Bio-Rad Image Lab™ Software - Manual (Page 93)

Regression Methods
User Guide | 93
Regression Methods
A regression method is used to calculate the molecular weight of the unknown
bands. The software uses the relative front and molecular weight values of the
standard bands to calculate the standard curve. This standard curve is then used to
calculate the values of the unknown bands. The shape of the standard curve is
based on the selected regression method. Choose one of the four regression
methods listed in Table 3 .
Linear (semilog) 2
Point-to-point (semilog) 2
Logistic 5
Cubic spline 5
If you do not have enough data points for the selected method, the molecular
weight of the unknown bands is not calculated.
You can check how well each regression method fits the data in the standard curve
window (see Standard Curve on page 112 for more information). The linear (semilog)
regression method provides a measurement that describes how well the standard
curve fits the data R
2
value. The closer the R
2
value is to 1.0, the better the data fit
the standard curve.
The molecular weight of each band is displayed in the Mol. Wt./Base Pair column in
the analysis table. See Molecular Weight (MW) Analysis Tools on page 131 for more
information about molecular weight.
For information about the calculations behind the regression methods, see
Appendix G, Regression Calculation Methods .
Table 3. Methods of generating a standard curve
Regression Method Minimum number
of standard bands