Sampling and Setting Flashcards
Population
All the elements we want to study
Organization, charts, blood sample
Sample
Smaller
Hands on
Tangible
What factors need to be considered in determining sample size?
Type of design
- Quantitative
- Qualitatative (narrative data, hands on, written, smaller sample size)
Type of sampling
- How are researchers going to get elements out of population?
- Is population easily accessible? (List of all nurses in Fraser Health vs rare sample)
What is the heterogeneity?
- Are we looking at things that are the same?
How frequently phenomenon occurs?
- If happens frequently then bigger sample size
Types of sampling
Probability (random)
- Every person in the population has an opportunity to participate
- Random sample, simple, stratified, cluster, systemic
Non-probability (non-random)
- Chosen with specific elements in mind
- Convienence, quota, purposive, network sampling
- Easier
- Cheaper
Simple random
Population defined Samling frame listed Subset from which sample chosen is selected Population - BC nurses Sampling frame - List of all nurses that practice in BC Randomly start choosing nurses
Stratified
Population divided into subgroups
Appropriated number of elements from each subgroup randomly selected based on their proportion in population
- BC nurses over age of 50
- If 60% over 50, make sure sample size has 60% nurses over 50 so accurately reflects BC nurses
Cluster
Successive random sampling of units
Units progress from large to small (multi-stage)
- Start with really big aspect then stage down to something more manageable
- Nursing students across Canada, randomly choose districts across Canada, BC/prairie/up north, randomly choose 3 nursing schools and 1 from each district, randomly choose nursing students from each
Systemic
Involves selection of subjects randomly drawn from a population list at fixed intervals
Need sampling frame (everyone in population)
- Phone book
Choose every 50th individual with random starting point
Non-probability sampling
Convenience
- Uses the most readily accessible persons or objects as subjects of a study
Quota
- ID the strata of the population and proportionally represents the strata in the sample
Purposive
- Researcher selects subjectives who are considered to be typical of the population
Network sampling
- Strategy for locating samples who are different to locate
- Uses social networks and facts that friends tend to have characteristics in common
- Subjects who meet eligibility criteria asked for assistance in getting in touch with people with same criteria (snowballing)
Theoretical sampling
Found in qualitative grounded theory studies
Purpose is to deliver categories and to offer interrelationships that occur in substantive theory
Used to strengthen and understand the evolving theory
Sample size
Increase homogeneity, decreases sample size
Increase attrition, increase sample size
Increase variable, increase sample size
Increase measurement sensitivity, decrease sample size
How is sample size determined?
Quantitative
Qualitative
- Data saturation (have they exhausted the themes and received all info they need?)
Errors for quantitative
Type 1
- Says there is a difference when there is NOT
- Rejecting the null hypothesis that is true (difference due change, reliability/validity of instruments)
Type 2
- Says there is no difference when there is one
- Accepting the null hypothesis that is false (caused by small sample size)
Sample critique for quantitative
What type of sample?
Is the sample representative?
- If probability, yes
- If convenience or quota, no
Are inclusions and exclusion criteria clearly presented?
Is the sample size sufficient?
To what population can the findings be generalized?
What are limitations to generalizability?
Sample critique for qualitative
What type of sample? Is it appropriate to design? Is the sample size appropriate? How is it substantiated? What are limitations to generalizability?
