Jonathan R. M. Hosking

Jonathan Hosking

Dr. J. R. M. Hosking                email: hosking@watson.ibm.com
IBM Research Division               phone: (914) 945-1031
Thomas J. Watson Research Center    fax:   (914) 945-3434
P.O. Box 218
Yorktown Heights, NY 10598

Interests and experience

Large-scale data analysis ("data mining" or data abstraction)
L-moments -- statistics for summarizing the information in data samples
Time-series analysis and forecasting
Estimation of the frequency of extreme events
Applications in environmental science and finance

Brief biography

Jonathan R. M. Hosking has been with the IBM Research Division, Yorktown Heights, N.Y., since 1986. He is a Research Staff Member in the Statistics group of the Mathematical Sciences Department. Previously he was with the Institute of Hydrology, Wallingford, England (1979-86). He holds an M.A. in Mathematics from Cambridge University and a Ph.D. in Statistics (time series analysis) from Southampton University (1979). He is the author of one book and over 50 research papers, covering such subjects as feature selection and ranking in classification problems, statistics for summarizing data samples (L-moments), "long-memory" time-series models -- useful for modelling series with complicated structure related to Mandelbrot's "fractals" -- and estimating the frequency of extreme environmental events. He has experience in applying statistical methods in financial modelling, business forecasting, and civil and environmental engineering.

Available software

LMOMENTS -- A collection of Fortran routines that facilitate the use of L-moments to calculate summary statistics of data samples and fit probability distributions to data.
Algorithm AS215: Maximum likelihood estimation of the parameters of the generalized extreme value distribution. Applied Statistics, 34 (1985), 301-310. (Fortran subroutine.)

Selected publications

Financial mathematics

Hosking, J., Bonti, G., and Siegel, D. (2000). Beyond the lognormal. Risk, 13:5 (May 2000), 59-62.

Data abstraction research

Coppersmith, D., Hong, S. J., and Hosking, J. R. M. (1999). Partitioning nominal attributes in decision trees. Data Mining and Knowledge Discovery, 3, 197-217.
Apte, C., Hong, S. J., Hosking, J., Lepre, J., Pednault, E., and Rosen, B. (1998). Decomposition of heterogeneous classification problems. Intelligent Data Analysis, 2, 81-96.
Hosking, J. R. M., Pednault, E. P. D., and Sudan, M. (1997). A statistical perspective on data mining. Future Generation Computer Systems, 13, 117-134.
Hong, S. J., Hosking, J. R. M., and Winograd, S. (1996). Use of randomization to normalize feature merits. In Information, Statistics and Induction in Science, Proceedings of the ISIS 96 conference, eds. D. L. Dowe, K. B. Korb and J. J. Oliver, pp. 10-19. World Scientific, Singapore.

L-moments

Hosking, J. R. M. (1990). L-moments: analysis and estimation of distributions using linear combinations of order statistics. Journal of the Royal Statistical Society, Series B, 52, 105-124.
Hosking, J. R. M. (1995). The use of L-moments in the analysis of censored data. In: Recent advances in life-testing and reliability, ed. N. Balakrishnan, pp. 545-564. CRC Press, Boca Raton, Fla.
Hosking, J. R. M., and Wallis, J. R. (1997). Regional frequency analysis: an approach based on L-moments. Cambridge University Press, Cambridge, U.K.

For more, see the L-moments page.

Long-memory time series

Hosking, J. R. M. (1981). Fractional differencing. Biometrika, 68, 165-176.
Hosking, J. R. M. (1996). Asymptotic distributions of the sample mean, autocovariances and autocorrelations of long-memory time series. Journal of Econometrics, 73, 261-284.

Forecasting and time series analysis

Wu, L. S.-Y., Hosking, J. R. M., and Doll, J. M. (1992). Business planning under uncertainty: will we attain our goal? International Journal of Forecasting, 8, 545-557.
Wu, L. S.-Y., Ravishanker, N., and Hosking, J. R. M. (1993). Reallocation outliers in time series. Applied Statistics, 42, 301-313.
Wu, L. S.-Y., Pai, J. S., and Hosking, J. R. M. (1996). An algorithm for estimating parameters of state-space models. Statistics and Probability Letters, 28, 99-106.

Last modified: 12 December 2003.

[ IBM Research home page ]