Abstract
The postal sector is adapting to the Internet technology (IT) revolution. Short message service (SMS) or email competes with correspondences (e-substitution). On the other hand, the purchase of physical products over the Internet (e-commerce) affects positively the volume of parcels delivered, a phenomenon expected to grow, spurred in part by digital single market goals. Because parcel growth is an e-commerce phenomenon, fixed broadband penetration appears more correlated with postal traffic than gross domestic product (GDP) (EGIDE et al. 2015).
ANACOM. The opinions expressed are those of the author and do not necessarily reflect the views of ANACOM.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
Notes
- 1.
- 2.
Namely, GDP.
- 3.
Increases of the costs have impact on the traffic volumes because these are the drivers for digitalization.
- 4.
This last, especially where e-government policies have been adopted, is the case in Portugal.
- 5.
Statistical indicators include data on traffic, revenues, postal network, and human and material resources. Data is subject to changes with revised or updated new quarterly information. More information is available at https://www.anacom.pt/render.jsp?categoryId=337756.
- 6.
Transposes the national legal system Directive 2008/6/EC of 20 February 2008. More information is available at https://www.anacom.pt/render.jsp?contentId=1127982.
- 7.
According to the definition, a postal item is an item addressed in the final form, which observes the physical and technical specifications that allows it to be sorted by a postal network, as well as delivered at the address indicated on the object itself or on its wrapping, namely, (a) correspondence, which consists of a communication in written form on any kind of physical medium, including direct mail; (b) editorial mail as books, catalogues, newspapers, and other periodicals; and (c) postal parcel, which is a package containing merchandise or objects with or without commercial value.
- 8.
The structural break analysis identified two breaks (4Q2007 and 4Q2011) in the time series of correspondence traffic.
- 9.
The structural break analysis identified one break in the time series of correspondence traffic (4Q2012).
- 10.
Fixed broadband accesses per 100 inhabitants. Data from ANACOM, Portugal.
- 11.
Data from Instituto Nacional de EstatÃstica, Portugal (www.ine.pt).
- 12.
E-initiatives (e-opportunities, e-school, and e-teachers) was launched by the Portuguese Government, in September 15, 2007, in order to promote the information and communication technologies, which permitted to students (young and adult) and teachers to receive a laptop and access to the Internet at a symbolic price, with training classes to explain how to work with the equipment. In 2 years, 852 thousands individuals took part in this program, 1/3 were less than 16 years old, 1/3 between 17 and 35 and the other 1/3 more than 35 years (15% with more than 45 years).
- 13.
The Pearson correlation coefficient was considered in correlation analysis.
- 14.
Law no. 17/2012, of 26 April, that transposes the national legal system Directive 2008/6/EC of 20 February 2008. More information is available at https://www.anacom.pt/render.jsp?contentId=1127982.
- 15.
Verified by the Augmented Dickey-Fuller test and Phillips-Perron test for unit root.
- 16.
An ARIMA with seasonality is denoted as SARIMA (p, d, q) (P, D, Q)s and is given by Π(Bs)Φ(B)ΔDsΔdYt = Θ(Bs)θ(B)εt. The nonseasonal AR and MA components are represented by polynomials Φ(B)B) and θ(B) of orders p and q, respectively, and the seasonal AR and MA components by Π(Bs) and Θ(Bs) of orders P and Q. Nonseasonal and seasonal difference components by Δd=(1-B)d and ΔDs=(1-BS)D, where, p, d, and q are the orders of nonseasonal AR, differencing, and MA, respectively; P, D, and Q are the orders of seasonal AR, differencing, and MA, respectively, and s represents seasonal order (s = 4 for quarterly data).
- 17.
General model is given by Π(BS)Φ(B)ΔDSΔdYt=Ψ(B)Xt+Θ(BS)θ(B)εt, where Xt are the exogenous variables.
- 18.
General model is given by Yt=β0+β1X1t+β2X2t+...+βpXpt, where Xpt (p = 1,…,r) are the independent variables, βt are the parameters, and βr is the number of regressors.
- 19.
Q4 was not included, to avoid multicollinearity problems.
- 20.
Breusch-Pagan test and White’s test, Ramsey RESET test, and Shapiro-Wilk W test for normal data
- 21.
Verified by the Augmented Dickey-Fuller test and Phillips-Perron test for unit root.
- 22.
General model is denoted as ARIMA (p, d, q) and given by Φ(B)Δdyt=θ(B)εt. The nonseasonal AR and MA components are represented by polynomials B and B of orders p and q, respectively, and d-difference components by Δd=(1-B)d; p, d, and q are the orders of nonseasonal AR, differentiation, and MA, respectively.
- 23.
General model is given by Φ(B)Δdyt = Ψ(B)Xt+θ(B)εt where Xt are the exogenous variables.
