How to ScienceMethodologySurvey DesignResponse Order

Response Order

On this page

  • Mechanisms
  • Studies
  • Summary
  • References

On this page

  • Mechanisms
  • Studies
  • Summary
  • References

When presenting a Likert-type scale, you must choose which end of the scale to present first. On a horizontal scale, should “Strongly agree” appear on the left or “Strongly disagree”? On a vertical scale, which appears at the top?

Mechanisms

Two mechanisms have been proposed to explain why response order can affect answers.

Satisficing (Krosnick, 1991) — when questions are difficult or motivation is low, respondents may select the first acceptable option without fully evaluating the rest. In visual surveys this biases responses toward earlier options; in telephone surveys toward later ones, since the last option heard remains most accessible in memory.

Anchoring-and-adjustment (Yan & Keusch, 2015) — respondents anchor on the first option and adjust insufficiently as they work through the remaining alternatives, biasing responses toward the starting point of the scale.

Studies

Table 1: Overview of empirical studies on response order effects.

SourceTopicScaleModeNSampleMain finding
Friedman et al. (1994)Student attitudes toward college5-pt agree–disagree, fully labeled, horizontalPAPI208US undergradsPrimacy effect: strongly-agree-first yields more agreement on favorably worded items
Weng & Cheng (2000)Personal distress5-pt fully labeled, within-subjectsPAPI858Taiwanese studentsNo substantial response order effects on means or psychometric properties
Rammstedt & Krebs (2007)Personality (BFI-10)7-pt endpoint-labeledPAPI315German studentsScale direction alone has no effect; number–label directional mismatch does affect responses
Yan & Keusch (2015)Country development ratings11-pt endpoint-labeled unipolarCATI498US adults (RDD)Primacy effect for high-rated countries; consistent with anchoring-and-adjustment
Malhotra (2008)Various attitudesMulti-item, horizontalCAWI397US adults (KnowledgePanel)Primacy effect strongest for fast, low-education respondents
Christian et al. (2009)VariousVarious, horizontal and verticalCAWI~3,156US undergradsResponse order effects mainly for vertical scales; nonlinear layout creates position bias
J. Höhne & Lenzner (2015)Various attitudes5-pt agree–disagree, horizontal and verticalPAPI (+ eye-tracking)84German participants (GESIS)Response order effects larger for vertical than horizontal; eye-tracking confirms skipping of terminal categories
Krebs & Hoffmeyer-Zlotnik (2010)Job importance8-pt endpoint-labeledPAPI436German studentsPrimacy effect: positive-first yields higher importance ratings; factor structure unaffected
Krebs & Bachner (2018)Job characteristics7-pt endpoint-labeled unipolarPAPI—German and Israeli studentsPrimacy effect present in both left-to-right and right-to-left reading-direction groups
Garbarski et al. (2015)Self-rated health5-pt fully labeled (excellent–poor)CAWI2,696US adults (KnowledgePanel)Primacy effect: excellent-first order yields better self-rated health
Garbarski et al. (2016) (Study 1)Self-rated health5-pt fully labeled (excellent–poor)CAWI1,347US adults (KnowledgePanel, TESS)Primacy effect: excellent-first yields better SRH
Garbarski et al. (2016) (Study 2)Self-rated health5-pt fully labeled (excellent–poor)CAWI499US adults (KnowledgePanel, RTI)Primacy effect replicated
Keusch (2018)Brand attribute ratings6-pt endpoint-labeled unipolarCAWI502Austrian non-probability panelPrimacy effect for all respondents; stronger for speeders; consistent with satisficing and anchoring-and-adjustment
J. K. Höhne & Krebs (2018)Various attitudes5-pt agree–disagree and item-specificPAPI930German studentsScale direction effects found for agree–disagree but not item-specific question formats
Liu & Keusch (2017)Various attitudes (ANES)Multi-item attitude scaleCAWI, CAPI—US adults (ANES 2012)Scale direction increases acquiescence in web mode but not face-to-face
Yan et al. (2018) (ANES 2008)Various political attitudesMulti-item, various formatsCAPI2,322US adults (ANES 2008)Scale direction effects stronger for non-attitudinal items and longer scales
Yan et al. (2018) (ANES 2012)Various political attitudesMulti-item, various formatsCAWI, CAPI5,914US adults (ANES 2012)Effects stronger for earlier items in battery; self-administered shows more effects than CAPI
Terentev & Maloshonok (2019)Course satisfaction and learning5-pt verticalCAWI~22,910MOOC learnersPrimacy effect in vertical item-by-item format (especially low-education); no effect in grid format
Smyth et al. (2019)Satisfaction4-pt fully labeled, horizontalCAWI, Mail—US adults, multiple surveysPositive-first ordering yields consistently higher satisfaction ratings
Garbarski et al. (2019)Self-rated health5-pt fully labeled (excellent–poor)CAWI2,945US adults (MTurk)Primacy effect robust across vertical, horizontal, and banked scale orientations
Krebs & Höhne (2021)VariousEndpoint-labeled, verticalCAWI3,401German non-probability access panelMinimal scale direction effects; device type (PC vs. smartphone) does not moderate effects
Stefkovics (2022)Political attitudes, life satisfaction5-pt agree–disagree, 11-pt numeric, 6-pt semantic differentialCAPI, CATI, CAWI—Hungarian adultsFew effects in interviewer-administered modes; scale direction effects emerge for numeric scale in online mode
Wöhner & Franzen (2024)Life satisfaction11-pt numeric (0–10)CAWI3,138Swiss adultsDescending scale yields ~0.7 pts lower satisfaction; ascending scale shows higher construct validity
Robie et al. (2022)Personality (HEXACO)5-pt fully labeledPAPI1,198Canadian studentsNo meaningful response order effects for incremental or decremental orderings

