Assignment Week 5 Review
armando_rguez95
Ch12Sampling.pptChapter 12
Sampling
Copyright © 2018, Elsevier Inc. All Rights Reserved.
Copyright © 2018, Elsevier Inc. All Rights Reserved.
*
- Process of selecting representative units of a population for study in a research investigation
- Usually found in the methods section
Sampling
*
Copyright © 2018, Elsevier Inc. All Rights Reserved.
Copyright © 2018, Elsevier Inc. All Rights Reserved.
*
- Population
- Well-defined set with specific properties
- May be humans, medical records, specimens
Sampling Concepts
*
Copyright © 2018, Elsevier Inc. All Rights Reserved.
Copyright © 2018, Elsevier Inc. All Rights Reserved.
*
- Target population
- The entire set of cases about which the researcher would like to make generalizations
Sampling Concepts (Cont.)
*
Copyright © 2018, Elsevier Inc. All Rights Reserved.
Copyright © 2018, Elsevier Inc. All Rights Reserved.
*
- Accessible population
- Available population that meets the criteria
Sampling Concepts (Cont.)
*
Copyright © 2018, Elsevier Inc. All Rights Reserved.
Copyright © 2018, Elsevier Inc. All Rights Reserved.
*
- Inclusion and exclusion criteria
- Inclusion criteria, also called eligibility criteria
- Exclusion criteria, also called delimitations
Sampling Concepts (Cont.)
*
Copyright © 2018, Elsevier Inc. All Rights Reserved.
Copyright © 2018, Elsevier Inc. All Rights Reserved.
*
- Inclusion and exclusion criteria
- Determine the subjects used in a study by defining the criteria used to include or exclude a subject from a study
- Must be explained by the researcher
- Control for extraneous variables or bias
Sampling Concepts (Cont.)
*
Copyright © 2018, Elsevier Inc. All Rights Reserved.
Copyright © 2018, Elsevier Inc. All Rights Reserved.
*
- Sampling: the process of selecting a portion or subset of the designated population
- Sample: a set of elements that make up the population
Samples and Sampling
*
Copyright © 2018, Elsevier Inc. All Rights Reserved.
Copyright © 2018, Elsevier Inc. All Rights Reserved.
*
- Element: the most basic unit about which information is collected
- In nursing research, “elements” are usually individuals.
Samples and Sampling (Cont.)
*
Copyright © 2018, Elsevier Inc. All Rights Reserved.
Copyright © 2018, Elsevier Inc. All Rights Reserved.
*
- Purpose: to be more efficient; it is not cost-effective, or even feasible, to study an entire population
- Should be representative; a representative sample has the same key characteristics as the entire population
Samples and Sampling (Cont.)
*
Copyright © 2018, Elsevier Inc. All Rights Reserved.
Copyright © 2018, Elsevier Inc. All Rights Reserved.
*
Types of Sampling
- Nonprobability
- Inclusion in a group is NOT random
- Less generalizable
- Less representative
- Three types:
- Convenience
- Quota
- Purposive
- Probability sampling
- Uses randomization to assign elements
- More generalizable
- More representative
- Three types:
- Simple random sampling
- Stratified random sampling
- Cluster sampling
Copyright © 2018, Elsevier Inc. All Rights Reserved.
*
Copyright © 2018, Elsevier Inc. All Rights Reserved.
*
- Convenience
- Use of the most readily accessible persons or objects as subjects in a study
- Easy to recruit subjects
- Risk of bias greatest in this type of sample
- Used most with quantitative nonexperimental or qualitative studies
Nonprobability Sampling
*
Copyright © 2018, Elsevier Inc. All Rights Reserved.
Copyright © 2018, Elsevier Inc. All Rights Reserved.
*
- Quota
- Knowledge about characteristics of the population of interest used to build representativeness into the sample
- Identifies the strata of the population and proportionally represents the strata in the sample
Nonprobability Sampling (Cont.)
*
Copyright © 2018, Elsevier Inc. All Rights Reserved.
Copyright © 2018, Elsevier Inc. All Rights Reserved.
*
- Purposive
- Subjects selected who are considered to be typical of the population
- Useful in studying populations with unusual/rare characteristics
- Assumes that errors of judgment in overrepresenting or underrepresenting characteristics of the population in the sample will tend to balance out
Nonprobability Sampling (Cont.)
*
Copyright © 2018, Elsevier Inc. All Rights Reserved.
Copyright © 2018, Elsevier Inc. All Rights Reserved.
*
- Network sampling (Snowballing)—used for locating samples that are difficult or impossible to locate in other ways
- Use of social networks
Nonprobability Sampling (Cont.)
