📚 High-Frequency Topics and Common Mistakes in Year 9 OCR Statistics | Year 9 OCR 统计：高频考点与易错题分析
Mastering Year 9 OCR Statistics means understanding not only the key concepts, but also the subtle mistakes that can cost valuable marks. In this article, we break down the topics that appear most often in assessments – from survey design and data types to averages, charts and probability – while highlighting the specific pitfalls that examiners look for. Each section pairs a clear explanation with targeted advice, helping you build a solid foundation and avoid common errors.
要掌握 Year 9 OCR 统计，不仅要理解核心概念，还要警惕那些容易被扣分的细微错误。本文梳理了评估中最常出现的内容——从调查设计、数据类型到平均数、图表和概率，并重点指出考官关注的具体陷阱。每个小节都将清晰的说明与有针对性的建议相结合，帮助你打下扎实基础，避开常见失误。
1. Designing Surveys and Spotting Bias | 调查设计与识别偏差
A question that leads the respondent towards a particular answer is biased. For example, 'Don't you think cycling is the best way to stay healthy?' pushes the person to agree. To keep a survey fair, questions must be neutral.
引导受访者给出特定答案的问题就是有偏差的。例如，“难道你不认为骑自行车是保持健康的最佳方式吗？”就是在促使对方同意。要想让调查公正，问题必须保持中立。
Even when questions are well written, a poor choice of sample can make the whole survey unreliable. Asking only members of a gym about exercise habits will over-represent people who are already active. A good sample should reflect the wider population being studied.
即使问题写得很好，样本选择不当也会让整个调查失去说服力。只询问健身房会员的运动习惯，就会过多代表已经保持活跃的人群。一个好的样本应当能反映所研究的更广泛人群。
2. Classifying Data: Qualitative, Quantitative, Discrete and Continuous | 数据分类：定性、定量、离散与连续
Qualitative data describe qualities or categories – like hair colour, types of pet or favourite film. Even if a category is recorded with numbers (such as a phone number or postcode), it remains qualitative because you cannot carry out arithmetic with the digits in a meaningful way.
定性数据描述的是性质或类别，例如头发颜色、宠物种类或最喜欢的电影。即便用数字记录类别（如电话号码或邮政编码），它依然是定性数据，因为你无法对这些数字进行有意义的算术运算。
Quantitative data can be split into discrete and continuous. Discrete data take only certain values, usually whole numbers – the number of students in a class is discrete. Continuous data can take any value within a range, such as height or mass. A common mistake is to treat shoe size as continuous; although it has halves, it is still discrete because it jumps from one size to the next.
定量数据可以分为离散和连续两类。离散数据只能取特定的值，通常是整数——一个班的学生人数就是离散数据。连续数据可以在一个范围内取任意值，例如身高或质量。一个常见的错误是把鞋码当作连续数据；虽然鞋码有半码，但它仍然是离散的，因为它从一个尺码跳到下一个尺码。
3. Random and Stratified Sampling | 随机与分层抽样
In a simple random sample, every member of the population has an equal chance of being chosen. Students often think that picking names out of a hat without shaking the hat is random – but if the names are not thoroughly mixed, some have a much higher chance of being selected.
在简单随机样本中，总体中的每个成员被选中的机会均等。学生常常以为不摇动帽子就直接从里面抽名字是随机的——但如果名字没有充分混合，有些名字被选中的概率就会高得多。
ample from each stratum in proportion to its size. The number from each group is calculated as (group size / total population) × sample size. A frequent error is to take the same number from each group regardless of size, which misrepresents the population.
分层抽样先将总体按共同特征（如年级或性别）分成若干层，然后从每一层中按比例随机抽取样本。每层应抽取的人数计算方式为：(该层人数 / 总人数) × 样本容量。一个常见错误是不管各层大小都抽取相同人数，这样会扭曲对总体的代表性。
4. Calculating the Mean, Median and Mode | 计算均值、中位数与众数
The mean is found by adding all the values and dividing by the number of values. The median is the middle value when data are ordered; for an even number of data items, you must take the mean of the two middle numbers. The mode is the value that appears most often.
均值是将所有数值相加再除以数值的个数得到的。中位数是数据排序后位于中间的数值；当数据个数为偶数时，必须取中间两个数的均值。众数是出现次数最多的数值。
One of the most frequent errors occurs with the median: forgetting to order the data before picking the middle. If you simply pick the middle number from the list as it is given, you are almost certain to get the wrong answer.
关于中位数最常见的错误之一是：挑选中间值之前忘记将数据排序。如果直接从给出的列表中取中间的那个数，几乎肯定会得到错误答案。
Another trick is being given data that include zero. Zero is a valid data value and must be included in the total and in the count. Leaving it out changes the mean dramatically.
