Formulating a Hypothesis in Statistics

A null hypothesis states that there is a significant statistical difference between the measure of A and B.

The cut-off point for deciding to accept or reject the null hypothesis is the probability value (1-β).

In hard sciences, the alpha level is usually relatively high, such as 0.1 or 0.2.

Type 1 error occurs when the researcher accepts the hypothesis when in fact it should be rejected.

A well-formed hypothesis is usually presented in the 'alternative' form.

If the probability value (p) is small, it indicates that the null hypothesis is likely true.

The probability of committing a type 1 error is always equal to the alpha level (α).

Setting α=0 can help avoid all type 1 errors.

Increasing the rigor of research can help reduce both type 1 and type 2 errors.

Chi-square test is used to determine differences in population means.

Pearson Correlation Test can help determine if there is a linear relationship between two variables.

A pre-existing variable is under the control of the researcher.

In experimental research, subjects are assigned to groups without bias.

It is easy to conduct a true experiment in computer science.

Setting up higher constraint empirical research is recommended when possible.

Type 1 and Type 2 errors are related to testing hypotheses.

The goal of scientific research is to find proof for claims made.