Forecasting Latin America’s Country Risk Scores by Means of a Dynamic Diffusion Model

Table 4

Estimated values of the contagion model parameters. The value of model parameter 𝛽_{𝑘(𝑖),𝑘} measures the contagion effect transmitted by the countries belonging to cluster 𝑘 (1≤𝑘≤4) on country 𝑖 (1≤𝑖≤18) belonging to cluster 𝑘(𝑖) according to assignment (5). Figures indicate that countries in clusters 𝑘=3,4 have a remarkable influence on the others, being lower on Chile (columns 3 and 4). In addition, it can be observed that Chile (cluster 1) has a strong influence on countries which belong to cluster 2 (element (2, 1), whose value is 0.01122).

𝛽𝑘(𝑖),𝑘	𝑘=1	𝑘=2	𝑘=3	𝑘=4
𝑘(𝑖)=1, 1≤𝑖≤1	0	0.01122	0.02525	0.01736
𝑘(𝑖)=2, 2≤𝑖≤7	0.05222	0.00007	0.04198	0.07828
𝑘(𝑖)=3, 8≤𝑖≤12	0.00047	0.00180	0.03809	0.04129
𝑘(𝑖)=4, 13≤𝑖≤18	0.00004	0.00283	0.04903	0.04771