To assess the drivers of economic growth, employment growth, and business investment, a system of provincial growth equations was estimated using annual provincial data for Canada’s ten provinces.
All variables were transformed into growth rates (log differences) or first differences to address non-stationarity identified through Augmented Dickey-Fuller testing.
The preferred model consists of three equations:
\[ \Delta GDP_t = \beta_1 \Delta INV_t + \beta_2 \Delta EXP_t + \beta_3 \Delta PROD_t + \beta_4 \Delta POP_t \]
\[ \Delta EMP_t = \gamma_1 \Delta GDP_t + \gamma_2 \Delta POP_t + \gamma_3 \Delta UR_t \]
\[ \Delta INV_t = \delta_1 \Delta EXP_t + \delta_2 \Delta WTI_t \]
Province fixed effects are included to control for persistent structural differences across provinces.
The estimated coefficients can be used to simulate the impacts of policy and economic shocks.
Examples include:
The national model examines the determinants of provincial GDP growth, employment growth, and investment growth.
| GDP Growth | Employment Growth | Investment Growth | |
|---|---|---|---|
| + p < 0.1, * p < 0.05, ** p < 0.01, *** p < 0.001 | |||
| (Intercept) | 0.005 | -0.000 | 0.010 |
| (0.004) | (0.002) | (0.019) | |
| dlinv | 0.060*** | ||
| (0.010) | |||
| dlexp | 0.065*** | 0.125* | |
| (0.008) | (0.058) | ||
| dlprod | 0.768*** | ||
| (0.049) | |||
| dlpop | 0.526*** | 0.845*** | |
| (0.128) | (0.066) | ||
| factor(province)British Columbia | 0.002 | 0.001 | 0.021 |
| (0.004) | (0.002) | (0.026) | |
| factor(province)Manitoba | -0.001 | 0.000 | -0.001 |
| (0.004) | (0.002) | (0.026) | |
| factor(province)New Brunswick | -0.002 | 0.003 | 0.002 |
| (0.005) | (0.002) | (0.026) | |
| factor(province)Newfoundland and Labrador | 0.002 | 0.004+ | 0.002 |
| (0.005) | (0.002) | (0.026) | |
| factor(province)Nova Scotia | 0.002 | 0.003 | -0.005 |
| (0.005) | (0.002) | (0.026) | |
| factor(province)Ontario | 0.002 | -0.000 | 0.007 |
| (0.004) | (0.002) | (0.026) | |
| factor(province)Prince Edward Island | 0.001 | 0.004+ | 0.010 |
| (0.004) | (0.002) | (0.026) | |
| factor(province)Quebec | 0.002 | 0.001 | 0.009 |
| (0.005) | (0.002) | (0.026) | |
| factor(province)Saskatchewan | -0.002 | 0.001 | -0.006 |
| (0.005) | (0.002) | (0.026) | |
| dlgdp | 0.139*** | ||
| (0.021) | |||
| durate | -0.012*** | ||
| (0.001) | |||
| dinterest_rate | 0.013* | ||
| (0.006) | |||
| dwti | 0.001* | ||
| (0.000) | |||
| Num.Obs. | 270 | 430 | 260 |
| R2 | 0.707 | 0.770 | 0.162 |
| R2 Adj. | 0.692 | 0.763 | 0.122 |
The estimated model was used to examine the effects of major economic and policy shocks.
| Scenario | GDP_Growth_Impact | Employment_Growth_Impact | Investment_Growth_Impact |
|---|---|---|---|
| 10% Export Decline (Tariff) | -0.57 | -0.07 | -1.11 |
| WTI -20 | -0.13 | -0.02 | -2.24 |
| WTI +20 | 0.13 | 0.02 | 2.24 |
| Population Growth +1% | 0.72 | 0.93 | 0.00 |
| Productivity Growth +2% | 1.96 | 0.24 | 0.00 |
| Unemployment Rate +1pp | 0.00 | -1.02 | 0.00 |
The national simulations suggest that:
To assess whether Alberta responds differently to economic shocks, the growth equations were re-estimated using Alberta observations only.
| GDP Growth | Employment Growth | Investment Growth | |
|---|---|---|---|
| + p < 0.1, * p < 0.05, ** p < 0.01, *** p < 0.001 | |||
| (Intercept) | -0.003 | -0.004 | -0.007 |
| (0.010) | (0.003) | (0.019) | |
| dlinv | 0.123* | ||
| (0.046) | |||
| dlexp | 0.062* | 0.343+ | |
| (0.029) | (0.190) | ||
| dlprod | 0.350 | ||
| (0.206) | |||
| dlpop | 0.996* | 1.231*** | |
| (0.452) | (0.158) | ||
| dlgdp | 0.015 | ||
| (0.056) | |||
| durate | -0.014*** | ||
| (0.001) | |||
| dwti | 0.003 | ||
| (0.002) | |||
| Num.Obs. | 27 | 43 | 27 |
| R2 | 0.836 | 0.888 | 0.618 |
| R2 Adj. | 0.807 | 0.879 | 0.586 |
| GDP_Growth_Impact | Employment_Growth_Impact | Investment_Growth_Impact | Scenario |
|---|---|---|---|
| -1.04 | -0.02 | -3.43 | 10% Export Decline (Tariff) |
| -0.70 | -0.01 | -5.66 | WTI -20 |
| 0.70 | 0.01 | 5.66 | WTI +20 |
| 1.00 | 1.25 | 0.00 | Population Growth +1% |
| 0.70 | 0.01 | 0.00 | Productivity Growth +2% |
The Alberta simulations indicate that:
The empirical results suggest that productivity growth, population growth, exports, and investment are the principal drivers of provincial economic performance.
The scenario analysis demonstrates that:
Overall, the results highlight the importance of productivity, trade competitiveness, workforce growth, and investment in supporting long-run economic performance.