Compound sum distributions with dependence

Nadarajah S., Kwong H. S., TANK F.

STATISTICS, cilt.55, sa.2, ss.409-425, 2021 (SCI-Expanded, Scopus) identifier identifier

  • Yayın Türü: Makale / Tam Makale
  • Cilt numarası: 55 Sayı: 2
  • Basım Tarihi: 2021
  • Doi Numarası: 10.1080/02331888.2021.1919110
  • Dergi Adı: STATISTICS
  • Derginin Tarandığı İndeksler: Science Citation Index Expanded (SCI-EXPANDED), Scopus, Academic Search Premier, ABI/INFORM, MathSciNet, zbMATH
  • Sayfa Sayıları: ss.409-425
  • Anahtar Kelimeler: Insurance, co-kurtosis, co-skewness, method of moments, Poisson distribution, SEVERITY, AGGREGATION, FREQUENCY, NUMBER, CLAIMS
  • Ankara Üniversitesi Adresli: Evet

Özet

Compound sum distributions (in particular, the classical compound Poisson distribution) assume that claim amounts are independent and independent of the number of claims. These may not be realistic assumptions. In this note, formulas for compound sum distributions are derived for the general case of dependence. The influence of dependence on the distributions is investigated. A data illustration is given.