Consider a repeated measurement regression model yij=g(xi)+[epsilon]ij where i=1,...,n, j=1,...,m, yij's are responses, g(·) is an unknown function, xi's are design points, [epsilon]ij's are random errors with a one-way error component structure, i.e. [epsilon]ij=[mu]i+[nu]ij, [mu]i and...

A new estimation is proposed for seemingly unrelated nonparametric regression models where variance of disturbance in an equation is larger than that in the preceding equation, and all of the correlation coefficients between the disturbances across the equations are positive.