Calculating the sum of individual squared deviations in SAS - statistics

Question

I'm trying to calculate the individual squared deviations to perform some calculations based on these values.
I have the following dataset:
data have;
input testid $ level $ values;
datalines;
HITT1D LC1 0.45
HITT1D LC1 0.49
HITT1D LC1 0.47
HITT1D LC2 0.43
HITT1D LC2 0.39
HITT1D LC2 0.42
HITT1D LC3 0.66
HITT1D LC3 0.63
HITT1D LC3 0.64
HBEF5D LC1 0.45
HBEF5D LC1 0.49
HBEF5D LC1 0.47
HBEF5D LC2 0.43
HBEF5D LC2 0.39
HBEF5D LC2 0.42
HBEF5D LC3 0.66
HBEF5D LC3 0.63
HBEF5D LC3 0.64
;
run;
I need to calculate:
the sum of all individual squared deviations for each combination of testid and level
and the sum of of all individual squared deviations for each testid
I used the following to calculate the average for a given testid and level:
proc means data=have ;
var values;
class testid level;
output out=class_stats mean = /autoname ;
run;
to subtract from the observations in order to replicate the following example:
in which "LOT" is equivalent to the level in the data and "subject" is equivalent to testid.
I have looked into the examples given here:
Calculate mean and std of a variable, in a datastep in SAS
but I can not replicate them as these data only has one class.
unfortunately, I can not find an easy way of doing this as I am an R user and I'm new to SAS. does anyone has a cleaver idea on how to do this in a simple way in SAS?
thanks

Answer 1

Sounds like you are asking for the CSS statistic.
Example:
proc means data=have css ;
class testid level ;
types testid testid*level ;
var values;
run;
Results:
The MEANS Procedure
Analysis Variable : values
N
testid Obs Corrected SS
-------------------------------
HBEF5D 9 0.0882889
HITT1D 9 0.0882889
-------------------------------
Analysis Variable : values
N
testid level Obs Corrected SS
-------------------------------------------
HBEF5D LC1 3 0.000800000
LC2 3 0.000866667
LC3 3 0.000466667
HITT1D LC1 3 0.000800000
LC2 3 0.000866667
LC3 3 0.000466667
-------------------------------------------