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 = (545 − 500)/75 = 0.6
答案
z = 0.6
5.置信区间
答案: 下限 = 61.31
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 = 2.228
误差范围
E = 2.228·4/√11 = 2.687
区间
64 ± 2.687 → [61.31, 66.69]
答案
下限 = 61.31
6.置信区间
答案: n = 569
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 = (1.645·29/2)² = 568.9
向上取整
样本量是整数,向下取整会使误差范围过大。
n = 569
答案
n = 569
7.假设检验与置信区间
答案: t = 2.705
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 = (6·3.5² + 9·5.5²)/15 = 23.05
sp = 4.801
标准误
SE = 4.801·√(1/7 + 1/10) = 2.366
检验统计量
t = (114.5 − 108.1)/2.366 = 2.705
答案
t = 2.705
df = 15 时,双侧 5% 的临界值为 2.131;|t| 更大,所以拒绝 H₀。
8.假设检验与置信区间
答案: z = 2.241
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.