Re: Significance level of a simulation

"Luis A. Afonso" wrote:
> Without further details nobody can help you. [...]

It's not needed to write what you wrote; the phrase I quoted is clear
enough.
I'll try to elaborate my question, but I know that a long post is annoying.

The process I simulate takes in input 2 parameters and outputs N integer
numbers with normal distribution (with known mean and variance).
Changing the value of the 2 parameters the N numbers can be:
1) too binned and they don't look as normally distributed (I use the KS test
to check that);
2) very well normally distributed;
3) a little binned, so that sometimes they look as normally distributed, but
sometimes they fails big the KS test (numbers not normally distributed).

I need a method which says:
when a1 <= parameter_1 <= a2 and b1 <= parameter_2 <= b2 and N < c, then the
numbers are normally distributed with a confidence of x%.

Cristiano


.

Relevant Pages

  • Re: jointly gaussian
    ... variables with normal distribution? ... if two random variables have a bivariate normal ... point leads me to suspect that you mean something else by the ... phrase "independent of each other" ...
    (comp.dsp)
  • Re: Histogram and Normality test
    ... The histogram is very close to the normal distribution, but the data always fails the normality hypothesis tests. ... I know reducing the number of bins help get a smoother curve, but am I correct in assuming that these spikes are the reason the tests fail? ...
    (comp.soft-sys.matlab)