On a problem of Andersson and Perlman

M. A. Steel, G. R. Wood*

*Corresponding author for this work

    Research output: Contribution to journalArticlepeer-review

    2 Citations (Scopus)


    We present a simple solution to a problem posed recently by Andersson and Perlman. This solution allows us to find the conditional independence assumptions necessary to permit maximum likelihood estimation of the parameters of a multivariate normal distribution, when certain observations are missing.

    Original languageEnglish
    Pages (from-to)381-382
    Number of pages2
    JournalStatistics and Probability Letters
    Issue number5
    Publication statusPublished - 2 Dec 1993


    • join-irreducible
    • lattice
    • missing data
    • Multivariate normal
    • parameter estimation


    Dive into the research topics of 'On a problem of Andersson and Perlman'. Together they form a unique fingerprint.

    Cite this