VOStat is a Web service providing interactive statistical analysis of astronomical tabular datasets. It is integrated into the suite of analysis and visualization tools associated with the international Virtual Observatory (VO) through the SAMP commu
nication system. A user supplies VOStat with a dataset extracted from the VO, or otherwise acquired, and chooses among $sim 60$ statistical functions. These include data transformations, plots and summaries, density estimation, one- and two-sample hypothesis tests, global and local regressions, multivariate analysis and clustering, spatial analysis, directional statistics, survival analysis (for censored data like upper limits), and time series analysis. The statistical operations are performed using the public domain {bf R} statistical software environment, including a small fraction of its $>4000$ {bf CRAN} add-on packages. The purpose of VOStat is to facilitate a wider range of statistical analyses than are commonly used in astronomy, and to promote use of more advanced methodology in {bf R} and {bf CRAN}.
In the past two years, the environment within which astronomers conduct their data analysis and management has rapidly changed. Working Groups associated with international societies and Big Data projects have emerged to support and stimulate the new
fields of astroinformatics and astrostatistics. Sponsoring societies include the Intenational Statistical Institute, International Astronomical Union, American Astronomical Society, and Large Synoptic Survey Telescope project. They enthusiastically support cross-disciplinary activities where the advanced capabilities of computer science, statistics and related fields of applied mathematics are applied to advance research on planets, stars, galaxies and the Universe. The ADASS community is encouraged to join these organizations and to explore and engage in their public communication Web site, the Astrostatistics and Astroinformatics Portal (http://asaip.psu.edu).
Observations of the spatial distributions of young stars in star-forming regions can be linked to the theory of clustered star formation using spatial statistical methods. The MYStIX project provides rich samples of young stars from the nearest high-
mass star-forming regions. Maps of stellar surface density reveal diverse structure and subclustering. Young stellar clusters and subclusters are fit with isothermal spheres and ellipsoids using the Bayesian Information Criterion to estimate the number of subclusters. Clustering is also investigated using Cartwright and Whitworths Q statistic and the inhomogeneous two-point correlation function. Mass segregation is detected in several cases, in both centrally concentrated and fractally structured star clusters, but a few clusters are not mass segregated.
This review outlines concepts of mathematical statistics, elements of probability theory, hypothesis tests and point estimation for use in the analysis of modern astronomical data. Least squares, maximum likelihood, and Bayesian approaches to statist
ical inference are treated. Resampling methods, particularly the bootstrap, provide valuable procedures when distributions functions of statistics are not known. Several approaches to model selection and good- ness of fit are considered. Applied statistics relevant to astronomical research are briefly discussed: nonparametric methods for use when little is known about the behavior of the astronomical populations or processes; data smoothing with kernel density estimation and nonparametric regression; unsupervised clustering and supervised classification procedures for multivariate problems; survival analysis for astronomical datasets with nondetections; time- and frequency-domain times series analysis for light curves; and spatial statistics to interpret the spatial distributions of points in low dimensions. Two types of resources are presented: about 40 recommended texts and monographs in various fields of statistics, and the public domain R software system for statistical analysis. Together with its sim 3500 (and growing) add-on CRAN packages, R implements a vast range of statistical procedures in a coherent high-level language with advanced graphics.
The full stellar population of NGC 6334, one of the most spectacular regions of massive star formation in the nearby Galaxy, have not been well-sampled in past studies. We analyze here a mosaic of two Chandra X-ray Observatory images of the region us
ing sensitive data analysis methods, giving a list of 1607 faint X-ray sources with arcsecond positions and approximate line-of-sight absorption. About 95 percent of these are expected to be cluster members, most lower mass pre-main sequence stars. Extrapolating to low X-ray levels, the total stellar population is estimated to be 20-30,000 pre-main sequence stars. The X-ray sources show a complicated spatial pattern with about 10 distinct star clusters. The heavily-obscured clusters are mostly associated with previously known far-infrared sources and radio HII regions. The lightly-obscured clusters are mostly newly identified in the X-ray images. Dozens of likely OB stars are found, both in clusters and dispersed throughout the region, suggesting that star formation in the complex has proceeded over millions of years. A number of extraordinarily heavily absorbed X-ray sources are associated with the active regions of star formation.
The Cepheus B (CepB) molecular cloud and a portion of the nearby CepOB3b OB association, one of the most active regions of star formation within 1 kpc, have been observed with the IRAC detector on board the Spitzer Space Telescope. The goals are to s
tudy protoplanetary disk evolution and processes of sequential triggered star formation in the region. Out of ~400 pre-main sequence (PMS) stars selected with an earlier Chandra X-ray Observatory observation, 95% are identified with mid-infrared sources and most of these are classified as diskless or disk-bearing stars. The discovery of the additional >200 IR-excess low-mass members gives a combined Chandra+Spitzer PMS sample complete down to 0.5 Mo outside of the cloud, and somewhat above 1 Mo in the cloud. Analyses of the nearly disk-unbiased combined Chandra+Spitzer selected stellar sample give several results. Our major finding is a spatio-temporal gradient of young stars from the hot molecular core towards the primary ionizing O star HD 217086. This strongly supports the radiation driven implosion (RDI) model of triggered star formation in the region. The empirical estimate for the shock velocity of 1 km/s is very similar to theoretical models of RDI in shocked molecular clouds...ABRIDGED... Other results include: 1. agreement of the disk fractions, their mass dependency, and fractions of transition disks with other clusters; 2. confirmation of the youthfulness of the embedded CepB cluster; 3. confirmation of the effect of suppression of time-integrated X-ray emission in disk-bearing versus diskless systems.
We present the first high spatial resolution Chandra X-ray study of NGC 2244, the 2 Myr old stellar cluster immersed in the Rosette Nebula. Over 900 X-ray sources are detected; 77% have optical or FLAMINGOS near-infrared (NIR) stellar counterparts an
d are mostly previously uncatalogued young stellar cluster members. All known OB stars with spectral type earlier than B1 are detected and the X-ray selected stellar population is estimated to be nearly complete between 0.5 and 3 Msun. The X-ray luminosity function (XLF) ranges from 29.4<logLx<32 ergs/s in the hard (2-8keV) band. By comparing the NGC 2244 and Orion Nebula Cluster XLFs, we estimate a total population of 2000 stars in NGC 2244. A number of further results emerge from our analysis: The XLF and the associated K-band luminosity function indicate a normal Salpeter initial mass function (IMF) for NGC 2244. This is inconsistent with the top-heavy IMF reported from earlier optical studies that lacked a good census of <4Msun stars. The spatial distribution of X-ray stars is strongly concentrated around the central O5 star, HD 46150. The other early O star, HD 46223, has few companions. The clusters stellar radial density profile shows two distinctive structures. This double structure, combined with the absence of mass segregation, indicates that this cluster is not in dynamical equilibrium. The spatial distribution of X-ray selected K-excess disk stars and embedded stars is asymmetric with an apparent deficit towards the north. The fraction of X-ray-selected cluster members with K-band excesses caused by inner protoplanetary disks is 6%, slightly lower than the 10% disk fraction estimated from the FLAMINGOS study based on the NIR-selected sample. This is due to the high efficiency of X-ray surveys in locating disk-free T Tauri stars.[Abridged]
