Lelkes & Weiss 2015 — skeptical counter: item-specific no better on criterion validity

Claim: Lelkes & Weiss (2015, Research & Politics, "Much ado about acquiescence"), using two ANES waves (n ≈ 5,900), found construct-specific questions were no better than agree/disagree on:

• Test-retest reliability — both averaged polychoric r = 0.63.
• Criterion validity — differences -0.02 to -0.05, confidence intervals overlapping.
• Even among acquiescence-prone respondents (low verbal ability, high agreeableness, face-to-face mode).

Their conclusion: construct-specific format "should not be considered a canonical solution."

Source: Lelkes & Weiss 2015, R&P. Important skeptical counterpoint.

Confidence: Verified — and reconciles with Saris 2010 via different facets: Saris measured CONVERGENT validity (MTMM), Lelkes & Weiss measured CRITERION validity.

Honest concession for Candid: Rewriting questions from agree/disagree to item-specific helps measurement quality but is not magic. The bigger win is converting JUDGMENTS to OBSERVATIONS entirely (R1 — Convert every judgment into an observation or counting task).