Professor Howard University Washington, District of Columbia, United States
Overview: Sample size has a significate effect on research findings, statistical power, and generalizability. This workshop will discuss the importance of choosing the appropriate sample size, factors affecting how large the sample should be, and will discuss how to calculate the sample required for a research project using the G*Power program.Proposal text:
Purpose: The purpose of this interactive workshop is fourfold: (1) to discuss the importance of choosing the appropriate sample size, (2) what factors impact sample size, (3) how large the size should be, and (4) how to calculate sample size.
Description: One of the most important questions in social work and social science research design is determining how large a sample should be and “how large is large”. Yet, this is perhaps the question given least consideration in many social work research projects. The determination of a sample size is often an important step in planning a quantitative research study not only because sample size impacts the generalizability of the results, but it also plays a major factor in selection test statistics used for analyses and producing more reliable results.
To this end, this three-hour workshop on research and evaluation will address the topics below:
1. Type of research hypotheses, one- versus two-tailed hypothesis 2. Level of significance (alpha) 3. Effect size 4. Power analysis 5. Computer software (G*Power) 6. Social work examples 7. Applications to social work research and to workshop participants.
Learning Objectives:
Understand the importance of selecting an appropriate sample size to detect significant results
Understand the various factors impacting how large the sample size should be for their research (alpha, desired power, direction of research hypothesis, effect size)
Learn how to utilize the computer program G*Power to calculate the minimum sample size appropriate for their research project as well compute priori and post statistical power.
