Bookmark and Share

Notice: On March 31, it was announced that Statalist is moving from an email list to a forum. The old list will shut down on April 23, and its replacement, is already up and running.

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

Re: st: Setting confidence intervals with -prvalue- after -ologit-

From   Nick Cox <>
Subject   Re: st: Setting confidence intervals with -prvalue- after -ologit-
Date   Thu, 1 Sep 2011 15:39:32 +0100

_pepred in this package insists on integer arguments; that is what
biting. The restriction is documented, but you need to look at the
specific help file. I don't know of any arguments for this except
convention, but you need to ask the authors.


On Thu, Sep 1, 2011 at 3:22 PM, MacLennan, Graeme
<> wrote:
> I am using -prvalue- from -spost- version 9 from (-findit spost-) to get predicted probabilities and differences after using -ologit-.  The command -prvalue- has a -level(#)- option to specify the width of confidence intervals. I wanted to use 97.5% Cis but it would appear that only integer values are accepted? The following syntax tells me that "option level() incorrectly specified" and  "invalid syntax" repectively. If this can be reproduced, I will send off an email to the address in the help file.  (Perhaps there is a good reason, or I am doing something stupid).
> Graeme.
> sysuse auto, clear
> ologit  rep78 price foreign, or level(97.5)
> prvalue, x(foreign=0) level(97.5)
> set level 97.5
> ologit  rep78 price foreign, or
> prvalue, x(foreign=0)

*   For searches and help try:

© Copyright 1996–2015 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   Site index