另一个陷阱是给出的数据中包含零。零是一个有效的数据值，在求和与计数时必须包括在内。遗漏零会显著改变均值。
5. Mean from a Frequency Table | 频率表求均值
When data are grouped in a frequency table, the mean is calculated using the formula:
Mean = ∑(f × x) / ∑f
当数据以频率表形式给出时，均值要使用以下公式计算：
均值 = ∑(频数 × 数值) / 总频数
iously underestimates the total sum. Remember to create an extra f × x column in your working.
学生常常忘记在相加之前将每个数据值乘以其频数。他们只将第一列的数值相加，这会严重低估总和。请务必在解题过程中额外增加一列 f × x。
For grouped frequency tables where data are given in intervals, you must use the midpoint of each interval as the x-value. The midpoint is (lower bound + upper bound) / 2. A typical mistake is to use the upper or lower bound instead of the midpoint.
对于数据以区间形式给出的分组频率表，必须用每个区间的中点作为 x 值。中点的计算方式是（下界 + 上界）/ 2。一个典型错误是使用上界或下界而不是中点。
6. Finding the Median from a Frequency Table | 频率表求中位数
To find the median from a frequency table, you first need the total frequency n. The position of the median is (n + 1)/2. Then you work through the cumulative frequencies until you reach that position.
要从频率表中求中位数，首先需要总频数 n。中位数的位置是 (n + 1)/2。然后你需要逐个累加频数，直到达到这个位置。
A very common slip is to use n/2 instead of (n+1)/2 for the position. While n/2 may occasionally give the same answer, it is not the correct method for discrete listed data and will often lead to the wrong value, especially in small data sets.
一个非常常见的错误是将位置算成 n/2 而不是 (n+1)/2。虽然 n/2 偶尔会得到相同答案，但它并不是处理离散列出数据的正确方法，特别是在小样本数据中常常会得到错误结果。
When data are grouped, you cannot read off an exact median; instead you identify the median class interval. Many candidates then stop, but you may need to give a reasoned estimate, such as the midpoint of that interval, or use the cumulative frequency graph if one is provided.
当数据已经是分组数据时，你无法直接读出精确的中位数，而只能确定中位数所在的组距区间。不少考生会就此止步，但有时还需要给出合理的估计值，如该区间的中点，或者在提供了累积频率图的情况下利用图像求解。
7. Range and Outliers | 极差与异常值
Range is simply the largest value minus the smallest value. It is a quick measure of spread, but it is easily distorted by a single extreme value. For example, in the set {4, 5, 5, 6, 30}, the range is 26, even though most values are clustered tightly.
极差就是最大值减去最小值。它是一种简单的离散程度度量，但很容易被个别的极端值扭曲。例如在数据集 {4, 5, 5, 6, 30} 中，极差是 26，尽管大多数数值都很集中。
When describing the effect of an outlier, students often simply state 'the range increases'. A higher-scoring answer will use numbers to explain how the range changes before and after removing the outlier, showing a deeper understanding of spread.
在描述异常值的影响时，学生往往只是简单地说“极差增大了”。能得高分的回答会用数字说明剔除异常值前后极差如何变化，从而展现出对离散程度更深入的理解。
8. Bar Charts and Dual Bar Charts | 条形图与双条形图
Bar charts are used for categorical or discrete data. The bars must have equal widths and gaps between them; if bars are different widths, the chart becomes misleading. A dual bar chart allows you to compare two sets of related data side by side.
条形图用于表示类别数据或离散数据。条形的宽度必须相等，且彼此之间要留有空隙；如果条形宽度不一，图表就会产生误导。双条形图则可以让你并排比较两组相关联的数据。
A labelling mistake that regularly appears in exams is forgetting to label both axes clearly and to provide a title. Without proper labels, even a correctly plotted chart will lose marks. Also check that the scale on the frequency axis goes up evenly and starts from zero; skipping numbers or using a broken axis without indication can misrepresent the data.
考试中经常出现的标注错误是忘记给两轴加上清晰的标签，并且缺少标题。如果标注不规范，即便是绘制正确的图表也会失分。同时还要检查频数轴的刻度是否均匀递增并从零开始；跳跃式刻度或未经说明就使用截断轴可能会歪曲数据原貌。
9. Pie Charts: Proportions and Angles | 饼图：比例与角度
In a pie chart, each category's angle is calculated by multiplying its fraction of the total by 360°:
Angle = (frequency / total frequency) × 360°
在饼图中，每个类别的角度由其占总体的比例乘以 360° 算出：
角度 = (频数 / 总频数) × 360°
The most common error here is using an incorrect total. If a frequency table has been built from raw data, always double-check that you have added up all the frequencies correctly. Another slip is forgetting that the angles should sum to 360°; use this to check your working.
