BUILDING AN ARDL REGRESSION MODEL FOR ANALYZING THE ECONOMIC DETERMINANTS OF BRAZIL’S MILITARY EXPENDITURES (2000–2024)
Abstract
This study investigates the economic determinants of Brazil’s military expenditures from 2000 to 2024 using an Autoregressive Distributed Lag (ARDL) model. Annual data (25 observations) were sourced from the World Bank, SIPRI, IMF, Statista, Macrotrends, and TradingEconomics. The dependent variable is military spending as a share of GDP (milex_gdp), while explanatory variables include GDP growth, logarithm of GDP per capita, trade openness, public debt-to-GDP ratio, inflation, unemployment, and logarithm of population. Missing values were imputed via linear interpolation and trend-based estimates to maintain data integrity. Stationarity tests confirmed a mix of I (0) and I (1) variables, validating the use of the ARDL framework, which flexibly handles such heterogeneity without requiring differencing. The model specification includes a one-period lag of the dependent variable to capture expenditure inertia, alongside contemporaneous effects of the economic covariates. The model specification includes a one-period lag of the dependent variable to capture expenditure inertia, alongside contemporaneous effects of the economic covariates. Empirical results reveal statistically significant short-run influences from GDP growth, per capita income, public debt, and unemployment, with expenditure persistence of approximately 40%. Trade openness, inflation, and population size show no robust impact. Long-run multipliers, derived from the error-correction form, indicate amplified responses over time, particularly for income and debt variables. A 2025 forecast projects military spending at around 1,03% of GDP, consistent with observed stability and moderate growth assumptions. The findings highlight a dynamic trade-off: economic expansion supports defense allocation, while rising unemployment or affluence shifts fiscal priorities toward social welfare. The ARDL approach proves well-suited for small-sample macroeconomic analysis characterized by inertia and mixed integration orders. Policy implications emphasize the interplay between fiscal capacity, growth cycles, and security priorities in emerging economies.
References
Hanck, C., Arnold, M., Gerber, A., & Schmelzer, M. (2024). Introduction to econometrics with R. University of Duisburg-Essen, Department of Business Administration and Economics, Chair of Econometrics. URL: https://www.econometrics-with-r.org/
Bachtiar, M., Ahmad, I., Sahabuddin, Z. A., & Trismadi, T. (2025). A comprehensive meta-analysis of determinants influencing military expenditure: New methodological insights and implications for defence budget allocation. Statistics, Politics and Policy, 16(1), 87–103. DOI: https://doi.org/10.1515/spp-2024-0012
Inal, V., Gurdal, T., Degirmenci, T., & Aydin, M. (2024). The effects of military expenditures on labor productivity, innovation and economic growth for the most militarized countries: Panel data analysis. Kybernetes, 53(3), 821–840. DOI: https://doi.org/10.1108/K-05-2023-0821
Pérez-Cárceles, M. C. (2025). Is defence expenditure a guarantee of human development? A panel data approach in the group of twenty. Applied Economics, 57(20), 2569–2580. DOI: https://doi.org/10.1080/00036846.2024.2301234
Jiménez, M. G. C., Correa-Quezada, R., Tulcanaza-Prieto, A. B., & Cueva-Rodríguez, L. (2025). Military expenditure and sustainable economic growth in Latin America. UCJC Business and Society Review, 22(84).
Chary, S. (2024). The nexus between arms imports, military expenditures and economic growth of the top arms importers in the world: A pooled mean group approach. Journal of Economic Studies, 51(4), 808–822. DOI: https://doi.org/10.1108/JES-03-2023-0135
Stockholm International Peace Research Institute. (2024). Trends in world military expenditure, 2023 [Fact sheet]. URL: https://www.sipri.org/sites/default/files/2024-04/2404_fs_milex_2023.pdf
Arbache, J., & Sarquis, S. J. (2018). Growth volatility and economic growth in Brazil. In E. L. Bacha & M. B. Bolle (Eds.), The Oxford handbook of the Brazilian economy (pp. 147–174). Oxford University Press. DOI: https://doi.org/10.1093/oxfordhb/9780190499983.013.9
Arruda, M. A. (2018). O programa de construção de submarinos (PROSUB) do Brasil. Hemisferio-Revista del Colegio Interamericano de Defensa, 4, 93–112.
Júnior, F. G. R. P., & Alves, M. A. B. (2022). Análise política do processo de compra e transferência de tecnologia dos caças Gripen. Austral: Brazilian Journal of Strategy & International Relations, 11(22). DOI: https://doi.org/10.22456/2238-6912.123456
Holland, M. (2019). Fiscal crisis in Brazil: Causes and remedy. Brazilian Journal of Political Economy, 39(1), 88–107. DOI: https://doi.org/10.1590/0101-31572019-2999
Guimarães, A. Q., & da Cunha Resende, M. F. (2024). The political economy of the Brazilian economic crisis (2014–2022): Economic policy, ideas and the limits of neoliberal austerity measures. In A. B. da Silva (Ed.), Social policies in times of austerity and populism (pp. 66–88). Routledge. DOI: https://doi.org/10.4324/9781003456789-5
Moyo, C., Khobai, H., Kolisi, N., & Mbeki, Z. (2018). Financial development and economic growth in Brazil: A non-linear ARDL approach. Unpublished manuscript.
World Bank. (n.d.). World Bank open data. Retrieved from: https://data.worldbank.org/
Stockholm International Peace Research Institute. (n.d.). SIPRI arms transfers database. Retrieved from: https://www.sipri.org/databases/armstransfers
International Monetary Fund. (n.d.). Access to economic and financial data. Retrieved from: https://data.imf.org/en
Statista. (n.d.). Brazil – Statistics & facts. Retrieved from: https://www.statista.com/topics/1537/brazil/
Macrotrends. (n.d.). Macrotrends – The premier research platform for long term investors. Retrieved from: https://www.macrotrends.net/
Instituto Brasileiro de Geografia e Estatística. (n.d.). Finanças públicas. Retrieved from: https://www.ibge.gov.br/estatisticas/economicas/financas-publicas.html
Statsmodels Development Team. (n.d.). statsmodels.regression.linear_model.OLS. Retrieved from: https://www.statsmodels.org/dev/generated/statsmodels.regression.linear_model.OLS.html

