Question: You are in a remote location and need to solve an ordinary least-squares problem with a large number of explanatory variables. You have access only to a computer programfor solving linear programming problems. Would you be able to solve your least-squares problem? Explain. (Your problem is to estimate the vector of parameters β and the vector of residuals u in the following statistical linear model:
y = Xβ + u
where X is a (N × K) matrix of pre determined regressors, β is a (K × 1) vector of unknown coefficients, y is a (N × 1) vector of realizations of the random variable Y, and u is a vector of random errors with zero mean and fixed variance.