For theoretical accounts of the mechanisms underlying these effects, see Krosnick (1991) (satisficing) and Schwarz et al. (1992) (cognitive elaboration model). Knauper (1999) is a meta-analysis of 14 Schuman & Presser telephone experiments showing that respondents aged 65+ are approximately twice as susceptible to response order effects as younger respondents, independent of education.

Summary

In self-administered surveys—whether CAWI or PAPI—a primacy effect is reliably observed: the first response option in a sequence attracts disproportionate endorsement. For agree–disagree scales, placing “Strongly agree” first inflates agreement relative to placing “Strongly disagree” first. In telephone (CATI) surveys, recency effects are more common. The effect is amplified for speeders and less motivated respondents (Keusch, 2018; Malhotra, 2008), older respondents (65+) (Knauper, 1999), non-attitudinal items, and longer scales (Yan et al., 2018). Switching to item-specific response options substantially reduces susceptibility to scale direction effects (J. K. Höhne & Krebs, 2018) and also improves reliability and validity (Dykema et al., 2022; Saris et al., 2010). When agree–disagree scales are unavoidable, a negative-to-positive ordering (Disagree→Agree) is recommended for self-administered surveys to reduce the risk of inflated agreement (Wöhner & Franzen, 2024; Yonnie Chyung et al., 2018).

References

Christian, L. M., Parsons, N. L., & Dillman, D. A. (2009). Designing Scalar Questions for Web Surveys. Sociological Methods & Research, 37(3), 393–425. https://doi.org/10.1177/0049124108330004

Dykema, J., Schaeffer, N. C., Garbarski, D., Assad, N., & Blixt, S. (2022). Towards a reconsideration of the use of agree-disagree questions in measuring subjective evaluations. Research in Social and Administrative Pharmacy, 18(2), 2335–2344. https://doi.org/10.1016/j.sapharm.2021.06.014

Friedman, H. H., Herskovitz, P. J., & Pollack, S. (1994). The biasing effects of scale-checking styles on response to a Likert scale. Proceedings of the American Statistical Association Annual Conference: Survey Research Methods, 792–795.

Garbarski, D., Schaeffer, N. C., & Dykema, J. (2015). The effects of response option order and question order on self-rated health. Quality of Life Research, 24(6), 1443–1453. https://doi.org/10.1007/s11136-014-0861-y

Garbarski, D., Schaeffer, N. C., & Dykema, J. (2016). The effect of response option order on self-rated health: A replication study. Quality of Life Research, 25(8), 2117–2121. https://doi.org/10.1007/s11136-016-1249-y

Garbarski, D., Schaeffer, N. C., & Dykema, J. (2019). The Effects of Features of Survey Measurement on Self-Rated Health: Response Option Order and Scale Orientation. Applied Research in Quality of Life, 14(2), 545–560. https://doi.org/10.1007/s11482-018-9628-x

Höhne, J. K., & Krebs, D. (2018). Scale direction effects in agree/disagree and item-specific questions: A comparison of question formats. International Journal of Social Research Methodology, 21(1), 91–103. https://doi.org/10.1080/13645579.2017.1325566

Höhne, J., & Lenzner, T. (2015). Investigating response order effects in web surveys using eye tracking. Psihologija, 48(4), 361–377. https://doi.org/10.2298/PSI1504361H

Keusch, F. (2018). Is satisficing responsible for response order effects in rating scale question? Survey Research Methods, Vol 12, 259–270 Pages. https://doi.org/10.18148/SRM/2018.V12I3.7263

