📚 Modelling Human Rights Data with A-Level Statistics | 用 A-Level 统计方法建模人权数据
Human rights indicators often appear as numerical or categorical data. This article connects these real-world datasets to the statistical tools in Edexcel A-Level Mathematics.
人权指标常以数值或分类数据的形式出现。本文将现实世界数据与 Edexcel A-Level 数学中的统计工具联系起来。
1. Data Types and Measurement Scales | 数据类型与测量尺度
In Edexcel Statistics, data can be quantitative (discrete or continuous) or qualitative (nominal or ordinal). Human rights variables include civil liberty scores (ordinal), prison populations (discrete), and income shares (continuous).
在 Edexcel 统计中，数据可分为定量（离散或连续）或定性（名义或有序）。人权变量包括公民自由得分（有序）、监狱人口（离散）和收入份额（连续）。
Nominal data classify categories such as country or treaty ratified; ordinal data rank outcomes like ‘fully free, partly free, not free’. These distinctions determine which statistical tests are valid.
名义数据用于区分国家或是否批准条约等类别；有序数据用于排序结果，如 “完全自由、部分自由、不自由”。这些区分决定了哪些统计检验有效。
2. Sampling and Data Collection | 抽样与数据收集
A reliable human rights study begins with a random sample. Simple random sampling, stratified sampling, and cluster sampling all appear in the Edexcel specification and can be applied to household surveys on access to justice or education.
可靠的人权研究始于随机样本。简单随机抽样、分层抽样和整群抽样均出现在 Edexcel 考纲中，可应用于关于司法或教育机会的家庭调查。
Bias arises from non-response or under-coverage of marginalised groups. In exam questions, you should identify sampling bias and suggest improvements such as oversampling rural areas.
无回应或边缘群体覆盖不足会产生偏差。在考试题目中，你应识别抽样偏差并提出改进措施，例如对农村地区进行过度抽样。
3. Measures of Central Tendency and Spread | 集中趋势与离散程度
The mean, median, and mode summarise an indicator such as years of schooling. The median is often preferred when the distribution is skewed by a few extreme countries.
均值、中位数和众数可概括如受教育年限等指标。当分布因少数极端国家而偏斜时，中位数通常更可取。
Standard deviation and interquartile range measure spread. A large standard deviation in press freedom scores signals high cross-country inequality in media freedom.
标准差和四分位距衡量离散程度。新闻自由得分的标准差较大，表明各国媒体自由的差异很大。
The variance formula Σ(xᵢ − x̄)²/n is central to Edexcel Statistics. You may be asked to interpret it in context using units.
方差公式 Σ(xᵢ − x̄)²/n 是 Edexcel 统计的核心。考试可能要求你在具体情境中解释其单位。
4. Probability Models for Binary Outcomes | 二元结果的概率模型
Many human rights outcomes are binary: a detention is lawful or unlawful, a child is enrolled or not. A binomial model requires fixed n, independent trials, and constant probability p.
许多人权结果是二元的：拘留合法或不合法，儿童入学或未入学。二项模型要求固定的 n、独立试验和恒定概率 p。
P(X = r) = ⁿCᵣ pʳ (1 − p)ⁿ⁻ʳ
The probability mass function is shown above. For example, if 80% of schools in a region meet safety standards, the probability that exactly 12 of 15 randomly chosen schools meet the standard is ¹⁵C₁₂ (0.8)¹² (0.2)³.
上述为概率质量函数。例如，若某地区 80% 的学校达到安全标准，则随机抽取 15 所学校中恰好 12 所达标的概率为 ¹⁵C₁₂ (0.8)¹² (0.2)³。
The mean np and variance np(1 − p) allow quick predictions. Edexcel exam questions often ask you to evaluate whether a binomial model is appropriate.
均值 np 和方差 np(1 − p) 可进行快速预测。Edexcel 考题常要求你判断二项模型是否合适。
5. The Normal Distribution and Human Rights Indicators | 正态分布与人权指标
Continuous indicators such as life expectancy or access-to-water percentages often approximate a normal distribution. The standard normal variable Z = (X − μ) / σ is used for probability calculations.
预期寿命或安全饮水覆盖率等连续指标往往近似服从正态分布。标准正态变量 Z = (X − μ) / σ 用于概率计算。
Z = (X − μ) / σ
If a country’s adult literacy rate has mean 85% and standard deviation 5%, the probability that a randomly selected region has literacy above 90% is P(Z > 1.0) = 0.1587.
