Collecting and classifying data

Collecting and classifying data

IB MYP Maths Extended: Revision notes

Studying this course? Keep your progress in one place.

Key facts

  • Data are categorical (words), discrete (counted, separate values) or continuous (measured, any value in a range).
  • A sample is taken from the population; a good sample is representative.
  • Sampling methods: simple random, systematic (every kkth), stratified (in proportion to each group), convenience (often biased).
  • Bias pushes results one way: unrepresentative samples, self-selection, non-response, leading questions.
  • Good questionnaires are clear and neutral, with a time period and answer boxes that do not overlap.

Types of data

Data are categorical (words), discrete (counted) or continuous (measured).

Categorical data are described in words or categories. Numerical data are numbers and are either discrete or continuous.

Discrete data take separate values, usually found by counting. Continuous data take any value in a range, usually found by measuring, and are always rounded when recorded.

  1. 1

    Categorical

    described in words, e.g. favourite colour

  2. 2

    Numerical: discrete

    separate values found by counting, e.g. number of siblings

  3. 3

    Numerical: continuous

    any value in a range found by measuring, e.g. height

Classifying data.

Categorical

How it is found:
Described in words
Examples:
Bag colour, favourite sport

Discrete

How it is found:
Counted
Examples:
Siblings, goals, shoe size

Continuous

How it is found:
Measured
Examples:
Height, mass, time

Is the time taken to run 100 m discrete or continuous?

Populations and samples

The population is everyone you want to know about; a sample is a smaller group chosen from it.

The population is every person or item you want to know about. A sample is a smaller group chosen from it.

A census asks the whole population, but this is often too slow or expensive, so we use a sample. A good sample is representative, meaning it has the same mix of people as the population. A larger sample is usually more reliable.

  1. 1

    Population

    everyone you want to know about

  2. 2

    Sample

    a smaller, representative group chosen from it

  3. 3

    Collect data

    from the sample

  4. 4

    Draw conclusions

    about the whole population

From population to conclusion.

Census

  • Asks the whole population
  • Often slow and expensive
  • Gives exact results

Sample

  • Asks a smaller group
  • Quicker and cheaper
  • Must be representative

Why is a sample often used instead of a census?

Sampling methods

Random, systematic, stratified and convenience sampling differ in how members are chosen.

In stratified sampling you split the population into groups (strata) and take a random sample from each in proportion to its size.

In systematic sampling for 600600 students and a sample of 3030, choose every 2020th student from a list, starting at a random point.

01020304050607080901001030507090

Simple random

  • Every member has an equal chance
  • Random numbers or a draw

Systematic

  • Every kth member from a list
  • Start at a random point

Stratified

  • Split into groups (strata)
  • Random sample from each, in proportion

Convenience

  • People who are easy to reach
  • Quick but often biased

Stratified sampling example

A club has 2 4002\,400 members, of whom 1 5001\,500 are adults. Choose a stratified sample of 120120.

A school has 600600 students and you want a systematic sample of 3030. You choose every kkth student. What is kk?

Bias

Bias pushes results in one direction; reduce it with random or stratified samples, neutral questions and follow-ups.

Bias means the results are pushed in one direction, so they do not truthfully represent the population.

To reduce bias, use a random or stratified sample, a larger sample and neutral questions, and follow up non-responders.

  1. 1

    Choose the sample fairly

    random or stratified

  2. 2

    Make it larger

    a bigger sample is less affected by chance

  3. 3

    Ask neutral questions

    no leading wording

  4. 4

    Follow up non-responders

    so their views are not missed

Reducing bias.

Example

Unrepresentative sample:
Asking people at only one place
Self-selection:
Volunteers, such as an online poll
Non-response:
Many chosen people do not reply
Leading question:
A question that suggests the answer

How to reduce it

Unrepresentative sample:
Use a random or stratified sample
Self-selection:
Choose people instead of inviting volunteers
Non-response:
Follow up non-responders
Leading question:
Use neutral wording

An online poll asks people to vote on whether the school day should start later. Which source of bias is this?

Questionnaires and collecting data

Ask clear, neutral questions with a time period and answer boxes that cover every answer without overlapping.

A good question is clear, neutral and gives a time period ("each school day"). Do not ask two questions in one.

Answer boxes should cover every possible answer and not overlap: None; Less than 1 hour; 1 to less than 2 hours; 2 hours or more.

Primary data are collected by you; secondary data were collected by someone else.

  1. 1

    Write clear questions

    neutral, with a time period

  2. 2

    Pilot

    try it on a few people

  3. 3

    Collect

    survey, observation or experiment

  4. 4

    Tally

    record counts as you go

From question to data

Which set of answer boxes is best for hours of homework?

Try an exam question

A school has 800800 students, of whom 320320 are in Year 10. A stratified sample of 5050 students is taken. (a) Calculate the number of Year 10 students in the sample. (b) An online poll is used instead. Give one reason it may be biased.

[4 marks]

That's the notes covered.

Carry on to the next subtopic.

Try a question

Which of the four pieces of information is continuous data?

1 mark, marked against the mark scheme

Revision notes