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 = −2
标准正态分布表
Φ(−2) = 0.02275
P = 1 − 0.02275 = 0.9772
答案
P = 0.9772
5.置信区间
答案: 下限 = 6.431 mmHg
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.
临界值
df = 10, t = 3.169
误差范围
E = 3.169·0.7/√11 = 0.6688
区间
7.1 ± 0.6688 → [6.431, 7.769]
答案
下限 = 6.431 mmHg
6.置信区间
答案: n = 417
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。
解出 n
n = (1.645·31/2.5)² = 416.1
向上取整
样本量是整数,向下取整会使误差范围过大。
n = 417
答案
n = 417
7.假设检验与置信区间
答案: t = −2.704
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.
合并方差
sp² = (6·7² + 14·4²)/20 = 25.9
sp = 5.089
标准误
SE = 5.089·√(1/7 + 1/15) = 2.33
检验统计量
t = (87 − 93.3)/2.33 = −2.704
答案
t = −2.704
df = 20 时,双侧 5% 的临界值为 2.086;|t| 更大,所以拒绝 H₀。
8.假设检验与置信区间
答案: n = 174
检验的样本量:在水平 α 下的单侧 z 检验中,要以功效 1 − β 检测出真实偏移 δ,标准误必须满足 δ = (z_α + z_β)·σ/√n,所以 n = ((z_α + z_β)·σ/δ)²,向上取整。