Knauper, B. (1999). The Impact of Age and Education on Response Order Effects in Attitude Measurement. Public Opinion Quarterly, 63(3), 347. https://doi.org/10.1086/297724

Krebs, D., & Bachner, Y. G. (2018). Effects of Rating Scale Direction under the Condition of Different Reading Direction. Methods, data, 21 Pages. https://doi.org/10.12758/MDA.2017.08

Krebs, D., & Hoffmeyer-Zlotnik, J. H. P. (2010). Positive First or Negative First?: Effects of the Order of Answering Categories on Response Behavior. Methodology, 6(3), 118–127. https://doi.org/10.1027/1614-2241/a000013

Krebs, D., & Höhne, J. K. (2021). Exploring Scale Direction Effects and Response Behavior across PC and Smartphone Surveys. Journal of Survey Statistics and Methodology, 9(3), 477–495. https://doi.org/10.1093/jssam/smz058

Krosnick, J. A. (1991). Response strategies for coping with the cognitive demands of attitude measures in surveys. Applied Cognitive Psychology, 5(3), 213–236. https://doi.org/10.1002/acp.2350050305

Liu, M., & Keusch, F. (2017). Effects of scale direction on response style of ordinal rating scales. Journal of Official Statistics, 33(1), 137–154. https://doi.org/10.1515/jos-2017-0008

Malhotra, N. (2008). Completion Time and Response Order Effects in Web Surveys. Public Opinion Quarterly, 72(5), 914–934. https://doi.org/10.1093/poq/nfn050

Rammstedt, B., & Krebs, D. (2007). Does Response Scale Format Affect the Answering of Personality Scales? Assessing the Big Five Dimensions of Personality with Different Response Scales in a Dependent Sample. European Journal of Psychological Assessment, 23(1), 32–38. https://doi.org/10.1027/1015-5759.23.1.32

Robie, C., Meade, A. W., Risavy, S. D., & Rasheed, S. (2022). Effects of Response Option Order on Likert-Type Psychometric Properties and Reactions. Educational and Psychological Measurement, 82(6), 1107–1129. https://doi.org/10.1177/00131644211069406

Saris, W., Revilla, M., Krosnick, J. A., & Shaeffer, E. M. (2010). Comparing Questions with Agree/Disagree Response Options to Questions with Item-Specific Response Options. Survey Research Methods, Vol 4, 61–79 Pages. https://doi.org/10.18148/SRM/2010.V4I1.2682

Schwarz, N., Hippler, H.-J., & Noelle-Neumann, E. (1992). A Cognitive Model of Response-Order Effects in Survey Measurement. In N. Schwarz & S. Sudman (Eds.), Context Effects in Social and Psychological Research (pp. 187–201). Springer New York. https://doi.org/10.1007/978-1-4612-2848-6_13

Smyth, J. D., Israel, G. D., Newberry, M. G., & Hull, R. G. (2019). Effects of Stem and Response Order on Response Patterns in Satisfaction Ratings. Field Methods, 31(3), 260–276. https://doi.org/10.1177/1525822X19860648

Stefkovics, Á. (2022). Are Scale Direction Effects the Same in Different Survey Modes? Comparison of a Face-to-Face, a Telephone, and an Online Survey Experiment. Field Methods, 34(3), 206–222. https://doi.org/10.1177/1525822X221105940

Terentev, E., & Maloshonok, N. (2019). The impact of response options ordering on respondents’ answers to rating questions: Results of two experiments. International Journal of Social Research Methodology, 22(2), 179–198. https://doi.org/10.1080/13645579.2018.1510660

Weng, L.-J., & Cheng, C.-P. (2000). Effects of Response Order on Likert-Type Scales. Educational and Psychological Measurement, 60(6), 908–924. https://doi.org/10.1177/00131640021970989

Wöhner, F., & Franzen, A. (2024). The Impact of Answer Scale Orientation on the Measurement of Life Satisfaction. Journal of Happiness Studies, 25(6), 78. https://doi.org/10.1007/s10902-024-00798-9

Yan, T., & Keusch, F. (2015). The effects of the direction of rating scales on survey responses in a telephone survey. Public Opinion Quarterly, 79(1), 145–165. https://doi.org/10.1093/poq/nfu062

Yan, T., Keusch, F., & He, L. (2018). The Impact of Question and Scale Characteristics on Scale Direction Effects. Survey Practice, 11(2), 1–10. https://doi.org/10.29115/SP-2018-0008

Yonnie Chyung, S. Y., Kennedy, M., & Campbell, I. (2018). Evidence-Based Survey Design: The Use of Ascending or Descending Order of Likert-Type Response Options. Performance Improvement, 57(9), 9–16. https://doi.org/10.1002/pfi.21800