Tests of Significance - Formula Sheet
- Samples: \( N^n \) with replacement, \( ^NC_n \) without.
- \( SE(\bar{X}) = \sigma/\sqrt{n} \); \( SE(p) = \sqrt{PQ/n} \).
- \( SE(\bar{X} - \bar{Y}) = \sqrt{\sigma_X^2/m + \sigma_Y^2/n} \); equal variances: \( \sigma\sqrt{1/m + 1/n} \).
- \( SE(p_X - p_Y) = \sqrt{\hat{p}\hat{q}(1/m + 1/n)} \), \( \hat{p} = \dfrac{mp_X + np_Y}{m + n} \), \( \hat{q} = 1 - \hat{p} \).
- One mean: \( z_0 = \dfrac{\bar{x} - \mu_0}{\sigma/\sqrt{n}} \) (use s if \( \sigma \) unknown).
- Proportion: \( z_0 = \dfrac{p - p_0}{\sqrt{p_0q_0/n}} \).
- Critical values of Z: 5%: 1.645 (one-sided), 1.96 (two-sided); 1%: 2.33 (one-sided), 2.58 (two-sided).
- Rules: \( |z_0| \geq z_{\alpha/2} \) (two-sided), \( z_0 > z_{\alpha} \) (right), \( z_0 < -z_{\alpha} \) (left).
- Type I error: reject true \( H_0 \). Type II error: do not reject false \( H_0 \). \( \alpha \) = upper limit of P(type I error).
- Large sample: \( n \geq 30 \); two samples \( m, n \geq 30 \); proportions also \( np > 5 \), \( n(1-p) > 5 \).
More for this chapter
Book Back Questions18 textbook MCQs · solved
Additional MCQs15 extra MCQs · solved
Practice TestInteractive · instant score
Book Back TestTest yourself on the textbook set
Additional MCQ TestTest yourself on the extra set
Study NotesConcepts & methods