Link [ pkgsrc | NetBSD | pkgsrc git mirror | PR fulltext-search | netbsd commit viewer ]


   
        usage: [branch:branch] [user:user] [path[@revision]] keyword [... [-excludekeyword [...]]] (e.g. branch:MAIN pkgtools/pkg)




switch to index mode

recent branches: MAIN (1m)  pkgsrc-2024Q1 (9d)  pkgsrc-2023Q4 (56d)  pkgsrc-2023Q2 (88d)  pkgsrc-2023Q3 (167d) 

2024-05-26 15:52:25 UTC Now

2024-01-24 11:49:19 UTC MAIN commitmail json YAML

(math/R-VGAM) Updated 1.1.8 to 1.1.9

                CHANGES IN VGAM VERSION 1.1-9

NEW FEATURES

    o  Soon: VGAM will require R >= 4.4.0 because plot.profile
        will move from \pkg{MASS} to \pkg{stats}. Sorry!
    o  Yettodo: modify dgaitdlog() to be like
        dgaitdpois() in terms of safeguarding against too
        much deflation and inflation (to return NaN).
        Ditto to dgaitdzeta() and dgaitdnbinom().
        Ditto for the p-type functions.
    o  New family functions: gammaff.mm(), hurea(d).
    o  New generic and/or methods functions: cops().
    o  acat(), cumulative(), cratio(), propodds(), sratio() handles
        argument 'thresholds' equalling 'symmetric1' and 'symmetric0'.
        Note from version 1.1-8 that 'equidistant' was added.
    o  Tested okay on R 4.3.0.

BUG FIXES and CHANGES

    o  wald.stat(..., orig.SE = TRUE, values0 = values0)
        assumed that values0 == 0.
    o  [rq]zinegbin() did not handle the case 'munb = NULL'
        when 'prob' was specified. Thanks to Giuseppe D for
        finding this bug.
    o  acat(), cumulative(), cratio(), propodds(), sratio()
        must have an intercept term.
    o  For vglm.fit(), slot "middle" is now "middle1",
        "fini" is now "fini1", and a new "start1" slot added.
    o  bigamma.mckay() moved into VGAMdata 1.1-9.
    o  nakagami() has a zero = "shape" argument.
    o  [dp]gaitdpois() have more range checking, e.g., for too
        much deflation and inflation.
    o  For more speed, several slow-checking .Rd files
        have been changed by using \dontrun{}.
    o  summary(posbernoulli.tb()) failed to print the confidence
        interval. Thanks to Carl Schwarz for picking this up.
    o  DFLOAT() changed to DBLE() in some .f files.

(mef)