Choosing a distribution and approximations 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
- Four conditions for a binomial model?
- Fixed number of trials, two outcomes, independent trials, constant probability of success.
- Give a situation where independence may fail.
- Students in the same tutor group (family or neighbourhood effects), so one outcome affects another.
- Why does sampling without replacement from a small population break the binomial model?
- The probability of success changes after each draw, so is not constant.
- How can a sample be chosen so that a binomial model is more suitable?
- Take a random sample from the whole population.
- When is a Normal model suitable?
- Continuous data that are symmetrical and bell-shaped.
- Name a feature that makes a Normal model unsuitable.
- Skewed data, a bounded variable, or a discrete variable with few values.
- When can be approximated by a Normal distribution?
- When is large and is close to 0.5.
- What is the Normal approximation to ?
- .
- Approximate by a Normal distribution.
- .
- Why is a continuity correction needed?
- The binomial is discrete and the Normal is continuous.
- becomes what in the Normal approximation?
- .
- becomes what in the Normal approximation?
- .
- becomes what in the Normal approximation?
- .
- Why is the approximation poor for ?
- is far from 0.5, so the distribution is skewed, and it gives probability to negative values.