Robustness of Linear Mixed Models (LMM) with random effects is investigated with the forward search (FS). Extending the FS to LMM offers new computational challenges, as some restrictions, imposed by the model and their estimates, are required. The method is illustrated by an application to real data where exports of coffee to European Union are analyzed to identify outliers that might be linked to potential frauds. An additional short simulation is presented to strengthen the usefulness of the proposed method.
Robust diagnostics for Linear Mixed Models with the forward search / Corbellini, Aldo; Grossi, Luigi; Laurini, Fabrizio. - (2022), pp. 79-86.
Robust diagnostics for Linear Mixed Models with the forward search
corbellini aldo;grossi luigi;laurini fabrizio
2022-01-01
Abstract
Robustness of Linear Mixed Models (LMM) with random effects is investigated with the forward search (FS). Extending the FS to LMM offers new computational challenges, as some restrictions, imposed by the model and their estimates, are required. The method is illustrated by an application to real data where exports of coffee to European Union are analyzed to identify outliers that might be linked to potential frauds. An additional short simulation is presented to strengthen the usefulness of the proposed method.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
