IA ideas library

Statistics IA ideas: real questions, real data, the right test

Statistics explorations work best when you have a genuine question with a yes/no or how-much answer, and data you can defend. The mathematics comes from choosing the right tool — correlation, regression, a chi-squared test, a t-test, a confidence interval — checking its conditions, and interpreting the result in context.

Every idea here says where the data comes from and which test fits it. AI students have the widest statistical toolkit; AA students can use regression, the normal and binomial distributions and, at HL, continuous random variables and Bayes' theorem.

Next step: shortlist ideas with the free IA topic explorer, which filters starting points by course, interest and how easy the data is to get. For feedback on your own draft, the IA package (€39 once) gives you 5 AI feedback credits and every annotated exemplar in full.

Doing the statistics: IA statistics, step by step — choosing the right test, χ² tests, t-tests, Spearman's rank and more, worked with every number shown, plus Analyse my data for your own numbers.

How statistics explorations reach the top bands

Personal engagement (C)

Collect at least some of the data yourself, or make real choices about a secondary dataset (which seasons, which countries, which outliers) and justify each one.

Reflection (D)

Reflect on the sample: who is missing, how it was chosen, and how that could bias the result. Say what a significant (or non-significant) result does and does not show.

Use of mathematics (E)

SL: A test that matches the question and the data, its conditions checked (expected frequencies, independence, normality), one calculation shown, and the p-value interpreted in context.

HL: HL inference: confidence intervals, a Poisson or further test, a test of a regression coefficient, or a justified comparison of tests; with the reasoning behind each step, not just technology output.

An HL version

Add a confidence interval for the effect you found, test a model assumption formally, or compare two tests and explain why they disagree.

Statistics & hypothesis testing ideas (13)

Also relevant (66)

Frequently asked questions

How much data do I need for a statistics IA?

Enough for your test to mean something: typically at least 30 paired values for correlation and regression, and enough in each category that expected frequencies are greater than 5 for a chi-squared test. Say why your sample size is appropriate.

Is a survey of my classmates acceptable data?

It can be, but reflect on how representative it is and on bias in self-reported answers. Measured data (reaction times, heart rates, timings) is usually more convincing than opinions.

Start your IA plan, free

Answer the planning questions: your question, the maths, the data and milestones back from your deadline. Then take it to your first teacher meeting.

Plan my IA free

Your plan is kept in this browser. A free account keeps it with your drafts on any device: Join free · Sign in

Related types of IA: Survey-based investigations

Other topics: Modelling · Calculus · Differential equations · Probability · Geometry & Voronoi · Finance · Sport · Environment · Health & biology · Networks & graphs · Pure maths · Art & music · Games & puzzles · Optimisation · Simulation · Cryptography · Numerical methods · Fractals & chaos · Matrices & Markov · Trig & navigation · Kinematics · Voting & game theory · Surveys

By interest: Computer science · Physics and engineering · Psychology and social sciences · Geography and travel · Chemistry · Biology · Economics · Business management · Sports, exercise and health science · Environmental systems and societies · Music · Visual arts · Design technology · By course: AA SL · AA HL · AI SL · AI HL