Stats Flashcards
What is a population?
The whole set of items that are of interest
What is a sampling frame?
A list where sampling units are individually named or numbered.
Advantages and disadvantages of a census
+ve: gives a completely accurate result
-ve: time consuming, expensive, cannot be used if testing destroys the item, more data to process which is harder
Advantages and disadvantages of simple random sampling
+ve: free of bias, easy and cheap, each sample unit has a known equal chance of selection.
-ve: not suitable when population size is large, sampling frame is needed
Advantages and disadvantages of systematic sampling
+ve: simple and quick to use, suitable for large samples and populations
-ve: sampling frame is needed, can introduce bias if sampling frame is not random
Advantages and disadvantages of stratified sampling
+ve: sample accurately reflects the population structure, guarantees proportional representation of groups within a population
-ve: population must be clearly classified into distinct strata, selection within each stratum has same -ve as simple random sampling
Advantages and disadvantages of quota sampling
+ve: allows small sample to still be representative of the population, no sampling frame, quick easy inexpensive, allows for easy comparison between different groups within a population
-ve: non-random sampling can introduce bias, population must be divided into groups, non-responses are not recorded as such
Advantages and disadvantages of opportunity sampling
+ve: easy to carry out, inexpensive
-ve: unlikely to provide a representative sample, highly dependent on individual researcher
Define random
Where the outcome is not known until the experiment is carried out
What is a random variable?
A variable whose value depends on the outcome of a random event
Sample space
The range of values that a random variable can take
Discrete
The variable is discrete if it can only take certain numerical values
What is a probability distribution?
Something that fully describes the probability of any outcome in the sample space. Can be a probability mass function, a table or a graph
Discrete uniform distribution
When all of the probabilities are the same in discrete data
How to tell if two events are mutually exclusive
P(A or B) = P(A) + P(B)