. R . R 2 . F b . D-W c . 1 Big Cities...

	R	R²	F^b	D-W^c

1 Big Cities (N = 47)^†
$\begin{matrix} PERON = 84.38 + \underset{{(.40)}^{a}}{.56 IND WORKERS} + \underset{(.51)}{.50 MIGRANTS} - \underset{(- .44)}{1.03 LITERACY} \\ + \underset{(.32)}{.000022 POPULATION} \end{matrix}$	.73	.53	11.7	2.31
2. Townships (N = 197)^†
$\begin{matrix} PERON = 64.58 + \underset{(.16)}{4.01 IND WAGE} + \underset{(.38)}{.69 MIGRANTS} + \underset{(.24)}{.02 HP / INDUSTRY} \\ + \underset{(.24)}{2.11 UNEMPLOYMENT} - \underset{(- .17)}{.26 GROWTH} + \underset{(.17)}{.32 WORKING CLASS} \\ + \underset{(.14)}{.15 INEQUALITY} - \underset{(- .16)}{.53 IND WORKERS} \end{matrix}$	.69	.47	21.2	1.05
3. Countryside (N = 95)^†
$\begin{matrix} PERON = 19.03 * - \underset{(- .30)}{.20 EU / IMMIGRANTS} + \underset{(.33)}{.91 MIGRANTS} + \underset{(.18)}{.14 SMALL HOLDINGS } \\ + \underset{(.18)}{.76 OLDER MEN } \end{matrix}$	.44	.19	5.3	.95

	R	R²	F^b	D-W^c

1 Big Cities (N = 47)^†
$\begin{matrix} PERON = 84.38 + \underset{{(.40)}^{a}}{.56 IND WORKERS} + \underset{(.51)}{.50 MIGRANTS} - \underset{(- .44)}{1.03 LITERACY} \\ + \underset{(.32)}{.000022 POPULATION} \end{matrix}$	.73	.53	11.7	2.31
2. Townships (N = 197)^†
$\begin{matrix} PERON = 64.58 + \underset{(.16)}{4.01 IND WAGE} + \underset{(.38)}{.69 MIGRANTS} + \underset{(.24)}{.02 HP / INDUSTRY} \\ + \underset{(.24)}{2.11 UNEMPLOYMENT} - \underset{(- .17)}{.26 GROWTH} + \underset{(.17)}{.32 WORKING CLASS} \\ + \underset{(.14)}{.15 INEQUALITY} - \underset{(- .16)}{.53 IND WORKERS} \end{matrix}$	.69	.47	21.2	1.05
3. Countryside (N = 95)^†
$\begin{matrix} PERON = 19.03 * - \underset{(- .30)}{.20 EU / IMMIGRANTS} + \underset{(.33)}{.91 MIGRANTS} + \underset{(.18)}{.14 SMALL HOLDINGS } \\ + \underset{(.18)}{.76 OLDER MEN } \end{matrix}$	.44	.19	5.3	.95

Numbers in parentheses are beta coefficients, which provide a standardized means of estimating and comparing the relative “weight” or importance of the independent variables. Beta is defined as the product of the slope times the ratio of the standard deviation of the independent variable to the standard deviation of the dependent variable.

F gives a way of estimating the statistical significance of the multiple correlation coefficient. All correlations here are highly significant.

D-W stands for the Durbin-Watson statistic, which estimates the significance of serial correlation among residual values. This effect seems to occur in equation 2 and possibly in equation 3, probably because the counties were grouped by province and Perón did uniformly better or worse in some provinces than in others; but this kind of serial correlation would not appear to affect the interpretive value of the equations in any serious way.

Value of constant not significant at the .05 level.

†

For the Big Cities equation, the average absolute value of product-moment correlation coefficients between all independent variables (excluding diagonals) is .28, and the maximum for any single pair is .56; for the Townships equation, the average is .15 and the maximum is .51; for the Countryside equation, the average is .15 and the maximum is .35.

View Large

This Feature Is Available To Subscribers Only