Main Issue Post: Position B – Nonprobability (Purposive) Sampling
I support the position that nonprobability sampling, specifically purposive sampling, represents the best strategy for selecting research participants in applied behavioral research. This approach allows researchers to intentionally select individuals who possess specific characteristics relevant to the research question, rather than relying on random selection (Etikan, Musa, & Alkassim, 2016). In disciplines like applied behavior analysis (ABA), where interventions are tailored to unique behavioral profiles, purposive sampling ensures relevance, feasibility, and ethical alignment.
For example, in a study examining the effectiveness of a token economy system for increasing task compliance in children with autism, researchers would purposively select participants who exhibit low task compliance and meet diagnostic criteria. Random sampling would be inefficient and potentially unethical, as it could include individuals for whom the intervention is irrelevant or inappropriate. Purposive sampling ensures that the sample is directly aligned with the study’s objectives and the population of interest.
Data Collection Method: Direct Observation
One of the most widely used data collection methods in ABA is direct observation. This method involves systematically recording instances of target behaviors in real time using tools such as event recording, interval sampling, or duration tracking (Cooper, Heron, & Heward, 2020).
- Strength: Direct observation yields objective, context-sensitive data essential for identifying antecedents, behaviors, and consequences. It supports high ecological validity and is indispensable for functional behavior assessments.
- Limitation: It can be time-intensive and may introduce observer bias or reactivity if not carefully managed.
Ethical Issue and Strategy
A key ethical concern in direct observation is informed consent, particularly when observing minors or individuals with disabilities. Participants or their guardians must understand the purpose, procedures, and use of the data.
- Strategy: Researchers should use clear, accessible consent forms and ensure confidentiality through secure data storage and de-identification. Training observers in ethical conduct and cultural sensitivity further protects participant rights (Lee, 2025).
Measurement Reliability and Validity in ABA
In ABA, reliability refers to the consistency of measurement—often assessed through interobserver agreement (IOA). Validity refers to whether the measurement accurately captures the behavior of interest.For instance, if two RBTs independently record instances of "task refusal" and achieve 90% IOA, the measure is reliable. However, if the operational definition of refusal includes behaviors that don’t impede task engagement (e.g., verbal protest without cessation), the measure may lack validity. As Cooper et al. (2020) emphasize, reliability is necessary but not sufficient for validity.References
- Cooper, J. O., Heron, T. E., & Heward, W. L. (2020). Applied behavior analysis (3rd ed.). Pearson.
- Etikan, I., Musa, S. A., & Alkassim, R. S. (2016). Comparison of convenience sampling and purposive sampling. American Journal of Theoretical and Applied Statistics, 5(1), 1–4.
- Lee, S. (2025). Ethics in data collection methods. Retrieved from Number Analytics