Skip to content
DraconiticResearch
Search Sources API
203,234 studies31 sourcesUpdated 22 min ago
PreprintCC BY 4.0arXiv

From Counting to Continuous Natural Exponential Families

Abstract

Natural exponential families (NEFs) are characterized by their variance functions (VFs), namely by the pair (V,M), where V expresses the variance as a function of the mean and M is the mean domain. This characterization naturally raises the inverse question: when is a given function V the VF of an NEF, and what structural properties of the family can be read directly from V? Bar-Lev (1987), as part of a more general result for absolutely monotone functions, showed that every nonzero polynomial V(m)=∑j=1r aj mj, aj≥ 0, is the VF of an infinitely divisible NEF on a positive mean domain. This polynomial class splits exhaustively into the cases a1>0 and a1=0. Bar-Lev, Letac and Ridder (2024) proved that, after scaling so that a1=1, the first case yields a counting NEF supported on ℕ0. We establish the complementary result: when a1=0, the corresponding NEF is absolutely continuous with respect to Lebesgue measure on the positive half-line. More generally, we prove absolute continuity whenever V(m)=m2G(m), where G is a nonzero power series with nonnegative coefficients. When G is a polynomial, the mean domain is the entire positive half-line. We also record several consequences for the cumulant structure and for statistical inference.

Related

  1. On Natural Exponential Families with Log-Affine Generalized Variance
    Zeyu Cao, Shaosai Huang
    arXivPreprintCC BY-NC-ND 4.0Full textProbabilityStatisticsarXiv
  2. Kullback–Leibler Asymmetry and Information Homogeneity in Natural Exponential Families
    Shaul K. Bar-Lev
    MathematicsPeer-reviewedCC BY 4.0General mathematicsCrossref
  3. Exact two-sided p-values in natural exponential families: coincidence, non-uniqueness, and sample-size stability
    Shaul K. Bar-Lev, Linard Hoessly
    arXivPreprintCC BY 4.0Full textStatisticsarXiv
  4. Equivalence on exponential families as Hessian manifolds and classification of exponential families of order 1 with constant Hessian sectional curvature
    Koichi Tojo, Taro Yoshino
    arXivPreprintarXiv licenceFull textGeometry & topologyStatisticsarXiv
  5. Two families of Young tableaux with periodic walls: Counting formulas and differential transcendence
    Feihu Liu, Jiahang Liu, Guoce Xin
    arXivPreprintCC BY 4.0Full textCombinatorics & discrete mathematicsarXiv
BibTeX
@misc{barlev2026from,
  title = {{From Counting to Continuous Natural Exponential Families}},
  author = {Shaul K. Bar-Lev},
  howpublished = {arXiv},
  year = {2026},
  month = oct,
  doi = {10.48550/arxiv.2610.05478},
  eprint = {2610.05478},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2610.05478},
  note = {CC BY 4.0},
}
RIS
TY  - UNPB
TI  - From Counting to Continuous Natural Exponential Families
AU  - Shaul K. Bar-Lev
PY  - 2026
DA  - 2026/10/04
PB  - arXiv
DO  - 10.48550/arxiv.2610.05478
UR  - https://arxiv.org/abs/2610.05478
AB  - Natural exponential families (NEFs) are characterized by their variance functions (VFs), namely by the pair (V,M), where V expresses the variance as a function of the mean and M is the mean domain. This characterization naturally raises the inverse question: when is a given function V the VF of an NEF, and what structural properties of the family can be read directly from V? Bar-Lev (1987), as part of a more general result for absolutely monotone functions, showed that every nonzero polynomial V(m)=∑_j=1^r a_j m^j, a_j≥ 0, is the VF of an infinitely divisible NEF on a positive mean domain. This polynomial class splits exhaustively into the cases a_1>0 and a_1=0. Bar-Lev, Letac and Ridder (2024) proved that, after scaling so that a_1=1, the first case yields a counting NEF supported on ℕ_0. We establish the complementary result: when a_1=0, the corresponding NEF is absolutely continuous with respect to Lebesgue measure on the positive half-line. More generally, we prove absolute continuity whenever V(m)=m^2G(m), where G is a nonzero power series with nonnegative coefficients. When G is a polynomial, the mean domain is the entire positive half-line. We also record several consequences for the cumulant structure and for statistical inference.
ER  -