6.2 Sampling Flashcards
Sampling
- Process of selecting representative units of a population in a study
- Usually found in the “methods” section
Definitions
Population
- The entire group of elements that meet the study’s inclusion requirements
Accessible Population
- Population that meets the target population criteria and is available
Sample
- Set of elements that make up the population
Inclusion Criteria
- Characteristics that restrict the population to a homogenous group of subjects (Eligible Criteria)
Exclusion Criteria
- Characteristics that restrict the population to a homogenous group of subjects
Samples/Sampling
- Selection of a portion of the population to represent the entire population
- When done properly claims can be made about the population based on data from the sample alone.
- Sample size and method of selection determines how well data is represented in the population
Nonprobability Sampling
- Elements are chosen with non-random methods
DRAWBACK
- Findings are less generalizable
- No way of estimating the probability of an element being included in a particular sample
- Carefully choose inclusion and exclusion criteria and have an optimal sample size to increase sample representativeness of the population
Types
- Convenience Sampling
- Quota Sampling
- Purposive Sampling
- Network (Snowball) Sampling
Probability Sampling
- Random Sampling (Selection)
- Goal is to obtain representative elements of populations
- Random means each element of the population has an equal and independent chance of being included in the sample.
- Element (members of the population) are selected from a sampling frame (lists all elements of a population)
ADVANTAGE
- Greater confidence that sample is not bias and is representative of the population being studied
TYPES
- Simple random sampling
- Stratified random sampling
- Multistage (Cluster) Sampling
Sample Size
Optimal Sample Size Depends On
- Type of design
- Type of sampling procedure
- Type of formula used for estimating optimal sample size
- Degree of precision required
- Heterogeneity of the attributes under investigation
- Frequency of the phenomena of interest occurring in the population
- Projected cost of using a particular sampling strategy
- LARGEST SAMPLE SIZE POSSIBLE IS THE BEST APPROACH
- Samples sizes that are too small are not generalizable
- COHEN’s POWER ANALYSIS TO DETERMINE OPTIMAL SAMPLE SIZE
Sample Size
Sometimes “larger sample is better” has exceptions
- Qualitative research tends to be fewer sample size until “data saturation” is reached
- Pilot studies (prelude to larger scale studies or parent studies) also use small sample sizes
