Dr. Zhou Zhou
Department of Statistics
University of Toronto
Title: " Simultaneous Inference of Linear Models with Time-Varying Coefficients "
The talk considers construction of simultaneous confidence tubes (SCT) for
time-varying regression coefficients in functional linear models. Using a
Gaussian approximation result for non-stationary multiple time series, we
show that the constructed SCTs have asymptotically correct nominal coverage
probabilities. Our results are applied to the problem of testing whether
the regression coefficients are of certain parametric forms, a fundamental
problem in the inference of functional linear models. As an application,
we analyze an environmental data set and study the relation between levels
of pollutants and hospital admissions. Another application involves testing
of parameter constancy in a capital asset pricing model.