NOAA/CDC LINEAR INVERSE MODEL (LIM)    Statistical Model

NOAA Climate Diagnostics Center
Boulder, Colorado, U.S.

Linear inverse modeling (LIM) combines the contemporaneous and lagged covariance statistics of a multivariate field in order to diagnose the best linear model for that field's dynamics. This best model is then used to make predictions, estimate confidence intervals, and diagnose how appropriate the linear model is.

Browse the LIM web page

contact: Ludmila.E.Matrosova@noaa.gov

References:
Penland, C. and T. Magorian, 1993: Prediction of Nino 3 sea surface temperatures using linear inverse modeling. J. Climate, 6, 1067-1076.
Penland, C. and P. D. Sardeshmukh, 1995: Error and sensitivity of geophysical eigensystems. J. Climate, 8, 1988-1998.
Penland, C. and L. Matrosova, 1998: Prediction of Tropical Atlantic Sea Surface Temperatures Using Linear Inverse Modeling. J. Climate, 11, 483-496.