📚 Year 11 SQA Statistics: Core Knowledge Points Review | Year 11 SQA 统计核心知识点梳理
This article provides a thorough walkthrough of the fundamental statistical concepts required for Year 11 SQA Statistics. Whether you are preparing for end-of-topic tests or final assessments, a clear understanding of data handling, probability and inference will give you a strong edge.
本文全面梳理了 Year 11 SQA 统计课程所要求的核心概念，从数据处理、概率到推断统计都有覆盖。无论你正在准备单元测验还是期末考试，清晰掌握这些知识点都会为你带来显著优势。
1. Types of Data and Data Collection | 数据类型与数据收集
Data is the raw material of statistics. We classify data as qualitative (categorical) or quantitative (numerical). Qualitative data describes attributes – for example, car colour or favourite film genre – while quantitative data records counts or measurements.
数据是统计学的原材料。我们将数据分为定性（分类）数据和定量（数值）数据。定性数据描述属性，比如汽车颜色或最喜欢的电影类型；定量数据则记录计数或测量值。
Quantitative data can be further split into discrete data (countable, like the number of students in a class) and continuous data (measurable on a scale, such as height, mass or time). This distinction is important because it determines which charts and statistics are appropriate.
定量数据还可细分为离散数据（可计数，如班级学生人数）和连续数据（可在标尺上测量，如身高、质量或时间）。这种区分很重要，因为它决定了哪些图表和统计量是合适的。
Primary data is gathered first-hand by the researcher for a specific investigation – think of a traffic survey you carry out yourself. Secondary data has been collected by someone else for another purpose, such as census data or published exam results. Using secondary data is often quicker and cheaper, but you must check its reliability.
一手数据是研究者为特定调查亲自收集的，比如你自己做的一项交通流量调查。二手数据是其他人为其他目的已收集好的，例如人口普查数据或已公布的考试成绩。使用二手数据通常更快、成本更低，但必须检查其可靠性。
2. Sampling Methods | 抽样方法
When a population is too large to study fully, we select a sample. A simple random sample gives every member an equal chance of being chosen, often using random number generators. This removes bias but can be impractical for large, spread-out groups.
当总体过大而无法全面研究时，我们会选取一个样本。简单随机抽样让每个成员被选中的机会均等，通常使用随机数生成器。这能消除偏差，但对于分布广的大型群体可能难以实施。
Stratified sampling divides the population into distinct groups (strata) and then takes a random sample from each in proportion to its size. This guarantees representation of key subgroups. Systematic sampling selects members at regular intervals from an ordered list – for example every 10th name on a register.
分层抽样将总体划分为不同的组（层），然后按比例从每一层中随机抽取样本。这能保证关键子群体的代表性。系统抽样从有序列表中每隔固定间隔选取成员，例如从名册上每隔 10 人抽取 1 人。
Convenience sampling (or opportunity sampling) picks individuals who are easiest to reach, such as friends in the canteen. It is quick but frequently leads to biased results. In SQA questions you will be expected to identify sampling flaws and suggest improvements.
便利抽样（或机会抽样）选择最容易接触到的个体，比如食堂里的朋友。这种方法快捷，但常常导致有偏差的结果。在 SQA 试题中，你需要识别抽样缺陷并提出改进建议。
3. Graphical Representation of Data | 数据的图形表示
Choosing the right chart makes patterns visible. A bar chart displays frequencies of categorical data; bars are separated to emphasise distinct categories. A pie chart shows proportions of a whole – useful for percentages, but harder to read when there are many slices.
选择合适的图表能让数据模式一目了然。条形图展示分类数据的频数，柱子之间留有间隙以强调类别独立。饼图表现各部分在整体中的占比，适用于百分比，但切片过多时不易阅读。
For discrete quantitative data a frequency diagram (bar chart with no gaps) or a stem-and-leaf diagram gives an ordered view while preserving raw values. For continuous data, histograms are essential. In a histogram the area of each bar is proportional to frequency, so bar widths may vary if class intervals are unequal.
对于离散定量数据，可以使用频数图（无间隙的条形图）或茎叶图，后者既能排序又保留了原始数值。对于连续数据，直方图必不可少。在直方图中，每个条形的面积与频数成正比，因此若组距不等，条形宽度会不同。
A line graph tracks changes over time, and a scatter graph displays the relationship between two numerical variables. SQA papers frequently ask you to interpret trends, compare distributions, and spot misleading features such as truncated axes.
