Studied by 0 people
Looks like no one added any tags here yet for you.
Three main methods:
1. Tables
2. Probability tree
3. Ven Diagram
Relative Risk:
P( / ) / P( / )
When the word DISCUSS if used...
State what the data can give you, and what it can't. (evaluate pros and cons)
Benefits of having large sample size...
A large sample size is positive because it can help us with accuracy.
Negative for small sample size...
Our estimates will be limited. Conclusions will be inaccurate.
Having only one sample taken...
Taken at only one location, at one point in time. May not represent other subgroups like teenagers.
DO or DO NOT / OF these people
Use probability tree for conditional probability.
Independence...
the probability of one event doesn't affect the probability of another event occuring...
P(A) X P(B) = P(A n B)
What are some assumptions you can make?
1. Events are independent.
2. There is no replacement.
3. That the size of the data is reliable for estimation.
Why an accuracy rate of 86% taken from a sample may not reflect true probability.
The accuracy rate may not be accurate because it may not to take into account other variables which may change the accuracy rate:
This includes:
1. Taken from only one sample, not representative, we need the whole population.
2.Training and experience.
3. Ethinicity and age.
and many other variables depending on the situation.
Purpose of a simulation.
The purpose of a simulation is to collect more data by creating more values. This helps us account for sampling variability. This is because the more data we have, the more accurate we can be in our conclusions.
With a simulation we can make a comparison between an occasional rate versus the expected usual rate created by the simulation.
What are some limitations?
Limitations are the same as assumptions:
One such assumption is INDEPENDENCE.
Theoretical vs Experimental
Our set of data may not represent true probability, because of other variables that may influence accuracy.
Some variables include...
One sample size taken, may not represent subgroups.
Small sample size, we do not have the whole population.
And other variables depending on the situation.
Limitations=
Assumptions.
These two terms are interchangeable.
It's what the data can and cannot tell you.
