Athens University Economics and Business (AUEB)
Private insurance demand, macroeconomic conditions, and economic sentiment: an econometric analysis of eight European countries
Abstract
dc:descriptionThis research employs multiple and quantile regression techniques to investigate the determinants of private insurance penetration, distinguishing between life and non-life insurance. Model specification is optimized through variable selection based on the AIC. To address serial correlation in the residuals, the models are augmented with ARMA components, while conditional heteroskedasticity is captured using GARCH specifications. The empirical analysis is based on a novel quarterly dataset covering eight European countries: Czechia, Denmark, Greece, Italy, Latvia, Norway, Slovenia, and Spain. It incorporates both “hard” macroeconomic indicators, such as income and inflation, and sentiment-based measures derived from Business Tendency Surveys (BTS), including the Business Confidence Index (BCI) and the World Uncertainty Index. The results from the country-specific models reveal substantial heterogeneity in both the magnitude and direction of the estimated effects. The quantile regression analysis further demonstrates that the elasticity of the explanatory variables varies considerably across the distribution of insurance penetration, highlighting the presence of non-linear and state-dependent relationships. Across countries, autoregressive terms emerge as key determinants of insurance demand, while economic sentiment indicators support the models in several cases. Panel regression results indicate that life insurance penetration is primarily associated with banking sector development and long-term interest rates, whereas non-life insurance penetration is linked to income, unemployment, financial sector conditions, external trade intensity, consumer spending behavior, and uncertainty. Furthermore, the study examines the direction of causality between private insurance and economic development using both bivariate and multivariate Granger causality frameworks. To capture the temporal dimension of these relationships, the analysis is extended to the frequency domain. The empirical findings indicate a strong and consistent interaction between income and life insurance penetration, whereas the relationship between income and non-life insurance appears comparatively weaker and less systematic. More broadly, the results reveal heterogeneous and time-varying patterns of causal interaction across countries.
Degree
thesis:*- Grantor dc:publisher
- Athens University Economics and Business (AUEB)
- Year dc:date
- 2026
Author and committee
dc:creator, dc:contributor.*- Authors dc:creator
-
- Stathopoulos, Konstantinos
- Σταθόπουλος, Κωνσταντίνος
Subjects
dc:subject × 27- Ποσοστιαία παλινδρόμηση
- Αιτιότητα κατά Granger στο πεδίο των συχνοτήτων
- Οικονομικό συναίσθημα
- Μακροοικονομικοί παράγοντες
- Ασφαλίσεις ζωής
- Ασφαλίσεις κατά ζημιών
- Ανάλυση πάνελ δεδομένων
- Ζήτηση ασφάλισης
- Έρευνα αγοράς
- Αιτιότητα κατά Granger
- Quantile regression
- Frequency-domain Granger causality
- Economic sentiment
- Macroeconomic determinants
- Life insurance
- Non-life insurance
- Panel data analysis
- Insurance demand
- Elastic net
- Market research
- Granger causality
- Οικονομικά και Επιχειρήσεις
- Κοινωνικές Επιστήμες
- Οικονομετρία
- Economics and Business
- Social Sciences
- Econometrics
Rights
- Language dc:language
- eng
Identifiers
dc:identifier.*- Identifier
- 10.12681/eadd/62744