5.2 THE KOLMOGOROV – SMIRNOV TEST
Figure 5.1 plots the sample distribution function for n = 100 and n = 1000 samples of data derived from a uniform distribution function F(x). The Kolmogorov – Smirnov Test is a goodness-of-fit test; is a sample of n data values X0, X1,…, Xn−1, derived from independent and identical random trials consistent with a specified distribution function F(x) = Pr{Xj ≤ x}? The law of large numbers implies that the sample distribution function
converges as the sample size n increases
with probability 1.
The Kolmogorov–Smirnov statistics
measures the vertical deviation of F(x) from the sample distribution function , where
- measures the deviation when and
- the deviation when
The Kolmogorov – Smirnov ...
Get Computer Security and Cryptography now with the O’Reilly learning platform.
O’Reilly members experience books, live events, courses curated by job role, and more from O’Reilly and nearly 200 top publishers.