BEA140 Week 1 Lecture Notes: The Statistical Process, Sources of Data, Error and Bias

This set of vocabulary flashcards covers fundamental statistical concepts, data collection methods, sampling techniques, types of bias, and variable classifications based on the BEA140 Week 1 lecture notes.

Statistics

The science of learning from data which deals with the collection, analysis, interpretation, and presentation of data to turn raw information into useful knowledge.

Descriptive Statistics

A branch of statistics focused on organizing and summarizing the data already in possession using graphical displays and numerical measures like mean, median, mode, or range.

Inferential Statistics

Statistical methods that use sample data to draw conclusions, make estimates, test claims, and make predictions about a wider population under uncertainty.

Population

The large, entire group of individuals or items that a researcher wants to understand.

Sample

The smaller, specific group collected from a population that the researcher actually observes and uses to gather data.

Population Parameter

A value that describes the whole population, usually denoted by Greek letters such as a mean of $\mu$ and a standard deviation of $\sigma$.

Sample Statistic

A value calculated from a specific sample, usually denoted by Roman letters such as a mean of $\bar{x}$ and a standard deviation of $s$.

GIGO Principle

Short for 'Garbage In, Garbage Out,' it refers to the idea that if input data are biased, incomplete, or inaccurate, the resulting analysis will be unreliable.

Primary Data

Data collected directly by the researcher for a specific research purpose, allowing control over the survey or experiment design.

Secondary Data

Data that have already been collected or published by others (e.g., government agencies or industry bodies) for a different purpose.

Survey

A data collection method that gathers information by asking people questions, useful for understanding opinions and attitudes but prone to response bias.

Observational Study

A method where a researcher records what happens naturally without interfering or applying treatments; it identifies associations but usually not causation.

Experiment

A rigorous method for studying cause-and-effect where a researcher deliberately controls one variable to measure its impact on another, often using a randomized controlled trial (RCT).

Probability Sampling

A category of sampling where every member of the population has a known, non-zero chance of being selected, providing a stronger basis for generalization.

Simple Random Sample

A sampling method where every member of the population has an equal chance of being selected.

Systematic Sampling

A sampling method where the researcher selects every $k$-th member from a population list.

Stratified Sampling

A sampling method where the population is divided into subgroups called strata, and a random sample is taken from each group.

Cluster Sampling

A method where the population is divided into clusters, and then individuals within randomly selected clusters are surveyed.

Non-Probability Sampling

A category of sampling where members of the population do not have a known or equal chance of being selected, making results harder to generalize.

Convenience Sampling

A non-probability sampling method that involves selecting individuals who are easy to reach.

Judgmental (Purposive) Sampling

A non-probability method where individuals are deliberately selected for their particular knowledge or expertise.

Quota Sampling

A non-probability method that ensures certain groups appear in the sample in predetermined proportions.

Sampling Error

A natural part of using a sample where the sample estimate differs from the true population value because the entire population was not observed.

Coverage Error

A non-sampling error that occurs when some members of the target population are excluded from the sampling frame.

Nonresponse Error

An error occurring when individuals selected for a sample do not respond, and those who do are systematically different from those who do not.

Response Error

An error that occurs when respondents provide inaccurate or misleading answers due to misunderstanding, memory loss, or social desirability.

Measurement Error

An error caused by problems with the way questions are written (e.g., leading questions), asked, or recorded.

Observation

A single case or unit in a dataset, such as one student, one customer, or one household.

Variable

A characteristic recorded for each individual observation in a dataset, such as age, income, or gender.

Qualitative (Categorical) Data

Data that describes qualities, groups, or labels and lacks numerical meaning.

Nominal Data

A type of categorical data where categories have no natural order or ranking (e.g., payment method or brand name).

Ordinal Data

A type of categorical data where categories have a meaningful order, but the distance between them is not measurable (e.g., satisfaction ratings).

Quantitative (Numerical) Data

Data representing values that can be counted or measured, allowing for arithmetic calculations.

Discrete Data

A type of numerical data consisting of countable values, often whole numbers (e.g., the number of customers).

Continuous Data

A type of numerical data resulting from measurement that can take any value within a range, including decimals (e.g., weight, income, or time).

Explanatory Variable

An independent variable that helps explain or predict another variable.

Response Variable

A dependent variable representing the outcome that the researcher is trying to explain, predict, or understand.

Univariate Data

A dataset analysis involving only one variable at a time to understand its pattern, centre, and spread.

Bivariate Data

A dataset analysis involving two variables studied together to understand their relationship.

Multivariate Data

A dataset analysis involving three or more variables simultaneously.