Variable Selection for Functional Logistic Regression in fMRI Data Analysis
fMRI Veri Analizinde Fonksiyonel Lojistik Regresyon İçin Değişken Seçimi

Nedret BİLLOR, Jessica GODWIN
2015 Turkiye Klinikleri Journal of Biostatistics  
unctional data analysis (FDA) is a relatively new area within the discipline of statistics. Functional data are data that have been measured discretely over a continuum, usually time. Instead of treating the many discrete measurements as individual observations, one makes the assumption that these measurements represent a smooth, underlying Turkiye Klinikleri J Biostat 2015;7(1) 1 Variable Selection for Functional Logistic Regression in fMRI Data Analysis ABS TRACT This study was motivated by
more » ... assification problem in Functional Magnetic Resonance Imaging (fMRI), a noninvasive imaging technique which allows an experimenter to take images of a subject's brain over time. As fMRI studies usually have a small number of subjects and we assume that there is a smooth, underlying curve describing the observations in fMRI data, this results in incredibly high-dimensional datasets that are functional in nature. High dimensionality is one of the biggest problems in statistical analysis of fMRI data. There is also a need for the development of better classification methods. One of the best things about fMRI technique is its noninvasiveness. If statistical classification methods are improved, it could aid the advancement of noninvasive diagnostic techniques for mental illness or even degenerative diseases such as Alzheimer's. In this paper, we develop a variable selection technique, which tackles high dimensionality and correlation problems in fMRI data, based on L 1 regularization-group lasso for the functional logistic regression model where the response is binary and represent two separate classes; the predictors are functional. We assess our method with a simulation study and an application to a real fMRI dataset. Ge liş Ta ri hi/Re ce i ved: 16.01.2015 Ka bul Ta ri hi/Ac cep ted: 11.02.2015 Ya zış ma Ad re si/Cor res pon den ce:
doi:10.5336/biostatic.2015-43642 fatcat:3dwauorg7zbiha4fcxqf7h7jpi