Linear congruential generator - how to choose seeds and statistical tests

I need to do a linear congruential generator that will successfully pass the selected statistical tests.

My question is: how to choose numbers for the generator properly and which statistical tests should I choose?

I thought about:

1. Chi-Square Frequency Test for Uniformity

   • Collect 10,000 numbers per generation method

   • Sub-divide[0.1) into 10 equal subdivisions

2. Kolmogorov-Smirnov Test for uniformity

   • Since K-S Test works better with a smaller set of numbers, you may use the first 100 out fo the 10,000 that you generated for the Chi-Square Frequency Test

Here is the code example:

        a = 30202383
        c = 99282983
        m = 16483727
        xi = 16**56

        def seed(x):
            global xi
            xi = x

        def rng():
            global xi
            xi = (a*xi + c)%m
            return xi

        for i in range(10):
            print (rng())