Introduction to Statistics: Data Types, Sampling, and Bias

A collection of vocabulary flashcards covering the fundamental types of data, sampling methods, and types of statistical bias found in lecture notes.

Numerical Data

Data in the form of any number.

Continuous Data

Data that can have any value (including decimals); for example, the height or weight of people.

Discrete Data

Data that can only have specific values (usually whole numbers), such as a certain amount of things you have.

Categorical Data

Data that is sorted into distinct groups or categories.

Ordinal Data

Data that can be ranked (poor, fair, good, very good), such as rating the taste of a certain food.

Nominal Data

Data that cannot be ranked, such as different colour eyes, or a favourite breed of dogs or cats.

Simple Random - Sample

Randomly choosing a specific number of people, such as taking names out of a hat.

Systematic - Sample

Putting the population into a list and randomly choosing people at regular intervals, such as every fifth person.

Stratified - Sample

A method where the population is divided into groups that share common characteristic and a simple random sample is taken from each group, such as $10\%$ of each group.

Cluster - Sample

Dividing the population into random groups, randomly choosing a number of the groups, and sampling each member of the chosen groups, such as randomly selecting five districts in each province and surveying every player.

Multistage - Sample

Dividing the population into a hierarchy and choosing a random sample at each level, such as randomly selecting $10$ stores, three departments in each store, and selecting $10$ employees in each of those apartments.

Voluntary - Sample

Allowing people to choose whether or not they want to participate in a survey, such as conducting a poll on junk food in schools where individuals only answer if they want to.

Convenience - Sample

Choosing individuals from the population who are easy to access, such as a local politician asking for opinions from people at a local park.

Response Bias

When respondents change their answers to influence the results, to avoid embarrassment, or to give the answer they think the questioner wants.

Sampling Bias

When the method used to select a sample makes some members of the population more likely to be chosen than others, resulting in a sample that does not accurately represent the entire population.

Measurement Bias

When the collection method is such that the characteristics are consistently over- or under-represented, causing the results to be higher or lower than the true value.

Non-Response Bias

When the opinions of respondents differ in meaningful ways from those of non-respondents, such as when only very happy or unhappy customers respond.