Analysis of Multiple Random Functions The primary focus of this research is to develop methodology for identifying patterns in multiple random functions. In my research related to this methodological area, I investigate methods under different assumptions starting with independence between random curves and extending this common assumption to spatial-dependence between curves and multidimensional random functions. The random function can take values in a continuous space (e.g. Gaussian random processes) or they can take discrete values (e.g. binary functional data). Relevant methods include clustering, regression and association analysis. 1. Serban, N., Wasserman, L. (2005) "CATS: Cluster Analysis by Transformation and Smoothing", Journal of the American Statistical Association, 100 (471), pp 990-999. [Paper Document] [Software] 2. Serban, N. (2008), "Clustering Curves in the Presence of Heteroscedastic Errors", Journal of Nonparametric Statistics, 20(7), 553-571. 3. Serban, N. (2008), "Clustering Confidence Sets", Journal of Statistical Planning and Inference, 139, 109 -124. 4. Serban, N. (2011), " Space-Time Varying Coefficient Models: The Equity of Service Accessibility", Annals of Applied Statistics, 5(3), 2024-2051. 5. Jiang, H., Serban, N. (2012), "Clustering Random Curves Under Spatial Interdependence with Application to Service Accessibility", Technometrics (featured with discussions), 54 (2), 108-119. [Paper Document] [Supplemental Materials] [Software] 6. Serban, N., Jiang, H. (2012), "Multilevel Functional Clustering Analysis", Biometrics, 68(3), 805-814. [Paper Document] [Supplemental Materials] [Software] 7. Serban, N., Jiang, H., (2012) "Association Analysis of Spatio-temporal Processes: A Functional Approach", unpublished web manuscript . Paper Document] [Supplemental Materials] [Software] 8. Serban, N., Staicu, A.M., Carroll, R. (2013), "Multilevel Spatially Correlated Binary Longitudinal Data", Biometrics, 9 (4), 903-913. [Paper Document] [Supplemental Materials] [Software] 9. Ngueyep, R., Serban, N. (2015), "Large Vector Auto Regressions for Multi-Layer Spatially Correlated Time Series", Technometrics, 57 (2), 207-216. [Paper Document] [Supplemental Materials] [Software] |

Back to Nicoleta Serbans Home page |