Tourist arrivals and overnight stays along the Croatian Adriatic Coast: Changes in persistence and seasonality from the COVID-19 disruption

Abstract

This study examines the changes in the persistence and seasonality inherent in the Croatian tourism sector in light of the onset of the COVID-19 pandemic. First, we differentiate between the changes in the persistence and seasonal behavior with respect to domestic and foreign tourist arrivals and overnight stays. Second, with nearly 90% of the Croatian tourism sector tied to the seven counties along the Adriatic coast we investigate the differential regional impact on persistence and seasonal behavior. Our results indicate the disruption was much more prominent for foreign tourist arrivals and overnight stays relative to domestic tourist arrivals and overnight stays with respect to the increased persistence associated with the onset of the pandemic along with the seasonal autoregressive component reduced considerably.

Keywords

COVID-19 pandemic tourist arrivals tourist overnight stays persistence fractional integration seasonality Croatia C22 L83 O41

Introduction

Croatia’s tourism sector serves a prominent role in the country’s overall economy in contributing nearly 40% to export revenues and 12% of overall GDP. More specifically, the Adriatic coast attracts 90% of tourist arrivals and overnight stays in Croatia. In light of the importance of the tourism sector to the Croatian economy, it is not surprising to find that the global COVID-19 pandemic adversely impacted both the tourism sector and the overall economy, as GDP fell 8.1% in 2020 (Payne et al., 2021, 2022). As noted by Payne et al. (2021), the question is whether the shock from the COVID-19 pandemic altered the persistence behavior inherent in key tourism indictors used by both policymakers and those in the tourism and hospitality industry to facilitate the modeling and forecasting necessary to inform tourism planning efforts.

Investigating the degree of persistence in relation to the transitory or permanent nature of shocks associated with tourism indicators is particularly relevant to understanding the appropriate policy response to restore tourism indicators to their original trend path. If a shock is considered transitory in nature then the shock will dissipate with the need for policy intervention less likely, whereas if a shock is deemed permanent than policy intervention may be required for restoration of the tourism indictor to its original trend path. Within this stream of the tourism literature, researchers have either used unit root/stationarity or fractional integration tests to infer the degree of persistence (i.e., integration) in tourism indicators.

Unit root/stationarity tests examine whether the differencing parameter, d, is either 0 (i.e., stationary) or 1 (i.e., first-difference stationary).¹ On the other hand, fractional integration models provide greater flexibility than standard unit root/stationarity tests by allowing the differencing parameter, d, to vary along a continuous range between 0 and 1, or even greater than 1 in magnitude.² There are several ranges of d (i.e., degrees of persistence) for a time series within a fractional integration framework: (1) stationary and mean-reverting (0 ≤ d < 0.5), whereby shocks will dissipate quickly as the time series returns to its original trend; (2) non-stationary, but mean-reverting (0.5 ≤ d < 1), shocks will be transitory with the time series taking longer to return to its original trend; and (3) non-stationary and non–mean-reverting (d ≥ 1), shocks will yield a permanent effect in establishing a new trend for the time series. The larger the differencing parameter, the greater the degree of persistence inherent in a time series, which measures the extent to which changes in current market conditions lead to permanent future changes.

Previous studies on the degree of persistence for Croatian tourism indicators in the pre–COVID-19 period include Gil-Alana et al. (2015; 2016) and Apergis et al. (2017). Using fractional integration techniques, Gil-Alana et al. (2015) examine foreign tourist arrivals and overnight stays for the coastal counties to show the degree of persistence is greater than zero but less than one. This suggests that shocks are largely transitory. Gil-Alana et al. (2016) investigate aggregate measures of domestic and foreign tourist arrivals and overnight stays to find shocks are transitory with mean reversion. Similar results are also found by Apergis et al. (2017). More recently, Payne et al. (2021) re-examine the degree of persistence for Croatia’s aggregate measures of foreign tourist arrivals and overnight stays to reveal that persistence has increased with the onset of the COVID-19 pandemic. This study extends the analysis of Payne et al. (2021) in the case of Croatia to include the seven counties along with the Adriatic coast in analyzing both domestic and foreign tourist arrivals as well as overnight stays to investigate the change in the persistence behavior and seasonality of the data. This is important since the aggregated results can differ from those which are disaggregated at the county level, implying that the effect of a given chock may differ from one county to another.

The second section discusses the data, methodology, and empirical results. The third section presents concluding remarks.

