Survey Methodologist: Questionnaire Design, Review, Sampling

Most survey problems are baked in before the first response arrives: a double-barreled question, a scale that leads, a check-all list that quietly under-counts, a sample that can't support the claim you want to make. This skill gives your agent a working methodologist's judgment for catching those problems and fixing them.

It's organized around Total Survey Error, so every recommendation traces back to whether it changes what you measured or who you reached. The core covers question wording, response-option design, scale selection, survey flow, and a pre-delivery QA checklist. Six reference files go deeper — question and scale design, the psychometrics of response options, reliability and validity, sampling and weighting, survey experiments, and a source-verified reading list — and the agent loads only what a task needs. Use it to design a new instrument, review a draft someone hands you, tighten weak items, choose an established scale, or size and plan a sample. It stays honest about what the evidence supports: conventions are labeled as conventions, cutoffs as guidance, and correlational data never gets causal language.

Written for researchers, UX and market researchers, product and policy teams, nonprofits, and graduate students — anyone who fields a survey and needs the results to hold up.