|
From: | marco atzeri |
Subject: | Re: Problems with Statistics package |
Date: | Wed, 30 May 2012 08:58:08 +0200 |
User-agent: | Mozilla/5.0 (Windows NT 6.1; WOW64; rv:12.0) Gecko/20120428 Thunderbird/12.0.1 |
On 5/30/2012 7:56 AM, Hannes wrote:
Hi everyone, I am using the octave statistics package right now, but have some unexpected (possibly bugged) results. I have attached a log that shows the problem. On a perfect grouping, anova produces p-val of 1 instead of 0. The f-statistic being displayed as -94353808874586048.0000 leads me to the conclusion that some internal number limits where exceeded, which is strange, because the example is very simple, the involved numbers very low etc. Could someone help me with that? Thank you very much! Best, Hannes PS: System is: octave:83> version ans = 3.2.4 octave:84> uname ans = { sysname = Linux nodename = research-macpro01 release = 3.2.0-24-generic version = #38-Ubuntu SMP Tue May 1 16:18:50 UTC 2012 machine = x86_64 }
There is an overflow: octave:4> anova(samples,grps) warning: division by zero One-way ANOVA Table: Source of Variation Sum of Squares df Empirical Var ********************************************************* Between Groups 944.4969 1 944.4969 Within Groups 0.0000 159 0.0000 --------------------------------------------------------- Total 944.4969 160 Test Statistic f Inf p-value 0.0000 ans = 0 octave:5> version ans = 3.6.1 octave:6> uname ans = scalar structure containing the fields: sysname = CYGWIN_NT-6.1-WOW64 nodename = MARCOATZERI release = 1.7.16s(0.261/5/3) version = 20120525 17:01:08 machine = i686 with statistics-1.1.0 Regards Marco
[Prev in Thread] | Current Thread | [Next in Thread] |