RSM 1 Lecture W6 Sampling.pdf

RSM1024 Research Methods in Psychology 1 Sampling Dr Wu Shin Ling OUR VISION: TO BE A WORLD CLASS UNIVERSITY  Population and Sample Probability Sampling Simple Random Sampling Stratified Random Sampling Clust...

RSM1024 Research Methods in Psychology 1 Sampling Dr Wu Shin Ling OUR VISION: TO BE A WORLD CLASS UNIVERSITY  Population and Sample Probability Sampling Simple Random Sampling Stratified Random Sampling Cluster Sampling Non-probability Sampling Overview Convenience Sampling Volunteer Sampling Quota Sampling Snowball Sampling Recruiting Participants Population and Sample Population: A group of individuals a researcher seeks to learn about from a research study. Sample: The group of individuals chosen from the population to represent it in a research study. Population and Sample Sampling error: The difference between the observations in a population and in the sample that represents that population in a study. Probability sample vs convenience sample Probability sample: Sample chosen such that individuals are chosen with a specific probability → most representative of the population Convenience sample: Sample chosen such that the probability of an individual being chosen cannot be determined → may not represent the population as well as a probability sample Probability Sample Individuals are chosen at random from the population such that the chance of any one individual being selected is known. Probability samples are most likely to be representative of the population, so you should use these samples whenever it is feasible to do so. Reduce the sampling error that exists.  Three types: Simple random sampling Stratified random sampling Probability Cluster sampling Sampling Simple Random Sampling Simple random sample: Sample chosen randomly from the population such that each individual has an equal chance of being selected. Access to ALL the individuals in the population is needed! → Difficult for large population Stratified Random Sampling Stratified random sample: Sample chosen from the population such that the in the population and the sample, proportion of individuals with a particular characteristic is equivalent Access to all the individuals in the population and the related proportion value is needed. → Solve location/ characteristic bias Cluster Sampling Cluster sample: Sample chosen randomly from clusters identified in the population Access to all the individuals in the selected clusters is needed. → more manageable → A portion of the population may be missed in the sample Cluster Sample School A 50 students Institution A School B 50 students School A 50 students All tertiary students Institution B in Malaysia School B 50 students School A 50 students Institution C School B 50 students  Three types: Non-probability Volunteer Sampling Sampling: Quota Sampling Convenience Snowball Sampling Sampling  Convenience Sample Individuals are chosen non-randomly from the population such that available individuals are chosen and the chance of any one individual being selected is not known. Thus, the sample may not represent the population as well as a probability sample but can be obtained more easily than a probability sample. Increase sampling error in the study Lowering its validity Internal – those who volunteered may have a different characteristics to begin with (confounding) External – not a good representation, thus difficult to generalize Volunteer Sample Sample chosen from the population such that available individuals are chosen based on who volunteers to participate. A sign-up system (E.g., an online sign-up system, a sign-up bulletin board), Volunteer samples are convenience samples because the probability of recruiting any individual from the population is not known due to a lack of random selection from the population or subset of the population. Sometimes involve Incentives (e.g., monetary compensation, extra credits, etc.). Volunteer Sample Quota Sample Sample chosen from the population such that available individuals are chosen with equivalent proportions of individuals for a specific characteristic in the population and sample. The quota sample makes use of convenience sampling techniques. ◦ It is like stratified random sampling in terms of proportion but it is not done randomly in regards to the subgroups. Snowball Sample Past participants recommend future participants. Normally use to recruit participants from a specialized population such as families with a child with Autism Spectrum Disorder, adults over 60 who run marathons, LGBT etc. Has disadvantage of introducing bias and lack of representative  Ethical issues Recuitment method Recruiting Incentives Participants Can you please participate in my study? Recruiting Participants Regardless of the type of sampling technique chosen, researchers must consider how to recruit the participants for a study. Consider the ethical issues involved. Recruiting Participants The issue of how to contact the participants to recruit them is related to the selection mechanism in some types of studies. The means of contacting participants is an important issue, as it may affect the sample size obtained for a study. Researchers should carefully consider recruitment techniques that may be most effective for their population. Recruiting Participants Incentives can also have an impact on the sample size obtained. For established institution participant pools, there may be incentives built into the recruitment process, such as completion of an assignment or extra credit in psychology courses. Other incentives, such as payment or tokens, could be used if the resources for these incentives exist. Using the Internet to Sample Internet Sample Samples obtained using the Internet are becoming more frequent in recent psychological research. Using the Internet to Sample Advantages ◦ Use of larger and more diverse samples ◦ Fewer opportunities for bias due to the limited interactions with participants ◦ Fewer constraints on the time and location of data collection, less time needed to collect a sample ◦ Fewer researchers needed to supervise the study procedures Using the Internet to Sample Disadvantages ◦ Some smaller subgroups in the population may require extra work to include in the sample because the number with access to the Internet may be too small to allow for adequate sampling. ◦ It may be difficult to control who completes a study on the Internet, making stratified random and quota samples more difficult to obtain and making it difficult to monitor repeat participation from the same individuals. Using the Internet to Sample Disadvantages ◦ It may also be difficult to balance group size in between-subjects designs. ◦ It is more difficult to monitor participants during the study procedure to rule out sources of bias (such as distractions) for Internet samples. Summary What are the differences between: population and a sample? probability and convenience sampling? Understand the advantages and disadvantages of different types of sampling technique is important. Suitable techniques should be used to recruit participants. Data collection No lecture on 3 June 2024 (Public Holiday). The workshops will be conducted as usual. Data collection will be conducted during Week 7 and 8. Google form for data collection will be posted on eLearn on Tuesday (4 June 2024, 10 am). The form will be closed on Week 9. All students are required to recruit 5 participants Participants: Between 18 years old to 25 years old, and currently a student pursuing tertiary education in Malaysia. Data Analysis – Week 10 38 Proof of data collection Upload 2 photos of data collection as proof. It can be a screenshot of the recruitment poster/notice on social media or a picture of collecting data physically. Upload by 18 June 2024 (Tuesday), 6pm. Upload the pictures here: https://forms.office.com/r/GQcfqkpsvP Must log in to your imail when uploading the images If unable to upload, you can share the link to your photos. Failure to collect the necessary data for this assessment may result in a penalty of marks being capped at 40% for the results and discussion section.  Practical Report 1 (Paired) Due 11 June 2024 (Tuesday), 2pm Only one member of your group should submit the practical report 1. There is ONE attempt for this assessment submission. Please make sure you upload the correct document. The file should be labeled with your Group number, underscore and then the file name (e.g., Group1_practicalreport1). 42 THANK YOU These teaching materials are protected under the Copyright Act 1987. Duplication, in any form, including digitally, is prohibited by law and a punishable offence. ©2024 OUR VISION: TO BE A WORLD CLASS UNIVERSITY