Data, methodology, and empirical results

The monthly data from 1998:1 to 2021:9 for domestic and foreign tourist arrivals and overnight stays, respectively, was obtained from the Croatian Bureau of Statistics. As evident from Figure 1, the onset of the COVID-19 pandemic created some disruption in domestic tourist arrivals, but has weathered the storm to even show an increase. This may be attributed to the prevalence of international travel restrictions whereby Croatian citizens substituted away from international travel toward domestic tourism. On the other hand, Figure 2 illustrates that foreign tourist arrivals experienced a more prominent shock. A similar scenario emerges when evaluating domestic and foreign overnight stays as shown in Figures 3 and 4, respectively.³

Figure 1.

Domestic tourist arrivals.

Figure 2.

Foreign tourist arrivals.

Figure 3.

Domestic tourist overnight stays.

Figure 4.

Foreign tourist overnight stays.

We utilize the following fractional integration modeling framework to assess the degree of persistence and seasonality in the tourism data as follows

y_{t} = α + β t + x_{t}; {(1 - B)}^{d} x_{t} = u_{t}, u_{t} = ρ u_{t - 12} + ε_{t},

(1)

where y_t refers to the observed data (in logs); α and β are unknown coefficients referring, respectively, to a constant and a (linear) time trend; B is the backshift operator, that is, B^kx_t = x_t-k; and d indicates the order of integration. Given the monthly nature of the data, u_t follows a seasonal (monthly) AR(1) process in which ε_t is an uncorrelated zero-mean process with constant variance. The model is estimated by using the Whittle function in the frequency domain with tests to determine the confidence band of the non-rejection values of the differencing parameter d based on a simple version of the test by Robinson (1994).

The analysis begins with an examination of the domestic and foreign tourist arrivals for the pre–COVID-19 pandemic covering the period 1998:1 to 2020:2.⁴ Table 1 displays the estimates of d for the selected model based on either one of the three classical assumptions: i) no terms, ii) with an intercept, and iii) with an intercept and a linear time trend. The selection of the appropriate specification is based on the statistical significance of the t-statistics at the 5% level for the intercept term and time trend of the respective models. As shown in Table 1, the selected models do not include time trends, but just an intercept term. In fact, the time trend is only found to be significant alongside the intercept term in the cases of Istria and Lika-Senj for the foreign tourist arrivals and Zadar and Sibenik-Knin for domestic tourist arrivals. The difference parameter, d, measuring the degree of persistence in the case of domestic tourist arrivals ranges from 0.19 in Sibenik-Knin to 0.40 in Istria. The point estimates of the differencing parameter, d, suggest domestic tourist arrivals are stationary with mean reversion. The seasonal autoregressive coefficient estimates range from 0.898 in Lika-Senj to 0.974 in Zadar, indicative of a strong seasonal component in the data. With respect to foreign tourist arrivals over this same period, the differencing parameter, d, ranges from 0.17 in Istria to 0.69 in Split-Dalmatia. With the exception of Zadar, Split-Dalmatia, and Dubrovnik-Neretva, the point estimates of the differencing parameter, d, indicate foreign tourist arrivals are stationary with mean reversion. The seasonal autoregressive coefficient estimates for foreign tourist arrivals are larger than domestic tourist arrivals and range from 0.968 in Sibenik-Knin to 0.988 in Primorje-Gorski kotar.

Table 1.

Coefficients from estimated models for arrivals. Pre-COVID period, 1998:1–2020:2.

Coastal county	Type	d (95%band)	Intercept (t-value)	Time trend (t-value)	Seasonal AR
Istria	Domestic	0.40 (0.32, 0.51)	9.455 (50.64)	—	0.939
Istria	Foreign	0.17 (0.07, 0.30)	10.623 (29.39)	0.0045 (2.01)	0.985
Primorje-Gorski kotar	Domestic	0.35 (0.25, 0.46)	10.040 (67.83)	—	0.959
Primorje-Gorski kotar	Foreign	0.42 (0.35, 0.49)	10.479 (20.19)	—	0.988
Lika-Senj	Domestic	0.32 (0.24, 0.41)	7.652 (43.79)	—	0.898
Lika-Senj	Foreign	0.35 (0.24, 0.50)	7.362 (11.59)	0.0112 (2.68)	0.979
Zadar	Domestic	0.22 (0.12, 0.35)	8.468 (33.14)	0.0033 (2.06)	0.974
Zadar	Foreign	0.55 (0.48, 0.88)	7.495 (8.35)	—	0.980
Sibenik-Knin	Domestic	0.19 (0.08, 0.33)	7.953 (31.56)	0.0040 (2.57)	0.961
Sibenik-Knin	Foreign	0.48 (0.41, 0.59)	7.633 (8.61)	—	0.968
Split-Dalmatia	Domestic	0.35 (0.27, 0.43)	9.456 (53.73)	—	0.971
Split-Dalmatia	Foreign	0.69 (0.59, 0.81)	8.633 (8.98)	—	0.983
Dubrovnik-Neretva	Domestic	0.29 (0.20, 0.41)	8.855 (74.98)	—	0.935
Dubrovnik-Neretva	Foreign	0.64 (0.57, 0.75)	8.522 (10.93)	—	0.978

