The compared subscript of the statistic gets the subscript of the statistic (that is, z α or z_{\alpha) orwithaOr z α / 2 z_{\alpha/2}witha / 2The subscript of) is determined based on a one-sided test or a two-sided test! !
其实就是:单侧时α的分子是 1,双侧时α的分子是 2
- For one-sided inspection: use α \alphaα ;
- The two-sided test is: use α / 2 \alpha/2α / 2。
Here the subscripts of the agreed statistics are all AAA:
var A = 统计量下标;
if(单侧检验)
A = α;
else
if(双侧检验)
A = α/2;
Of course t A, F α / 2 t_{A}, F_{\alpha/2}tA、Fa / 2The value of etc. still needs to be determined according to the degree of freedom of the specific topic (of course, for the z statistic, it is 1.645, 1.96 and 2.58)
z statistics
- ∣ z ∣ < ∣ z A ∣ |z |< |z_{A}| ∣z∣<∣zA∣:Do not reject the null hypothesisH 0 H_0H0;
- ∣ z ∣ > ∣ z A ∣ |z |> |z_{A}| ∣z∣>∣zA∣ : Reject the null hypothesisH 0 H_0H0。
t statistic
- ∣ t ∣ < ∣ t A ∣ |t| < |t_{A}| ∣t∣<∣tA∣:Do not reject the null hypothesisH 0 H_0H0;
- ∣ t ∣ > ∣ t A ∣ |t| > |t_{A}| ∣t∣>∣tA∣ : Reject the null hypothesisH 0 H_0H0。
χ 2 \ chi ^ 2 χ2 statistics
χ 2 \ chi ^ 2 χ2 Statistics are usually one-sided test, so hereA = α A = \alphaA=α , directly useα \alphaα a
- χ 2 <χ α 2 \ chi ^ 2 <\ chi ^ 2_ \ alpha χ2<χa2: Do not reject the null hypothesis H 0 H_0H0;
- χ 2 ≥ χ α 2 \ chi ^ 2 \ ge \ chi ^ 2_ \ alpha χ2≥χa2: Reject the null hypothesis H 0 H_0H0。
F statistics
- One-sided inspection:
- F < F α F < F_{\alpha} F<Fa: Do not reject the null hypothesis H 0 H_0H0;
- F > F α F > F_{\alpha} F>Fa: Reject the null hypothesis H 0 H_0H0;
- Two-sided inspection:
- F 1 - α / 2 ≤ F ≤ F α / 2 F_ {1- \ alpha / 2} \ le F \ le F _ {\ alpha / 2} F1 - a / 2≤F≤Fa / 2: Do not reject the null hypothesis H 0 H_0H0。
- F < F 1 − α / 2 或 F > F α / 2 F < F_{1-\alpha/2} 或 F > F_{\alpha/2} F<F1 - a / 2Or F>Fa / 2: Reject the null hypothesis H 0 H_0H0。
P value test
- P > A P > A P>A : Do not reject the null hypothesisH 0 H_0H0;
- P < A P < A P<A : Reject the null hypothesisH 0 H_0H0。