Python/Numpy/Scipy, Solving non-linear least squares, with grouped covariates? -
basically, i'm trying make function happen:
where i'm solving beta. gamma, alpha, , x data.
originally, used summary statistic mean(xi/gamma_i), meant in summation pre-calculated, , present simple np array non-linear optimizer... there's no way pre-calculate summary statistic, it's not clear how beta affect f when f changing in response alpha_i. thus, i'm not sure how go presenting array. possible embed covariates lists (numpy objects) still present numpy array, , unpack list within residual function? going wrong way?
Comments
Post a Comment