Are Microstates Necessarily Led by Their Bigger Neighbors’ Business Cycle? The Case of Liechtenstein and Switzerland

Abstract

This paper investigates Liechtenstein’s business cycle compared to its neighboring countries (Switzerland, Austria) and other countries with strong economic relations with Liechtenstein (Germany, Italy, France, USA). In contrast to the widespread notion of small countries “importing” the business cycle from bigger nations, it is shown that the real GDP of the microstate Liechtenstein is a leading indicator for the economy of its bigger neighbor Switzerland, regarding the growth rates as well as the output gap. This finding is based on cross correlation analyses and single- and multi-equation Granger causality tests, applying annual data from 1972 until 2014 or 2015. The significant GDP lead of one year is robust across all the various time frames and model specifications and seems to be driven by the goods exports. Also, Liechtenstein seems to react earlier to US business cycle fluctuations. This finding is not only interesting in the context of Liechtenstein and Switzerland but also encourages further research as it indicates the possibility that very small states are not only more exposed to foreign shocks, react more sensitively to international economic fluctuations, and are more volatile than their big “patron” nations—all stylized facts from small state economics literature—, but that their business cycles could be affected earlier.

This is a preview of subscription content, log in to check access.

Fig. 1
Fig. 2
Fig. 3
Fig. 4

Notes

  1. 1.

    Natella and O’Sullivan (2015, pp. 8–9) have carried out a short explorative analysis and claim that smaller countries tend to lead larger ones.

  2. 2.

    Switzerland and Liechtenstein share a monetary union (with the Swiss Franc as common currency) along with a mutual economic area and a customs treaty. They also feature other strong political and institutional relations.

  3. 3.

    So far, there exists no study on the business cycle timing of Liechtenstein apart from Brunhart (2013), chapter 5 of which was the starting point to this translated, methodically extended, and data updated version.

  4. 4.

    For an extensive summary see Graff (2011, pp. 5–8) and Layton et al. (2015, pp. 24–25).

  5. 5.

    German indicators are frequently applied for the prediction of Austria’s business cycle. The OECD Composite Leading Indicator of Austria for instance contains the IFO Business Climate Index of Germany as an individual leading indicator.

  6. 6.

    Scheiblecker (2007) examines the lead and lag of various German and European time series to the Austrian gross value added. Bofinger et al. (2009) explore the international business cycle connection of Germany and the related shock transmissions. Dueker and Wesche (2003) analyze the synchronization and leading pattern of Germany, the UK, the US, Italy, and France. Crowley and Mayes (2008) discover a high commonality of the business cycle phases of France, Germany, and Italy applying wavelet analysis. Altissimo et al. (2000) identify a lagging pattern of Italy’s business cycle (measured as a composite indicator consisting of almost 200 indicator variables) compared to the US, the UK, Germany, and France, while Pelagatti and Negri (2010) find a lead of four to six months of Milan’s industrial production to Italy’s as a whole.

  7. 7.

    The reason for this is that GDP data on Liechtenstein exists only from 1972 until 2014 so far (with a publication lag of more than one year) and only in annual frequency. See Table 8 and “Additional Remarks” in section of Appendix 2 for further information on the used data series. All the used time series are downloadable from http://andreas.brunhart.com/data.

  8. 8.

    The real GDP series and output gap series of all the seven countries have been tested whether they are stationary or not using the augmented unit root test of Dickey and Fuller (1979), the unit root test of Phillips and Perron (1988), and the stationary test of Kwiatkowski et al. (1992). It has been concluded that the real GDP series follow a stochastic trend and are therefore all integrated of order one (the null hypothesis of a random walk with drift cannot be rejected). In order to circumvent the risk of spurious regression the series have been transformed into annual differences of the natural logarithms. The output gap series are integrated of order zero (stationary).

  9. 9.

    Electronic supplementary Tables 9 to 15 and Figures 6 to 11 are shown in the web appendix which can be downloaded as PDF-file from http://andreas.brunhart.com/data.

  10. 10.

    The cross correlation coefficient of Liechtenstein's lead to Switzerland is even higher than the Swiss autocorrelation itself.

