J , issn =

work page doi:10.1016/0167-6687(92)90058-j
[35]

Scandinavian Journal of Statistics , number =

Asmussen, S. Scandinavian Journal of Statistics , number =. doi:10.2307/4616418 , isbn =

work page doi:10.2307/4616418
[36]

doi:10.2307/2348382 , isbn =

Asmussen, S. doi:10.2307/2348382 , isbn =

work page doi:10.2307/2348382
[37]

Insurance: Mathematics and Economics , keywords =

Avanzi, Benjamin and Taylor, Greg and Vu, Phuong Anh and Wong, Bernard , doi =. Insurance: Mathematics and Economics , keywords =
[38]

Azizpour, Shahriar and Giesecke, Kay , doi =
[39]

Bahnemann, D , doi =
[40]

Statistics

Bahraoui, Zuhair and Bolanc. Statistics. doi:10.1016/j.insmatheco.2008.07.005 , issn =

work page doi:10.1016/j.insmatheco.2008.07.005 2008
[41]

doi:10.1007/b101765 , isbn =

Balakrishnan, N and Lai, Chin Diew , booktitle =. doi:10.1007/b101765 , isbn =

work page doi:10.1007/b101765
[42]

Journal of Multivariate Analysis , keywords =

Balakrishnan, Narayanaswamy and Risti. Journal of Multivariate Analysis , keywords =. doi:10.1016/j.jmva.2015.09.012 , issn =

work page doi:10.1016/j.jmva.2015.09.012 2015
[43]

The Annals of Probability , keywords =

Balkema, A A and de Haan, L , doi =. The Annals of Probability , keywords =
[44]

Journal of Financial Stability , keywords =

Balla, Eliana and Ergen, Ibrahim and Migueis, Marco , doi =. Journal of Financial Stability , keywords =
[45]

doi:10.1016/j.ejor.2016.10.052 , journal =

Balog, D and B. doi:10.1016/j.ejor.2016.10.052 , journal =

work page doi:10.1016/j.ejor.2016.10.052 2016
[46]

Insurance: Mathematics and Economics , month =

Barg. Insurance: Mathematics and Economics , month =. doi:10.1016/j.insmatheco.2009.08.002 , issn =

work page doi:10.1016/j.insmatheco.2009.08.002 2009
[47]

Bauer, Daniel and Zanjani, George H. , doi =. SSRN Electronic Journal , keywords =
[48]

doi:10.1007/978-1-4614-0155-1_29 , pages =

Bauer, Daniel and Zanjani, George H , booktitle =. doi:10.1007/978-1-4614-0155-1_29 , pages =

work page doi:10.1007/978-1-4614-0155-1_29
[49]

Management Science , keywords =

Bauer, Daniel and Zanjani, George , doi =. Management Science , keywords =
[50]

Insurance: Mathematics and Economics , keywords =

B. Insurance: Mathematics and Economics , keywords =. doi:10.1016/j.insmatheco.2018.06.009 , eprint =

work page doi:10.1016/j.insmatheco.2018.06.009 2018
[51]

doi:10.1017/s1748499519000113 , journal =

B. doi:10.1017/s1748499519000113 , journal =

work page doi:10.1017/s1748499519000113
[52]

doi:10.2139/ssrn.2609162 , keywords =

Beers, David T and Nadeau, Jean-s. doi:10.2139/ssrn.2609162 , keywords =

work page doi:10.2139/ssrn.2609162
[53]

Statistical Papers , number =

Behboodian, Javad and Dolati, Ali and. Statistical Papers , number =. doi:10.1007/s00362-006-0332-9 , issn =

work page doi:10.1007/s00362-006-0332-9
[54]

ASTIN Bulletin , number =

Beirlant, J and Matthys, G and Dierckx, G , doi =. ASTIN Bulletin , number =
[55]

The Journal of Risk , number =

Belles-Sampera, Jaume and Guillen, Montserrat and Santolino, Miguel , doi =. The Journal of Risk , number =
[56]

