Failures in survey experiments
SRM Special Issue: Learning Through Failures
In recent years, social scientists have increasingly relied on survey experiments to estimate causal effects. As with any experimental design, survey experiments can fail, deviate from (preregistered) plans, or yield results that researchers did not anticipate. Researchers find themselves in situations with null, unexpected, inconsistent, or inconclusive results and must then decide if these are a product of the theory being tested, the experimental design, or both. The insights gained from such failures are often not widely shared, although they could be useful to improve the experiment design, research quality and transparency.
The planned special issue for Survey Research Methods is dedicated to learning from survey experiments that failed or led to unexpected results. Sharing the design and results from failed survey experiments, carefully considering their possible flaws, and discussing unexpected findings is useful to the development of theory (e.g., identifying scope conditions) and methods, and contributes to transparent research practice.
We invite submissions of short papers, essays, comments (of up to 3,000 words), and full-length articles (of up to 8,000 words) for this special issue, including case studies of failed survey experiments, meta-analyses, systematic reviews, as well as theoretical, methodological, and statistical contributions that may or may not rely on empirical data, simulated data, or no data at all.
FAQ
Are there any special requirements for the submission of papers to the Special Issue?
To submit, go to the SRM website and upload the article as a PDF, just like a standard SRM article; be sure to mention the special issue in the field for Author comments. In addition to the general Author Guidelines a maximum of one table is allowed per article (there are, however, no additional restrictions on the number of figures and graphs for the special issue).
Will the papers undergo peer-review?
Reviewing policies follow the common standards of SRM: Each submitted paper will be assigned to one of the two editors of the special issue. This supervising editor will then select two expert reviewers. The reviews and the reading of the supervising editor will be used for the final decision.
Can I submit an article about failures in survey research more generally?
Probably not. We only accept submissions that deal with actual or potential failures in survey experiments. Studies that failed but are not survey experiments might be of interest to this Special Issue if and only if learning from the failure in question can help to improve survey experiments. That could apply, for example, to other experimental studies or studies that use instruments (e.g., item batteries, stimuli) typically used in survey experiments.
Can I submit an article about failures in experimental research more generally?
Maybe. While our Special Issue’s focus will be on actual or potential failures in survey experiments, studies that failed but are not survey experiments might be of interest to this Special Issue if learning from the failure in question can help to improve survey experiments. That could certainly apply to other experimental studies. If you are wondering whether the contribution you have in mind fits in this Special Issue, we suggest you make use of the optional step of submitting an extended abstract (500-1000 words) to failures_srm@wzb.eu for pre-screening by the editors by September 01, 2024.
I have a question not answered on this site; how can I reach you?
Please send any questions you might have to failures_srm@wzb.eu