BUCHI NIRCal - Manual (Page 154)

NIRCal 5.5 Software Manual
154 NIRCal 5.5 Manual, Version A
Property statistics
Row
Name Description
84 C-Set BIAS Always zero by definition.
85 V-Set BIAS Average deviation between the predicted = NIR and original = lab
method values. Should be as close to zero as possible (no
systematic deviation).
86 C-Set SEE (SEC) Standard error of estimation of the C-Set. Should be as small as
possible, but comparable to the standard deviation of the
laboratory method.
87 V-Set SEE (SEP) Standard error of prediction of the V-Set. Should be as small as
possible, but comparable to the standard deviation of the labor
method.
88 Consistency Relation between the standard error of estimation of C- and V-
Set: SEC/SEP * 100.
Should be around 100 (80-110).
90 C-Set Regression
Coefficient "r" shows, how well the predicted values of C-Set match the
original values on average. Should be as close to 1 as possible (r
> 0.9). NOTE:r is not r^2 (r-square), r can also be nagative.
91 V-Set Regression
Coefficient "r" shows, how well the predicted values of V-Set match the
original values on average. Should be as close to 1 as possible (r
> 0.9)
92 C-Set Regression
Intercept r= a + bx, where "a"= intercept of the C-Set. Should be as close to
0 as possible
93 V-Set Regression
Intercept r= a + bx, where "a"= intercept of the V-Set. Should be as close to
0 as possible
94 C-Set Regression Slope r= a + bx, where "b"= slope of the C-Set. Should be as close to 1
as possible