Notes: Selected models include intercept only and intercept with time trend.

When we extend the estimation period to include the period of the COVID-19 pandemic (1998:1 to 2021:9), we observe in Table 2 the intercept terms are statistically significant with the trend insignificant, as well as changes in the degree of persistence and seasonal behavior with respect to tourist arrivals.⁵ In terms of domestic tourist arrivals, the difference parameter, d, ranges from 0.41 in Lika-Senj to 0.66 in Istria and Split-Dalmatia, an increase relative to the pre–COVID-19 period. With the exception of Lika-Senj, the point estimates of the differencing parameter, d, indicate domestic tourist arrivals are non-stationary, but mean-reverting. Hence, shocks will be transitory with domestic tourist arrivals taking longer to return to its original trend. The seasonal autoregressive coefficient estimates are much lower, ranging from 0.464 in Istria to 0.853 in Zadar. In regard to foreign tourist arrivals, the differencing parameter, d, is much higher, ranging from 0.76 in Istria to 1.08 in Split-Dalmatia. With the exception of Split-Dalmatia, the point estimates of the differencing parameter, d, suggest foreign tourist arrivals are non-stationary, but mean-reverting, whereas in the pre–COVID-19 period foreign tourist arrivals are stationary with mean reversion. Such behavior suggests that shocks will be transitory, but long-lasting. As in the case of domestic tourist arrivals, the foreign tourist arrivals also reveal elevated persistence levels and less prominent seasonality.

Table 2.

Coefficients from estimated models for arrivals. Full period, 1998:1–2021:9.

Coastal county	Type	d (95%band)	Intercept (t-value)	Time trend (t-value)	Seasonal AR
Istria	Domestic	0.66 (0.48, 0.89)	9.278 (21.13)	—	0.464
Istria	Foreign	0.76 (0.55, 0.95)	9.057 (8.16)	—	0.763
Primorje-Gorski kotar	Domestic	0.59 (0.40, 0.84)	9.798 (26.22)	—	0.587
Primorje-Gorski kotar	Foreign	0.93 (0.76, 1.12)	8.489 (8.78)	—	0.787
Lika-Senj	Domestic	0.41 (0.29, 0.58)	7.626 (27.96)	—	0.711
Lika-Senj	Foreign	0.90 (0.71, 1.12)	6.015 (5.37)	—	0.739
Zadar	Domestic	0.57 (0.28, 0.80)	8.057 (13.88)	—	0.853
Zadar	Foreign	0.94 (0.78, 1.14)	5.369 (4.77)	—	0.811
Sibenik-Knin	Domestic	0.60 (0.42, 0.80)	7.424 (11.31)	—	0.797
Sibenik-Knin	Foreign	0.94 (0.78, 1.12)	5.037 (3.88)	—	0.835
Split-Dalmatia	Domestic	0.66 (0.47, 0.88)	9.050 (19.65)	—	0.678
Split-Dalmatia	Foreign	1.08 (0.90, 1.32)	7.993 (8.28)	—	0.810
Dubrovnik-Neretva	Domestic	0.56 (0.36, 0.79)	8.529 (22.70)	—	0.536
Dubrovnik-Neretva	Foreign	0.97 (0.80, 1.18)	7.733 (8.34)	—	0.711

Notes: Selected model with intercept only.

