Leading indicators of financial stress in Croatia: a regime switching approach
https://doi.org/10.3326/pse.47.2.3 | Published online: June 12, 2023 Table 1
Brief description of variables used in the study
Source: CNB (2022). Figure 1
HIFS values (left hand side) and the one-step-ahead and filtered probability of being in the regime of higher stress (right hand side) Source: CNB (2022) and author’s calculation (for probabilities). Table 2
Regime switching estimation results for a 2-regime AR(2) model for HIFS
Note: βij is the estimated parameter for constant governing the regime switching in eq. (3). AIC and Log L denote the Akaike information criterion and log likelihood value respectively. Values in parentheses denote standard error of the estimator. *, ** and *** denote statistical significance at 10%, 5% and 1% respectively. Source: Author’s calculation. Figure 2
Box plot for log likelihood values across all 964 models Note: Shaded areas denote 95% confidence interval for the median value. “balance sheets”, “burden”, “credit”, “external”, “house” and “mispricing” denote the six categories of measures from table 1: strength of balance sheets, private sector debt burden, credit dynamics, external imbalances, potential overvaluation of house prices and mispricing of risks respectively. t_4, t_5, t_6 and t_7 denote models that include indicator variables lagged for 4, 5, 6 and 7 quarters respectively. Source: Author’s calculation. Figure 3
Box plot for AIC values across all 964 models Note: Shaded areas denote 95% confidence interval for the median value. “balance sheets”, “burden”, “credit”, “external”, “house” and “mispricing” denote the six categories of measures from table 1: strength of balance sheets, private sector debt burden, credit dynamics, external imbalances, potential overvaluation of house prices and mispricing of risks respectively. t_4, t_5, t_6 and t_7 denote models that include indicator variables lagged for 4, 5, 6 and 7 quarters respectively. Source: Author’s calculation. Figure 4
Empirical density functions of log likelihood values across all 964 models Note: “balance sheets”, “burden”, “credit”, “external”, “house” and “mispricing” denote the six categories of measures from table 1: strength of balance sheets, private sector debt burden, credit dynamics, external imbalances, potential overvaluation of house prices and mispricing of risks respectively. t_4, t_5, t_6 and t_7 denote models that include indicator variables lagged for 4, 5, 6 and 7 quarters respectively. Source: Author’s calculation. Table 3
Significant coefficients, probability of transitioning from lower to higher risk regime (upper panel) and significant coefficients, probability of staying in the higher risk regime (lower panel)
Note: 1600, 25K, 85K, 125K and 400K denote the value of the smoothing parameter in HP gap, in values of 1,600, 25,000, 85,000, 125,000 and 400,000 respectively. 1y and 2y are one and two years, CNFP is credit to nonfinancial corporations, HPI is house price index, Capital/Assets is the capital-to-assets ratio. t-4, t-5, t-6 and t-7 denote models that include indicator variables lagged for 4, 5, 6 and 7 quarters respectively. HH denotes credit to households, Net ext debt denotes net external debt, NX is net exports share in GDP, whereas NX cumsum is sum of net exports over 4 quarters share in sum of GDP over 4 quarters, P-to-I is the price to income ratio, HPI is house price index, Deposits/Credit denotes the deposit-to-credit ratio, P-to-Income is house price-to-income ratio, CNFC is credit to nonfinancial corporations, H D-to-I is household debt to income ratio. Source: Author’s calculation. Table A1
SIC information criterion on different specifications of ARMA(p,q) model for variable HIFS
Source: Author’s calculation. Figure A2
Log likelihood statistics for regime switching models with variable indicators included in the equation (3) Note: “balance sheets”, “burden”, “credit”, “external”, “house” and “mispricing” denote the six categories of measures from table 1: strength of balance sheets, private sector debt burden, credit dynamics, external imbalances, potential overvaluation of house prices and mispricing of risks respectively. t_4, t_5, t_6 and t_7 denote models that include indicator variables lagged for 4, 5, 6 and 7 quarters respectively. Source: Author’s calculation. This is an Open Access article distributed under a Creative Commons Attribution-NonCommercial 4.0 International License (CC-BY-NC) which permits non commercial use and redistribution, as long as you give appropriate credit, provide a link to the license, and indicate if changes were made.
|
June, 2023 II/2023 |
|||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
