Sampling Methods: Lecture 3 PDF

Sampling Methods: Techniques for Data Collection in Research Lecture 3 Dr. Bsmah Bojan Pharm.D, MSc, PhD Dr. Fahad Alkenani, BPharm, RPh, MSc, DIPBA, PhD, C-KPI, C-DA, CSPP Department of Pharmacy Practice, College of Pharmacy, Taibah Un...

Sampling Methods: Techniques for Data Collection in Research Lecture 3 Dr. Bsmah Bojan Pharm.D, MSc, PhD Dr. Fahad Alkenani, BPharm, RPh, MSc, DIPBA, PhD, C-KPI, C-DA, CSPP Department of Pharmacy Practice, College of Pharmacy, Taibah University 2024-1446 Outlines 1. Sampling and population 2. Sampling Methods: Probability sampling Non-Probability sampling 3. Sample size 4. Sampling Error Introduction to Sampling in Pharmacy Research What is Sampling?: A sample is a subset of population elements A sample is a smaller, manageable version of a larger group. It is a subset containing the characteristics of a larger population. Samples are used in statistical testing when population sizes are too large for the test to include all possible members. Recall Process of selecting elements from a population. Element is the basic unit of a population - usually humans Why Do We Use Sampling? 1. Saves Time and Resources: It's more efficient and practical to study a sample rather than the entire population. 2. Improves Accuracy: When done correctly, sampling can accurately reflect population characteristics. Example: Testing a new blood pressure medication in 100 patients instead of the entire population of patients with hypertension. Terms Population: refer to an entire group or elements with common characteristics. Sampling: is the process whereby a small proportion or subgroup of population is selected for analysis. Sample: refer to the small subgroup which is thought to be representative of the larger population.  Information From Samples Can Lead to Faulty Conclusions Sample Bias: The systematic overrepresentation or underrepresentation of a population in the chosen sample Sampling the Entire Population When your population is very small. When you have extensive resources. When you don’t expect a very high response. Census. Steps in the Sampling Process 1 2 3 4 5 Identify the Identify the Determine the Select Implement the target accessible size of the sampling plan population population sample needed technique  The sample needs to be Critical factor representative of your population of interest. Generalizability of your results is dependent on this facto  SAMPLING METHOD Non-Probability Samples Probability Sampling (Incidental Sampling) (Random Sampling) Non-Probability Sampling (Non-Random Sampling) Selecting sampling units based on subjective considerations, such as personal judgment or convenience (accidental). It is less preferred to probability sampling. Potential bias. Less representative of the target population. Most commonly used. 1. Convenience Sampling: Choosing individuals who are easiest to access. Example: Sampling patients who visit a specific pharmacy during a week to study customer satisfaction. 2. Purposive Sampling: Selecting individuals based on specific characteristics relevant to the research. Example: Choosing patients who have been using a medication for at least six months to assess long-term effects. 3. Quota sampling: Selecting a sample based on predefined characteristics of the population. - It has subgroups which can be pre- determined: gender (male/female), occupational status. Example: A researcher employs quota sampling to study medication adherence in a pharmacy, selecting 100 patients to match population proportions of age (40% 18-50, 60% over 50) and condition (60% hypertension, 40% diabetes). 4. Snowball sampling: Sampling technique where participants recruit other participants for a study, particularly useful for hard-to-reach populations. Example: A researcher studies medication use among undocumented immigrants by initially recruiting participants through community health centers, then asking these participants to refer others. Probability (Random)Sampling All members of the population have an equal chance of selection. The best method and more expensive method of sampling. More likely to be representative of the relevant population. Using a method such as a dice, coins, hat or random number tables to select randomly from the list the number of members required for the sample. 1. Simple Random Sampling: Each member of the population has an equal chance of being selected. Applicable when population is small, homogeneous & readily available. Example: Randomly selecting patients from a list to test a new drug. 2. Stratified Sampling: The population is divided into subgroups (strata), and random samples are taken from each. Example: Dividing patients by age group to ensure equal representation in a clinical trial. 3. Systematic Sampling: general procedure is to select every 5th or 6th participant from the population. If the population elements are in random order then this will be very representative of random sampling. Example: Choosing every 10th student from a list of 1,000 after starting at a randomly selected position. Sampling Error Definition: Sampling error arises due to the natural variability in the population and the fact that samples are smaller than the entire population. It occurs because a sample is only a subset of the entire population, and thus it may not perfectly represent the whole. Causes: 1. Sample Size: Smaller samples are more prone to larger sampling errors. 2. Population Heterogeneity: More diverse populations may lead to greater sampling error. How Many Participants? Need to have enough to assure reliability of results (often termed the “power” of the study). Becomes very important during statistical tests. Powerful studies (big N) can detect small differences between groups. Sample Size Definition: It refers to the number of observations or data points included in a sample drawn from a population. Importance of sample size: 1. Accuracy: Larger sample sizes generally lead to more accurate estimates of population parameters. 2. Statistical Power: A bigger sample improves the ability to detect a true effect or difference when one exists. 3. Confidence Intervals: Larger samples yield narrower confidence intervals, providing a more precise range for the population parameter. Factors Influencing Population Size: The total number of individuals in the population can impact the Sample Size required sample size. Margin of Error: A smaller margin of error requires a larger sample size. Confidence Level: Higher confidence levels (e.g., 95% vs. 90%) necessitate larger samples. Variability: More variability in the population increases the required sample size to achieve reliable results. Sample Size Calculation The formula for calculating sample size (for estimating a 𝑍 2.𝑝.(1−𝑝) proportion) is: 𝑛= 𝐸2 Where: n = required sample size. Z= Z-score (confidence level). p = Estimated proportion of the population. E = Margin of error. Identifying Sampling Methods For each of the following scenarios, identify which sampling method is being used and explain your choice. 1. A researcher wants to evaluate the effectiveness of a new diabetes medication. They divide patients into two groups based on age (under 50 and over 50) and then randomly select 50 patients from each group for the study. 2. A pharmacy conducts a study to evaluate customer satisfaction by handing out surveys to patients who visit the pharmacy during the first week of each month. 3. A clinical trial is conducted to test a new cancer drug, but only patients who have been using similar medications for more than six months are selected for the study. 4. A researcher is studying the effects of a cholesterol-lowering drug. They randomly select 100 patients from a list of all patients in the hospital.