  11. 11.

    The AICC was proposed by Hurvich and Tsai (1989) and is given by the following formula: \( - 2l + 2k + 2k\left( {k + 1} \right)/\left( {T - k - 1} \right) \). The number of observations is \( T \), the number of parameters is \( k \), and \( l \) depicts the log likelihood of the estimated model. The first two summands represent the original information criteria by Akaike (1974). An additional penalty term for additional parameters \( k \) is included, which is beneficial in applications dealing with small samples as is the case here. An AICC with lower value is preferred.

  12. 12.

    Higher lag orders than one in the Granger tests here are not preferable (according to AICC). Still, the significance of \( \beta_{1} \) is confirmed in most settings with higher orders, yet with insignificant coefficients \( \beta_{p} \) (for \( p > 1 \)).

  13. 13.

    Even though Germany and Liechtenstein do not share a common border, the distance in only 50 km. Additionally, Germany is Liechtenstein‘s second most important trade partner (export and import of goods), after Switzerland.

  14. 14.

    Austria’s lead to Germany is not stable across all the various model settings. Also, it is highly sensitive to the choice of time sub-samples. If, for instance, rolling regressions with 25-year windows are applied (1991–2015 to 1974–1998), then the lead is only significant from 1977–2001 to 1974–1998.

  15. 15.

    Additionally to Liechtenstein’s lead to Switzerland, another (yet implausible) significant positive lead appears: France to Austria (see Electronic supplementary Table 12). A priori, there is no theoretical explanation for France’s business cycle lead to Austria. The countries are not neighboring and it is not easy to think of a special economic link between the two or other ties implying the lead. Maybe, the explanation could lie in the combination to the surprising claim of Aguiar-Conraria and Soares (2011) that France is somewhat leading Germany (and the Euro zone) and the tight business cycle link between Germany and Austria. The regressions in Electronic supplementary Table 13 show the strong contemporaneous correlation between the US and the French business cycle, while Austria is lagging behind the US real GDP growth. Hence, France might react earlier to international influences (similar reasoning for Liechtenstein and Switzerland in Sect. 4). However, compared with the Liechtenstein/Switzerland case, France’s business cycle (real GDP growth rates and HP cycle) features no clear visual anticipation (lead) of the Austrian business cycle turning points. Also, the significance is sensitive to the choice of the time sub-sample (rolling regression time windows, 25 years): The coefficient is not stable over time and the p value is considerably higher than 0.1 for the most recent time windows (see Electronic supplementary Figure 11). There is also a weakly significant positive lead of France versus Italy.

  16. 16.

    Already the goods exports without services usually account for more than 70% of GDP (author’s approximations based on official export figures and the foreign sales structure as a proxy for exports to Switzerland, which are not included in the official export figures). The exports are almost twice as high as the imports.

  17. 17.

    The Swiss Federal Customs Administration publishes trade of goods figures for each Swiss canton and Liechtenstein. They do not include the trade between cantons and between Switzerland and Liechtenstein.

  18. 18.

    Liechtenstein‘s goods imports show no lead to Switzerland. Also, Liechtenstein’s national income time series from 1954 to 2013 shows no clear significant lead to Switzerland (neither in the full time sample, nor in the comparable time sample 1972–2013). Thus, Liechtenstein’s economic lead seems to be driven by the domestic production (determined by international demand) rather than income generated from Liechtenstein’s investments abroad.

  19. 19.

    It rather seems that the Swiss financial sector leads Liechtenstein’s. Note that these tentative results provide only little additional support, as only 17 annual observations exist for Liechtenstein’s sectoral gross value added (1998–2014). Also, the sectoral classification of the financial services sector in the national accounts of both countries is not fully comparable (while the classification of the industrial sector is comparable).

  20. 20.

    KOFL Liechtenstein Economic Institute provided rough flash estimates of Liechtenstein’s GDP along with their GDP prediction, but was closed down in 2014. The GDP flash estimate by Liechtenstein’s national Office of Statistics still has a publication lag of 14 months and is therefore not applicable to forecasting purposes.

