TY  - JOUR
AV  - public
TI  - A Study of Panel Logit Model and Adaptive Neuro-Fuzzy Inference System in the Prediction of Financial Distress Periods
Y1  - 2010/04//
KW  - ANFIS
KW  -  Binary logistic regression
KW  -  Financial distress
KW  -  Panel data
UR  - http://eprints.imtlucca.it/1635/
JF  - World Academy of Science, Engineering and Technology
A1  - Giovanis, Eleftherios
SN  - 2010-376X
PB  - World Academy of Science, Engineering and Technology
N2  - The purpose of this paper is to present two different
approaches of financial distress pre-warning models appropriate for risk supervisors, investors and policy makers. We examine a sample of the financial institutions and electronic companies of Taiwan Security Exchange (TSE) market from 2002 through 2008. We present a binary logistic regression with paned data analysis. With the pooled binary logistic regression we build a model including more variables in the regression than with random effects, while the in-sample and out-sample forecasting performance is higher in random effects estimation than in pooled regression. On the other hand we estimate an Adaptive Neuro-Fuzzy Inference System (ANFIS) with Gaussian and Generalized Bell (Gbell) functions and we find that ANFIS outperforms significant Logit regressions in both in-sample and out-of-sample periods, indicating that ANFIS is a
more appropriate tool for financial risk managers and for the economic policy makers in central banks and national statistical services.
SP  - 646
ID  - eprints1635
EP  - 652
VL  - 40
ER  -