© Emilia Tomczyk. Article available under the CC BY-SA 4.0 licence
This paper applies the Kullback-Leibler divergence (KLD) to quantify discrepancies between expectations and subsequent assessments in business tendency surveys for Polish manufacturing firms. Using monthly survey data from May 2004 to January 2026, it examines how closely firms’ expectations align with subsequent assessments across key economic variables and how this relationship evolves during the COVID-19 pandemic. The results indicate that, under normal conditions, expectations and assessments remain closely aligned, suggesting a high degree of consistency. However, during the pandemic, the KLD increased across all variables, with statistically significant rises observed for some of them, indicating a widening gap between expectations and assessments. The strongest effects are found for aggregate economic indicators, particularly the general economic situation and, to a lesser extent, firms’ financial standing. On the other hand, employment and inventories exhibit relatively greater stability. Overall, the results demonstrate that the KLD provides a useful distribution-based measure for identifying regime shifts in expectation formation and for assessing the information content of survey data under changing economic conditions.
Kullback–Leibler divergence (KLD), business tendency surveys (BTS), survey data, expectations, COVID-19
C10, D84, E32
Hołda, M. (2019). Newspaper-based economic uncertainty indices for Poland (NBP Working Paper No. 310). https://static.nbp.pl/publikacje/materialy-i-studia/310_en.pdf.
Ishizaki, R., & Inoue, M. (2024). Short-term Kullback–Leibler divergence analysis to extract unstable periods in financial time series. Evolutionary and Institutional Economics Review, 21, 227–236. https://doi.org/10.1007/s40844-024-00284-0.
Joyce, J. M. (2011). Kullback–Leibler divergence. In M. Lovrić (Ed.), International Encyclopedia of Statistical Science (pp. 720–722). https://doi.org/10.1007/978-3-642-04898-2_327.
Kalinowski, S., & Kokocińska, M. (2015). Business tendency survey data. Where do the respondents’ opinions come from?. Economics and Business Review, 1(4), 69–83. https://doi.org/10.18559/ebr.2015.4.5.
Kocięcki, A., Łyziak, T., & Stanisławska, E. (2022). Subjective Expectations and Uncertainty (NBP Working Papers No. 345). https://static.nbp.pl/publikacje/materialy-i-studia/345_en.pdf.
Kowalczyk, B., & Tomczyk, E. (2008). Rationality of Expectations of Industrial Enterprises – Analysis Based on Business Tendency Surveys with Item Non-respons. Bank i Kredyt, 39(8), 3–11.
Kullback, S., & Leibler, R. A. (1951). On information and sufficiency. The Annals of Mathematical Statistics, 22(1), 79–86. https://doi.org/10.1214/aoms/1177729694.
Lahiri, K., & Sheng, X. (2010). Measuring forecast uncertainty by disagreement: The missing link. Journal of Applied Econometrics, 25(4), 514–538. https://doi.org/10.1002/jae.1167.
Lahmiri, S., & Bekiros, S. (2020). The impact of COVID-19 pandemic upon stability and sequential irregularity of equity and cryptocurrency markets. Chaos, Solitons & Fractals, 138, 1–6. https://doi.org/10.1016/j.chaos.2020.109936.
Łyziak, T. (2016). Financial crisis, low inflation environment and short-term inflation expectations in Poland. Bank i Kredyt, 47(3), 285–300.
Meyer, B. H., Mihaylov, E., Barrero, J. M., Davis, S. J., Altig, D., & Bloom, N. (2022). Pandemic-Era uncertainty (NBER Working Paper No. 29958). https://doi.org/10.3386/w29958.
Mokinski, F., Sheng, X., & Yang, J. (2015). Measuring Disagreement in Qualitative Expectations. Journal of Forecasting, 34(5), 405–426. https://doi.org/10.1002/for.2340.
Morikawa, M. (2023). Firms’ subjective uncertainty and forecast errors: Survey evidence from Japan. Applied Economics Letters, 30(1), 33–36. https://doi.org/10.1080/13504851.2021.1971611.
Pawelec, A. (2021). Analiza struktury wydatków konsumpcyjnych polskich gospodarstw domowych według typu biologicznego. Metody Ilościowe w Badaniach Ekonomicznych, 22(3), 87–96. https://doi.org/10.22630/MIBE.2021.22.3.8.
Ratuszny, E., & Walczyk, K. (2022). Use of data from business tendency surveys in output gap estimation. In S. Białowąs (Ed.), Economic tendency surveys and economic policy – measuring output gaps and growth potentials (pp. 30–38). Poznań University of Economics and Business. https://doi.org/10.18559/978-83-8211-129-3/2.
Rich, R., & Tracy, J. (2021). A closer look at the behavior of uncertainty and disagreement: Micro evidence from the euro area. Journal of Money, Credit and Banking, 53(1), 233–253. https://doi.org/10.1111/jmcb.12728.
Tomczyk, E. (2011). Application of measures of entropy, information content and dissimilarity of structures to business tendency survey data. Przegląd Statystyczny. Statistical Review, 58(1–2), 88–101. https://doi.org/10.59139/ps.2011.01-02.6.
Tomczyk, E. (2023). Dynamics of survey responses before and during the pandemic: entropy and dissimilarity measures applied to business tendency survey data. Statistics in Transition new series, 24(2), 185–199. https://doi.org/10.59170/stattrans-2023-027.
Tomczyk, E., & Kowalczyk, B. (2023). Consensus in Business Tendency Surveys: Comparison of Alternative Measures. Gospodarka Narodowa. The Polish Journal of Economics, (4), 17–29. https://doi.org/10.33119/GN/174277.
Wędrowska, E. (2011). Application of Kullback–Leibler relative entropy for studies on the divergence of household expenditures structures. Olsztyn Economic Journal, 6(1), 133–142.
Ziembińska, P. (2021). Quality of Tests of Expectation Formation for Revised Data. Central European Journal of Economic Modelling and Econometrics, 13(4), 405–453. https://doi.org/10.24425/cejeme.2021.139836 .
.
