In Figure 4, the maximum change of electrical signal on the leaf is 0.0033 V, and the minimum is 0.000 V, the median is 0.0017 V, the average is 0.0006 V, the standard deviation is 0.001092, and the coefficient of dispersion is 1.82.

After removing the two unreliable data, we find that the maximum number of the changes of electrical signal on leaf is 0.0003 V, the minimum is 0.0000 V, the median is 0.0002 V, the average is 0.00012 V, the standard deviation is 8.57E - 05, and the coefficient of dispersion is 0.623.

where [alpha] is the

coefficient of dispersion and [gamma] is the nonlinear coefficient.

The coefficient of dispersion measures the horizontal uniformity of assessments.

The coefficient of dispersion for CAUV assessments is 43.0%.

where V(x, t) > 0 is the drift of the process, that is, the mean advective velocity, [alpha] is the order of fractional differentiation, [D.sub.+](x, t) = (1 + [beta]) D(x, t)/2, [D.sub._](x, t) = (1 - [beta]) D(x, t)/2, D(x, t) > 0 is the

coefficient of dispersion, and -1 [less than or equal to] [beta] [less than or equal to] 1 indicates the relative weight of forward versus backward transition probability.

A useful measure of accuracy is the

coefficient of dispersion (COD), which is the average error (average residual) produced by the regression estimates; the COD equals the median residual/median selling price.

He devotes considerable attention to discussing the most accepted measure of assessment uniformity: the

coefficient of dispersion (COD).

Table 1 Ratio Statistics for Unstandardized Predicted Value/Sale Price per Square Foot Mean 1.051 Median 1.001 Minimum .728 Maximum 1.662 Standard deviation .229 Range .934 Price-related differential 1.035 Coefficient of dispersion .181 Coefficient of variation (mean-centered) 21.8% (median-centered) 23.4% Coefficient of concentration (within 50% of median inclusive) 95.7%

(1.) The coefficient of variation (COV) is the standard error of the estimate divided by the mean value of the dependent variable; a measure of the relative chance for error in a forecast or estimate of the dependent variable; the coefficient of dispersion (COD) is the ratio of a measure of absolute dispersion to the appropriate average, usually expressed as a percentage; computed from either the quartile or the mean deviation, but usually expressed as a ratio of the standard deviation to the mean; a measure of relative dispersion.