若某国成人识字率的均值为 85%、标准差为 5%，则随机选择一个地区识字率超过 90% 的概率为 P(Z > 1.0) = 0.1587。
The inverse normal function is used to find thresholds, such as the literacy level below which the worst 10% of regions fall.
反查正态分布函数可用于确定阈值，例如最差 10% 地区所低于的识字水平。
6. Hypothesis Testing for Proportions | 比例假设检验
Hypothesis testing for a proportion uses the normal approximation when np > 5 and n(1 − p) > 5. For example, test whether the proportion of detainees receiving a fair trial is less than the claimed 0.75.
比例假设检验在 np > 5 且 n(1 − p) > 5 时使用正态近似。例如，检验接受公平审判的被拘留者比例是否低于所称的 0.75。
Set H₀: p = 0.75 and H₁: p < 0.75. Calculate the test statistic z = (p̂ − p₀) / √[p₀(1 − p₀)/n]. Compare with the critical value at the 5% significance level.
设 H₀: p = 0.75，H₁: p < 0.75。计算检验统计量 z = (p̂ − p₀) / √[p₀(1 − p₀)/n]。与 5% 显著性水平下的临界值比较。
The conclusion must be written in context: ‘There is insufficient evidence at the 5% level to conclude that the fair-trial rate is below 0.75.’
结论必须结合语境表述：”在 5% 水平下，尚无充分证据表明公平审判率低于 0.75。”
7. Correlation and Regression | 相关与回归
Scatter diagrams and the product moment correlation coefficient (PMCC) assess linear association between two indicators, such as press freedom index and voter turnout.
散点图和积矩相关系数（PMCC）可评估两个指标之间的线性关系，例如新闻自由指数与选民投票率。
r = Sxy / √(Sxx × Syy)
The PMCC r ranges from −1 to 1. A positive r suggests higher press freedom accompanies higher turnout, but correlation does not imply causation.
PMCC r 的取值范围为 −1 到 1。正的 r 表明更高的新闻自由伴随更高的投票率，但相关不代表因果。
Least squares regression gives a line y = a + bx, where b = Sxy / Sxx. Use it to predict an outcome, but beware of extrapolation beyond the observed range.
最小二乘回归给出直线 y = a + bx，其中 b = Sxy / Sxx。可用于预测结果，但要注意超出观测范围的外推风险。
8. Contingency Tables and Chi-Squared Tests | 列联表与卡方检验
Categorical human rights data can be arranged in a contingency table, for example access to legal aid (yes/no) by region (urban/rural). The chi-squared statistic χ² = Σ (Oᵢ − Eᵢ)² / Eᵢ tests independence.
分类人权数据可排成列联表，例如按地区（城市/农村）分类的法律援助获得情况（是/否）。卡方统计量 χ² = Σ (Oᵢ − Eᵢ)² / Eᵢ 用于独立性检验。
χ² = Σ (Oᵢ − Eᵢ)² / Eᵢ
The degrees of freedom are (rows − 1)(columns − 1). If the calculated χ² exceeds the critical value, reject the null hypothesis of no association.
自由度为（行数 − 1）×（列数 − 1）。若计算得到的 χ² 超过临界值，则拒绝无关联的原假设。
Edexcel questions often provide expected frequencies; you must interpret the result in the context of the original data.
Edexcel 考题常给出期望频数；你必须结合原始数据解释结果。
9. Time Series and Trend Analysis | 时间序列与趋势分析
Human rights performance is monitored over time using time series. Moving averages smooth short-term fluctuations in indicators such as annual reports of child labour.
人权表现通过时间序列进行监测。移动平均可平滑童工年度报告等指标的短期波动。
Seasonal variation may appear when data are collected quarterly. Edexcel requires you to calculate centred moving averages and estimate seasonal effects.
按季度收集的数据可能出现季节波动。Edexcel 要求你计算中心移动平均并估计季节效应。
Trend lines help evaluate whether a policy intervention, such as a new education law, is associated with a sustained improvement in enrolment.
趋势线有助于评估某项政策干预（如新教育法）是否与入学率持续改善相关。
10
Published by TutorHao | A-Level Mathematics Revision Series | aleveler.com
更多咨询请联系16621398022（同微信）
屏轩国际教育cambridge primary/secondary checkpoint, cat4, ukiset,ukcat,igcse,alevel,PAT,STEP,MAT, ibdp,ap,ssat,sat,sat2课程辅导，国外大学本科硕士研究生博士课程论文辅导Cancel reply