Top 100 Secondary 2 G3 Vocabulary List for Punggol | Mathematics: Statistics, Data Interpretation and Probability helps students read histograms, dot diagrams and stem-and-leaf plots, calculate suitable averages and interpret the chance of one event. These 100 explained terms include original examples and are arranged by the decisions they help a student make. Worked tasks show why the denominator, scale and interpretation matter as much as the answer.
Start with the question and the units: what is being counted, displayed or selected? A class average does not automatically describe every student in Singapore, and probability 0.4 does not guarantee four successes in the next ten trials. This is an original eduKate learning list, not an official MOE or SEAB Top 100 requirement or an examination forecast. Follow your teacher’s current Secondary 2 G3 Mathematics scope; later combined-event probability is not presented as a compulsory Secondary 2 calculation.
- For: Secondary 2 G3 students and parents in Punggol.
- Coverage: 100 terms, ten groups, clear meanings and original examples.
- Core skills: dot diagrams, histograms, stem-and-leaf plots, averages and single-event chance.
- Important: distinguish sample from population and exact from estimated mean.
- Practice: ungrouped data, grouped means, a spinner and misleading charts.
- Support: identify the first reasoning or interpretation error before adding more worksheets.
Scope · 100 words · Worked averages · Grouped mean · Probability · Practice · Parents · Sources
What Secondary 2 G3 Mathematics expects in this area
The MOE G2/G3 Mathematics syllabuses identify dot diagrams, histograms, stem-and-leaf diagrams, mean, median, mode, grouped-data mean and probability of single events in Secondary Two G3. Combined-event probability appears later in the syllabus. The language below includes foundations and useful extension terms, but this is not a replacement for your school textbook, assessment notice or teacher’s requirements.
A numerical answer can be right while the interpretation is wrong. Before dividing, identify what the numerator represents and whether the denominator is the full number of observations or equally likely outcomes. Before trusting a graph, check the baseline, class intervals, units and source. Learning these habits reduces the chance of confident but unsupported conclusions.
100 vocabulary terms for data and probability
Words 1–10: Data foundations
| No. | Term | Meaning | Original example |
|---|---|---|---|
| 1 | Data | Recorded information collected for a purpose. | Survey data give the books read by each fictional student. |
| 2 | Dataset | A collection of observations considered together. | Five journey times form a dataset. |
| 3 | Observation | One recorded value or category. | Eight minutes is one observation. |
| 4 | Variable | A characteristic taking different values. | Travel time is the variable. |
| 5 | Categorical data | Information describing membership of groups. | Favourite subject produces categorical responses. |
| 6 | Numerical data | Information represented as counts or measurements. | Number of visits is numerical data. |
| 7 | Discrete data | Numerical data taking separated values. | A notebook count is discrete. |
| 8 | Continuous data | Numerical measurements varying over an interval. | Distance may include fractional metres. |
| 9 | Population | All units a study aims to describe. | Every student in the fictional class is the population. |
| 10 | Sample | A selected portion of that population. | Seven selected students form a sample. |
Words 11–20: Collection and tables
| No. | Term | Meaning | Original example |
|---|---|---|---|
| 11 | Frequency | The count for a value or category. | Three appears twice, giving frequency two. |
| 12 | Frequency table | A list of categories and their counts. | The table shows trips in each time band. |
| 13 | Tally | A counting system using repeated marks. | Mark each valid response once. |
| 14 | Class interval | A grouped range of numerical values. | 10 to under 20 is one class. |
| 15 | Lower bound | The bottom boundary of a class interval. | Ten starts the 10-to-under-20 class. |
| 16 | Upper bound | The top boundary of a class interval. | Twenty is excluded from 10 to under 20. |
| 17 | Class width | Difference between the class boundaries. | This ten-minute class has width ten. |
| 18 | Total frequency | The sum of recorded frequencies. | The total frequency counts the six trips. |
| 19 | Ungrouped data | Individual values listed separately. | The numbers 2, 3 and 7 are ungrouped. |
| 20 | Grouped data | Values gathered into intervals. | Five times occur in the 10–under-20 class. |
Words 21–30: Dot and stem-leaf
| No. | Term | Meaning | Original example |
|---|---|---|---|
| 21 | Dot diagram | A plot placing marks over their recorded values. | Three dots over 4 mean frequency three. |
| 22 | Dot stack | Marks placed above one value. | The tallest stack shows the most frequent value. |
