This project investigates the "Premature Deindustrialization" of the Philippines. While many claim that skipping the industrialization stage has hindered the Philippines compared to Vietnam, this data-driven analysis using Multiple Linear Regression suggests that the Philippines has successfully developed a "Service-Led" model for poverty reduction that is statistically more efficient than its stagnant manufacturing sector.
- Language: Python 3.x
- Libraries:
wbgapi(World Bank API),pandas,statsmodels,matplotlib - Data Source: World Bank Open Data (2000–2025)
- Methodology: Ordinary Least Squares (OLS) Regression with Linear Interpolation for missing poverty data.
I ran two separate OLS models to compare the "Engines of Growth":
| Variable | Philippines (PHL) | Vietnam (VNM) |
|---|---|---|
| Manufacturing Coef | -0.19 (Not Significant) | -2.23 (Highly Significant) |
| Services Coef | -1.29 (Highly Significant) | -0.82 (Significant) |
| P-value (Mfg) | 0.740 | 0.000 |
| R-Squared | 0.892 | 0.972 |
- Vietnam follows the classic "Tiger" model where factories are the primary tool for lifting people out of poverty.
- The Philippines has "leapfrogged" into a service-driven economy. While Manufacturing has a negligible impact on poverty (P-value 0.740), the Services sector is 57% more efficient at reducing poverty in the PH than it is in Vietnam.
The graph shows Vietnam's manufacturing as a % of GDP pulling away while the Philippines remains flat, confirming the "skipped step" in industrialization.
- Install dependencies:
pip install wbgapi pandas statsmodels matplotlib - Run
macro_scout.pyto fetch data and generate graphs. - Run
regression_analysis.pyto view the OLS summary.
Author: Jovit Paul B. Magadan Background: MBA / Agricultural Engineer