  21. 21.

    A quarterly (coincident) composite business cycle indicator, consisting of twenty individual sub-annual coincident indicators with a low publication lag, has been elaborated for Liechtenstein’s economy, but not published yet. Future work could also deal with the question if this quarterly index also shows leading properties to Switzerland (similar to Siliverstovs (2011), who uses the KOF Economic Barometer for predicting Swiss quarterly GDP).

  22. 22.

    Future research could also examine whether individual regions, cantons or cities in Switzerland have leading tendencies to the entire national economy, as Pelagatti and Negri (2010) have done for the industrial production of Italy and Milan, whereas the latter is used as leading predictor.

  23. 23.

    Those companies willing to provide data granted access to balance sheets and profit and loss statements for the years 1972 until 2008. The employment figures of each company were used to weigh their EBITDA and to multiply them to the gross operating surplus proxy of the whole sector. The hereby captured shares of employment by the included companies as percentage of the whole sector are around 35% in the industry sector and around 38% in the financial services sector in 2008 (Liechtenstein economy’s total employment was about 33’300 people in 2008). See Brunhart (2012, pp. 43–60) for more details on the GDP backward calculation methodology.

  24. 24.

    See Brunhart (2012, pp. 60–66) for more details on the GDP backward calculation’s evaluation.

  25. 25.

    The tests here are an updated version (three additional annual observations) of the cointegration tests thoroughly explained in Brunhart (2013, pp. 44–46 and pp. 70–81). If, nonetheless, a vector error correction model is estimated, Liechtenstein’s lead is still significant (in the error correction part).

  26. 26.

    In ARDL models, individual lagged variables may be excluded from the equation. They are—to some extent—nested versions of VAR models, while in VAR models each country‘s real GDP growth is regressed on all other countries’ lags. As the emphasis is on lead properties, the contemporaneous regressors (for example \( \Delta { \log }\left[ {GDPL_{t} } \right] \)) are excluded from the ARDL models.

  27. 27.

    Note the high degree of autocorrelation in output gap series and that caution is advisable when it comes to interpreting p-values in regression models with output gaps obtained by a HP filter (see Meyer and Winker 2005).

References

  1. Aguiar-Conraria, L., & Soares, M. J. (2011). Business cycle synchronization and the Euro: A wavelet analysis. Journal of Macroeconomics, 33(3), 477–489.

    Article  Google Scholar 

  2. Akaike, H. (1974). A new look at the statistical model identification. IEEE Transactions on Automatic Control, 19(6), 716–723.

    Article  Google Scholar 

  3. Altissimo, F., Marchetti, D. J. & Oneto, G. P. (2000). The Italian business cycle: coincident and leading indicators and some stylized facts. Temi di Discussione, 377, Banca d’Italia.

  4. Amt für Statistik (2016a). Statistisches Jahrbuch Liechtensteins 2016. Vaduz.

  5. Amt für Statistik (2016b). Volkswirtschaftliche GesamtrechnungSchätzrechnung Bruttoinlandsprodukt 2014. Vaduz.

  6. Berge, T. J. (2012). Has globalization increased the synchronicity of international business cycles? Economic Review, Third Quarter 2012, Federal Reserve Bank of Kansas City, pp. 5–39.

  7. Bofinger, P., Franz, W., Schmidt, C. M., Weder di Mauro, B. & Wiegard, W. (2009). Deutschland im internationalen KonjunkturzusammenhangExpertise im Auftrag der Bundesregierung. Sachverständigenrat zur Begutachtung der gesamtwirtschaftlichen Entwicklung.

  8. Brunhart, A. (2012). Identification of Liechtenstein‘s historic economic growth and business cycles by econometric extensions of economic data series, KOFL Working Papers, 14, Konjunkturforschungsstelle Liechtenstein.

  9. Brunhart, A. (2013). Der Klein(st)staat Liechtenstein und seine grossen Nachbarländer: Eine wachstums- und konjunkturanalytische Gegenüberstellung. Arbeitspapiere Liechtenstein-Institut, 44.