| 23 | Stem-and-leaf diagram | A display splitting numbers into stems and leaves. | The stem 2 and leaf 7 represent 27. |
| 24 | Stem | The leading part of a represented value. | Stem 1 groups teen values in this example. |
| 25 | Leaf | The final part completing the value. | Leaf 4 on stem 2 represents 24. |
| 26 | Key | Notation specifying how the display is read. | A key can say stem 2 and leaf 7 equals 27. |
| 27 | Ordered leaves | Leaves shown in ascending order within a stem. | Order leaves to locate the median. |
| 28 | Repeated value | A value occurring more than once. | Two leaves of 6 represent repetition. |
| 29 | Distribution | The arrangement of values across the range. | Most times lie near five minutes. |
| 30 | Clustering | Observations concentrated near one another. | The points cluster around the middle. |
Words 31–40: Graphs and displays
| No. | Term | Meaning | Original example |
|---|---|---|---|
| 31 | Histogram | Adjacent bars showing frequencies for numerical intervals. | The histogram groups journeys by time. |
| 32 | Bar chart | Separated bars comparing categories. | Bars compare preferred school subjects. |
| 33 | Horizontal axis | The axis usually running left to right. | Label the horizontal axis in minutes. |
| 34 | Vertical axis | The axis usually running bottom to top. | For equal-width intervals label frequency vertically. |
| 35 | Scale | How displayed positions represent quantities. | Use a consistent scale of five. |
| 36 | Axis break | A visible indication part of an axis is omitted. | Mark a skipped interval clearly. |
| 37 | Truncated axis | An axis that starts above zero or ends early. | A truncated axis can exaggerate differences. |
| 38 | Pictogram | A chart where symbols represent counts. | One book icon represents two students. |
| 39 | Graph title | A label telling readers the display’s subject. | State what class and period were measured. |
| 40 | Misleading display | A representation encouraging a false impression. | An unlabeled scale can distort comparisons. |
Words 41–50: Central tendency
| No. | Term | Meaning | Original example |
|---|---|---|---|
| 41 | Arithmetic mean | The total of values divided by their count. | The mean of 2, 4 and 6 is four. |
| 42 | Median | The middle ordered value, averaging two middle ones when needed. | The median of 2, 4, 8, 10 is six. |
| 43 | Mode | The value occurring most often. | The mode of 1, 2, 2, 5 is two. |
| 44 | Bimodal | Having exactly two values tied for highest frequency. | 1, 1, 3, 3, 5 is bimodal. |
| 45 | No mode | No value is more frequent than the others. | All different values give no most frequent value. |
| 46 | Range | The maximum minus the minimum. | From 3 to 11 the range is eight. |
| 47 | Outlier | A value unusually distant from the main group. | A score of 99 among scores near ten needs checking. |
| 48 | Extreme value | A very high or low observation. | An extreme value can move the mean. |
| 49 | Central tendency | The typical or central location of a dataset. | Mean and median describe central tendency. |
| 50 | Spread | How widely the values differ. | Two classes share a mean but differ in spread. |
Words 51–60: Grouped-data means
| No. | Term | Meaning | Original example |
|---|---|---|---|
| 51 | Class midpoint | The halfway value of an interval. | The midpoint of 10–under-20 is 15. |
| 52 | Estimated mean | A mean approximated using class representatives. | Grouped data yield an estimated mean. |
| 53 | Frequency product | Class midpoint multiplied by frequency. | 15 times 3 contributes 45. |
| 54 | Weighted total | The sum of midpoint-frequency products. | Add contributions across every class. |
| 55 | Arithmetic total | The sum of observed numbers. | The values 2,3,3,5,12 total 25. |
| 56 | Denominator | The bottom quantity of a fraction. | Total frequency is the mean denominator. |
| 57 | Numerator | The top quantity of a fraction. | The summed contributions form the numerator. |
| 58 | Approximation | A value close to an exact result. | 13.3 is approximate rather than exact. |
| 59 | Rounding | Replacing a value at required precision. | Round 13.333 to 13.3 at the end. |
| 60 | Precision | The fineness of a measurement or representation. | Times to the minute have limited precision. |
Words 61–70: Basic probability
| No. | Term | Meaning | Original example |
|---|---|---|---|
| 61 | Probability | A number between zero and one measuring chance. | One quarter expresses one in four under the model. |
| 62 | Random experiment | A process whose outcome is uncertain. | Draw one counter from a mixed bag. |
| 63 | Trial | One performance of an experiment. | One spinner turn is a trial. |
| 64 | Outcome | A result that the experiment may produce. | Blue is a possible spinner outcome. |
| 65 | Sample space | The set of all possible outcomes. | A fair die has outcomes one to six. |
| 66 | Event | The outcomes satisfying a stated condition. | An even roll includes 2, 4 and 6. |
| 67 | Favourable outcome | An outcome matching the event. | Five and six are favourable for above four. |
