13 Note that, since we now have an additional time dimension, the com-
patibility between the CLM and Poisson approaches requires the inclusion
of dummies for each combination of time period and sector.
14A number of counties in Virginia are merged with independent cities.
This is because the data for some independent variables (those obtained
from the Regional Economic Information System database) are reported in
this manner.
15Note also that the correlation between the spatial distribution of new
plants in 1989 and 1997 is 99,7%. The distribution of these plants by the 2-
digits SIC sectors in the two considered years also exhibit a strong correlation
(96,4%).
16 While industry-level wages would be preferable, these data present a
high number of missing values at the county level.
17In the definition of this variable we include SICs 20 to 39 (Manufac-
turing), SICs 50 and 51 (Wholesale), SICs 52 to 59 (Retail), SICs 60 to 67
(Finance, Insurance and Real State), and SICs 70 to 89 (Services Industries).
18 All variables were introduced in logarithmic form. Wages and salary
earnings per job, personal income and population were taken from the Re-
32