1d:T566,# Estimate parameters of linear regression model with compositional covariates using method suggested by Pixu shi. The model uses scaled lasoo approach for model selection. ```r classo(Xt, y, C, we = NULL, type = 1, control = list()) ``` ## Arguments - `Xt`: CLR transformed predictor matrix. - `y`: model response vector - `C`: sub-compositional matrix - `we`: specify weight of model parameter - `type`: 1/2 for l1 / l2 loss in the model - `control`: a list of internal parameters controlling the model fitting ## Returns - **beta**: model parameter estimate ## Examples ```r library(robregcc) library(magrittr) data(simulate_robregcc) X <- simulate_robregcc$X; y <- simulate_robregcc$y C <- simulate_robregcc$C n <- nrow(X); p <- ncol(X); k <- nrow(C) # Predictor transformation due to compositional constraint: Xt <- cbind(1,X) # accounting for intercept in predictor C <- cbind(0,C) # accounting for intercept in constraint bw <- c(0,rep(1,p)) # weight matrix to not penalize intercept # Non-robust regression, [Pixu Shi 2016] control <- robregcc_option(maxiter = 5000, tol = 1e-7, lminfac = 1e-12) fit.nr <- classo(Xt, y, C, we = bw, type = 1, control = control) ``` ## References Shi, P., Zhang, A. and Li, H., 2016. **Regression analysis for microbiome compositional data. The Annals of Applied Statistics**, 10(2), pp.1019-1040.1e:T49a,M7.49933 0.25C3.49635 0.25 0.25 3.49593 0.25 7.50024C0.25 10.703 2.32715 13.4206 5.2081 14.3797C5.57084 14.446 5.70302 14.2222 5.70302 14.0299C5.70302 13.8576 5.69679 13.4019 5.69323 12.797C3.67661 13.235 3.25112 11.825 3.25112 11.825C2.92132 10.9874 2.44599 10.7644 2.44599 10.7644C1.78773 10.3149 2.49584 10.3238 2.49584 10.3238C3.22353 10.375 3.60629 11.0711 3.60629 11.0711C4.25298 12.1788 5.30335 11.8588 5.71638 11.6732C5.78225 11.205 5.96962 10.8854 6.17658 10.7043C4.56675 10.5209 2.87415 9.89918 2.87415 7.12104C2.87415 6.32925 3.15677 5.68257 3.62053 5.17563C3.54576 4.99226 3.29697 4.25521 3.69174 3.25691C3.69174 3.25691 4.30015 3.06196 5

classo function