Browsing by Author "MARTINEZ, S"

Now showing 1 - 4 of 4
  • No Thumbnail Available
    Item
    A REGULARIZATION RESULT OF THE CONTINUOUS PMC MARKOV SEMIGROUPS
    (1991) BERTOGLIO, N; DARTNELL, P; MARTINEZ, S; MARTIN, JS
    Let (W(t))t is-an-element-of R+ be the PMC Markov semigroup and assume usual regular conditions on the probability space (X, Beta, mu). We show that there exist a class of mu-preserving transition kernels (Q(t))t is-an-element-of R+ and a full mu-measure set X approximately such that the action of Q(t) on L2 (mu) is given by W(t), and the semigroup equality Q(t)Q(s)f(x) = Q(t + s)f(x) is verified for any bounded measurable function f, for any x is-an-element-of X approximately and for any t, s is-an-element-of R+.
  • Thumbnail Image
    Item
    MEASURE PRESERVING MARKOV-PROCESSES DENSELY SIMILAR TO ENDOMORPHISMS
    (ELSEVIER SCIENCE BV, 1991) BERTOGLIO, N; MARTINEZ, S
    We characterize the contractions densely similar to the adjoint of some isometry. We deduce a sufficient condition in order to have the evolution of a measure preserving Markov process densely similar to the evolution of an endomorphism on the set of L2-states. This study is in the scope of the reciprocal of the Misra-Prigogine construction in K-systems.
  • Thumbnail Image
    Item
    ON A TEST FOR GENERALIZED UPPER TRUNCATED WEIBULL-DISTRIBUTIONS
    (ELSEVIER SCIENCE BV, 1991) MARTINEZ, S; QUINTANA, F
    We study upper truncated Weibull random variables with density given by g-beta,delta,tau(t) = beta-delta-t-delta-1 exp(-beta-t-delta)(1 - exp(-beta-tau-delta))-1 for 0 less-than-or-equal-to t less-than-or-equal-to tau (tau is the truncation parameter), delta > 0 and beta is-an-element-of R. Denoting by beta triple-overdot, delta triple-overdot and tau triple-overdot the maximum likelihood estimators we show that sign(beta triple-overdot) = sign(1/2 - G(n)), where G(n) = (1/n)SIGMA-i =1n(T(i)/tau triple-overdot) delta triple-overdot. It is also shown that 4 square-root 3n(1/2 - G(n)(beta = 0)) converges to a normalized Guassian. This result is then used to provide a test for the hypothesis-beta = 0.
  • No Thumbnail Available
    Item