Computational Statistics and Data Analysis

Source code (C++) of the fast exact CDF and KDE algorithms described in the research manuscript entitled "Fast multivariate empirical cumulative distribution function with connection to kernel density estimation"

This file includes the data and code that are utilized in the submitted paper "Functional Outlier Detection and Taxonomy by Sequential Transformations".

The resting-state functional magnetic resonance imaging data is from the Autism Brain Imaging Data Exchange study. The primary goal of this study was to understand how brain activity is associated with autism spectrum disorder, a disease with substantial heterogeneities among chlidren. Functional magnetic resonance imaging measures blood oxygen levels linked to neural activity, and resting-state functional magnetic resonance imaging measures brain activity only when the brain is not performing any tasks. This study aggregated 20 resting-state functional magnetic resonance imaging datasets from 17 experiment sites. For each subject, the resting-state functional magnetic resonance imaging signal was recorded for each voxel in the brain over multiple time-points. Standard imaging pre-processing steps (Di Martino et al., 2014) included motion correction, slice-timing correction, and spatial smoothing. The entire brain was registered into the 3mm standard Montreal Neurological Institute space, which consists of 38 547 voxels in 90 brain regions defined by the automated anatomical labelling system (Hervé et al., 2012). To select imaging biomarkers for study prediction, we considered the fractional amplitude of low-frequency fluctuations (Zou et al., 2008), defined as the ratio of the power spectrum for frequencies 0·01–0·08 Hz to the entire frequency range.

The vertical acceleration (VAC) is an important proxy of the vertical vibration of the hull. Two VAC series (unit: m/s^2) from two measurement points along the hull girder are given. Each data series consists of 1696 observations over 1 hour (3,600 seconds). They are irregularly spaced. See the article for more detailed description.

A supplement with all R code used in the revised manuscript. The same supplement has been posted at the following web address: www.stat.rice.edu/~ms88/local.dependence.tar.gz

This Zip file contains Julia program (version 1.1.1) for implementing the cMFM described in "Bayesian subgroup analysis in regression using mixture models."

Matlab code used in the preparation of ROBUST DESIGNS FOR DOSE-RESPONSE STUDIES: MODEL AND LABELLING ROBUSTNESS

Here we include both the R codes and data for the case study and simulation examples in the paper.

Here we provide the "supplementary_example.R" file to reproduce examples in R. Intermediate output in the analysis: CAL500 Data: "cal500_analysis_fulldata.rda" LSOA Data: "lsoa_analysis_fulldata.rda" Preprocessed response data from raw CAL500 data: "CAL500_response.csv" Preprocessed LSOA data: "lsoa_grrr_target44_feature294.rda" Predictor variables description: "feature_3988_294_names.csv" Response variables description: "target_3988_44_names.csv"

This dataset contains our algorithm implementation as well as the Raman spectral data presented in "Bayesian Modeling and Computation for Analyte Quantification in Complex Mixtures Using Raman Spectroscopy". Detailed execution comments are provided in the Python files.