  10. Cheung, Y.-W., & Westermann, F. (1999). An analysis of German effects on the Austrian business cycle. Weltwirtschaftliches Archiv, 135(3), 522–531.

    Article  Google Scholar 

  11. Crowley, P. M., & Mayes, D. G. (2008). How fused is the Euro area core? An evaluation of growth cycle co-movement and synchronization using wavelet analysis. Journal of Business Cycle Measurement and Analysis, 4(1), 63–95.

    Google Scholar 

  12. Dickey, D., & Fuller, W. A. (1979). Distribution of the estimators for autoregressive time series with a unit root. Journal of the American Statistical Association, 74(366), 427–431.

    Article  Google Scholar 

  13. Dueker, M., & Wesche, K. (2003). European business cycles: New indices and analysis of their synchronicity. Economic Inquiry, 41(1), 116–131.

    Article  Google Scholar 

  14. Easterly, W., & Kraay, A. (2000). Small States, small problems? Income, growth, and volatility in small states. World Development, 28(11), 2013–2027.

    Article  Google Scholar 

  15. Engle, R. F., & Granger, C. W. J. (1987). Co-integration and error-correction: Representation, estimation and testing. Econometrica, 55(2), 251–276.

    Article  Google Scholar 

  16. Fenz, G., & Schneider, M. (2006). Is Germany’s influence on Austria waning? Synchronization and transmission of cyclical shocks. Monetary Policy & the Economy, Q2(06), 24–45.

    Google Scholar 

  17. Gogas, P. (2013). Business cycle synchronisation in the European Union: The effect of the common currency. Journal of Business Cycle Measurement and Analysis, 2013(1), 1–14.

    Article  Google Scholar 

  18. Graff, M. (2005). Internationale Konjunkturverbunde. KOF Working Paper, 108, KOF Swiss Economic Institute.

  19. Graff, M. (2006). Internationale Konjunkturverbunde. Jahrbücher für Nationalökonomie und Statistik, 226(4), 385–417.

    Article  Google Scholar 

  20. Graff, M. (2011). International business cycles: How do they relate to Switzerland? KOF Working Paper, 291, KOF Swiss Economic Institute.

  21. Granger, C. W. J. (1969). Investigating causal relations by econometric models and cross-spectral methods. Econometrica, 37(3), 424–438.

    Article  Google Scholar 

  22. Hodrick, R. J., & Prescott, E. C. (1997). Postwar business cycles: An empirical investigation. Journal of Money, Credit, and Banking, 29(1), 1–16.

    Article  Google Scholar 

  23. Hurvich, C. M., & Tsai, C. L. (1989). Regression and time series model selection in small samples. Biometrika, 76, 297–307.

    Article  Google Scholar 

  24. Indergand, R., Leist, S., & Mahlstein, K. (2013). Wie konjunkturell abhängig ist die Schweiz vom Ausland? Die Volkswirtschaft, 2013(1/2), 4–9.

    Google Scholar 

  25. Johansen, S. (1988). Statistical analysis of cointegration vectors. Journal of Economic Dynamics and Control, 12(2–3), 231–254.

    Article  Google Scholar 

  26. Johansen, S. (1992). Determination of cointegration rank in the presence of a linear trend. Oxford Bulletin of Economics and Statistics, 54, 383–397.

    Article  Google Scholar 

  27. Kwiatkowski, D., Phillips, P. C. B., Schmidt, P., & Shin, Y. (1992). Testing the null hypothesis of stationarity against the alternative of a unit root: How sure are we that economic time series have a unit root? Journal of Econometrics, 54, 159–178.

    Article  Google Scholar 

  28. Layton, A. P., Banerji, A., & Achuthan, L. (2015). The world and ‘the world business cycle chronology’. OECD Journal of Business Cycle Measurement and Analysis, 2015(1), 23–40.

    Article  Google Scholar 

  29. Meyer, M., & Winker, P. (2005). Using HP filtered data for econometric analysis: some evidence from monte carlo simulations. Allgemeines Statistisches Archiv, 89, 303–320.

