Skip to contentSkip to search

Linear relationship

A linear relationship has a constant rate of change and can be represented by a straight-line equation. In a two-variable model y = a + bx, b is the change in y for a one-unit increase in x and a is the value at x = 0 when that value is meaningful. A non-zero intercept means the relationship is not direct proportion. A prescribed exact equation differs from a statistical regression line estimated from noisy observations, and either model needs a relevant range and assumptions.

Worked example

A delivery cost model is $100 plus $4 per order. At 20 orders it gives $180; at 30 orders it gives $220. Ten more orders add $40, and the $100 intercept means cost is not directly proportional to orders.

Common mistake

Assuming every straight line passes through zero, or treating a fitted line as proof that changes in one variable cause the other.

Where it appears in your exams

QualificationExamRelationshipPeriod
ACCA PM Supporting September 2026–June 2027