*
Copyright © 2018, Elsevier Inc. All Rights Reserved.
Copyright © 2018, Elsevier Inc. All Rights Reserved.
- Critiquing convenience samples
- What motivated some of the people to participate and others not to participate (self-selection)?
- What kind of data would have been obtained if nonparticipants had also responded?
Nonprobability Sampling (Cont.)
*
Copyright © 2018, Elsevier Inc. All Rights Reserved.
Copyright © 2018, Elsevier Inc. All Rights Reserved.
*
- Critiquing convenience samples
- How representative are the people who did participate in relation to the population?
- What kind of confidence can you have in the evidence provided by the findings?
Nonprobability Sampling (Cont.)
*
Copyright © 2018, Elsevier Inc. All Rights Reserved.
Copyright © 2018, Elsevier Inc. All Rights Reserved.
*
- Uses random selection
- Each element of the population has an equal and independent chance of being included in the sample.
- Strongest type of sampling strategy
- Used in experimental and quasi-experimental studies
Probability Sampling
*
Copyright © 2018, Elsevier Inc. All Rights Reserved.
Copyright © 2018, Elsevier Inc. All Rights Reserved.
*
- Simple random sampling
- Researcher defines the population (a set), lists all the units of the population (a sampling frame), and selects a sample of units (a subset) from which the sample will be chosen.
Probability Sampling (Cont.)
*
Copyright © 2018, Elsevier Inc. All Rights Reserved.
Copyright © 2018, Elsevier Inc. All Rights Reserved.
*
- Advantages: simple random sampling
- Sample selection is not subject to conscious biases.
- Representativeness of the sample is maximized.
Probability Sampling (Cont.)
*
Copyright © 2018, Elsevier Inc. All Rights Reserved.
Copyright © 2018, Elsevier Inc. All Rights Reserved.
*
- Advantages: simple random sampling
- Differences in the characteristics of the sample and the population are purely a function of chance.
- Probability of choosing a nonrepresentative sample decreases as the size of the sample increases.
Probability Sampling (Cont.)
*
Copyright © 2018, Elsevier Inc. All Rights Reserved.
Copyright © 2018, Elsevier Inc. All Rights Reserved.
*
- Disadvantages: simple random sampling
- Time consuming and usually inefficient method of obtaining a random sample
Probability Sampling (Cont.)
*
Copyright © 2018, Elsevier Inc. All Rights Reserved.
Copyright © 2018, Elsevier Inc. All Rights Reserved.
*
- Stratified random sampling
- Population divided into homogeneous strata or subgroups
- Allows more representativeness
Probability Sampling (Cont.)
*
Copyright © 2018, Elsevier Inc. All Rights Reserved.
Copyright © 2018, Elsevier Inc. All Rights Reserved.
*
Probability Sampling (Cont.)
*
Copyright © 2018, Elsevier Inc. All Rights Reserved.
Copyright © 2018, Elsevier Inc. All Rights Reserved.
*
- Advantages: stratified random sampling
- Enhanced representativeness of the sample
- Makes comparisons among subsets
- Disproportionately small stratum oversampled to adjust for underrepresentation
Probability Sampling (Cont.)
*
Copyright © 2018, Elsevier Inc. All Rights Reserved.
Copyright © 2018, Elsevier Inc. All Rights Reserved.
*
- Disadvantages: stratified random sampling
- It is difficult to obtain a population list containing complete critical variable information.
- It is time consuming.
- Enrolling proportional strata is challenging.
- A large-scale study is costly and takes time.
Probability Sampling (Cont.)
*
Copyright © 2018, Elsevier Inc. All Rights Reserved.
Copyright © 2018, Elsevier Inc. All Rights Reserved.
*
- Multistage (cluster) sampling
- A successive random sampling of units (clusters) that progress from large to small
- Sampling units or clusters that can be selected by simple random or stratified random sampling methods
Probability Sampling (Cont.)
*
Copyright © 2018, Elsevier Inc. All Rights Reserved.
Copyright © 2018, Elsevier Inc. All Rights Reserved.
*
- Multistage (cluster) sampling
- Advantages
- More economical in terms of time and money
- Disadvantages
- More sampling errors tend to occur than with simple random or stratified random sampling.
- Appropriate handling of the statistical data from cluster samples is complex.
Probability Sampling (Cont.)
*
Copyright © 2018, Elsevier Inc. All Rights Reserved.
Copyright © 2018, Elsevier Inc. All Rights Reserved.
*
Sampling Strategies
*
Copyright © 2018, Elsevier Inc. All Rights Reserved.
