Help with reading code

-----Original Message-----
From: r-help-bounces at r-project.org

On Behalf Of Dana77
Sent: Wednesday, December 03, 2008 3:24 PM
To: r-help at r-project.org
Subject: [R] Help with reading code


I would like to give out the equation for calculating the maximum
likelihood.
Below is the code, but I still have problems with it.  After I read

code, I found there are two cases for "w(weights)".  If  "w" is not

then the equation is given as "val <- 0.5 * (sum(log(w)) - N * (log(2

pi)
+ 1 - log(N) +
        log(sum(w * res^2))))". However, if "w" is zero, then I do not
know
what equation it should be since it does not make any sense for

Hope
someone can help me to figure this out. Thanks!




function (object, REML = FALSE, ...)
{
    res <- object$residuals
    p <- object$rank
    N <- length(res)
    if (is.null(w <- object$weights)) {
        w <- rep.int(1, N)
    }
    else {
        excl <- w == 0  #####I can not understand the following lines

        if (any(excl)) { ### If there are any observations to exclude
            res <- res[!excl]   ### then keep the ones with weight not

            N <- length(res)
            w <- w[!excl]        }

    }
    N0 <- N
    if (REML)
        N <- N - p
    val <- 0.5 * (sum(log(w)) - N * (log(2 * pi) + 1 - log(N) +
        log(sum(w * res^2))))

    if (REML)
        val <- val - sum(log(abs(diag(object$qr$qr)[1:p])))
    attr(val, "nall") <- N0
    attr(val, "nobs") <- N
    attr(val, "df") <- p + 1
    class(val) <- "logLik"
    val
}


Best,

Dana
--
View this message in context: http://www.nabble.com/Help-with-reading-
code-tp20823979p20823979.html
Sent from the R help mailing list archive at Nabble.com.