nep-for New Economics Papers
on Forecasting
Issue of 2011‒12‒05
three papers chosen by
Rob J Hyndman
Monash University

  1. Forecasting the Number of Visitors in a Unique Recreational Site- A Retrospective View By Mira G. Baron; Natalia Zaitsev
  2. Leading Indicators of Real Activity and Inflation for Turkey, 2001-2010 By Sumru Altug; Erhan Uluceviz
  3. The impact of location on housing prices: applying the Artificial Neural Network Model as an analytical tool. By Laura Fernández-Durán; Alicia Llorca; Nancy Ruiz; Soledad Valero; Vicente Botti

  1. By: Mira G. Baron; Natalia Zaitsev
    Abstract: We examine in the research forecasts prepared by us fifteen years ago. We examine the assumptions made as well as the results, comparing the forecasts to reality. We concentrate on the forecasts of number of visitors, which enables to examine economic impact, and is crucial in analyzing ecological carrying capacity. Our case study was a wetland that was drained in the '50s, resulting in severe environmental damages. In the '90s part of the area was re-flooded and a small lake was created. We forecasted the number of visitors, the expected revenues and benefits. The area is currently called Agmon Hula, located in the previous Hula marsh (North of Israel). The commodity planned was a site which offers safari, birds' sanctuary, horse riding, swimming in a pool, picnicking. We asked recreationists in adjacent national parks and nature reserves on their willingness to visit the planned park and their willingness to pay (WTP), using CVM methods. In reality, the site started operation in 2005 as a birds' sanctuary, due to its success in attracting birds. 500 million birds pass the area twice per year migrating to the south in the fall and returning north in the spring. Our forecast for 380 thousand visitors in the first year of operation did not materialize. We could have predicted a smaller number closer to the real number (220 thousand) if we would have considered the percentage that ranked birds' sanctuary as one of their two favorite activities. The prediction assumed an annual increase in the number of visitors of 2-6%, but actually, the increase in the first five years of operation is 8% annually. In the prediction, we disregarded tourists, but they were 7-17% of the visitors. Updating the prediction of number of visitors is easy, and is a crucial aspect in predicting carrying capacity.
    Date: 2011–09
    URL: http://d.repec.org/n?u=RePEc:wiw:wiwrsa:ersa11p834&r=for
  2. By: Sumru Altug (Koç University and CEPR); Erhan Uluceviz (Istanbul Bilgi University)
    Abstract: This paper develops a set of leading indicators of industrial production growth and consumer price inflation for the period 2001-2010. The choice of indicators is based on pseudo out-of-sample forecasting exercise implemented by Stock and Watson (2003), amongst others. We find that asset prices that reflect expectational factors or interest rates that capture the costs of borrowing for the Turkish economy tend to have the greatest predictive power for future real activity and inflation. Our findings provide evidence on the factors determining real activity and inflation in a period of disinflation and normalization for the Turkish economy.
    Keywords: Real activity, inflation, leading indicators, out-of-sample forecasting, combination forecasts, inflation targeting, Turkey
    JEL: E1 E32 E37 E58 F43 O52
    Date: 2011–11
    URL: http://d.repec.org/n?u=RePEc:koc:wpaper:1134&r=for
  3. By: Laura Fernández-Durán; Alicia Llorca; Nancy Ruiz; Soledad Valero; Vicente Botti
    Abstract: The location of a residential property in a city directly affects its market price. Each location represents different values in variables such as accessibility, neighbourhood, traffic, socio-economic level and proximity to green areas, among others. In addition, that location has an influence on the choice and on the offer price of each residential property. The development of artificial intelligence, allows us to use alternative tools to the traditional methods of econometric modelling. This has led us to conduct a study of the residential property market in the city of Valencia (Spain). In this study, we will attempt to explain the aspects that determine the demand for housing and the behaviour of prices in the urban space. We used an artificial neutral network as a price forecasting tool, since this system shows a considerable improvement in the accuracy of ratings over traditional models. With the help of this system, we attempted to quantify the impact on residential property prices of issues such as accessibility, level of service standards of public utilities, quality of urban planning, environmental surroundings and other locational aspects.
    Date: 2011–09
    URL: http://d.repec.org/n?u=RePEc:wiw:wiwrsa:ersa11p1595&r=for

This nep-for issue is ©2011 by Rob J Hyndman. It is provided as is without any express or implied warranty. It may be freely redistributed in whole or in part for any purpose. If distributed in part, please include this notice.
General information on the NEP project can be found at http://nep.repec.org. For comments please write to the director of NEP, Marco Novarese at <director@nep.repec.org>. Put “NEP” in the subject, otherwise your mail may be rejected.
NEP’s infrastructure is sponsored by the School of Economics and Finance of Massey University in New Zealand.