| 68 | Equally likely | Having identical probabilities. | A fair die gives each face the same chance. |
| 69 | Theoretical probability | Chance calculated from a defined outcome model. | Two of six faces give probability one third. |
| 70 | Probability fraction | A fraction recording an event’s chance. | Two fifths can be written 2/5. |
Words 71–80: Interpreting chance
| No. | Term | Meaning | Original example |
|---|---|---|---|
| 71 | Impossible event | An event with probability zero. | A normal six-sided die cannot show seven. |
| 72 | Certain event | An event with probability one. | A die shows a face numbered one through six. |
| 73 | Likely | An informal description of high probability. | A chance of 0.8 is likely. |
| 74 | Unlikely | An informal description of low probability. | A chance of 0.1 is unlikely. |
| 75 | Probability scale | A line from zero to one representing chance. | 0.5 sits halfway along the scale. |
| 76 | Complementary event | The set of outcomes not in the original event. | Not-even is the complement of even. |
| 77 | Fair experiment | A set-up giving intended outcomes equal chances. | A fair coin model gives heads probability half. |
| 78 | Biased experiment | A set-up where intended outcomes are not equally likely. | Unequal spinner regions may produce unequal chances. |
| 79 | Experimental probability | The observed share of trials with an event. | Nine successes in 30 trials gives 0.3. |
| 80 | Relative frequency | Event count divided by number of trials. | Twelve blues in 40 turns gives 12/40. |
Words 81–90: Chance and models
| No. | Term | Meaning | Original example |
|---|---|---|---|
| 81 | Single event | An event in a defined random situation. | Find the chance of one red draw. |
| 82 | One-step selection | A selection involving one draw or action. | One draw needs no two-stage tree. |
| 83 | Replacement | Returning an item before another draw. | Replacement changes the model for subsequent draws. |
| 84 | Without replacement | Not returning an item before a later draw. | This affects later draws, not the one-draw calculation. |
| 85 | Prediction | An evidence-based expectation. | Expect about 20 reds per 100 trials at probability one fifth. |
| 86 | Variation | Differences in results across repeated trials. | Small batches can vary substantially. |
| 87 | Simulation | A rule-based imitation of an experiment. | Simulate many virtual coin tosses. |
| 88 | Long-run tendency | The pattern seen over many repetitions. | Relative frequency may approach theoretical chance. |
| 89 | Independence | When one event does not change another event’s chance. | Combined independent events are a later study topic. |
| 90 | Model validity | Whether assumptions fit the situation. | A fair-die model fails for a loaded die. |
Words 91–100: Mathematical communication
| No. | Term | Meaning | Original example |
|---|---|---|---|
| 91 | Interpret | Explain a result in context. | Five means five visits per student on average. |
| 92 | Compare | Identify meaningful differences or similarities. | Compare medians using the correct units. |
| 93 | Calculate | Use operations to find a numerical result. | Order the data before calculating the median. |
| 94 | Determine | Establish a value from supplied information. | Determine favourable outcomes first. |
| 95 | Estimate | Find a suitable approximate result. | Estimate a mean from grouped midpoints. |
| 96 | Represent | Display information in a meaningful format. | Represent values with a dot diagram. |
| 97 | Explain | Give reasons for a calculation or conclusion. | Explain why an outlier affects the mean. |
| 98 | Justify | Support a decision with mathematical grounds. | Justify choosing the median over the mean. |
| 99 | Check | Test the result against the situation. | Check probability lies between zero and one. |
| 100 | Communicate | Present quantities and reasoning clearly. | State the sample size beside the percentage. |
Worked data example: three different averages
Five fictional sorting times are 2, 3, 3, 5 and 12 minutes. The mean is (2 + 3 + 3 + 5 + 12)/5 = 5 minutes. The ordered middle observation is 3, so the median is 3 minutes. The most frequent value is also 3, so the mode is 3 minutes. The range is 12 − 2 = 10 minutes. These answers are all correct but describe different properties.
The 12-minute value raises the mean without moving the median. It may be a genuine slow attempt rather than an error; verify before excluding it. If the question asks for a central typical attempt, the median may be useful. If it asks for total time distributed equally over all five attempts, the mean answers a different question. Do not announce one as universally superior without saying what is being measured.
For an even number of observations such as 4, 5, 7 and 10, the median is (5 + 7)/2 = 6. It is not automatically one of the original values. Sorting first is essential; choosing the two middle positions from an unsorted list can produce a plausible but wrong result.
