How to do partial least squares in market research?

Partial Least Squares Regression is an addition of multiple linear regression models. In its simplest form, a linear model details of the linear relationship between a dependent variable (response) variable Y and a set of predictor variables, X, so

Y = a0 + a2x2 + ... + a1X1 + apXp

In this equation,  

For the intercept, a0 is the regression coefficient and the values ​​of ai are the regression coefficients of the variables over a p calculated from the data.

For example, 

You could approximate the height of a person based on the person's weight and gender. You can also use linear regression to predict the corresponding regression coefficients from a data sample, which can measure the height, weight, gender and observation of subjects.