    Article  Google Scholar 

  30. Müller, M. & Woitek, U. (2012). Wohlstand, Wachstum und Konjunktur. In P. M. Halbeisen, M. Müller & B. Veyrassat (eds.), Wirtschaftsgeschichte der Schweiz im 20. Jahrhundert (pp. 91–222). Basel: Schwabe.

  31. Natella, S., & O’Sullivan, M. (2015). The success of small countries and markets. Zürich: Credit Suisse AG.

    Google Scholar 

  32. Newey, W., & West, K. (1987). A Simple positive semi-definite, heteroskedasticity and autocorrelation consistent covariance matrix. Econometrica, 55, 703–708.

    Article  Google Scholar 

  33. Oehry, W. (2000). Der Aufbau einer Volkswirtschaftlichen Gesamtrechnung im Kleinstaat Liechtenstein. Schaan: GMG Juris Verlags-AG.

    Google Scholar 

  34. Okun, A. M. (1962). Potential GNP: Its measurement and its significance. In Proceedings of the business and economic statistics section, American Statistical Association, pp. 98–103.

  35. Pelagatti, M. M., & Negri, V. (2010). The industrial cycle of milan as an accurate leading indicator for the Italian business cycle. Journal of Business Cycle Measurement and Analysis, 2010(2), 19–35.

    Google Scholar 

  36. Pesaran, M. H., & Shin, Y. (1998). Generalized impulse response analysis in linear multivariate models. Economics Letters, 58(1), 17–29.

    Article  Google Scholar 

  37. Phillips, P. C. B., & Ouliaris, S. (1990). Asymptotic properties of residual based tests for cointegration. Econometrica, 58(1), 165–193.

    Article  Google Scholar 

  38. Phillips, P. C. B., & Perron, P. (1988). Testing for a unit root in time series regression. Biometrika, 75(2), 335–346.

    Article  Google Scholar 

  39. Prettner, K., & Kunst, R. M. (2012). The dynamic interrelations between unequal neighbors: An Austro-German case study. Empirical Economics, 43, 741–761.

    Article  Google Scholar 

  40. Scheiblecker, M. (2007). Datierung von Konjunkturwendepunkten in Österreich. WIFO Monatsberichte, 2007(9), 715–730.

    Google Scholar 

  41. Schlag, C.-H. (2012). Konjunktur- und Wachstumsanalyse für das Fürstentum Liechtenstein. Frankenraum im Gegenwind. KOFL Konjunkturbericht, 2012, Konjunkturforschungsstelle Liechtenstein.

  42. Siliverstovs, B. (2011). The real-time predictive content of the KOF economic barometer. Swiss Journal of Economics and Statistics, 147(3), 353–375.

    Google Scholar 

  43. Thorhallsson, B. (2010). The Icelandic crash and its consequences: A small state without economic and political shelter. In R. Steinmetz & A. Wivel (Eds.), Small states in Europe, challenges and opportunities (pp. 199–214). Abingdon: Routledge.

    Google Scholar 

  44. Tondl, G. & Traistaru-Siedschlag, I. (2006). Regional growth cycle convergence in the European Union. EI Working Papers, 71, Europainstitut, University of Economics and Business Administration, Vienna.

  45. White, H. (1980). A heteroskedastic-consistent covariance matrix and a direct test of heteroskedasticity. Econometrica, 48, 817–838.

    Article  Google Scholar 

Download references

Acknowledgements

The author would like to thank Berno Büchel (University of Fribourg), Martin Kocher (Institute for Advanced Studies Vienna), Wilfried Marxer (Liechtenstein Institute), and two anonymous referees for useful comments.

Author information

Affiliations

Authors

Corresponding author

Correspondence to Andreas Brunhart.

Electronic supplementary material

Below is the link to the electronic supplementary material.

Supplementary material 1 (PDF 1382 kb)

Appendices

Appendix 1: Graphs and Tables

See Tables 6, 7 and 8 and Fig. 5.

