IGCSE AQA Statistics: Core Knowledge Points Summary | IGCSE AQA 统计：核心知识点梳理

📚 IGCSE AQA Statistics: Core Knowledge Points Summary | IGCSE AQA 统计：核心知识点梳理

This article provides a comprehensive summary of the core topics covered in the AQA IGCSE Statistics syllabus (8382). From data collection and representation to probability distributions and time series analysis, mastering these foundations is essential for success. Each section is presented with clear bilingual explanations to support learners of all backgrounds.

本文全面梳理了 AQA IGCSE 统计学（8382）课程的核心知识点，涵盖数据收集与表示、概率分布、相关回归、时间序列分析等内容。每部分均提供中英双语讲解，帮助学生扎实掌握考试重点。

1. Types of Data and Data Collection | 数据类型与数据收集

Data can be classified as primary data (collected directly by the researcher) or secondary data (obtained from existing sources). Primary data is tailored to the research question but may be time-consuming to collect; secondary data is readily available but may lack precision.

数据可分为一手数据（研究者直接收集）和二手数据（来自已有资料）。一手数据针对性强但收集耗时；二手数据获取便利但可能不够精确。

Furthermore, data types include qualitative (categorical) data, such as eye colour or car brand, and quantitative (numerical) data, which can be discrete (countable, e.g., number of students) or continuous (measurable, e.g., height). Ordinal data is a type of categorical data with a natural order, like satisfaction ratings.

此外，数据类型包括定性（分类）数据，如眼睛颜色或汽车品牌，以及定量（数值）数据。定量数据又分为离散型（可数，如学生人数）和连续型（可测量，如身高）。有序数据是一种具有自然顺序的分类数据，例如满意度评分。

2. Sampling Techniques | 抽样技术

Simple random sampling gives every member of the population an equal chance of selection, often using random number generators. It minimises bias but may not represent specific subgroups.

简单随机抽样使总体中每个个体被选中的机会均等，通常使用随机数生成器。该方法偏差最小，但可能无法代表特定子群体。

Stratified sampling divides the population into strata (e.g., age groups) and takes a random sample from each proportionally. This ensures representation of key subgroups, improving accuracy.

分层抽样将总体分成层（如年龄组），并从各层按比例随机抽取样本。这确保了关键子群体的代表性，从而提高准确性。

Systematic sampling selects every kth item after a random start; it is simple to implement but can introduce bias if a hidden pattern exists. Quota sampling is non-random, where interviewers fill quotas for categories, which is cheap but prone to selection bias. Cluster sampling involves dividing the population into clusters, randomly selecting some clusters, and sampling all members within them.

系统抽样在随机起点后每隔k个抽取一个单位；实施简单，但若存在隐藏模式会引入偏差。配额抽样为非随机抽样，调查员按类别配额选取样本，成本低但易产生选择偏差。整群抽样先将总体分为群，随机抽取若干群并对群内所有个体进行调查。

3. Data Representation: Charts and Diagrams | 数据表示：图表与图示

Bar charts display categorical data with bars of equal width; the height represents frequency. Pie charts show proportions of a whole, with each sector angle proportional to frequency (angle = (frequency / total) × 360°).

条形图用等宽条形表示分类数据，高度代表频数。饼图展示各部分占总体的比例，每个扇形的角度与频数成比例（角度 = (频数/总数) × 360°）。

For continuous grouped data, histograms are used where the area of each bar equals frequency. Frequency density (frequency ÷ class width) is plotted on the vertical axis. A frequency polygon joins midpoints of histogram bars with straight lines and is useful for comparing distributions.

对于连续分组数据，使用直方图，其中每个条形的面积等于频数。纵轴表示频率密度（频数÷组距）。频率多边形将直方图条形的中点用直线连接，便于比较分布。

Cumulative frequency curves (ogives) are plotted with upper class boundaries against cumulative frequency; the median and quartiles can be read directly. Box plots (box-and-whisker diagrams) show the minimum, lower quartile, median, upper quartile, and maximum, highlighting spread and skewness. Stem-and-leaf diagrams order data and retain raw values.

累积频率曲线（形曲线）以上组界为横坐标、累积频数为纵坐标绘制；可直接读取中位数和四分位数。箱线图（盒须图）显示最小值、下四分位数、中位数、上四分位数和最大值，直观展示离散程度和偏态。茎叶图既能排序又保留原始数据。

4. Measures of Central Tendency | 集中趋势的量度

The mean (x̄) is the arithmetic average, calculated as Σx/n for raw data or Σfx/Σf for grouped data. It uses all values but is sensitive to outliers. The median is the middle value when data is ordered; it is unaffected by extreme values but may not utilise all data. The mode is the most frequent value, easy to find but not always unique or representative.

均值（x̄）是算术平均数，原始数据用 Σx/n 计算，分组数据用 Σfx/Σf 计算。它使用全部数值，但对异常值敏感。中位数是将数据排序后的中间值；不受极端值影响，但未利用全部信息。众数是出现次数最多的值，易于确定，但可能不唯一或代表性不足。

Weighted mean assigns different weights to values, used when some observations are more important: weighted mean = Σ(wx) / Σw. For symmetrical distributions, mean = median = mode; for skewed distributions, the mean is pulled toward the tail.

加权均值赋予各值不同权重，用于某些观测值更重要的情况：加权均值 = Σ(wx) / Σw。对于对称分布，均值=中位数=众数；对于偏态分布，均值会偏向拖尾方向。

5. Measures of Dispersion | 离散程度的量度

Range = maximum – minimum, simple but ignores distribution. Interquartile range (IQR) = Q3 – Q1, covering the middle 50% of data, resistant to outliers.

极差 = 最大值 – 最小值，计算简单但忽略分布形状。四分位距 (IQR) = Q3 – Q1，包含中间50%的数据，不受异常值影响。

Variance (σ² or s²) measures average squared deviation from the mean. For a population: σ² = Σ(x – μ)²/N; sample variance uses n–1 in denominator. Standard deviation (σ or s) is the square root of variance, giving spread in original units. For grouped data, σ² = [Σfx² – (Σfx)²/Σ

Published by TutorHao | IGCSE 统计 Revision Series | aleveler.com

更多咨询请联系16621398022（同微信）