Lecture 5B, part 2 Flashcards
Details about sampling frames
Samples should be representative, and the sampled pop should contain the same variation as the pop that it is selected from (otherwise selection bias can result)
Properly drawn sample provides info appropriate for describing the pop composing the sampling frame
Sample is only representative of the pop that it is selected from
Aspects of probability sampling
Each element/unit has an equal chance of being selected in the sample independent of any other event in the selection process
Can assign a numeric value to the probability of any one person being chosen for the study/requires that the number of potential participants in the study pop must be known
Advantages of probability sampling
Although never perfectly representative, more likely to avoid the problem of selection bias
Permits estimates of accuracy or representativeness
Aspects of non-probability sampling
Each element may have an unequal or unknown chance of being selected in the sample (the probability of selection is unknown)
Used when no sampling frame is available
Types of probability sampling methods
Simple random
Systematic random
Stratified random
Cluster
Multi-stage
Definition of simple random sampling
Every individual in the sampling frame has the same probability of being selected for the sample
Sampling ratio definition
Proportion of elements in the pop that are being selected
When is systematic random sampling used?
When simple random sampling may not be efficient or too laborious
What does systematic random sampling require?
A list, where every kth element in the total list is chosen (systematically) for inclusion in the sample
Sampling interval defintiion
Standard distance between elements selected in the sample
Disadvantage of systematic random sampling?
Since it requires a list, representativeness depends on the random arrangement of the subjects
Selection bias results if list is subject to periodicity (such as a cyclical pattern)
How can bias be avoided with systematic random sampling?
The first person should be selected at random
When is stratified random sampling used?
When researchers want to assign a greater than random probability of selecting units with particular characteristics (also called over-sampling)
What does stratified random sampling ensure?
Appropriate numbers of elements are drawn from homogenous subjects of the pop
How many characteristics can be used in stratified random sampling?
More than one