DOI QR코드

DOI QR Code

Measuring economic sentiment using ordinary response options

  • Park, Inho (Department of Statistics, Pukyong National University) ;
  • Kim, Tae Yoon (Department of Statistics, Keimyung University)
  • Received : 2017.01.14
  • Accepted : 2017.02.17
  • Published : 2017.03.31

Abstract

Economic sentiment is typically measured using ordinary response options. The University of Michigan and the United States Conference Board are two widely used major indexes that have separately established independent consumer sentiment indexes based on three-level ordinary response options: positive, neutral, and negative. Notwithstanding, limited attention has been paid to the structural differences in their built-in formulas, which are referred to the disparate micro scoring schemes applied to an individual question. This paper examines the structural difference of the two indexes and then addresses situations where one is more reliable than the other. Real data from business tendency surveys of the Organization for Economic Cooperation and Development are used to illustrate our points empirically. As a conclusion, it is stressed that the two indexes should be handled with care when applied to economic sentiment comparison studies.

Keywords

References

  1. Bram J and Ludvigson S (1998). Does consumer confidence forecast household expenditure?: a sentiment index horse race, FRBNY Economic Policy Review, 4, 59-78.
  2. Curtin RT (2002). Survey of consumers: theory, methods, and interpretation. In Proceedings of the NABE 44th Annual Meeting,Washington, DC.
  3. Linden F (1982). The consumer as forecaster, Public Opinion Quarterly, 46, 353-360. https://doi.org/10.1086/268732
  4. Ludvigson SC (2004). Consumer confidence and consumer spending, The Journal of Economic Perspectives, 18, 29-50. https://doi.org/10.1257/0895330041371222
  5. Organization for Economic Cooperation and Development (2003). Business Tendency Surveys: A Handbook, Organization for Economic Cooperation and Development, Paris.
  6. Park M (2015). Nonresponse adjusted raking ratio estimation, Communications for Statistical Applications and Methods, 22, 655-664. https://doi.org/10.5351/CSAM.2015.22.6.655
  7. Sarndal CE, Swensson B, and Wretman J (1992). Model Assisted Survey Sampling, Springer-Verlag, New York.
  8. Seiler C (2013). Nonresponse in Business Tendency Surveys: Theoretical Disclosure and Empirical Evidence (Doctoral dissertation), Ludwig-Maximilians-Universitat Munchen, Munchen.
  9. Stangl A (2006). Are symmetrical scales symmetrical?: applications of the visual analog scale in business tendency surveys. In Proceedings of the 28th CIRET Conference, Rome.