Updated · By Pete Bromfield, former Head of Maths with IB examining experience

IA idea · Matrices, transformations & Markov chains

Does rain today predict rain tomorrow? A Markov chain for the weather

AI HLAA HL Solid Also in: Environment, Probability

Research question

Using a daily rainfall record for your town, how well does a two-state Markov chain (wet/dry) predict the lengths of wet and dry spells, and does adding a memory of two days improve it?

Make it yours, then agree it with your teacher.

Next step: plan this IA free — the planner opens with this question filled in. For feedback on your own draft, the IA package (€39 once) gives you 5 AI feedback credits and every annotated exemplar in full.

Why it makes a good exploration

Weather is the classic Markov example, but testing it on real local data is rarely done. The prediction of spell lengths gives a sharp test of the Markov assumption.

The mathematics you'll need

  • Transition probabilities estimated from counts
  • Matrix powers and the steady state
  • Spell lengths as a geometric distribution
  • Chi-squared goodness of fit for spell lengths
  • Extending to a four-state chain for two-day memory

Where the data comes from

Find a daily rainfall record for a station near you; many national weather services publish daily station data free. Cite the station and years. A school weather station also works if it has a long record.

A possible outline

  1. Clean the data and define 'wet'.
  2. Estimate the transition matrix and steady state.
  3. Predict the distribution of spell lengths and compare with the data.
  4. Build the two-day-memory chain and compare.
  5. Reflect on seasons and on the threshold for 'wet'.

Pitfalls that cost marks

  • Mixing seasons so the probabilities aren't constant.
  • Comparing only the steady state, which almost any model gets right.
  • No test of the spell-length prediction.

Showing personal engagement

  • Use your own town's record.
  • Try different wet thresholds and see what changes.
  • Compare summer with winter.

See Criterion C: personal engagement for what examiners look for.

Which course is it for?

CourseFitMaths to lean on
AA SLNot a natural fitThe core technique sits in the AI course or at HL; an AA SL student could use it only as clearly explained new mathematics.
AA HLGood fitTransition probabilities estimated from counts; Matrix powers and the steady state
AI SLNot a natural fitThe mathematics is mainly AA or HL (calculus or proof beyond AI SL); an AI SL version would need a data-driven, technology-based approach.
AI HLGood fitTransition probabilities estimated from counts; Matrix powers and the steady state

Level: Solid. Needs some independent work beyond class examples. See how the IA differs between AA and AI, SL and HL.

How this idea reaches the top bands

Reflection (D)

For this idea, start with the weak points: mixing seasons so the probabilities aren't constant; and comparing only the steady state, which almost any model gets right. Say how each one affects your answer.

Use of mathematics (E)

HL: transition probabilities estimated from counts; matrix powers and the steady state; spell lengths as a geometric distribution; chi-squared goodness of fit for spell lengths; extending to a four-state chain for two-day memory, each explained in your own words and carried out correctly.

How matrices & markov explorations reach the top bands in general: Matrices, transformations & Markov chains IA ideas. Guides: A · B · C · D · E · self-grade sheet.

Taking it further

Fit separate chains for each season, or compare two climates.

Extending it for HL

Add an HL technique the question genuinely needs: what an HL matrices & markov exploration adds.

Frequently asked questions

Which IB Maths course is this IA idea for?

It works for AI HL and AA HL. We rate it Solid: it needs some independent work beyond class examples.

What mathematics does this IA use?

Transition probabilities estimated from counts, matrix powers and the steady state, spell lengths as a geometric distribution, chi-squared goodness of fit for spell lengths and extending to a four-state chain for two-day memory.

Where can I get data for this IA?

Find a daily rainfall record for a station near you; many national weather services publish daily station data free. Cite the station and years. A school weather station also works if it has a long record. Checked sources and tools: Desmos graphing calculator.

Turn this idea into your IA

The planner opens with “Does rain today predict rain tomorrow? A Markov chain for the weather” filled in: the question, the maths and the data sources.

Plan this IA free

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

Also: free IA self-check · A–E checklist (PDF) · have a draft? AI feedback or a review with Pete (€100)

Writing it up: how to write a Maths IA, step by step · structure and format · mistakes that cost marks · IA modelling, step by step

Similar ideas

All matrices & markov ideas · AI HL ideas · AA HL ideas · All 239 IA ideas