Table 6 VAR(1) models with various country samples and deterministic regressors (emphasis on Switzerland as dependent variable, real GDP in dlogs)
Table 7 VAR(1) models with output gap
Table 8 Data sources
Fig. 5
figure5

The rolling regression model is an ARDL model of the following form, using 25-year windows from 2015 back to 1974 (the time dummies are skipped, as they do not fall into all of the time windows): \(\Delta\log {[GDP{S_t}]} = \mu + \alpha \cdot\Delta\log {[GDP{S_{t-1}}]} + \beta \cdot \Delta\log {[GDP{S_{t-1}}]} + \gamma \cdot \Delta\log {[GDP{S_{t-1}}]} + \delta \cdot \Delta\log {[GDP{S_{t-1}}]}+{{\epsilon}_t}\). GDPS t : Real GDP of Switzerland; GDPL t : Real GDP of Liechtenstein; GDPA t : Real GDP of Austria; GDPG t : Real GDP of Germany. The rising p-values of Liechtenstein’s lagged variable (lead to Switzerland, 1975–1999 and 1974–1998) are explainable by the oil crisis’ impact. If the 1975 dummy is included, then the p-values are 0.0197 (1975–1999) and 0.0170 (1974–1998)

Liechtenstein’s one year lead, rolling regression (Coefficient and p value of \( \Delta { \log }\left[ {\varvec{GDPL}_{{\varvec{t} - 1}} } \right]) \).

Electronic supplementary Tables 9–15 and Figures 6–11 are shown in the web appendix that can be downloaded as PDF-file from http://andreas.brunhart.com/data.

Appendix 2: Additional Remarks

Liechtenstein’s GDP figures are internationally comparable as the national accounts follow the rules of the European System of Accounts (ESA). Yet, ESA 95 is still applied and the switch to ESA 2010 in December 2016 only affects GDP figures from 2013 on (no further backward estimates published). Thus, for all countries ESA 95 figures are used in this paper. The other countries’ GDP data was retrieved from the UN National Accounts Main Aggregate Data Base whose GDP figures rely on the OECD data base, which in turns compiles data from the national statistical offices. Note that some of the earlier GDP data originate from earlier ESA versions. For instance, Switzerland did not publish ESA 95 figures for the years before 1990. Instead, GDP growth from older ESA versions were used to account for the level shift effect caused by the introduction of ESA 95 and to provide a more consistent official GDP time series.

Liechtenstein’s nominal GDP figures from 1972 to 1997 are backward estimations published in the official Statistical Yearbook of Liechtenstein (see Amt für Statistik 2016a, p. 168). The figures originate from Brunhart (2012), where the methodology of the backward estimation procedure and its evaluation are outlined. The gross domestic product was compiled by using the generation of income account identity of Liechtenstein’s national accounting scheme: GDP = compensation of employees + taxes on production and imports + gross operating surplus − subsidies. The components could be well approximated by applying official figures, with the exception of the gross operating surplus which had to be estimated using a proxy. By compiling EBITDA figures of most of the biggest industrial and financial corporations in Liechtenstein a proxy for the retropolation of the gross operating surplus (operating profits) could be compiled.Footnote 23

The analytical results of Sects. 3 and 4 are independent of the fact that some of Liechtenstein’s GDP figures are backward estimates. The main arguments for the adequacy of the backwardly estimated GDP figures shall be summarized in the following: As mentioned, the applied backward estimation method is based on the structure of the official national account of Liechtenstein (generation of income account side). The cyclical pattern (timing and magnitude), the turning points and the growth trend are well confirmed by the historical national income series and other important economic time series of Liechtenstein. The comparison of the backward estimation method with the official figures for the years from 1998 until 2008 has revealed a convincingly good fit, with very high correlation coefficients (level 0.9974, growth rates 0.9608).Footnote 24 The methodology was also inspected by the national account department of the national Office of Statistics and the obtained GDP observations were integrated into the national Statistical Yearbook. Moreover and in relation to the lead of Liechtenstein to Switzerland, if Figs. 2 and 3 are inspected it becomes evident that also in the phase from 1998 on (after the official national accounts were introduced) several turning points were anticipated one year before Switzerland. A simple Granger test with the sample from 1998 till 2015 (therefore containing only official GDP data) also indicates a causal 1-year lead of Liechtenstein to Switzerland: The relevant coefficient has a positive sign and a p value of 0.0348 for real GDP growth rates or 0.0369 for the real GDP output gap (0.0220 and 0.0281 without degree of freedom adjustment). Hence, the lead is not just an artefact of the backward estimation method, which is additionally supported by the finding that also Liechtenstein’s quarterly goods exports and the industrial gross value added time series are Granger causally leading the Swiss counterpart.

