Abstract
In this paper the \(\gamma \)–order Generalized Fisher’s entropy type Information measure (\(\gamma \)–GFI) is adopted as a criterion for the selection of the best Logit model. Thus the appropriate Relative Risk model can be evaluated through an algorithm. The case of the entropy power is also discussed as such a criterion. Analysis of a real breast cancer data set is conducted to demonstrate the proposed algorithm, while algorithm’s realizations, through MATLAB scripts, are cited in Appendix.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Burnham, K.P., Anderson, D.R.: Kullback-Leibler information as a basis for strong inference in ecological studies. Wild Life Res. 28, 111–119 (2001)
Cover, T.M., Thomas, J.A.: Elements of Information Theory, 2nd edn. Wiley, Hoboken (2006)
Dippon, J., Fritz, P., Kohler, M.: A statistical approach to case based reasoning, with application to breast cancer data. Comp. Stat. Data Anal. 40, 579–602 (2002)
Edler, L., Kitsos, C.P.: Recent Advances in Qualitative Methods in Cancer and Human Health Risk Assessment. Wiley, Chichester (2005)
Feigelson, S.H., McKean-Cowdlin, R., Henderson, E.B.: Concerning the CYP17 MspA1 polymorphism and breast cancer risk: a meta-analysis. Mutagenesis 17, 445–446 (2002)
Ferentinos, K., Papaioannou, T.: New parametric measures of information. Inf. Control 51, 193–208 (1981)
Finney, D.J.: Statistical Method in Biological Assay. Hafner, New York (1952)
Ford, I., Kitsos, C.P., Titterington, D.M.: Recent advances in nonlinear experimental design. Technometrics 31, 49–60 (1989)
Huang, C.S., Chern, H.D., Chang, K.J., Cheng, C.W., Hsu, S.M., Shen, C.Y.: Breast risk cancer associated with genotype polymorphism of the estrogen-metabolizing CYP17, CYP1A1 and COMT—a multigenic study on cancer susceptibility. Cancer Res. 59, 4870–4875 (1999)
Jaynes, E.T.: Information theory and statistical mechanics. Phys. Rev. 106, 620–630 (1957)
Kitsos, C.P., Toulias, T.L.: A min-max entropy algorithm for relative risk problems. Submitted
Kitsos, C.P., Toulias, T.L.: On the information matrix of the truncated cosinor model. Br. J. Math. Comput. Sci. 3(3) (2013)
Kitsos, C.P.: On the logit methods for Ca problems. In: Statistical Methods for Biomedical and Technical Systems, pp. 335–340. Limassol, Cyprus (2006)
Kitsos, C.P.: The Ca risk assessment as a bioassay. In: 55th Session of the International Statistical Institute. Sydney (2005)
Kitsos, C.P., Tavoularis, N.K.: Logarithmic Sobolev inequalities for information measures. IEEE Trans. Inf. Theory 55(6), 2554–2561 (2009)
Kitsos, C.P.: Estimating the relative risk for breast cancer. Biom. Lett. 47(2), 133–146 (2010)
Kitsos, C.P., Toulias, T.L.: New information measures for the generalized normal distribution. Information 1, 13–27 (2010)
Kitsos, C.P.: Invariant canonical form for the multiple logistic regression. Math. Eng. Sci. Aerosp. (MESA) 38(1), 267–275 (2011)
Kitsos, C.P.: Cancer Bioassays: A Statistical Approach. LAMBERT Academic Publishing, Saarbrucken (2012)
Kitsos, C.P., Toulias, T.L.: Bounds for the generalized entropy type information measure. J. Commun. Comput. 9(1), 56–64 (2012)
Kitsos, C.P., Toulias, T.L., Trandafir, C.P.: On the multivariate \(\gamma \)-ordered normal distribution. Far East J. Theor. Stat. 38(1), 49–73 (2012)
Soofi, E.S.: Principal information approaches. J. Am. Stat. Assoc. 95(452), 4352–4374 (2007)
Zarikas, V., Gikas, V., Kitsos, C.P.: Evaluation of the optimal design “cosinor model” for enhancing the potential of robotic theodolite kinematic observations. Measurement 43(10), 1416–1424 (2010)
Acknowledgments
The authors would like to thank the referees who improved the language as well as the content of this paper, with their valuable comments.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Appendices
Appendix 1
A study on the min–max behavior of the generalized entropy power \(\mathrm N_\delta (X_\gamma )\) applied on a \(\gamma \)-order normally distributed random variable is given below.
