Journal article Open Access
The purpose of this paper is to explain the importance of randomness in data analysis. We point out the difference between random data and random selection. The scope of this paper is limited to randomness in discrete data. We explain the various tests used by NIST as the basis to understand randomness testing in discrete data. We also present an indirect test for randomness by relying on trend testing. Randomness is defined as lacking predictable pattern. Predictable pattern may be seen through trend. We argue that if there is a significant trend, the series is not random and vice versa. In this paper, we claim that trend test may be used an indirect test for randomness.
ARTICLE 5, Vol 4, No 1, Direct and Indirect Tests for Randomness.pdf