Table 2
General model results

Warning View the most recent version.

Archived Content

Information identified as archived is provided for reference, research or recordkeeping purposes. It is not subject to the Government of Canada Web Standards and has not been altered or updated since it was archived. Please "contact us" to request a format other than those available.

Archived

This page has been archived on the Web.

Symbols  Next table  Previous table

General model results
Table summary
This table displays the results of models for a single cross-section, fixed-effects panel and fixed effects panel with two-stage least squares. The row headers describe the variables used in the models (plant and place characteristics). The column headers identify the estimated model and associated coefficient and p-value alternating across the models.
  Single cross-section, 1999 1 Fixed-effects panel, 1989 and 1999 2 Fixed-effects panel, 1989 and 1999 (2SLS) 3
Model 1 Model 2 Model 3
  coefficient p-value coefficient p-value coefficient p-value
Plant characteristics  
Ratio of profit to value added 0.813 <0.001 0.750 <0.001 0.730 <0.001
Production workers -0.031 <0.001 -0.109 <0.001 -0.120 <0.001
Ratio of non-production workers to production workers 0.274 <0.001 0.384 <0.001 0.400 <0.001
Multi-plant status (reference is single plant) 0.190 <0.001 0.086 0.002 0.060 0.041
Foreign-plant status (reference is domestic) 0.103 <0.001 0.094 <0.001 0.070 0.001
Place characteristics  
Labour mix -0.838 <0.001 -0.508 <0.001 -1.190 <0.001
Local density upstream suppliers 0.014 <0.001 0.100 <0.001 0.380 0.049
Plants within 5 kilometres 0.013 <0.001 0.021 <0.001 0.100 0.032
Plants within 200 kilomètres ... ... ... ... -0.240 0.055
Population 0.079 <0.001 -0.149 <0.001 -0.200 0.055
Constant 12.190 <0.001 0.044 <0.001 -0.014 0.656
General model results (continued)
  Model 1 Model 2 Model 3
Number of observations 20,424 11,323 10,615
R-squared 0.661 0.466 0.360
Root mean squared error 0.290 0.430 0.470
1.
Reports results from a single cross-section of plants in 1999.
2.
Report results from panel models estimated over the two years 1989 and 1999. Results are from a fixed-effects regression model.
3.
Report results from panel models estimated over the two years 1989 and 1999. Results are from a fixed-effects regression model incorporating instrumental variables to control for potential endogeneity. The term 2SLS stands for "two-stage least squares."
Note(s):
In all regressions, standard errors are corrected for heteroscedasticity and potential correlation of errors across plants within the same census metropolitan area or census agglomeration.
Source(s):
Statistics Canada, Annual Survey of Manufacturers, 1989 and 1999.
Date modified: