Hypothesis testing is a procedure that allows us to (depending on certain decision rules) confirm a starting hypothesis, called the null hypothesis, or to reject this null hypothesis in favor of the alternative hypothesis. 

Hypothesis testing usually involves the following steps:

1. Formulate the hypothesis:

• The null hypothesis H0,
• The alternative hypothesis H1.

2. Determine the significance level ? of the test.
3. Determine the probability distribution that corresponds to the sampling distribution.
4. Calculate the critical value of the null hypothesis and calculate rejection/acceptance interval(s).
5. Establish the decision rules:
   • If the statistics observed in the sample are located in the acceptance region, do not reject the null hypothesis H₀;
   • If the statistics observed on the sample are located in the rejection region, reject the null hypothesis H₀ and accept the alternative hypothesis H₁.
6. Take the decision to accept or to reject the null hypothesis on the basis of the observed sample.

Stats Master VCL supports three most common types od hypothesis testing: 

Testing on one sample 

We are testing if chosen sample parameter p is equal to presumed value p₀. In mathematical form this can be written as:

H0: p=p0
H1: p<>p0

Testing on two samples 

We are testing whether two samples, both described by a particular parameter, are the same or different. If p₁ describes first sample and p₁ second sample, then the following two cases arise:

H0: p1=p2
H1: p1<>p2

H0: p1-p2=0
H1: p1-p2<>0

Testing on more than two samples 

As for a test performed on two samples, hypothesis testing is performed on more than two samples to determine whether these populations are different, based on comparing the same parameter from all of the populations being tested. Only one scenario is possible:

H0:
p1=p2=...=pn H1:
p1<>p2<>...<>pn