这里最常见的错误是使用了错误的总频数。如果频率表是由原始数据构建的，一定要反复核对所有频数相加是否正确。另一个疏忽是忘记所有角度之和应为 360°；你可以用这一点来验算自己的计算。
When interpreting a pie chart, remember that larger angles represent larger frequencies, but the chart does not show actual frequencies unless they are given on the chart. Many students incorrectly estimate frequencies just by looking at the size of the sector without referring to the key or the totals.
解读饼图时，要记住较大的角度代表较大的频数，但除非图表中给出了具体数字，否则饼图本身并不显示实际频数。许多学生仅凭观察扇形的大小就估算频数，而不参考图例或总数，这是不正确的。
10. Scatter Graphs: Describing Correlation | 散点图：描述相关性
A scatter graph shows the relationship between two sets of continuous data. Correlation describes the direction and strength of the relationship. Positive correlation means as one variable increases, the other tends to increase; negative correlation means one increases while the other decreases.
散点图展示两组连续数据之间的关系。相关性描述的是关系的方向和强度。正相关意味着一个变量增大时，另一个变量也趋于增大；负相关则是一个增大而另一个减小。
Students often lose marks by describing correlation as 'positive' or 'negative' without mentioning strength. Use terms like 'strong positive correlation', 'weak negative correlation' or 'no correlation'. Also, avoid the classic trap of claiming correlation means causation – just because two variables are linked on a graph does not prove that one causes the other.
如果只讲“正相关”或“负相关”而不提及强度，往往会丢分。可以使用“强正相关”“弱负相关”或“无相关”等描述。同时，要避开那个经典的陷阱：相关性不等于因果关系——仅仅因为两个变量在图上存在关联，并不能证明其中一个导致了另一个。
11. Basic Probability: Equally Likely Outcomes and Mutually Exclusive Events | 基础概率：等可能结果与互斥事件
The probability of an event is calculated as:
P(event) = number of favourable outcomes / total number of equally likely outcomes
一个事件的概率按下式计算：
P(事件) = 有利结果数 / 等可能结果总数
The requirement for outcomes to be equally likely is easily forgotten. When rolling a biased die, the probability of getting a six is not simply 1/6, because the faces are not equally likely. You must use given probabilities or experimental data instead.
结果必须等可能这一要求很容易被忘记。投掷一枚不均匀的骰子时，得到六点的概率并不是简单的 1/6，因为各面出现的可能性并不均等。此时必须使用给定的概率或实验数据。
Mutually exclusive events cannot happen at the same time. For mutually exclusive events A and B, the probability of A or B occurring is P(A) + P(B). A common mistake is to add probabilities for events that are not mutually exclusive without subtracting the overlap – but at Year 9, questions are normally designed so that events are mutually exclusive.
互斥事件是指不可能同时发生的事件。对于互斥事件 A 和 B，A 或 B 发生的概率为 P(A) + P(B)。常见的错误是把非互斥事件的概率直接相加而没有减去重叠部分，不过 Year 9 阶段的题目通常都设计成互斥事件。
12. Comparing Distributions: Mean and Range Together | 比较分布：均值与极差结合
When asked to compare two sets of data, you must comment on both a measure of central tendency (usually the mean or median) and a measure of spread (usually the range). Writing only 'Set A has a higher mean' without mentioning spread will restrict marks.
当要求比较两组数据时，必须同时评论集中趋势的度量（通常是均值或中位数）和离散程度的度量（通常是极差）。只写“组 A 的均值更高”而不提及离散程度，会使得分受限。
Use comparative language: 'On average, the rainfall in April was higher than in March, but the range was also larger, showing more variation from day to day.' A richer answer will link the statistics to the real-world context of the question, demonstrating that you understand what the numbers mean.
要使用比较性语言：“平均来看，四月的降雨量高于三月，但极差也更大，说明每天的降雨量变化更剧烈。”更充实的答案会将统计值联系到题目的现实情境，表明你真正理解这些数字的含义。
h the average and the range. Even if the numbers are already given, writing something like 'Set A mean = 12, range = 8, while Set B mean = 15, range = 4' proves you have identified the correct values and makes your comparison concrete.
许多考生忘记引用平均数和极差的实际数值。即便题目中已经给出，写出“组 A 均值 = 12，极差 = 8，而组 B 均值 = 15，极差 = 4”这样的语句，可以证明你找对了数值，并使你的比较更加具体实在。
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