U.S. Immigration Policy & Mexican Illegal Immigrants. A Case Study
V.Qualitative Analysis
The hypothesis is based upon the assumption that Mexican illegal immigrants will
keep crossing the border regardless of U.S. law enforcement. Therefore, from a rational
choice perspective, I will use GDP per capita for the U.S. and Mexico as indicators for
economic incentives. The number of Mexican illegal immigrants is defined as the
dependent variable.
The data is represented by 10 year periods from 1850 – 2000, since the population
census is conducted every 10 years, with 13 observations.
Once a simple regression is run using Minitab the following results are generated:
Mexican Immigrants (thousands) = - 809 - 1.01 GDP per capita MX + 0.435 GDP Per Capita US (Dollars)
Predictor
Coefficient
SE Coef
T
P
Constant
-808.6
347.7 -2.33
0.045
GDP per capita MX
-1.0080
0.3380 -2.98
0.015
GDP Per Capita US (Dollars)
0.43544
0.06513
6.69
0.000
S = 640.429 R-Sq = 95.0% R-Sq(adj) = 93.9%
Based upon a 95% confidence level, the flow of Mexican illegal immigrants is explained
by US GDP per capita and Mexico GDP per capita, with a p-value of 0.000, and 0.045
respectively.
It is worth noting that the year 2000 is singled out as an outlier. This phenomenon
can be explained by the unusual increase in GPD per capita in both countries. Also since
the data reflects information in 10 year periods the increase in Mexican immigrants from
4,447 (thousands) to 8,780 (thousands) can be explained by the transformation that took
place in Mexico during this decade, i.e. economic crisis 1994, Luis Donaldo Colosio
assassination and uncertainty for the democratic transition that took place during 2000.
Regardless of this unusual observation, the validity of the model is strong, as can
be evidenced by the overall fitting of the statistical model and data points, R
2
(goodness
of fit). It is expected that the normal plot of residuals “should generally form a straight
line if the residuals are normally distributed. If the points on the plot depart from a
straight line, the normality assumption may be invalid” (Minitab). The following graph
22
There is no data available for GDP per capita for the following years: 1860, 1880, and 1920
Convention