Copyright © 2018, Elsevier Inc. All Rights Reserved.
*
- Largest sample size possible
- Data saturation
- Pilot study
Sample Size
*
Copyright © 2018, Elsevier Inc. All Rights Reserved.
Copyright © 2018, Elsevier Inc. All Rights Reserved.
*
- Have the sample characteristics been completely described?
- Can the parameters of the study population be inferred from the description of the sample?
Sampling Critiquing Criteria
*
Copyright © 2018, Elsevier Inc. All Rights Reserved.
Copyright © 2018, Elsevier Inc. All Rights Reserved.
*
- To what extent is the sample representative of the population?
- Are the criteria eligibility in the sample specifically identified?
- Have sample delimitations been established?
Sampling Critiquing Criteria (Cont.)
*
Copyright © 2018, Elsevier Inc. All Rights Reserved.
Copyright © 2018, Elsevier Inc. All Rights Reserved.
*
- Would it be possible to replicate the study population?
- How was the sample selected? Is the method of sample selection appropriate?
- What kind of bias, if any, is introduced by this method?
Sampling Critiquing Criteria (Cont.)
*
Copyright © 2018, Elsevier Inc. All Rights Reserved.
Copyright © 2018, Elsevier Inc. All Rights Reserved.
*
- Is the sample size appropriate? How is it substantiated?
- Are there indications that rights of subjects have been ensured?
- Does the researcher identify the limitations in generalizability of the findings?
Sampling Critiquing Criteria (Cont.)
*
Copyright © 2018, Elsevier Inc. All Rights Reserved.
Copyright © 2018, Elsevier Inc. All Rights Reserved.
*
- Is the sampling strategy appropriate for the design and level of evidence provided by the design?
- Does the researcher indicate how replication of the study with other samples would provide increased support for the findings?
Sampling Critiquing Criteria (Cont.)
*
Copyright © 2018, Elsevier Inc. All Rights Reserved.
Copyright © 2018, Elsevier Inc. All Rights Reserved.
*
When calculating sample size using power analysis, the total sample size needs to consider that attrition or dropouts will occur.
10%
15%
25%
30%
Approximately what percent of extra subjects are needed to ensure the ability to detect differences between groups or that the effect of an intervention remains intact?
*
Copyright © 2018, Elsevier Inc. All Rights Reserved.
Copyright © 2018, Elsevier Inc. All Rights Reserved.
ANSWER: B
RATIONALE: When calculating sample size using power analysis, the total sample size needs to consider that attrition, or dropouts, will occur and build in approximately 15% extra subjects to make sure that the ability to detect differences between groups or the effect of an intervention remains intact. When expected differences are large, it does not take a very large sample to ensure that differences will be revealed through statistical analysis. When an appropriate sample size, including power analysis for calculation of sample size and sampling strategy have been used, the researcher can feel more confident that the sample is representative of the accessible population rather than biased.
*
50
68
112
480
To determine ethnic differences in cancer pain among four ethnic groups in the United States, what is the appropriate number of patients per ethnic group that should be used in the study?
*
Copyright © 2018, Elsevier Inc. All Rights Reserved.
Copyright © 2018, Elsevier Inc. All Rights Reserved.
ANSWER: B
RATIONALE: Using power analysis, the researcher must estimate how large of a difference will be observed among the four ethnic groups (i.e., to test differences in cancer pain, symptoms accompanying pain, and functional status). If a moderate difference is expected, a conventional effect size of 0.20 is assumed. With a significance level of 0.05, a minimum of 68 participants per ethnic group would be needed to detect a statistically significant difference between the groups with a power of 0.80.
*
When comprehensive results are desired
To increase generalizability of the findings
When the population size is very small
When the study is highly funded
When might an entire population be used in a research study?
*
Copyright © 2018, Elsevier Inc. All Rights Reserved.
Copyright © 2018, Elsevier Inc. All Rights Reserved.
ANSWER: C
RATIONALE: When the population size is very small. The only time it makes sense to use an entire population is when the population is very narrowly identified and thus very small and accessible.
*
Snowball sampling
Simple random sampling
Cluster sampling
Matching
What type of sampling includes using the Internet and social networking to locate samples that are otherwise difficult or impossible to locate?
*
Copyright © 2018, Elsevier Inc. All Rights Reserved.
Copyright © 2018, Elsevier Inc. All Rights Reserved.
ANSWER: A
RATIONALE: Snowball sampling; networking sampling, sometimes referred to as snowballing, is a strategy used for locating samples that are difficult or impossible to locate in other ways.
*
