A Score Based Test for Functional Linear Concurrent Regression

A novel method for testing the null hypothesis of no effect a covariate on response is proposed in functional linear concurrent regression. An equivalent random effects formulation regression model established under which problem reduces to zero variance component effects. For this purpose, one-sided score test approach used, an extension classical test. Theoretical justification provided as why procedure has correct levels (asymptotically) using standard assumptions. Using numerical simulations, shown have desired type I error rate and higher power compared bootstrapped F currently existing literature. The give good performances even when data are sparsely observed, contaminated with noise. Applications demonstrated gait study child mortality.