Hi Steve,
Thanks for the answer, but I was trying to avoid that approach because my
events are either two different alpha regressors or two spike regressors,
and in both cases they are known to fit positively and negatively.
Thanks again,
Jose
> Hi - if you simply want to find out which of 2 EVs fits better then
> you can use a direct contrast between them - i.e. [1 -1] - assuming
> that they are both fitting positively not negatively.
>
> Cheers, Steve.
>
>
>
> On 29 Jun 2006, at 18:52, José Pedro Marques wrote:
>
>> Hi,
>>
>> Can a f-test be used in order to compare the contributions of two EVs
>> which represent very similar models and in this way find which
>> model best
>> fits my data?
>>
>> If so, how should I set up such a test in this case:
>>
>> EV1 1 0
>> -EV1 -1 0
>> EV2 0 1
>> -EV2 0 -1
>>
>> Thanks in advance,
>> Jose
>
>
> ------------------------------------------------------------------------
> ---
> Stephen M. Smith, Professor of Biomedical Engineering
> Associate Director, Oxford University FMRIB Centre
>
> FMRIB, JR Hospital, Headington, Oxford OX3 9DU, UK
> +44 (0) 1865 222726 (fax 222717)
> [log in to unmask] http://www.fmrib.ox.ac.uk/~steve
> ------------------------------------------------------------------------
> ---
>
>
--
José Pedro Marques, PhD
IBILI, Universidade de Coimbra,
PORTUGAL
|