This should work...

Key note that this takes into account 'bias'. Bias is basically defined to be used to determine
whether the input set is complete or a sampling, and has to do with the accuracy of the information.
If the input set is a complete list of values (a popluation), set Bias = 0. If it is a sample from a
larger set, set it to Bias = 1.


;* ************************************************************
;*  FUNCTION STDDEV ( Values, Bias )
;*      Values - DynArray of values to use
;*      Bias - value determining if this is a
;*              sampling, or full set
;*
;*      - Calculates standard deviation from a set
;*          of values.  Returns the standard deviation
;*
;*  Written by Dave Meeks, February 2004
;* ************************************************************
FUNCTION STDDEV( Values, Bias )

    ;* Error checking, just assure we have either 0 or 1
    IF Bias NE 0 THEN
        Bias = 1
    END

    ;* Get sum and mean
    NumValues = DCOUNT( Values, @FM )
    SumValues = SUM( Values )
    Mean      = SumValues/NumValues
    Variance  = 0

    ;* get variance
    FOR I = 1 TO NumValues
        Variance = Variance + PWR(Values<I>-Mean,2)
    NEXT I

    ;* get standard deviation
    StdDev = SQRT( Variance / ( NumValues - Bias ) )
    RETURN( StdDev )
    END



At 08:35 AM 2/9/2004 -0500, you wrote:
Is there a Universe Basic command to calculate standard deviation?  If not,
does anyone have a sub?

======================================================================== David T. Meeks || "All my life I'm taken by surprise Architect, Technology Office || I'm someone's waste of time Ascential Software || Now I walk a balanced line [EMAIL PROTECTED] || and step into tomorrow" - IQ ======================================================================== -- u2-users mailing list [EMAIL PROTECTED] http://www.oliver.com/mailman/listinfo/u2-users

Reply via email to