折线图追踪数据随时间的变化，散点图则展示两个数值变量之间的关系。SQA 试题经常要求你解读趋势、比较分布并识别纵轴截断等误导性特征。
4. Measures of Central Tendency | 集中趋势的度量
An average summarises the centre of a data set. The mean is calculated by adding all values and dividing by the number of values. For a sample we write:
平均数概括了数据集的中心。均值通过将所有数值相加再除以数值个数计算得出。对于样本，记作：
x̄ = Σx / n
The median is the middle value when data are ordered. It is unaffected by extreme scores, making it a better summary for skewed distributions. The mode is the most frequent value and is the only average that can be used with qualitative data.
中位数是将数据排序后位于中间的值。它不受极端值影响，因此在偏态分布中是更好的概括。众数是出现频率最高的值，也是唯一可用于定性数据的平均数。
When a frequency table is used, the median position is found at (n+1)/2, and the mean is estimated using midpoints of class intervals. Always check whether an extreme value is pulling the mean away from the median – that tells you about skew.
使用频数表时，中位数的位置由 (n+1)/2 确定，均值则利用组中值进行估算。始终要检查是否有极端值将均值拉离中位数，这能反映分布的偏斜情况。
5. Measures of Spread | 离散程度的度量
An average alone can be misleading. Spread measures how consistent or varied the data are. The range (maximum − minimum) is quick to compute but heavily influenced by outliers.
单看平均数可能产生误导。离散程度衡量数据的一致性或波动性。极差（全距，最大值 − 最小值）计算快速，但受异常值影响很大。
The interquartile range (IQR = Q3 − Q1) covers the middle 50% is we use standard deviation, which measures the typical distance of values from the mean.
四分位距（IQR = 上四分位数 − 下四分位数）覆盖中间 50% 的数据，能抵抗极端值的影响。它配合中位数和箱线图使用效果很好。如需更精细的分析，我们使用标准差，它衡量数据值与均值的典型距离。
Sample standard deviation: s = √[ Σ(x − x̄)² / (n − 1) ]
A smaller standard deviation means data points cluster more tightly around the mean; a larger one indicates greater spread. In SQA statistics you will be expected to interpret these values in context, not just calculate them.
标准差越小，数据点越紧密地聚集在均值周围；标准差越大，表明离散程度越高。在 SQA 统计考试中，你不仅要会计算，还要能结合具体情境解读这些数值。
6. Boxplots and Interquartile Range | 箱线图与四分位距
s extend to the most extreme values that are not outliers. Outliers are typically defined as points lying more than 1.5 × IQR beyond the quartiles.
箱线图（盒须图）展示五数概括：最小值、下四分位数 Q1、中位数、上四分位数 Q3 和最大值。箱体覆盖 IQR，须线延伸至非异常值的最极端点。异常值通常定义为距离四分位数超过 1.5 倍 IQR 的点。
Comparing boxplots side-by-side lets you assess differences in centre, spread and skew. A boxplot with a long upper whisker and a short lower whisker hints at positive skew. SQA questions often ask you to comment on visible differences between two groups, such as higher median or greater consistency (smaller IQR).
并排比较箱线图可以评估中心位置、离散程度和偏态的差异。上须长而下须短的箱线图通常暗示正偏态。SQA 试题常要求你评论两组数据之间的明显差异，例如中位数更高或一致性更好（IQR 更小）。
7. Scatter Plots and Correlation | 散点图与相关性
A scatter graph reveals the relationship between two numerical variables. If the points show an upward trend, there is positive correlation; a downward trend indicates negative correlation. If no pattern appears, correlation is weak or zero.
散点图揭示两个数值变量之间的关系。若数据点呈上升趋势，则为正相关；下降趋势表示负相关。如果没有明显模式，则相关性很弱或为零。
Correlation does not imply causation – can be used to estimate one variable given the other, but predictions far outside the data range (extrapolation) may be unreliable.
相关关系并不意味着因果关系——这是 SQA 评述题中的常见陷阱。你可以用目测法画一条最佳拟合线，使线两侧的点数大致平衡。这条线的方程 (y = mx + c) 可用于从一个变量估算另一个变量，但超出数据范围的外推预测可能不可靠。
You may also be introduced to the correlation coefficient r, which measures the strength and direction of a linear relationship on a scale from −1 to +1. A value close to +1 or −1 indicates strong linear association.
