Study on how to elevate the discriminating ability of the discriminating model of the financial statement fraud

By summarizing the factor of the financial statement fraud in existing research outcome, the paper confirms the discriminating characteristic of the financial statement fraud and sets up a theoretic model to discriminate the financial statement fraud. Using radial basis function neural network, regarding to the swatch that the listed company that is punished by the Securities Regulatory Commission or the Ministry of Finance, and according to the clustering elements, validating across by set one aside, the paper verifies respectively the 22 characteristics and 31 characteristics of discriminating model. According to the clustering elements, validating across by set one aside, the paper verifies respectively the 31 characteristics and 8 characteristics selected by Fisher-ratio of discriminating model. The research outcome indicates the discriminating ability of the model including 8 characteristics is better elevated than the traditional model including 31 characteristics by comparing the disciplinary error and the forecast precision.

Cultivar Selection and Test Site Evaluation of Cotton Regional Trials in Jiangsu Province Based on GGE Biplot

This study was to evaluate the high yielding and stability of candidate cultivars, depict the adaptive planting region, analyze trial location discrim-ination ability and representativeness, as wel as identify the ideal cultivar and trial location, with the aim to provide theory background for cultivar selection and rea-sonable scheme of test location in Jiangsu Province. [Method] The GGE biplot method was used to analyze the lint cotton yield of 12 experimental genotypes in the 6 test locations （three replicates in each） of the cotton regional trial in Jiangsu Province in 2013. [Result] The effects of genotype （G）, environment （E）, and geno-type by environment interaction （G＆#215;E） on lint cotton yield were al highly significant （P〈0.01）, which made it necessary to further explore the specific pattern of geno-type by environment interaction. Jinmian118 （G4） and SF3303 （G5） were the best ideal genotypes screened by the ＂ideal cultivar＂ and ＂ideal location＂ view of GGE biplot, and the ordination of test sites based on the ideal index were in the order of Dafeng （DF）, Yanliang （YL）, Liuhe （LH）, Dongtai （DT）, Yancheng （YC）, and Nantong （NT）, among which NT was relatively weak in representing of the whole target cot-ton planting region in Jiangsu Province. The ＂similarity among locations＂ view of GGE biplot clustered al trial locations into one group, showing that the test sites in the cotton planting region in Jiangsu Province were in the same mega-environment. The ＂which-won-where＂ view of GGE biplot indicated that cotton cultivar Jinmian118 （G4） was the most appropriate cultivar in the homogeneous cotton planting region in Jiangsu Province. [Conclusion] Among the candidate cultivars, Jinmian118 and SF3303 were identified as the most ideal cultivars in this set of conventional cotton regional trial in Jiangsu Province; the test site of Dafeng ranked the first out of al locations in terms of discrimination and representativeness, and al test locations were clustered into the same mega-environmet, which indicated the high efficiency of cultivar selection in the cotton regional trial in Jiangsu Province.