Next, we shift our analysis toward domestic and foreign overnight stays for the coastal counties during the pre–COVID-19 period as shown in Table 3. With the exception of foreign tourist overnight stays in Lika-Senj and domestic tourist overnight stays in Sibenik-Knin which include both intercept and trend terms, the model specifications for the rest of the counties only include an intercept term. The difference parameter, d, measuring the degree of persistence in the case of domestic tourist overnight stays ranges from 0.19 in Sibenik-Knin to 0.46 in Zadar. The point estimates of the differencing parameter, d, show domestic tourist overnight stays are stationary with mean reversion. The seasonal autoregressive coefficient estimates range from 0.929 in Lika-Senj to 0.984 in Primorje-Gorski kotar reflective of a strong seasonal component in the data. With respect to foreign tourist overnight stays over this same period, the differencing parameter, d, ranges from 0.31 in Istria to 0.65 in Dubrovnik-Neretva. With the exception of Zadar, Split-Dalmatia, and Dubrovnik-Neretva, the point estimates of the differencing parameter, d, indicate foreign tourist overnight stays are stationary with mean reversion. The seasonal autoregressive coefficient estimates for foreign tourist overnight stays range from 0.976 in Sibenik-Knin to 0.990 in Primorje-Gorski kotar.

Table 3.

Coefficients from estimated models for overnight stays. Pre–COVID period, 1998:1–2020:2.

Coastal county	Type	d (95%band)	Intercept (t-value)	Time trend (t-value)	Seasonal AR
Istria	Domestic	0.39 (0.28, 0.54)	10.751 (44.74)	—	0.950
Istria	Foreign	0.31 (0.23, 0.41)	12.516 (27.04)	—	0.978
Primorje-Gorski kotar	Domestic	0.34 (0.20, 0.50)	11.130 (48.48)	—	0.984
Primorje-Gorski kotar	Foreign	0.40 (0.32, 0.50)	11.933 (20.56)	—	0.990
Lika-Senj	Domestic	0.34 (0.24, 0.48)	8.503 (28.88)	—	0.929
Lika-Senj	Foreign	0.38 (0.24, 0.54)	7.965 (9.21)	0.0114 (1.97)	0.983
Zadar	Domestic	0.46 (0.34, 0.63)	9.603 (16.70)	—	0.965
Zadar	Foreign	0.53 (0.46, 0.64)	8.804 (8.46)	—	0.982
Sibenik-Knin	Domestic	0.19 (0.06, 0.33)	8.938 (27.33)	0.0046 (2.27)	0.964
Sibenik-Knin	Foreign	0.49 (0.42, 0.58)	8.923 (8.68)	—	0.976
Split-Dalmatia	Domestic	0.35 (0.22, 0.50)	10.559 (38.76)	—	0.983
Split-Dalmatia	Foreign	0.60 (0.51, 0.73)	10.452 (9.83)	—	0.985
Dubrovnik-Neretva	Domestic	0.33 (0.23, 0.46)	9.968 (10.76)	—	0.961
Dubrovnik-Neretva	Foreign	0.65 (0.56, 0.77)	9.857 (10.76)	—	0.981

Notes: Selected models include intercept only and intercept with time trend.

By extending the estimation period to include the period of the COVID-19 pandemic (1998:1 to 2021:9), we observe in Table 4 the intercept terms are statistically significant with the time trend insignificant along with changes in the degree of persistence and seasonal behavior with respect to tourist overnight stays. In terms of domestic tourist overnight stays, the difference parameter, d, increases with a range of 0.46 in Lika-Senj to 0.80 in Split-Dalmatia. With the exception of Lika-Senj, the point estimates of the differencing parameter, d, indicate domestic tourist overnight stays are non-stationary, but mean-reverting. The seasonal autoregressive coefficient estimates decrease with a range of 0.632 in Istria to 0.913 in Zadar. In terms of foreign tourist overnight stays, the differencing parameter, d, is much higher, ranging from 0.97 in Istria and Sibenik-Knin to 1.20 in Dubrovnik-Neretva. Other than Istria and Sibenik-Knin, the point estimates of the differencing parameter, d, exceed one, indicative of non-stationary and non–mean-reverting behavior. Such behavior suggests that shocks will be permanent in altering the trend path of foreign overnight stays. In comparing the results across domestic and foreign tourist arrivals and overnight stays, it appears the shock associated with the COVID-19 pandemic is more pronounced with respect to foreign tourist overnight stays.

Table 4.

Coefficients from estimated models for overnight stays. Full period, 1998:1–2021:9.