- 24.
Q1 is excluded to avoid multicollinearity problems.
- 25.
Breusch-Pagan test and White’s test, Ramsey RESET test, and Shapiro-Wilk W test for normal data.
References
ANACOM. (2011). Challenges facing the postal sector as it moves to full liberalization. https://www.anacom.pt/render.jsp?contentId=1092318
ANACOM. (2015). Study on the development of the postal sector. https://www.anacom.pt/render.jsp?contentId=1361251
ANACOM. (2018). The communications sector 2017. https://www.anacom.pt/render.jsp?categoryId=349440
Box, G. E. P., & Jenkins, G. M. (1970). Time series analysis: Forecasting and control. San Francisco: Holden-Day.
Box, G., Jenkins, G., & Reinsel, G. (1994). Time series analysis: Forecasting and control (3rd ed.). Hoboken: Prentice-Hall.
Brockwell, P., & Davis, R. (1991). Time series: Theory and methods (2nd ed.). New York: Springer.
Cazals, C., & Florens, J.-P. (2002). Econometrics of mail demand. In M. A. Crew & P. R. Kleindorfer (Eds.), Postal and delivery services (pp. 119–140). Boston: Kluwer Academic Publishers.
Cazals, C., Florens, J. P., Veruete-Mckay, L., Rodriguez, F., & Soteri, S. (2010). UK letter mail demand: A content based time series analysis using overlapping market survey statistical techniques. Available at https://www.tse-fr.eu/publications/uk-letter-mail-demand-content-based-time-series-analysis-using-overlapping-market-survey-statistical
Copenhagen Economics. (2018). Main developments in the postal sector (2013–2016). Luxembourg: Publications Office of the European Union.
CTT. (2018). E-commerce report 2018.
EGIDE, IMR & ANACOM. (2015). Study on the development of the postal sector. https://www.anacom.pt/render.jsp?contentId=1361251
Enders, W. (1995). Applied econometric time series. New York: Wiley.
ERGP. (2019). Developments in the postal sector and implications for regulation. Available at https://ec.europa.eu/docsroom/documents/34881/attachments/1/translations/en/renditions/native
Holt, C. E. (1957). Forecasting seasonals and trends by exponentially weighted averages (O.N.R. Memorandum No. 52). Pittsburgh: Carnegie Institute of Technology.
Jarosik, M., Nankervis, J., Pope, J., Soteri, S., & Veruete-McKay, L. (2002). Reforming the postal sector in the face of electronic competition. In M. A. Crew & P. R. Kleindorfer (Eds.), Postal and delivery services: delivering on competition (pp. 194–210). Boston: Springer.
Murteira, B., Muller, D., & Turkman, K. (1993). Análise de sucessões cronológicas. Lisboa: Mc Graw Hill.
Nikali, H., Mattila, J., Rintanen, I., & Huunhtanen, V. (2017). Demand and regulation for e-commerce in goods. In M. A. Crew & T. J. Brennan (Eds.), The future of the postal sector in a digital world (pp. 247–260). Cham: Springer Verlag.
StataCorp LLC. (2017). Stata time-series reference manual: Release 15. Texas: College Station.
UPU. (2014). Development strategies for the postal sector: an economic perspective. Delft: Eburon Academic Publishers.
UPU. (2018). Postal economic outlook 2018. Universal postal union postal statistics. Available online in http://www.upu.int/en/resources/postal-statistics/latest-results.html
UPU. (2019). Postal economic outlook 2019. Universal postal union postal statistics. Available online in http://www.upu.int/en/resources/postal-statistics/latest-results.html
Wik. (2006). Main developments in the postal sector (2004–2006). New York: Springer.
Wik. (2009). The evolution of the European postal market since 1997. Available at https://ec.europa.eu/growth/sectors/postal-services/studies_en
Wik. (2019). Development of cross-border e-commerce through parcel delivery. Luxembourg: Publications Office of the European Union.
Winters, P. R. (1960). Forecasting sales by exponentially weighted moving averages. Management Science, 6, 324–342.
Yaffee, R., & McGee, R. (2000). Time series analysis and forecasting, with applications of SAS and SPSS. San Diego: Academic Press.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this chapter
Cite this chapter
Machado, C., Silva, F. (2020). Postal Traffic in Portugal: Applying Time Series Modeling. In: Parcu, P.L., Brennan, T.J., Glass, V. (eds) The Changing Postal Environment. Topics in Regulatory Economics and Policy. Springer, Cham. https://doi.org/10.1007/978-3-030-34532-7_15
Download citation
DOI: https://doi.org/10.1007/978-3-030-34532-7_15
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-34531-0
Online ISBN: 978-3-030-34532-7
eBook Packages: Economics and FinanceEconomics and Finance (R0)