4.13 Non-linear regression Flashcards
Studying this course? Keep your progress in one place.

Flip each card. Be honest: the ones you mark Not yet come back first.
14 cards
Tap a card to flip it. Swipe right if you knew it, left if not.
See all 14 cards
- What does a least squares regression curve minimise?
- The sum of the squares of the residuals.
- What is a residual?
- The observed value minus the value predicted by the model.
- What does measure?
- The sum of squared residuals; a smaller value means a closer fit of the model.
- What does tell you?
- The proportion of the variability in the second variable accounted for by the model.
- What is the relationship between and for a linear model?
- .
- Is alone a good way to choose between models?
- No; consider context, extrapolation, complexity and whether the model makes sense.
- Form of an exponential model?
- ; successive values at equal steps form a geometric sequence with ratio .
- Form of a power model?
- .
- Form of a sine model, and its period?
- ; period with in radians.
- What is the amplitude of ?
- .
- In , what does mean?
- The quantity grows by a factor of per unit, i.e. growth.
- Why is extrapolation risky?
- The model is only supported by data in a given range and may not hold outside it.
- A model has . How should you interpret this?
- of the variability in the second variable is accounted for by the model.
- What types of regression can be examined?
- Linear, quadratic, cubic, exponential, power and sine.