\magnification=1200
\baselineskip=20pt
\nopagenumbers
\font\big=cmr12 scaled \magstep2

\centerline{\bf STANFORD UNIVERSITY}
\centerline{\bf DEPARTMENT OF STATISTICS}
\centerline{\big DEPARTMENTAL SEMINAR}
\bigskip

\baselineskip=12pt
\centerline{4:15 p.m., Tuesday, July 10, 2001}
\centerline{Sequoia Hall Rm. 200}
\centerline{(Cookies at 3:45 in 1st Floor Lounge)}

\bigskip
\baselineskip=15pt
\centerline{\sl Sam Oman}
\centerline{\sl Department of Statistics}
\centerline{\sl Hebrew University of Jerusalem}
\bigskip
\centerline{\bf A Comparison of Some Estimating Equation Techniques for Analyzing 
Spatially Distributed Binary Responses}

\bigskip

In many applications one models a binary response Y, observed at sites on a
apatial lattice, in terms of corresponding vectors of explanatory
variables.  A  full likelihood-based approach typically requires Markov
Chain Monte Carlo, and may be computationally infeasible for large lattices.

Heagerty and Lele (1998, JASA) recently proposed analyzing such data with a
hierarchical generalized linear model, using composite likelihood to
estimate the regression vector and covariance parameters of the underlying
random field. 

This gives a "GEE2-like" (Liang, Zeger and Qaqish, 1992 JRSSB) estimating
equation.
        
We illustrate this method, together with some of the practical difficulties
in its implementation, in a detailed analysis of data on vegetation change
in a region of natural forest in northern Israel.  We then discuss two
computationally simpler alternitives, both in the spirit of generalized
estimating equations.

This work is joint with V. Landsman, Y. Carmel and R. Kadmon.

\bye