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 = −1
标准正态分布表
Φ(−1) = 0.1587
P = 1 − 0.1587 = 0.8413
答案
P = 0.8413
5.置信区间
答案: 下限 = −0.8205 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 = 15, t = 2.947
误差范围
E = 2.947·6/√16 = 4.421
区间
3.6 ± 4.421 → [−0.8205, 8.021]
答案
下限 = −0.8205 mmHg
6.置信区间
答案: n = 2655
Confidence interval for a proportion: p̂ ± z·√(p̂(1 − p̂)/n), where p̂ = x/n. To reach a margin E you need n ≥ z²·p(1 − p)/E², rounded up; without a prior estimate use p = 0.5, which gives the largest n.
解出 n
n = 2.576²·0.8·0.2/0.02² = 2654
向上取整
n = 2655
答案
n = 2655
7.假设检验与置信区间
答案: t = −2.008
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 = (16·9² + 8·2.5²)/24 = 56.08
sp = 7.489
标准误
SE = 7.489·√(1/17 + 1/9) = 3.087
检验统计量
t = (85 − 91.2)/3.087 = −2.008
答案
t = −2.008
df = 24 时,双侧 5% 的临界值为 2.064;|t| 更小,所以不拒绝 H₀。
8.假设检验与置信区间
答案: U = 504.6
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)。