[R] OrdFacReg

Peter Ehlers ehlers at ucalgary.ca
Wed Feb 10 11:52:14 CET 2010


Andrew,

I've never used OrdFacReg, but a glance at the documentation
suggests that you may have to pass your data through
prepareData() first. Suggestions:

1. run the example in the docs and see if you can
understand the bits and pieces;

2. is NB an ordered factor or is it just an integer vector?
use str();

3. must NB reside in a matrix?

  -Peter Ehlers

Andrew Kosydar wrote:
> Hi Dennis,
> 
> Thank you for your response.  No, NB is not a matrix, and I have no 
> covariates.  Here's a very small sample of the data:
> 
> effect    NB
>  -0.003200    1
>  -0.120800    3
>  -0.003200    2
>  -7.690000    1
>  -1.442100    2
>  -0.000900    1
>  -0.014200    3
>  -5.015000    0
>  -0.001400    2
>  -0.008000    3
>  -2.337000    2
>  -0.004050    1
>  -0.101400    1
>  -0.002100    0
>  -0.003600    2
>  -0.002400    3
>  -1.123000    1
>  -0.000600    2
> 
> I am purely interested in whether an increase in "NB" (for ex: from 0 to 
> 1, or 3 to 4) predicts a directional change with "effect".
> 
> Any advise is greatly appreciated.
> 
> Many thanks,
> 
> Andrew
> 
> 
> 
> 
> 
> 
> 
>>
>> On Tue, 9 Feb 2010, Dennis Murphy wrote:
>>
>>> Is NB a matrix? See the help page; you also have to specify which
>>> covariate(s)
>>> are ordinal.
>>>
>>> HTH,
>>> Dennis
>>>
>>> On Tue, Feb 9, 2010 at 5:53 PM, Andrew Kosydar
>>> <drewdogy at u.washington.edu> wrote:
>>>       Hello All,
>>>
>>>       I have a dataset with a continuous response variable and
>>>       an ordered factor predictor.  I am very interested in
>>>       using the package OrdFacReg to run my analysis, but I am
>>>       having a difficult time deciphering the code and making
>>>       it work for my dataset.  Given that this is a new
>>>       package, I was unable to find any posts regarding
>>>       OrdFacReg or examples to use as a template.  Normally, I
>>>       would run the analysis as an anova with the following
>>>       code:
>>>
>>>
>>>       NB.aov<-aov(effect~NB, data=LH.df)
>>>
>>>
>>>       To give you some background, "effect" is a continuous
>>>       variable and "NB" is ordered 0, 1, 2, 3, 4.  I tried
>>>       each of following code to no avail:
>>>
>>>       ordFacReg(effect, NB)
>>>       ordFacReg(effect, NB, ordering="i", type="LS")
>>>       ordFacReg(effect, NB, fact, ordfact, ordering="i",
>>>       type="LS", intercept)
>>>
>>>
>>>
>>>       I truly appreciate any insights or suggestions on how to
>>>       best structure the code in order to perform an analysis
>>>       with ordFacReg.
>>>
>>>       Most Respectfully,
>>>
>>>       Andrew
>>>
>>>
>>>
>>>
>>>       Andrew Kosydar
>>>       University of Washington
>>>       Department of Biology
>>>       24 Kincaid Hall, Box 351800
>>>       Seattle, WA 98195
>>>       USA
>>>
>>>       ______________________________________________
>>>       R-help at r-project.org mailing list
>>>       https://stat.ethz.ch/mailman/listinfo/r-help
>>>       PLEASE do read the posting guide
>>>       http://www.R-project.org/posting-guide.html
>>>       and provide commented, minimal, self-contained,
>>>       reproducible code.
>>>
>>>
>>>
>>>
>>
> 
> ------------------------------------------------------------------------
> 
> ______________________________________________
> R-help at r-project.org mailing list
> https://stat.ethz.ch/mailman/listinfo/r-help
> PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
> and provide commented, minimal, self-contained, reproducible code.

-- 
Peter Ehlers
University of Calgary



More information about the R-help mailing list