The name is absent



88

5.3 Application: Revisiting the impact of the GLB

Act

In this Section, we revisit the application in Chapter 4. We use the same data set
but focus on identifying and locating a change-point. Section 5.3.1 explains the basic
setups for this application. Results are shown in Section 5.3.2. Conclusions are
included in Section 5.3.3.

5.3.1 Basic setups

Please note that the data structure and covariates used in Section 5.3 are the same
as in Chapter 4.

In order to estimate λs, we let θmin = Jan. 1994 and θmax = Dec. 2005, which
is the range of the time horizon considered. In order to locate the potential change-
point
θ, we tested December 1999. The reason is that from the cumulative hazard
curve in Figure 4.11, it seems that there might be a change-point of the cumulative
hazard function around December 1999. Since the true value of
τ is unknown, we did
a sensitivity analysis for
τ = 0.5 and τ = —0.5, respectively.

5.3.2 Results of the tests

Test 7 with θ = December 99; τ =0.5

Table 5.1 shows the parameter estimates for both βs and λs. Note that the values



More intriguing information

1. Naïve Bayes vs. Decision Trees vs. Neural Networks in the Classification of Training Web Pages
2. The name is absent
3. The name is absent
4. The name is absent
5. Declining Discount Rates: Evidence from the UK
6. Tissue Tracking Imaging for Identifying the Origin of Idiopathic Ventricular Arrhythmias: A New Role of Cardiac Ultrasound in Electrophysiology
7. FDI Implications of Recent European Court of Justice Decision on Corporation Tax Matters
8. WP RR 17 - Industrial relations in the transport sector in the Netherlands
9. The magnitude and Cyclical Behavior of Financial Market Frictions
10. National urban policy responses in the European Union: Towards a European urban policy?