stats chapter 7

null hypothesis (H_o)

null hypothesis is supported unless the data proves that it is false. Default assumption usually saying there is no effect.

alternative hypothesis (H_a)

hypothesis is supported if the data provided is sufficient enough to reject null hypothesis. Trying to find evidence for it. There is an affect.

significance level test (α)

maximum probability of type I error that we tolerate in a significance test. Usually around 0.01, 0.05, 0.10.

Type I error

the error of rejecting a true null hypothesis

Type II error

the error of not rejecting the a false hypothesis.

If 𝐻𝑎: 𝜇 > 𝜇0 then p-value

= P(z > observed z) right tail test in minitab

If 𝐻𝑎: 𝜇 < 𝜇0 then p-value

= P(z < observed z) left tail test minitab

If 𝐻𝑎: 𝜇 ≠ 𝜇0 then p-value

=2P(z > |observed z|) 2 tail test in minitab

If the p-value < α

reject H₀ and accept H_a

If the p-value > α

we fail to reject H₀