Bellini, Fabio and Laeven, Roger J. A. and Rosazza Gianin, Emanuela , doi =. Robust return risk measures , url =. Mathematics and Financial Economics , number =
[57]

Journal of Multivariate Analysis , month =

Belzunce, F. Journal of Multivariate Analysis , month =. doi:10.1016/j.jmva.2009.01.013 , issn =

work page doi:10.1016/j.jmva.2009.01.013 2009
[58]

Journal of Economic Perspectives , month =

Benartzi, Shlomo and Previtero, Alessandro and Thaler, Richard H , doi =. Journal of Economic Perspectives , month =
[59]

Journal of Financial Planning , pages =

Bengen, William P , doi =. Journal of Financial Planning , pages =
[60]

Geophysical Research Letters , month =

Benson, David A and Schumer, Rina and Meerschaert, Mark M , doi =. Geophysical Research Letters , month =
[61]

Bernard, C and Vanduffel, S , doi =
[62]

doi:10.2139/ssrn.2572508 , journal =

Bernard, C and R. doi:10.2139/ssrn.2572508 , journal =

work page doi:10.2139/ssrn.2572508
[63]

Metrika , keywords =

Bernhart, German and. Metrika , keywords =. doi:10.1007/s00184-012-0382-z , issn =

work page doi:10.1007/s00184-012-0382-z
[64]

Bielecki, T R and Rutkowski, M , doi =
[65]

The Geneva Papers on Risk and Insurance Issues and Practice , month =

Biener, Christian and Eling, Martin , doi =. The Geneva Papers on Risk and Insurance Issues and Practice , month =
[66]

Studying mixability with supermodular aggregating functions , year =

Valeria Bignozzi and Giovanni Puccetti , journal =. Studying mixability with supermodular aggregating functions , year =. doi:10.1016/j.spl.2015.01.032 , keywords =

work page doi:10.1016/j.spl.2015.01.032 2015
[67]

The Annals of Mathematical Statistics , number =

Bildikar, Sheela and Patil, G P , doi =. The Annals of Mathematical Statistics , number =
[68]

Bingham, N H and Goldie, C M and Teugels, Jef L , doi =
[69]

SSRN Electronic Journal , month =

Bjork, Tomas and Murgoci, Agatha , doi =. SSRN Electronic Journal , month =
[70]

Finance and Stochastics , keywords =

Bjork, Thomas and Murgoci, Agatha , doi =. Finance and Stochastics , keywords =
[71]

Blackwell, David and MacQueen, James B , doi =. Ann. Statist. , language =
[72]

Stochastic Models , month =

Bladt, Mogens and Neuts, Marcel F , doi =. Stochastic Models , month =
[73]

ASTIN Bulletin , keywords =

Bladt, Mogens , doi =. ASTIN Bulletin , keywords =
[74]

Stochastic Models , keywords =

Bladt, Mogens and Nielsen, Bo Friis , doi =. Stochastic Models , keywords =
[75]

Scandinavian Actuarial Journal , keywords =

Bladt, Mogens and Nielsen, Bo Friis and Samorodnitsky, Gennady , doi =. Scandinavian Actuarial Journal , keywords =
[76]

Extremes , keywords =

Bladt, Mogens and Rojas-Nandayapa, Leonardo , doi =. Extremes , keywords =. arXiv , arxivid =:1705.04357 , issn =

work page arXiv
[77]

Blanchet, Jose and Lam, Henry and Tang, Qihe and Yuan, Zhongyi , doi =
[78]

Lecture Notes-Monograph Series , month =

Block, Henry W and Savits, Thomas H and Shaked, Moshe , doi =. Lecture Notes-Monograph Series , month =
[79]

Block and Thomas H

Henry W. Block and Thomas H. Savits and Moshe Shaked , doi =. The Annals of Probability , keywords =
[80]

doi:10.1142/s0219024904002360 , journal =

B. doi:10.1142/s0219024904002360 , journal =

work page doi:10.1142/s0219024904002360

Showing first 80 references.