Chapter 11 - Understanding Sampling.pptx
- 2. The Survey Design • Introduce readers to the basic purpose and rationale for survey research. Example: The primary purpose of this study is to empirically evaluate whether the number of overtime hours worked predicts subsequent burnout symptoms in a sample of emergency room nurses. • Indicate why a survey method is the preferred type of approach for this study. Indicate whether the survey will be cross-sectional—with the data collected at one point in time— or whether it will be longitudinal—with data collected over time.
- 3. The Survey Design • Specify the form of data collection. E.g., mail, telephone, the Internet, personal interviews, or group administration, google form etc. • Regardless of the form of data collection, provide a rationale for the procedure, using arguments based on its strengths and weaknesses, costs, data availability, and convenience.
- 4. The Population and Sample (to be described in a research plan) Population • Identify the Population: Clearly define who or what constitutes the population of the study. • State the Size of the Population: Provide an estimate of the population size, if it can be determined. • Means of Identifying Individuals: Describe methods used to identify and select individuals from the population. • Access Considerations: Address potential issues related to gaining access to the population.
- 5. Why Sample? • Studying entire populations (censuses) is often impractical, expensive, and time- consuming. • Sampling allows for efficient data collection, enabling inferences about the population based on a representative subset. • Accurate sampling is crucial for valid and reliable research conclusions. Biased samples can lead to erroneous generalizations.
- 6. Essential Terminology • Population: The entire group of individuals or entities that the research is interested in studying. This is the target of the inference. • Sample: A subset of the population selected for study. Data is collected from the sample to represent the larger population. • Sampling Frame: A list or description of the population from which the sample is drawn. Ideally, this should accurately reflect the population.
- 7. Essential Terminology • Sampling Error: The difference between the characteristics of the sample and the characteristics of the population. Some degree of sampling error is always expected, and it is minimized through appropriate sampling techniques. • Sampling Bias: Systematic error introduced into the sample selection process. This leads to a sample that does not accurately represent the population.
- 8. Probability Sampling Each member of the population has a known, non-zero probability of being selected for the sample. This allows researchers to make inferences about the population with a known margin of error and to estimate the confidence level of the results. • Simple Random Sampling: Every member of the population has an equal chance of being selected. This is often done using random number generators or lottery-style methods. It's straightforward but may not be representative if the population is diverse. • Stratified Random Sampling: The population is divided into subgroups (strata) based on relevant characteristics (e.g., age, gender, income). A random sample is then taken from each stratum, ensuring representation from all groups. This improves the accuracy of estimates for each stratum and the overall population.
- 9. Probability Sampling • Cluster Sampling: The population is divided into clusters (e.g., geographical areas, schools), and a random sample of clusters is selected. All members within the selected clusters are then included in the sample. This is efficient for large, geographically dispersed populations but may have higher sampling error than other methods. • Systematic Sampling: Members of the population are selected at regular intervals (e.g., every 10th person). This is simple to implement but can be problematic if there's a pattern in the population that aligns with the sampling interval.
- 10. Probability Sampling • Multistage Sampling: This combines different probability sampling methods. For example, you might first use cluster sampling to select regions, then stratified random sampling within those regions, and finally simple random sampling to select individuals. This is common in large-scale surveys.
- 11. Non-Probability Sampling The probability of selection is unknown; therefore, generalization to the population is limited. Useful in exploratory research or when probability sampling is not feasible. • Convenience Sampling: Selecting participants based on their accessibility and availability. This is easy and inexpensive but highly susceptible to bias, as the sample may not be representative of the population. • Quota Sampling: Similar to stratified sampling, but the selection within each stratum is not random; researchers select participants until they meet pre-defined quotas for each stratum. This is more convenient than stratified random sampling but still prone to bias.
- 12. Non-Probability Sampling • Purposive Sampling (Judgmental Sampling): Researchers select participants based on their knowledge or judgment about who will be most informative for the study. This is useful for exploratory research or when studying specific populations but relies heavily on researcher expertise and may be subjective. • Snowball Sampling: Participants are asked to refer other potential participants. This is useful for reaching hard-to-reach populations but can result in biased samples due to the self-selection process.
- 13. Sample Size Considerations How Big Should My Sample Be? • Sample size depends on the population size, desired level of precision (margin of error), and acceptable level of confidence. • Larger samples generally lead to more precise estimates and lower sampling error. • Power analysis can help determine the appropriate sample size to detect a meaningful effect. • Too small a sample can lead to inaccurate conclusions, while an excessively large sample might be inefficient.
- 14. Choosing the Right Method The optimal sampling method depends on several factors, including: • Research question: What are you trying to find out? • Population characteristics: How diverse is the population? • Resources: What is your budget and timeframe? • Desired level of accuracy: How precise do your estimates need to be?