[BioC] dif between toptable and topTable

[Mark Robinson]

Sebastien.

Yes, it is right.  Have a look at the code for the two functions ...  
different defaults ... specifically with respect to what parameters  
those p-values (and t/F statistics) are calculated on.

In fact, you'll notice that 'topTable' can call 'toptable'.

M.


On 16/01/2008, at 4:09 PM, Sebastien Gerega wrote:

> Hi,
> I can see in the topTable documentation that "|toptable| is an earlier
> interface and is
> retained only for backward compatibility." However, if this is the  
> case
> I would have
> thought I would get the same results with both methods. Instead  
> this is
> what I get
> with topTable
>                ID p.s.X.n.s.X        t        F      P.Value     
> adj.P.Val
> 10878 201429_s_at -0.10536776 14.17887 42456.21 5.325611e-29  
> 9.481334e-26
> 18250 208834_x_at -0.01423163 14.00786 41650.35 6.079627e-29  
> 9.481334e-26
> 22094 212788_x_at  0.01454676 14.20958 41614.89 6.115511e-29  
> 9.481334e-26
> 18241 208825_x_at -0.02691777 14.00615 41546.70 6.185202e-29  
> 9.481334e-26
>
> and this is what I get using toptable
>           logFC        t      P.Value    adj.P.Val        B
> 36960 13.278474 55.61688 1.183004e-17 6.468076e-13 28.81054
> 32762  9.208360 49.09926 6.570132e-17 1.284238e-12 27.66241
> 54191 10.949433 47.88478 9.270056e-17 1.284238e-12 27.41920
> 14250  7.630690 47.83800 9.395430e-17 1.284238e-12 27.40963
>
> the p-values are different as are the columns provided.
> Is this right, and if so why is it the case?
> thanks,
> Sebastien
>
> _______________________________________________
> Bioconductor mailing list
> Bioconductor at stat.math.ethz.ch
> https://stat.ethz.ch/mailman/listinfo/bioconductor
> Search the archives: http://news.gmane.org/ 
> gmane.science.biology.informatics.conductor