Search results for "SAMPLE SELECTION"
showing 4 items of 14 documents
Corruption-Related Disclosure in the Banking Industry: Evidence From GIPSI Countries
2022
This paper empirically investigates corruption-related disclosure in the banking industry, aiming to identify the most relevant theories which explain why financial institutions disclose corruption-related information to the public in their annual financial reports.Using a total sample of 88 banks from the GIPSI countries during the period 2011-2019, our results reveal that, on average, banks involved in corruption issues disclose less on corruption-related information than banks not involved in any corruption scandal. Moreover, banks not involved in corruption cases disclose even more information after other banks’ corruption events become public. These basic relationships, however, are sh…
A genetic algorithm approach to purify the classifier training labels for the analysis of remote sensing imagery
2017
This paper proposes a Genetic Algorithm (GA) approach to clean a given classifier training set for remote sensing image analysis. Starting from an initial set of training data, the new method called GA-Training Label Purifying (GA-TLP) consists of the significant training sample selection using GAs in order to maximize the classifier accuracy. This means to retain the most informative samples and to remove the uncertain, redundant, and misclassified ones. As a result of the selection process, we can obtain a purified training set. The proposed model is implemented and evaluated using a LANDSAT 7 ETM+ image. The experimental results confirm the effectiveness of the proposed approach.
Optimization criteria in sample selection step of local regression for quantitative analysis of large soil NIRS database
2012
International audience; Large soil spectral libraries compiling thousands of NIR (Near Infrared) reflectance spectra have been created encompassing a wide diversity and heterogeneity of spectra. Among the many chemometric approaches to the calibration of chemical and physical properties from these large libraries, local calibrations have the advantage of being able to select the most similar spectra to the spectrum of a target sample. This is particularly relevant when dealing with highly heterogeneous media such as soils, where the mineral matrix has a strong influence on spectral features. A crucial step in the implementation of local calibration procedures is the construction of local ne…
Estimating regional differences in returns to education when schooling and location are determined endogenously
2010
While the growing supply of university skills is known to have agglomerated towards the large centers in Finland, there is no research knowledge available on the development of regional demands. This paper attempts to fill this gap by analyzing regional variation in the private-sector return to university education in Finland for the period 1970 - 2004. In the analysis, we focus on studying 1) whether there are differences in the return to university between different region types, and 2) to what extent can these differences - if they exist - be explained by differences in regional skill supply and unemployment. For the econometric analysis, we use a large register-based dataset constructed…