Appendix 3: Model Variation and Robustness Checks

The regression models with variables in growth rates might involve the shortcoming that they neglect potential long-term relationships between the variables in levels (for example a connected long-run growth path). If such relationships exist then another way to cope with non-stationary data should be taken, namely the estimation of error correction models to capture both the short-run dynamics between the differences of the data and the long-term equilibria (cointegration) between the variables in levels. Cointegration tests of Johansen (1988 and 1992) including Switzerland, Liechtenstein, Austria and Germany have been carried out to check whether such equilibria exist. Additionally, single-equation tests following Engle and Granger (1987) and Phillips and Ouliaris (1990) including Switzerland and Liechtenstein have been conducted, additionally allowing for trend breaks in the cointegration relation. Yet, the generated test results do not indicate any cointegrating relationships. Thus, no error correction models are introduced.Footnote 25

As an alternative to the multi-equation setting, also single-equation Autoregressive Distributed Lag (ARDL) models are applied with special focus on Swiss GDP growth as dependent variable.Footnote 26 Doing so, the model fit compared to ordinary VAR settings can be improved, according to AICC of the equation with Swiss real GDP growth as dependent variable. Also, one additional observation can be applied in the ARDL-setting (as GDP data for Liechtenstein is only available until 2014, for all the other countries until 2015). Liechtenstein’s significant one year lead to Swiss real GDP growth also appears in the ARDL models and is robust across all settings, as shown in Electronic supplementary Table 11.

It turns out that the main conclusions of the leading property of Liechtenstein to Switzerland are insensitive to the selection and combination of the time dummies and also to the choice of lag lengths (see Tables 3, 4, 6, Electronic supplementary Tables 11 and 12). This also applies to the choice of intercept with or without linear time trend. The solid conclusion that Liechtenstein’s economy exhibits a highly significant Granger causal lead is also very robust across all the various time samples, as shown by recursive coefficient estimates and rolling regression windows (see Fig. 5 and Electronic supplementary Figure 8, Table 15 and their footnotes, and also the related discussion at the end of Sect. 4). Moreover, if heteroskedasticity robust standard error estimates by White (1980) or Newey and West (1987) are applied, then no notable changes occur: The p value of Liechtenstein’s lead remains low. Also the abandonment of the degree of freedom adjustment yields no changes in the results worth mentioning.

If output gaps instead of real GDP growth rates are applied, the highly significant lead of Liechtenstein versus Switzerland remains, regarding cross correlations and also all the applied VAR country samples (see Tables 7 and Electronic supplementary Table 10).Footnote 27

Unfortunately, more sophisticated models are not appropriate because of the small sample size. Otherwise, enhanced systems such as structural VAR or Seemingly Unrelated Regression (SUR) with imposed restrictions based on theoretical considerations could have been taken into account. However, it is questionable if a priori restrictions are advisable at all in the context of the analysis of the two countries in focus: Structural equation system modeling would probably have led to the decision to restrict the lead of Liechtenstein versus Switzerland to zero by the reasoning that Liechtenstein imports its business cycle. This justifies the non-theoretical application beyond the mere fact of the methodological constraints of the small sample size.

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Brunhart, A. Are Microstates Necessarily Led by Their Bigger Neighbors’ Business Cycle? The Case of Liechtenstein and Switzerland. J Bus Cycle Res 13, 29–52 (2017). https://doi.org/10.1007/s41549-017-0013-x

Download citation

Keywords

  • Business cycles
  • Leading indicators
  • Microstates
  • Liechtenstein
  • Switzerland
  • VAR models
  • Granger causality

JEL Classification

  • C22
  • C32
  • E32
  • O52