Protein multiple regression modeling

Use of multiple regression techniques in the study of functional properties of food proteins is not new I76) Most food scientists have some familiarity with basic statistical concepts and some access to competent statistical advice. At least one good basic text on statistical modelling for biological scientists exists (7 ). A number of more advanced texts covering use of regression in modelling are available (, ). ... 

Preparation of Standards and Curves In the absence of a true blank control matrix, standards can be prepared in a protein buffer at multiple (generally 9 11) concentrations for the initial test of assay range. For method validation and sample assay, 6 8 nonzero concentrations of standards plus anchor points should be used to define a curvilinear standard curve. If a commercial kit is to be used, it is preferred that the standards be prepared from a bulk reference material to assure the consistencies of the standard as well as adding enough standard points to properly define the regression model. Before replacing the kit standards with those prepared... 

In total, = 30 calibration samples are available. The NIR spectrum of one sample is given in Figure 6.8. We will use the inverse calibration method (cf. Eq. (6.81)), that is, according to the general equation of multiple regression (Eq. (6.41)), the protein content is arranged in the y vector and the matrix X contains the NIR spectra. In order to keep the calibration model small, only the five most... 

Multiple r2 values of 0.9346 and 0.9280 were obtained for these equations of capacity and stability, respectively. The relative importance of each respective partial regression coefficient was determined by comparison of B values (32). These evaluations indicate that the most important variables in the two models for foam capacity and stability are soluble protein, soluble and insoluble carbohydrate and ash, and insoluble fiber. 

Another intricacy in the complicated application of NIR technology to grains and seeds is that, because of inclusion of several major constituents in their makeup, wavelengths selected during model development do not necessarily conform to the absorbers of the constituents for which the models are developed. Table 7.1.7 shows the wavelengths selected by multiple linear regression (MLR) for prediction of moisture in maize, oil in canola seed, and protein content in wheat and lentil. 

---