American Statistical Association New York City Metropolitan Area Chapter New York State Psychiatric Institute at Columbia University Medical Center Biostatistics Seminar

We introduce an approach for estimating the coefficient function in the functional linear model with scalar responses and functional predictors (e.g., curves, spectra, or images). The problem is transformed to a variable selection problem by transformation into the wavelet domain, taking advantage of the sparse representation allowed by wavelet bases. When the number of measurement points is much larger than the number of samples, we reduce the dimensionality by applying a pre-screening step followed by a variable selection step (e.g., penalized least squares).