描述统计:平均数是总和除以 n;中位数是排序后数据的中间值(n 为偶数时取中间两个数的平均)。样本标准差 s = √(Σ(x − x̄)²/(n − 1))。z 分数 z = (x − μ)/σ 表示某个值离平均数多少个标准差。
标准化
z = 0.4
标准正态分布表
Φ(0.4) = 0.6554
P = 0.6554
答案
P = 0.6554
5.置信区间
答案: E = 19.11
均值的置信区间:x̄ ± 误差范围。总体 σ 已知时,误差范围为 z·σ/√n;只有样本标准差 s 时,用自由度为 n − 1 的 t:t·s/√n。临界值:z = 1.645(90%)、1.96(95%)、2.576(99%)。要使误差范围不超过 E,需要 n ≥ (z·σ/E)²,并向上取整。
临界值
df = n − 1 = 10, t = 3.169
误差范围
E = 3.169·20/√11 = 19.11
答案
E = 19.11
6.置信区间
答案: 上限 = −2.365 kg
Interval for a difference: estimate ± critical value × standard error. For two independent means with known σ: SE = √(σ₁²/n₁ + σ₂²/n₂) and z. With equal unknown variances: pooled s_p and t with n₁ + n₂ − 2 degrees of freedom. For paired data, work with the differences: d̄ ± t·s_d/√n.
合并标准差
sp² = (5·8.5² + 5·8²)/10 = 68.13
sp = 8.254
误差范围
E = 1.812·8.254·√(1/6 + 1/6) = 8.635
区间
−11 ± 8.635 → [−19.63, −2.365]
答案
上限 = −2.365 kg
7.假设检验与置信区间
答案: t = −1.8
均值检验:检验统计量衡量样本均值离 H₀ 所声称的值有多少个标准误:σ 已知时 z = (x̄ − μ₀)/(σ/√n),由样本估计时 t = (x̄ − μ₀)/(s/√n)。置信区间为 x̄ ±(临界值)·(标准误)。
标准误
SE = 20/√36 = 20/6 = 3.333
检验统计量
t = (44 − 50)/3.333 = −1.8
答案
t = −1.8
t0.025; df = 35 = 2.03
|t| < 2.03,所以在 5% 水平下不拒绝 H₀(双侧)。
8.假设检验与置信区间
答案: z = 1.831
Hypothesis test: the test statistic = (estimate − value under H₀)/(standard error under H₀). The p-value is the probability, assuming H₀ is true, of a statistic at least as extreme as the one observed: the area in one tail for a one-sided H₁, twice the tail area for a two-sided H₁. Reject H₀ when p ≤ α.