Coastal county	Type	d (95%band)	Intercept (t-value)	Time trend (t-value)	Seasonal AR
Istria	Domestic	0.68 (0.50, 0.92)	10.707 (20.26)	—	0.632
Istria	Foreign	0.97 (0.81, 1.14)	9.774 (8.20)	—	0.856
Primorje-Gorski kotar	Domestic	0.67 (0.49, 0.88)	10.791 (19.00)	—	0.837
Primorje-Gorski kotar	Foreign	1.16 (1.02, 1.34)	9.818 (10.19)	—	0.888
Lika-Senj	Domestic	0.46 (0.33, 0.62)	8.430 (18.61)	—	0.848
Lika-Senj	Foreign	1.06 (0.91, 1.24)	6.191 (5.08)	—	0.860
Zadar	Domestic	0.77 (0.57, 0.95)	8.742 (9.30)	—	0.913
Zadar	Foreign	1.12 (0.98, 1.28)	6.316 (5.40)	—	0.901
Sibenik-Knin	Domestic	0.70 (0.49, 0.89)	7.828 (8.58)	—	0.868
Sibenik-Knin	Foreign	0.97 (0.83, 1.13)	6.891 (4.94)	—	0.906
Split-Dalmatia	Domestic	0.80 (0.62, 1.01)	10.184 (14.79)	—	0.877
Split-Dalmatia	Foreign	1.15 (1.00, 1.34)	9.502 (9.03)	—	0.910
Dubrovnik-Neretva	Domestic	0.70 (0.50, 0.90)	9.393 (16.47)	—	0.748
Dubrovnik-Neretva	Foreign	1.20 (1.04, 1.40)	9.041 (10.31)	—	0.853

Notes: Selected model with intercept only.

Concluding remarks

Without question the global COVID-19 pandemic has had a tremendous impact on the global tourism and hospitality industry. This disruption has been particularly significant for small open economies like Croatia which rely heavily on the tourism sector as a major source for export revenues, and overall contribution to the country’s GDP. Through the use of fractional integration techniques, this empirical study differentiates between the transitory and permanent nature of the COVID-19 shock with respect to domestic and foreign tourist arrivals as well as overnight stays across Croatia’s seven coastal counties, which constitute almost 90% of the country’s tourist arrivals and overnight stays. Such analysis is relevant for the use of historical information in the construction of tourism demand models and the generation of forecasts to project future tourism trends.

The results indicate an increase in the degree of persistence with the emergence of the COVID-19 pandemic and a decrease in the seasonal autoregressive component of the respective data. Since the shock from the COVID-19 pandemic has elevated the degree of persistence associated with the shock in conjunction with the change in the seasonality observed, sustained marketing and promotion campaigns to restore tourism are warranted. Related to these marketing and promotion campaigns is the importance of updates on the assessment of the spread of the COVID-19 virus and the appropriate health measures to ensure tourists stay safe.⁶ Moreover, consideration should be given to the investment required to enhance the sustainability of the tourism sector, both economically and environmentally, in order to mitigate future shocks and increase the resilience and sustainability of the tourism sector through regional diversification and specialization.

The degrees of persistence observed in our results during the pre–COVID period are similar to those reported by Gil-Alana et al. (2015, 2016) and Apergis et al. (2017) with the order of integration ranging from zero to less than one. Likewise, with the inclusion of the COVID period, our results demonstrate some variation across coastal counties, but the observed increase in the degree of persistence is similar to the studies by Payne et al. (2021) and Gil-Alana and Poza (2021) who also find an increase in the degree of persistence with the inclusion of the COVID time period. Moreover, our results are also similar to previous studies in which the effects of shocks on tourism-related time series are generally transitory with long-lasting effects. However, the COVID-19 pandemic may have changed the nature of the persistence in the data with the long-range dependence significantly increasing during this period.

Footnotes

Declaration of conflicting interests

The author(s) declared no potential conflicts of interest with respect to the research, authorship, and/or publication of this article.

Funding

The author(s) received no financial support for the research, authorship, and/or publication of this article.

ORCID iDs

James E Payne

Luis A Gil-Alana

Andrea Mervar

Notes

Author biographies

James E. Payne, PhD, serves as the Dean of the College of Business Administration at The University of Texas at El Paso and holds the Paul L. Foster and Alejandra de la Vega Foster Distinguished Chair in International Business. Dr. Payne has authored over 270 peer-reviewed journal articles and serves on the editorial board of a number of academic journals.