Let \(X_\gamma \in {\fancyscript{N}}^p_\gamma (\mu ,{\Sigma })\). For \(\delta > 1\), numerically can be verified (see Fig. 1) that,
The dual case hold for \(\delta < 0\) (\(\max /\min \) reversion). Moreover, for \(|\det {\Sigma }| \le 1\), see also Fig. 3, the following holds:
For \(|\det {\Sigma }| \ge 1\), Fig. 3, we have
Appendix 2
A study on the min–max behavior of \(\mathrm N_\delta (X_{j;\gamma })\) and \(\mathrm J_\delta (X_{j;\gamma })\) applied on the \(\gamma \)-order normally distributed risk variables \(X_{j,\gamma }\), \(j = 1,2,\dots ,5\) is given below.
Figure 4, verifies that
i.e. the \(\max _{\gamma > 1}\mathrm N_\delta (X_{j;\gamma })\) corresponds, for \(\delta > 1\), to the usual Normal distribution, and therefore,
with \(m_j\) as in Table 3. Moreover, the \(\max _{\gamma > 1}\mathrm N_\delta (X_{j;\gamma })\) for \(\delta < 0\) corresponds to the usual Laplace distribution, i.e.
while for \(\delta > 1\), through (23) with \(\frac{\gamma -1}{\gamma }\rightarrow 1\), is given by
with \(m^*_j\) as in Table 6 (compared with Table 3).
For the \(\delta \)–GFI, we have that \(\mathrm J_\delta (X_\gamma )\) is a monotone function of \(\delta \ge \gamma (1.4628-1)+1\) for all \(X_\gamma \sim {\fancyscript{N}}_{\gamma \ge 1}(\mu ,1)\), see proof of Proposition 3.1 in [20]. Thus \(\mathrm J_\delta (X_\gamma )\) is an increasing function of \(\delta \ge 2\). Therefore,
The above relation holds for \(X_\gamma \sim {\fancyscript{N}}_{\gamma \ge 1}(\mu ,\sigma ^2)\), due to (16), assuming \(\sigma \ge 1\), and hence
Through (23) we have
Numerically we can derive that (see Table 6)
Appendix 3
Appendix 3.1. MATLAB script for the evaluations of Table 3. The 5th column of the Data matrix correspond to the data for Age, COMT, CYP17, Menarche and Menopause risk variables, while the b0 and b1 arrays contain the coefficients from Table 2.
Appendix 3.2. MATLAB script for the evaluations of Table 4. Array s2 and variable k are defined in the previous script.
Appendix 3.3. MATLAB script for the evaluations of Table 5. Array V and MATLAB function Var are defined in the previous script.
Rights and permissions
Copyright information
© 2015 Springer International Publishing Switzerland
About this paper
Cite this paper
Kitsos, C.P., Toulias, T.L. (2015). Generalized Information Criteria for the Best Logit Model. In: Kitsos, C., Oliveira, T., Rigas, A., Gulati, S. (eds) Theory and Practice of Risk Assessment. Springer Proceedings in Mathematics & Statistics, vol 136. Springer, Cham. https://doi.org/10.1007/978-3-319-18029-8_1
Download citation
DOI: https://doi.org/10.1007/978-3-319-18029-8_1
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-18028-1
Online ISBN: 978-3-319-18029-8
eBook Packages: Mathematics and StatisticsMathematics and Statistics (R0)