Plain-English definitions
Research and statistics glossary
39 research and statistics terms students meet in projects, theses and vivas, each linked to a guide or tool.
Abstract
A short summary (usually 150–300 words) of the problem, method, main result and conclusion.
Learn moreAlternative hypothesis (H1)
The claim that there is an effect, difference or relationship; tested against the null hypothesis.
Learn moreBaseline model
A simple reference model, such as predicting the majority class, that a proposed model must beat.
Learn moreConfidence interval
A range of plausible values for a population quantity, given the sample and method.
Learn moreConvenience sampling
Selecting participants who are easy to reach; quick, but limits generalisation.
Learn moreCronbach's alpha
A measure of internal consistency for a multi-item scale; 0.70 or above is often treated as acceptable.
Learn moreCross-sectional study
Data collected at one point in time; good for associations, weak for cause.
Learn moreData leakage
When information from the test set influences training, making results look better than they are.
Learn moreEffect size
How large a difference or relationship is, separate from whether it is statistically significant.
Learn moreFeasibility
Whether a project can realistically be finished with the time, data, tools and skills available.
Learn moreLikert scale
A rating scale, such as 1 (strongly disagree) to 5 (strongly agree), usually combined across several items.
Learn moreMargin of error
How far a sample estimate may differ from the population value at a chosen confidence level.
Learn moreMethodology
The overall plan for how you answer your research questions: design, data, sampling and analysis.
Learn moreNull hypothesis (H0)
The default claim of no effect or no difference that a test tries to reject.
Learn morep-value
The probability of results at least this extreme if the null hypothesis were true. It is not the probability that the hypothesis is true.
Learn morePilot study
A small trial run of a questionnaire or method to find problems before the main study.
Learn morePrecision and recall
Precision: how many predicted positives were correct. Recall: how many actual positives were found.
Learn moreStatistical power
The chance a test detects an effect that really exists; usually planned at 80%.
Learn moreNo terms match. Try a shorter word.
Free 15-minute clarity call
Ready to talk about your project?
Share your programme, topic, current stage and deadline. Scope and any fee are confirmed before a paid session starts.