PDF Week 7. NRES1. Population. Sampling..pdf

Population and Sample in Research Dr. Adrian M. Lawsin, RN Professor, Nursing Research Learning Objectives On completing this lecture, you will be able to: Describe sampling theory with its relevant...

Population and Sample in Research Dr. Adrian M. Lawsin, RN Professor, Nursing Research Learning Objectives On completing this lecture, you will be able to: Describe sampling theory with its relevant concepts. Identify the speci c types of sampling methods implemented in quantitative and qualitative studies. Determine the sample size in selected studies. fi Flow of Steps in Research  6. Selecting a research design 7. Developing intervention protocols Phase 2: 8. Identifying the population The design and 9. Designing the sampling plan planning phase 10.Specifying the methods to measure research variables 11.Developing methods to safeguard subjects 12.Finalizing the research plan Phase 2: The Design and Planning Phase In the second major phase of a quantitative study, researchers decide on the methods they will use to address the research question. STEP 6 Selecting a research design The research design is the overall plan for obtaining answers to the research questions. Quantitative designs tend to be structured and controlled, with the goal of minimizing bias. The research design is the architectural backbone of the study. STEP 7 Developing Protocols for the Intervention An intervention protocol for the study must be developed, specifying exactly what the intervention will entail (e.g., who will administer it, over how long a period the treatment will last, and so on) and what the alternative condition will be. In non-experimental research, this step is not necessary.  STEP 8 Identifying the Population A population is all the individuals or objects with common, de ning characteristics Researchers specify population characteristics through eligibility criteria. Researchers establish criteria to determine whether a person qualifies as a member of the population (inclusion criteria) or should be excluded (exclusion criteria). fi  Joseph and colleagues (2016) studied children’s sensitivity to sucrose detection (sweet taste). To be eligible, children had to be healthy and between the ages of 7 and 14 years. Children were excluded if they had a major medical illness, such as diabetes, heart disease, or asthma. Example of Inclusion and Exclusion Criteria STEP 9 Designing the Sampling Plan Sampling involves selecting cases (sample) to represent the population. A sample, is a subset of the population. Strata are subpopulations, mutually exclusive segments of a population based on a speci c characteristic. A sampling plan speci es how the sample will be selected and how many subjects there will be. The goal is to have a sample that adequately re ects the population’s traits. fi fl fi  Importance of Sampling in Quantitative Research Generalizability. Well-designed samples allow researchers to apply ndings from the sample to the entire population. Cost-E ectiveness. Sampling is more practical and cost-e ective than studying the entire population. Accuracy. Careful sampling minimizes bias, improving the validity of the research results. ff ff fi Sampling Designs in Quanti Nonprobability Sampling Probability Sampling Sample elements are selected by involves random selection of nonrandom methods in which every elements from a population. Each element does not have an equal element in the population has an chance to be included. equal, independent chance of being selected. This can introduce bias, but it is sometimes used for exploratory This reduces bias and increases research. generalizability. Nonprobability Sampling Convenience Sampling selecting the most conveniently A Nurse distributes available people as participants. questionnaires about vitamin use studies. It is the weakest form of to college students leaving the sampling, but it is also the most library is sampling by commonly used. convenience. Quota Sampling If the population is known to researchers identify population have 50% males and 50% strata and gure out how many females, then the sample should people are needed from each have similar percentages. stratum. fi  Nonprobability Sampling Consecutive Sampling involves recruiting all people from In a study of ventilator-associated an accessible population over a pneumonia in intensive care unit speci c time interval or for a (ICU) patients, a consecutive sample speci ed sample size. might consist of all eligible patients who were admitted to an ICU over a 6-month period. Purposive Sampling Hewitt and Cappiello (2015) invited a involves using researchers’ purposively sampled panel of knowledge about the population experts knowledgeable in the to handpick sample members. provision of reproductive health care to o er their viewpoints for identifying essential nursing competencies for prevention and care relating to unintended pregnancy. ff fi fi Snowball Sampling early sample members are asked to identify and refer other people who meet the eligibility criteria.  