Date:         Tue, 8 Apr 1997 12:02:04 -0400
Reply-To:     "William B. Ware" <wbware@EMAIL.UNC.EDU>
Sender:       "SPSSX(r) Discussion" <SPSSX-L@UGA.CC.UGA.EDU>
From:         "William B. Ware" <wbware@EMAIL.UNC.EDU>
Subject:      Re: t from p
Comments: To: "David A. Rowe" <darowe@FRANK.MTSU.EDU>
In-Reply-To:  <97Apr8.094643-0400_edt.1042-129314+50@email.unc.edu>
Content-Type: TEXT/PLAIN; charset=US-ASCII

On Tue, 8 Apr 1997, David A. Rowe wrote:
 
> Does anyone know the formula to calculate t from a given p and df? I
> recently saw a posting of the formula for obtaining the p for a given t
> and given df, but I need to do the opposite: calculate the critical t for
> a given, atypical critical/nominal p like .0167 - when using Bonferroni
> adjustments (I have tables for Dunn-Bonferroni, but would like the formula
> also). Thanks in advance.
 
Given that you posted to SPSSX-L, I assume that you would prefer to use
SPSS.  You can get the critical values using a function.  For the two
tailed critical value of t at the .05 level, request
 
idf.t(.975, df)
 
You can do this from the interface by going
 
Transform
        Compute
                Name the target variable, find the function that you want,
                move it up to the expression, and supply the values you
                want.
 
If you have access to EXCEL, you can get the two tailed values by entering
 
=tinv(.05,df) in a cell.
 
______________________________________________________________________________
 
William B. Ware, Professor and Chair                   Educational Psychology
CB# 3500                                               EMAIL:   wbware@unc.edu
University of North Carolina                           PHONE:   (919)-966-5266
Chapel Hill, NC      27599-3500                        FAX:     (919)-962-1533
 
URL:http://www.unc.edu/~wbware/
______________________________________________________________________________