Luis Alberiko Gil-Alana, PhD, serves as a Faculty Fellow of the Navarra Center for International Development and Professor of Econometrics and Quantitative Methods in the School of Economics and Business Administration at the University of Navarra, in Pamplona, Spain. Dr. Gil-Alana has published extensively in theoretical and applied econometrics and also in macroeconomics, finance and many other disciplines including climatology, tourism, economic development and energy and environmental issues.

Andrea Mervar, PhD, is affiliated with The Institute of Economics, Zagreb in Croatia. She is a Senior Research Associate in the Department for Macroeconomics and International Economics. Dr. Mervar’s research interests include analysis of short-term macroeconomic trends, economic growth and aggregate productivity, international economics as well as tourism economics. Dr. Mervar has been involved in a large number of research projects and has extensive experience as an editor of economic journals.

María Goenechea is Professor of Financial Issues at the Francisco de Vitoria University (Madrid, Spain). She completed her PhD at Universidad Internacional de Cataluña (Barcelona, Spain) in 2017 in the area of Human, Legal and Social Sciences. She has a degree in Law and Economics from Universidad Pontificia Comillas (Madrid, Spain) and she began her professional career in the area of tax advice for large firms, and in the last few years has started on academic research.

References

Al-Shboul

Anwar

(2017) Long memory behavior in Singapore’s tourism market. International Journal of Tourism Research 19(5): 524–534.

Andraz

Cuerreiro

RFC

Rodriguez

PMM

(2018) Persistence of travel and leisure sector equity indices. Empirical Economics 54(4): 1801–1825.

Apergis

Mervar

Payne

(2017) Forecasting disaggregated tourist arrivals in Croatia: Evidence of seasonal univariate time series models. Tourism Economics 23(1): 78–98.

Assaf

Barros

Gil-Alana

(2011) Persistence in the short- and long-term tourist arrivals to Australia. Journal of Travel Research 50(2): 213–229.

Assaf

Gil-Alana

Barros

(2012) Persistence characteristics of tourism arrivals to Australia. International Journal of Tourism Research 14(2): 165–176.

AKM

Ramasamy

Yeung

MCH

(2005) The effects of SARS on the Hong Kong tourism industry: An empirical evaluation. Asia Pacific Journal of Tourism Research 10(1): 85–95.

Baig

Hussain

(2020) Do shocks have permanent or transitory effects on tourist inflow? An application of stationarity tests with structural breaks: evidence re-examined for Gilgit-Baltistan, Pakistan. Asia Pacific Journal of Tourism Research 25(2): 120–130.

Bassil

Saleh

Anwar

(2014) Is tourism in Lebanon subject to permanent or transitory exogenous shocks? Tourism Analysis 19(6): 781–790.

Bhattacharya

Narayan

(2005) Testing for the random walk hypothesis in the case of visitor arrivals: Evidence from Indian tourism. Applied Economics 37(13): 1485–1490.

10.

Caporale

Gil-Alana

(2019) UK overseas visitors: Seasonality and persistence. Tourism Economics 25(5): 827–831.

11.

Charles

Darne

Hoarau

J-F

(2019) How resilient is La reunion in terms of international tourism attractiveness: An assessment from unit root tests with structural breaks from 1981-2015. Applied Economics 51(24): 2639–2653.

12.

Chen

Malinda

(2014) Long memory and multiple structural breaks in returns of travel and tourism indexes. Journal of Business and Economics 5(9): 1460–1472.

13.

Chu

F-L

(2008) A fractionally integrated autoregressive moving average approach to forecasting tourism demand. Tourism Management 29(1): 79–88.

14.

Chu

H-P

Chang

H-L

, et al. (2008) Are visitor arrivals to Taiwan stationary? An empirical study based on panel SURADF tests. Empirical Economics Letters 7(10): 1001–1007.

15.

Chu

F-L

(2009) Forecasting tourism demand with ARMA-based methods. Tourism Management 30(5): 740–751.

16.

Chu

H-P

Yeh

M-L

Chang

T-Y

(2014) Are visitor arrivals to China stationary? An empirical note. Asia Pacific Journal of Tourism Research 19(2): 248–256.

17.

Cunado

Gil-Alana

Perez de Gracia

(2004) Modelling monthly Spanish tourism: A seasonal fractonally integrated approach. Tourism Economics 10(1): 79–94.

18.

Cunado

Gil-Alana

Perez de Gracia

(2005) The nature of seasonality in Spanish tourism time series. Tourism Economics 11(4): 483–499.

19.