Grouped-data mean: an estimate, not an exact reconstruction
In a fictional table, the class 0–under 10 minutes has frequency 2, 10–under 20 has frequency 3, and 20–under 30 has frequency 1. Use midpoints 5, 15 and 25. The weighted total is 5×2 + 15×3 + 25×1 = 80. The total frequency is six. The estimated mean is 80/6 ≈ 13.3 minutes to one decimal place.
It is an estimate because the original individual values inside the classes have not been supplied. Dividing the sum of just the three midpoints by three would incorrectly ignore the class frequencies. Keep the interval boundaries, the estimated nature of the result and the units visible in the explanation.
Single-event probability: define the sample space
A fictional bag contains two red and three blue otherwise identical counters. One counter is drawn after mixing, and every counter is assumed equally likely. The chance of red is 2/5 = 0.4 = 40%; the chance of not-red is 3/5. These complementary probabilities sum to one. The chance of red is not ‘guaranteed twice in every five drawings’.
A fair six-sided die has six equally likely face outcomes. Rolling a number greater than 4 has two favourable outcomes, 5 and 6, so its probability is 2/6 = 1/3. That is a one-step event. Do not use independent-event multiplication or two-stage probability trees unless the current school question actually introduces those later concepts.
Experimental probability is a fraction calculated from observed trials. If a spinner produces blue on 9 out of 30 turns, its experimental share is 9/30 = 0.3. This may differ from the theoretical chance because of random variation, a biased spinner or a small set of observations. The results alone do not establish which explanation is correct.
Why graphs sometimes mislead
Imagine fictional means of 20 minutes for Class A and 22 minutes for Class B. A graph with its vertical axis beginning at 19 may exaggerate the apparent size difference. The numerical difference remains two minutes. Before making a claim, look at the baseline, units, number of observations and whether the same measurement period was used.
A histogram of numerical intervals differs from a bar chart of named categories. The histogram’s adjacent bars signify intervals; separate bars in a category chart need not imply neighbouring numerical ranges. For equal-width classes, bar height can express frequency. Further work is needed if widths differ, and advanced conventions should not be assumed compulsory for the current task.
Quick questions and explained answers
- 1. What is the median of 4, 10, 5, 7? Answer: sort 4, 5, 7, 10 and average the middle pair: 6.
- 2. Six outcomes total 42. What is their mean? Answer: 42/6 = 7, with units if supplied.
- 3. A midpoint of 15 has frequency 4. What is the frequency product? Answer: 60.
- 4. What is P(roll above 4) on a fair die? Answer: 2/6 = 1/3.
- 5. What is P(roll 8) on a usual six-sided die? Answer: 0; this is outside the sample space.
- 6. A survey has 18 yes answers, but no sample size. Can you calculate the yes percentage? Answer: No, the denominator is missing.
The first error tells you what to practise: ordering for median, frequency weights for grouped mean, sample-space counting for chance, or evidence limits for graphs. After correcting a mistake, change one number or condition and ask the student to solve an unfamiliar version independently.
Home practice and parent decisions
Choose one ten-word group linked to this week’s classwork. Have the student read a small table, calculate something useful and explain the result in a complete sentence. On another day, change the values or give a different display. A strong learner should be able to explain why a small sample cannot automatically establish a national trend.
If considering tuition, bring a school question with its full chart or table and the student’s attempted answer. Ask how the tutor will diagnose whether the issue is vocabulary, arithmetic, diagram reading or interpretation, and how a new question will demonstrate improvement. A three-person discussion can surface alternative methods, but each student should complete their own final check.
Frequently asked questions
- Are all 100 terms examinable? No. This is a teaching selection with foundations and optional extension vocabulary.
- Does probability 0.4 mean exactly four successes in ten trials? No. It expresses a model chance, not a guarantee.
- Is a grouped mean exact? Generally not when individual values are unknown; it is estimated from midpoints.
- Must all charts have a zero baseline? Context matters, but any truncation must be interpreted honestly rather than concealing the effect.
- What if my school uses a different sequence? Follow the school’s current instructions; use the ten-word groups as support.
Official references and related eduKate guides
- MOE: G2/G3 Mathematics syllabuses.
- SEAB: Secondary Education Certificate — later national examination context.
- Secondary 2 G3 Mathematics subject guide.
- Geometry, Measurement and Trigonometry vocabulary.
Reviewed 17 November 2026. Every dataset and numerical classroom scenario above is fictional and provided for learning, not a measurement of real Punggol people or an official examination question.

