The importance of being the upper bound in the bivariate family

Article English OPEN
Cuadras, C. M.;
(2006)
  • Publisher: Institut d'Estadística de Catalunya
  • Subject: Distribució (Teoria de la probabilitat) | Diagonal expansion | Inference | Distribution (Probability theory) | Anàlisi multivariable | :62 Statistics::62F Parametric inference [Classificació AMS] | Mathematical statistics | Goodness-of-fit | Multivariate analysis | Hoeffding’s lemma | Correspondence analysis (Statistics) | :62 Statistics::62H Multivariate analysis [Classificació AMS] | Given marginals | Anàlisi de correspondències (Estadística) | Inferència | Logit analysi | Fréchet-Hoeffding bounds | Bayes test in 2 × 2 tables | Estadística matemàtica | :60 Probability theory and stochastic processes::60E Distribution theory [Classificació AMS] | Lorenz curve
    arxiv: Computer Science::Databases

Any bivariate cdf is bounded by the Fr ´echet-Hoeffding lower and upper bounds. We illustrate the importance of the upper bound in several ways. Any bivariate distribution can be written in terms of this bound, which is implicit in logit analysis and the Lorenz curve, a... View more