Cunado

Gil-Alana

Perez de Gracia

(2008a) Persistence in international monthly arrivals in the Canary Islands. Tourism Economics 14(1): 123–129.

20.

Cunado

Gil-Alana

Perez de Gracia

(2008b) Fractional integration and structural breaks: Evidence from international monthly arrivals in the USA. Tourism Economics 14(1): 13–23.

21.

Dash

Suresh

Tiwari

(2017) Are tourist arrivals stationary? Evidence from BRIC countries. Current Issues in Tourism 20(3): 221–224.

22.

Dedeoglu

(2016) Are shocks to Turkey’s tourist arrivals permanent? Ekonometri ve Istatistik sayi 24: 30–39.

23.

Gil-Alana

Perez de Gracia

Cunado

(2004) Seasonal fractional integration in the Spanish tourism quarterly time series. Journal of Travel Research 42(4): 408–414.

24.

Gil-Alana

(2005) Modelling international monthly arrivals using seasonal univariate long-memory processes. Tourism Management 26(6): 867–878.

25.

Gil-Alana

Cunado

Perez de Gracia

(2008) Tourism in the Canary Islands: Forecasting using several seasonal time series models. Journal of Forecasting 27(7): 621–636.

26.

Gil-Alana

(2009) Americans traveling to Europe: A new perspective based on persistence. Tourism and Hospitality Research 9(1): 3–8.

27.

Gil-Alana

(2010) International arrivals in the Canary Islands: Persistence, long memory, seasonality, and other implicit dynamics. Tourism Economics 16(2): 287–302.

28.

Gil-Alana

Fischer

(2010) International traveling and trade: Further evidence for the case of Spanish wine based on fractional vector autoregressive specifications. Applied Economics 42(19): 2417–2434.

29.

Gil-Alana

(2011) Tourism in South Africa-time series persistence and the nature of the shocks: Are they transitory or permanent? African Journal of Business Management 5(12): 4686–4698.

30.

Gil-Alana

Mudida

Perez Gracia

(2014) Persistence, long memory and seasonality in Kenyan tourism series. Annals of Tourism Research 46: 89–101.

31.

Gil-Alana

Mervar

Payne

(2015) Measuring persistence in Croatian tourism: Evidence from the Adriatic region. Applied Economics 47(46): 4901–4917.

32.

Gil-Alana

Mervar

Payne

(2016) Modeling the degree of persistence in Croatian tourism. Tourism Economics 22(3): 655–664.

33.

Gil-Alana

Huijbens

(2018) Tourism in Iceland: Persistence and seasonality. Annals of Tourism Research 68: 20–29.

34.

Gil-Alana

Gil-Lopez

Roman

(2019) Tourism persistence in Spain: National versus international visitors. Tourism Economics 27: 614–625.

35.

Gil-Alana

Ruiz-Alba

Ayestaran

, et al. (2020) Arrivals and departures: Seasonality, persistence, and time trends. Applied Economics 52: 5077–5087.

36.

Gil-Alana

Payne

(2020) Persistence, seasonality, and fractional integration within a nonlinear framework: Evidence from U.S. citizens overseas travel. Tourism Economics 28: 654–660.

37.

Gil-Alana

Poza

(2021) The impact of COVID-19 on the Spanish tourism sector. Tourism Economics 28: 646–653.

38.

Kyophilavong

Tiwari

Jozwik

, et al. (2019) Are tourist arrivals stationary? Evidence from Laos. Anatolia: An International Journal of Tourism and Hospitality Research 30(4): 622–625.

39.

Lean

Smyth

(2009) Asian financial crisis, avian flu and tourist threats: Are shocks to Malaysian tourist arrivals permanent or transitory? Asia Pacific Journal of Tourism Research 14(3): 301–321.

40.

Lee

(2009) Are tourist arrivals stationary? Evidence from Singapore. International Journal of Tourism Research 11(4): 409–414.

41.

Lee

(2010) Whether a shock has a temporary or permanent effect on visitor arrivals in Singapore. Tourism Review International 14(1): 43–46.

42.

Lee

Ying

Yang

GJA

(2014) Assessing whether tourist arrivals are stationary: Evidence from Taiwan using sequential panel selection method. Journal of China Tourism Research 10(2): 206–221.

43.

Lorde

Francis

Skeete

(2009) Are shocks to Barbados long-stay visitor arrivals permanent or temporary: A short empirical note. Journal of Public Sector Policy Analysis 3: 3–19.

