Page 205 - Contributed Paper Session (CPS) - Volume 4

CPS2174 Septian R. et al.
4. Conclusion
It can be concluded that the logistic model averaging using randomized
approach for cunstructing the model candidate seems to be good alternative
in prediction case of high dimensional data of tumor class of patients. Based
on the 100 replication of modeling process, the method has good
performance when the number of predictor variables in model candidate (m)
is 50. It is indicated from the mean, standard deviation, and also number of
replication which has very good prediction based on accuracy, sensitivity, and
specificity value.

References
1. Perrone MP. 1993. Improving Regression Estimation: Averaging Methods
for Variance Reduction with Extensions to General Convex Measure
Optimization [dissertation]. Providence(US): Brown University.
2. Rahardiantoro S, Sartono B, Kurnia A. 2017. Model Averaging for
Predicting the Exposure to Aflatoxin B1 Using DNA Methylation in White
Blood Cells of Infants. IOP Conf. Series: Earth and Environmental Science.
58 (2017) 012019.
3. Ghosh D, Yuan Z. 2009. An Improved Model Averaging Scheme for
Logistic Regression. J Multivar Anal. 100(8): 1670–1681.
4. The Cancer Genome Atlas Research Network, Weinstein JH, Collisson EA,
Mills GB, Shaw KRM, Ozenberger BA, Ellrott K, Shmulevich I, Sander C,
Stuart JM. 2013. The Cancer Genome Atlas Pan-Cancer Analysis Project.
Nature Genetics 45, no. 10 (September 26, 2013): 1113-1120.
5. Ando T, Li KC. 2014. A Model-Averaging Approach for High-Dimensional
Regression, Journal of the American Statistical Association. 194: 254-265.
6. Claeskens G, Hjort NL. 2008. Model Selection and Model Averaging. New
York (US): Cambridge University Press.
7. Kuhn M. 2008. Building Predictive Models in R Using The caret Package,
Journal of Statistical Software.

194 | I S I W S C 2 0 1 9