Model selection with Gini indices under auto-calibration
نویسندگان
چکیده
The Gini index does not give a strictly consistent scoring function. Therefore, simply maximizing the may lead to wrong model choice. main issue is that rank-based score calibration-sensitive. We show allows for if we restrict it class of auto-calibrated regression models. That is, on models know true maximizes index.
منابع مشابه
Multidimensional Generalized Gini Indices
The axioms used to characterize the generalized Gini social evaluation orderings for one-dimensional distributions are extended to the multidimensional attributes case. A social evaluation ordering is shown to have a two-stage aggregation representation if these axioms and a separability assumption are satisfied. In the first stage, the distributions of each attribute are aggregated using gener...
متن کاملFlexible Calibration: Minimal Cases for Auto-Calibration
This paper deals with the concept of auto-calibration, i.e. methods to calibrate a camera on-line. In particular, we deal with minimal conditions on the intrinsic parameters needed to make a Euclidean reconstruction, called flexible calibration. The main theoretical results are that it is only needed to know that one intrinsic parameter is constant. The method is based on an initial projective ...
متن کاملAn Introduction to Hybrid Model Inventory Control with a Green Supplier Selection Model under Uncertainty
In the current decade, determining the most appropriate supplier as a strategic factor in the supply chain has attracted lots of consideration. On the other hand, organizations do necessary measures to implement green supply chain management in order to improve environmental and economic performance. An important way to implement green supply chain management, could be revising the method of pu...
متن کاملAsymptotic and Bootstrap Inference for the Generalized Gini Indices
The Gini index represents a special case of the generalized Gini indices, which permit to choose a level of inequality aversion and to stress the different proportions of the income distribution. In order to apply these indices to income sample data, it is necessary to use reliable inferential procedures. In fact, also if often in income studies we have large samples for which the precision of ...
متن کاملSelection using Gini Measure of Income Inequality
A variety of measures are used to compare income inequalities, many of which have been derived from Lorenz curve. However, classical Gini coefficient and its variations are probably the most commonly used measures of income inequality. They are considered as the best measures by many scientists, but it is also recognized that the choice of age-grouping affects the Gini measures (Formby, et al. ...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: European Actuarial Journal
سال: 2023
ISSN: ['2190-9733', '2190-9741']
DOI: https://doi.org/10.1007/s13385-022-00339-9