Member Avatar for McLaren

Hello,

I am tring to test with this software:
http://www.stat.fsu.edu/pub/diehard/

I make Hex file of random integers with 8 digis per integer, 10 integers per line as in documentaion.

Then run
ASC2BIN.EXE

but it creates just empty file.

My file looks like this:

493489c07f3ba47470011f170b9f5960668068d25732147d44af029b0bfed2a6682b77cb76a5d488

this is one line, but can be aded as much as I need those lines.
What could be wrong?

  • 1 Contributor
  • 3 Replies
  • 406 Views
  • 3 Days Discussion Span
  • Latest Post Latest Post by McLaren
Member Avatar for McLaren

everything ok. Needs longer file. One row probably was not enough

Member Avatar for McLaren

I am having one more question - how to interpret test result maybe someone knows?

There are those p-values, but there is no normal answer what does it mean. There is full of sentences what it does not mean :D

for example:

The p-value is not the probability that the null hypothesis is true, nor is it the probability that the alternative hypothesis is false.
In fact, frequentist statistics does not, and cannot, attach probabilities to hypotheses. Comparison of Bayesian and classical approaches shows that a p-value can be very close to zero while the posterior probability of the null is very close to unity (if there is no alternative hypothesis with a large enough a priori probability and which would explain the results more easily). This is Lindley's paradox.

BUt found explainations as well:

A p-value is the evidence against a null hypothesis. It does not tell you that the null hypothesis is correct or right, only if there is significant evidence to reject it or not. Commonly a p-value under 0.05 is considered significant.

So ok - when less than 0.05 I can reject hyphotesis that my rng is good. But then I took test which should fail.

For example this:

http://pastebin.com/t8yhFUPL

we can see at the end:

The 9 p-values were
        .272641   .364408   .994693   .235347   .923025
        .905169   .159363   .338623   .002076
  A KSTEST for the 9 p-values yields  .767290

so it is more than 0.05 so I am interpreting that is passes.

if you look there

http://www.stat.fsu.edu/pub/diehard/cdrom/

there is file canada.bit which I was testing. And in the cdrom.doc it is told that this test should fail.

So how to understand?

Be a part of the DaniWeb community

We're a friendly, industry-focused community of developers, IT pros, digital marketers, and technology enthusiasts meeting, networking, learning, and sharing knowledge.