The optimal lag(s), p, were determined by the t-stat significance of the last lagged dependent variable at the 10% significance level by setting the maximum number of lags to 12. The optimal Fourier frequency k^* was selected by minimizing the sum of squared residuals from OLS estimation with k∈[1,…,5]. Ftrig is the usual F-statistic for testing the null hypothesis of the absence of trigonometric terms (i.e., δ₁=δ₂=0) in equation (14) for the model with level shift and in equation (15) for the model with level and trend shift by using k = k^*. The critical values for Ft_NL test are available for the level shift model in Christopoulos and León-Ledesma (2010). We simulate the critical values for the level and trend shift model based on Monte Carlo simulations as defined in Christopoulos and León-Ledesma (2010, p. 1082).

(1%),

(5%) and

(10%)