Probability Sampling Simple Random Sampling The most basic of the probability sampling plans. It is achieved by randomly selecting elements from a sampling frame. A Sampling Frame is a list of every Neta et al. (2015) studied adherence to member of the population using the foot self-care in patients with diabetes sampling criteria to define eligibility. mellitus in Brazil. The population included The list of elements from which the 8,709 patients with type 2 diabetes. The sample will be chosen. researchers randomly sampled 368 of these patients.  Probability Sampling Strati ed Random Sampling The population is rst divided into two or more strata, from which elements are randomly selected. Like with quota sampling, the aim of stratified sampling is to enhance representativeness. Buettner-Schmidt and colleagues (2015) studied the impact of smoking legislation on smoke pollution levels in bars and restaurants in North Dakota. A total of 135 venues were randomly sampled from three strata: restaurants, bars in communities with ordinances stronger than the state law, and bars not in such communities. fi fi  Probability Sampling Systematic Sampling involves the selection of every nth case from a list, such as every 10th person on a patient list. Systematic sampling can be done so that an essentially random sample is drawn. Ridout and colleagues (2014) studied the incidence of failure to communicate vital information as patients progressed through the perioperative process. From a population of 1,858 patient records in a health care system meeting eligibility criteria, the researchers selected every sixth case, for a sample of 294 cases. Sample Size QUANTITATIVE  Sample Size Determination. QUANTI The sample size depends on: Population Size. Larger populations generally require larger samples. Margin of Error. How much error you are willing to tolerate (smaller margins require larger samples). Commonly set at 0.05 or 5%. Con dence Level. Usually 95% (represented by a Z- value of 1.96 in statistical formulas). Variance. The variability within the population. If unsure, a 50% variance is often used for conservative estimates. fi The COCHRAN FORMULA Commonly used in survey research, especially when you're sampling a large population and want to ensure your results are reliable. Cochran's formula ensures that your sample size is large enough to provide reliable, statistically significant results without surveying the entire population, making it a powerful tool for survey research. Cochran, W. G. (1977). Sampling Techniques (3rd ed.). John Wiley & Sons. Israel, G. D. (1992). Determining Sample Size. University of Florida IFAS Extension.  Steps & Example COCHRAN FORMULA STEPS EXAMPLE 1.Set the con dence level (usually Con dence level = 95% → Z = 1.96 95%), which corresponds to a Z- value (e.g., 1.96). Estimated proportion (p) = 0.5 (since we don't know the actual proportion) 2.Estimate the population proportion (p). If you don't know Margin of error (e) = 0.05 the exact proportion, use 0.5 (this maximizes the required sample size). 3.Determine the margin of error (e). For example, if you want a 5% error margin, e = 0.05. The researcher would need a sample size of 4.Plug these values into the about 384 respondents for a large population formula to calculate the required to ensure a provide reliable and statistically sample size. signi cant results. fi fi fi Sample Size QUALITATIVE  Sample Size Determination. QUALI Key Considerations for Sample Size in Qualitative Research: Purpose of the Study. Qualitative research seeks to understand how and why things happen, rather than quantifying outcomes. The sample size should be large enough to ensure data saturation but small enough to manage the depth of analysis required. DATA SATURATION. Saturation is reached when no new information or themes are emerging from the data. Once the researcher notices repetitive patterns, the sample size is considered su cient. Studies typically report achieving saturation anywhere from 5 to 30 participants. ffi Phenomenology. Often involves 5-10 participants, focusing on deep exploration of lived experiences. Grounded Theory. May require 20-30 participants or more, as it aims to develop a theory from the data. Ethnography. Depending on the depth of immersion in a culture or setting, this can vary greatly, but usually fewer participants are studied intensively over a long period. Case Study. A single case study might focus on 1-5 cases, with detailed analysis of each case.  Pragmatic Considerations in Qualitative Sampling. Resources (time, budget, and availability of participants) often in uence sample size decisions. Small, manageable sample sizes are often used in qualitative research because of the intensive nature of data collection (e.g., interviews, focus groups, observations) and analysis. Guest, G., Bunce, A., & Johnson, L. (2006). How Many Interviews Are Enough? An Experiment with Data Saturation and Variability. Creswell, J. W., & Poth, C. N. (2017). Qualitative Inquiry & Research Design: Choosing Among Five Approaches. fl  References Polit, D. F., & Beck, C. T. (2021). Essentials of Nursing Research: Appraising Evidence for Nursing Practice. Wolters Kluwer. Polit, D. F., & Beck, C. T. (2021). Nursing Research: Generating and Assessing Evidence for Nursing Practice. Wolters Kluwer Health, Lippincott Williams and Wilkins. Nieswiadomy, R. M., & Bailey, C. (2018). Foundations of Nursing Research. Pearson Education, Inc. Salamat, RN! Dr. Adrian M. Lawsin, RN Professor, Nursing Research