44.

Narayan

(2005a) The structure of tourist expenditure in Fiji: Evidence from unit root structural break tests. Applied Economics 37(10): 1157–1161.

45.

Narayan

(2005b) Did Rabuka’s military coups have a permanent effect or a transitory effect on tourist expenditure in Fiji: Evidence from Vogelsang’s structural break test. Tourism Management 26(4): 509–515.

46.

Narayan

(2005c) Testing the unit root hypothesis when the alternative is a trend break stationary process: An application to tourist arrivals in Fiji. Tourism Economics 11(3): 351–364.

47.

Narayan

(2008) Examining the behavior of visitor arrivals to Australia from 28 different countries. Transportation Research Part A 42(5): 751–761.

48.

Narayan

Prasad

(2008) Examining the behaviour of visitor arrivals to Australia from twenty different countries: An application of panel unit root tests. Economic Papers 27(3): 265–271.

49.

Nowman

Van Dellen

(2012) Forecasting overseas visitors to the U.K. using continuous time and autoregressive fractional integrated moving average models with discrete data. Tourism Economics 18(4): 835–844.

50.

Payne

Gil-Alana

(2018) Data measurement and the change in persistence of tourist arrivals to the United States in the aftermath of the September 11^th terrorist attacks. Tourism Economics 24(1): 41–50.

51.

Payne

Gil-Alana

Mervar

(2021) Persistence in Croatian tourism: The impact of COVID-19. Tourism Economics. OnlineFirst.

52.

Payne

Nazlioglu

Mervar

(2022) Economic policy uncertainty and international tourist arrivals: A disaggregated analysis of the Croatian Adriatic coast. Tourism Economics. OnlineFirst.

53.

Perez-Rodriguez

Santana-Gallego

(2020) Modelling tourism receipts and associated risk, using long-range dependence models. Tourism Economics 26(1): 70–96.

54.

Robinson

(1994) Efficient tests of nonstationary hypothesis. Journal of the American Statistical Association 89(428): 1420–1437.

55.

Saleh

Verma

Ihalanayake

(2011) Do external shocks have a permanent or a transitory effect on Thailand’s tourism industry? Tourism Analysis 16(4): 483–491.

56.

Solarin

(2015) September 11 attacks, H₁N₁ influenza, global financial crisis, and tourist arrivals in Sarawak. Anatolia: An International Journal of Tourism and Hospitality Research 26(2): 298–300.

57.

Solarin

(2016) Global financial crisis and stationarity of tourist arrivals: Evidence from Mauritius. Current Issues in Tourism 19(9): 869–875.

58.

Smyth

Nielsen

Mishra

(2009) I’ve been to Bali Too’ (and I will Be going back): Are terrorist shocks to Bali’s tourist arrivals permanent or transitory? Applied Economics 41(11): 1367–1378.

59.

Stucka

(2000) Physical Indicators of Foreign Tourist Activity in Croatia: OLS Model in Instrazivanja. Zagreb: Croatian National Bank, pp. 1–7.

60.

Tan

S-H

Tan

S-K

(2014) Are shocks to Singapore’s tourist arrivals permanent or transitory? An application of stationarity test with structural breaks. Current Issues in Tourism 17(6): 480–486.

61.

Tang

Wong

(2009) The SARS epidemic and international visitor arrivals to Cambodia: Is the impact permanent or transitory? Tourism Economics 15(4): 883–890.

62.

Tiwari

Dash

Narayanan

(2018) Foreign tourist arrivals in India from major source countries: An empirical analysis. Current Issues in Tourism 21(10): 1137–1156.

63.

Valadkhani

O’Mahony

(2018) Identifying structural changes and regime switching in growing and declining inbound tourism markets in Australia. Current Issues in Tourism 21(3): 277–300.

64.

Xie

Tiwari

Chang

(2018) Investigating stationarity in tourist arrivals to India using panel KPSS with sharp drifts and smooth breaks. Applied Economics 50(46): 4985–4998.

65.

Yang

GJ-A

Ying

Y-H

Chang

, et al. (2014) Investigating stationarity in tourist arrivals to Taiwan using panel KPSS with sharp drifts and smooth breaks. Tourism Analysis 19(5): 573–580.

66.

Yucel

(2021) Are shocks to tourist arrivals permanent or transitory? A comprehensive analysis on the top 20 most-visited countries. Current Issues in Tourism 24(16): 2294–2311.