900
Views
1
CrossRef citations to date
0
Altmetric
Articles

Empirical likelihood inference in autoregressive models with time-varying variances

ORCID Icon & ORCID Icon
Pages 129-138 | Received 25 Dec 2020, Accepted 05 Apr 2021, Published online: 22 Apr 2021

Figures & data

Table 1. Comparison of the rejection rates of five methods in Model 1 for β1{0.1,0.5,0.9}, κ{0.1,0.5,0.9}, δ{0.2,1,5} and the sample size T{60,200}, based on 5000 replications.

Table 2. Comparison of the rejection rates of five methods in Model 2 for β1{0.1,0.5,0.9}, [κ0,κ1]=[0.1,0.9], [σ0,σ1,σ2]{[0.2,5,0.2],[5,0.2,5]} and the sample size T{60,200}, based on 5000 replications.

Table 3. Comparison of the rejection rates of five methods in Model 3 for β1{0.1,0.5,0.9}, m{1,2}, δ{0.2,5} and the sample size t{60,200}, based on 5000 replications.

Figure 1. The relationship between the rejection rates of OLS, t1, t2, t3, EL and the true coefficient β1 in Model 1 (a single abrupt point model). The abrupt point κ=0.1, δ=0.2. The true parameter β1 increases gradually from 0.1 to 0.9. (a) The sample T = 60; (b) the sample T = 200.

Figure 1. The relationship between the rejection rates of OLS, t1, t2, t3, EL and the true coefficient β1 in Model 1 (a single abrupt point model). The abrupt point κ=0.1, δ=0.2. The true parameter β1 increases gradually from 0.1 to 0.9. (a) The sample T = 60; (b) the sample T = 200.

Figure 2. The relationship between the rejection rates of OLS, t1, t2, t3, EL and the true coefficient β1 in Model 2 (two abrupt points model). The abrupt points κ1=0.1, κ2=0.9, [σ0,σ1,σ2]=[0.2,5,0.2]. The true parameter β1 increases gradually from 0.1 to 0.9. (a) The sample T = 60; (b) the sample T = 200.

Figure 2. The relationship between the rejection rates of OLS, t1, t2, t3, EL and the true coefficient β1 in Model 2 (two abrupt points model). The abrupt points κ1=0.1, κ2=0.9, [σ0,σ1,σ2]=[0.2,5,0.2]. The true parameter β1 increases gradually from 0.1 to 0.9. (a) The sample T = 60; (b) the sample T = 200.

Figure 3. The relationship between the rejection rates of OLS, t1, t2, t3, EL corresponding to the true coefficient β1 in Model 3 (continuous function variance model), and m = 1, δ=0.2. The true parameter β1 increases gradually from 0.1 to 0.9. (a) The sample T = 60; (b) the sample T = 200.

Figure 3. The relationship between the rejection rates of OLS, t1, t2, t3, EL corresponding to the true coefficient β1 in Model 3 (continuous function variance model), and m = 1, δ=0.2. The true parameter β1 increases gradually from 0.1 to 0.9. (a) The sample T = 60; (b) the sample T = 200.