你还需要了解相关系数 r，它衡量线性关系的强度和方向，取值范围介于 −1 到 +1 之间。数值接近 +1 或 −1 表示线性关联很强。
8. Introduction to Probability | 概率基础
Probability quantifies the chance that an event will happen. For equally likely outcomes:
概率量化了事件发生的可能性。对于等可能结果：
P(A) = Number of favourable outcomes / Total number of outcomes
l work with simple events, complementary events (P(not A) = 1 − P(A)) and combined events.
概率的范围从 0（不可能）到 1（必然）。所有可能结果的概率之和为 1。在 SQA 统计中，你将处理简单事件、互补事件（P(非 A) = 1 − P(A)）以及组合事件。
time; for such events P(A or B) = P(A) + P(B). Independent events do not affect each other' × P(B). Understanding these rules is vital for tackling structured probability questions.
互斥事件不能同时发生，此时 P(A 或 B) = P(A) + P(B)。独立事件彼此的概率互不影响，此时 P(A 与 B) = P(A) × P(B)。理解这些规则对解答结构化的概率问题至关重要。
9. Venn Diagrams and Tree Diagrams | 维恩图与树形图
Venn diagrams visualise sets and their overlaps. A rectangle represents the sample space, circles represent events, and the overlap shows the intersection P(A ∩ B). SQA tasks include shading regions, finding missing probabilities and solving word problems with given values.
维恩图将集合及其重叠可视化。矩形代表样本空间，圆圈代表事件，重叠部分表示交集 P(A ∩ B)。SQA 任务包括在图中涂色标注区域、寻找缺失概率以及利用给定数值解答文字题。
Tree diagrams organise stages of probability experiments, such as drawing two counters from a bag without replacement. Branch labels show probabilities at each stage, and the rule of multiplication along branches gives P(A and B). When events are dependent, the second set of probabilities changes to reflect the earlier outcome.
树形图用于整理多阶段概率实验，例如从不放回抽取两个计数器的情境。分支上标注各阶段的概率，沿分支相乘即得 P(A 与 B)。若事件相互依赖，第二阶段的概率会根据前面的结果而改变。
Adding the probabilities of all branches that lead to the same final outcome gives the total probability of that outcome. This is particularly powerful for repeated experiments. Always check that branch probabilities at each node sum to 1.
将所有通向同一最终结果的分支概率相加，即可得到该结果的总概率。这对重复实验尤为有效。务必检查每个节点上各分支概率之和是否为 1。
10. The Normal Distribution and Standard Scores | 正态分布与标准分
Many natural measurements – heights, masses, IQ scores – follow a bell-shaped normal distribution. The curve is symmetric about the mean, and its spread is determined by the standard deviation. In a normal distribution about 68% of values lie within 1 standard deviation of the mean, 95% within 2, and 99.7% within 3.
许多自然测量值——身高、体重、智商分数——都服从钟形的正态分布。曲线关于均值对称，其散布程度由标准差决定。在正态分布中，约 68% 的值落在距离均值 1 个标准差的范围内，95% 在 2 个标准差内，99.7% 在 3 个标准差内。
A standard score (z-score) tells you how many standard deviations a data point is above or below the mean:
标准分（z 分数）告诉你一个数据点高于或低于均值多少个标准差：
z = (x − μ) / σ
Using z-scores you can compare values from different normal distributions or find probabilities using standard normal tables. In SQA statistics you will be expected to calculate z-scores, interpret their meaning, and apply the empirical rule to real-life examples.
利用 z 分数，你可以比较来自不同正态分布的值，或使用标准正态分布表查找概率。在 SQA 统计中，你需要能够计算 z 分数、解释其含义，并将经验法则应用于实际例子。
Remember that not all data are normally distributed. Always check whether a data set is roughly symmetric and bell-shaped before applying normal model rules. Skewed data require median and IQR instead of mean and standard deviation for description.
请记住，并非所有数据都服从正态分布。在应用正态模型规则之前，一定要检查数据集是否大致对称、是否为钟形。对于偏态数据，应使用中位数和 IQR 而非均值和标准差进行描述。
Published by TutorHao | Statistics Revision Series | aleveler.com
更多咨询请联系16621398022（同微信）
或截图后用「扫一扫 → 相册」选择本图