Survey methods for neuropsychologists: A review of typical methodological pitfalls and suggested solutions

Abstract

Objective: Survey research has enjoyed an increase in popularity, in part due to the availability of user-friendly software programs for online survey development and deployment. Neuropsychologists often use this methodology to learn about common clinical practices and attitudes in the field or to assess outcomes for patients. This paper aims to provide an overview of sound methods and common problems in survey research, along with specific recommendations for neuropsychologists wishing to conduct their own surveys or judge the quality of survey research. We also discuss some recent challenges and changes in the field of survey methodology.

Method: We provide a brief literature review on survey design and methodology, as well as a review of recent studies addressing current challenges such as sampling, measurement, and response rates.

Results: We suggest best practices that should be implemented when designing, administering and reporting on neuropsychological survey-based research studies. We discuss two approaches to improve survey design, Total Survey Error and the Tailored Design Method.

Conclusions: In spite of the current challenges in modern survey research, with lower response rates and the proliferation of internet surveys, survey research continues to be a valuable tool in neuropsychology. We offer a list of DO’s and DON’T’s to guide neuropsychologists planning to conduct surveys of their field.

Keywords:

• Survey research
• neuropsychology
• methodology
• total survey error
• tailored design method

Disclosure statement

No potential conflict of interest was reported by the authors.

Notes

1 Some surveys generate sampled cases via clustering procedures that produce a probability sample without actually listing or enumerating the entire frame of persons or units from which the sample is drawn.

2 Qualtrics and some other platforms for online surveys allow the researcher to detect the IP address of the device used by the respondent, and to accept only one survey response from any given IP address, a measure that reduces but does not eliminate the chance of duplicate or multiple responses from the same person in an anonymous survey.

3 Separate reporting of response rates by sample type is required (in multi-sample studies) by the AAPOR Code of Professional Ethics and Practice (AAPOR, 2015a, 2015b).