Forecasting tourism demand to Catalonia: neural networks vs. time series models

The increasing interest aroused by more advanced forecasting techniques, together with the requirement for more accurate forecasts of tourismdemand at the destination level due to the constant growth of world tourism, has lead us to evaluate the forecasting performance of neural modelling relative to that of time seriesmethods at a regional level. Seasonality and volatility are important features of tourism data, which makes it a particularly favourable context in which to compare the forecasting performance of linear models to that of nonlinear alternative approaches. Pre-processed official statistical data of overnight stays and tourist arrivals fromall the different countries of origin to Catalonia from 2001 to 2009 is used in the study. When comparing the forecasting accuracy of the different techniques for different time horizons, autoregressive integrated moving average models outperform self-exciting threshold autoregressions and artificial neural network models, especially for shorter horizons. These results suggest that the there is a trade-off between the degree of pre-processing and the accuracy of the forecasts obtained with neural networks, which are more suitable in the presence of nonlinearity in the data. In spite of the significant differences between countries, which can be explained by different patterns of consumer behaviour,we also find that forecasts of tourist arrivals aremore accurate than forecasts of overnight stays.

Predictability of music descriptor time series and its application to cover song detection

Intuitively, music has both predictable and unpredictable components. In this work we assess this qualitative statement in a quantitative way using common time series models fitted to state-of-the-art music descriptors. These descriptors cover different musical facets and are extracted from a large collection of real audio recordings comprising a variety of musical genres. Our findings show that music descriptor time series exhibit a certain predictability not only for short time intervals, but also for mid-term and relatively long intervals. This fact is observed independently of the descriptor, musical facet and time series model we consider. Moreover, we show that our findings are not only of theoretical relevance but can also have practical impact. To this end we demonstrate that music predictability at relatively long time intervals can be exploited in a real-world application, namely the automatic identification of cover songs (i.e. different renditions or versions of the same musical piece). Importantly, this prediction strategy yields a parameter-free approach for cover song identification that is substantially faster, allows for reduced computational storage and still maintains highly competitive accuracies when compared to state-of-the-art systems.

Credit markets and the propagation of monetary policy shocks

This paper analyzes the propagation of monetary policy shocks through the creation of credit in an economy. Models of the monetary transmission mechanism typically feature responses which last for a few quarters contrary to what the empirical evidence suggests. To propagate the impact of monetary shocks over time, these models introduce adjustment costs by which agents find it optimal to change their decisions slowly. This paper presents another explanation that does not rely on any sort of adjustment costs or stickiness. In our economy, agents own assets and make occupational choices. Banks intermediate between agents demanding and supplying assets. Our interpretation is based on the way banks create credit and how the monetary authority affects the process of financial intermediation through its monetary policy. As the central bank lowers the interest rate by buying government bonds in exchange for reserves, high productive entrepreneurs are able to borrow more resources from low productivity agents. We show that this movement of capital among agents sets in motion a response of the economy that resembles an expansionary phase of the cycle.

Discursos de gènere, nacionalisme i respostes col•lectives de les dones a Catalunya i Irlanda

El projecte realitzat se situa en el marc de la història contemporània, i s’ha centrat en primer lloc, en l’anàlisi, des d’una perspectiva comparativa, del desenvolupament dels discursos de gènere a Catalunya durant la Dictadura Franquista i a la Irlanda postcolonial. Mitjançant l’anàlisi del discurs, s’han estudiat els models de feminitat imposats pel Franquisme i les seves bases ideològiques com són el valors catòlics i l’antindividualisme. En el cas irlandès, s’ha analitzat com, a través de determinades institucions gestionades per l’Església Catòlica, es controlaven aquelles dones que es desviaven del model de gènere que propugnava l’Estat Irlandès, molt similar al proposat pel Franquisme i també basat en els catolicisme. De la mateix manera, s’ha estudiat com el feminisme Català i irlandès dels anys 1970 i 1980 van contrarestar aquests models de gènere imposats, a través de l’anàlisi d’un conjunt d’expressions culturals produïdes per ambdós moviments feministes. La perspectiva comparativa del projecte ha permès: El coneixement dels mecanismes culturals de repressió de les dones així com la seva institucionalització. Revelant els paral•lelismes pel que fa a les polítiques de gènere entre els dos casos estudiats malgrat diferències significatives entre els dos contextos (Catalunya es troba sota una dictadura, Irlanda és un Estat democràtic). La importància de l’agència de les dones i les seves diverses estratègies de resistència, especialment a través d’expressions culturals més efímeres o considerades frívoles que, malgrat el poc reconeixement que han obtingut, són molt eficaces en la deconstrucció de discursos de gènere repressius envers les dones. Ha posat de manifest, també, la importància de l’experiència i les pràctiques personals i íntimes com a pràctiques de resistència. Així mateix, ha visibilitzat les dinàmiques pròpies de moviments feministes.

Adoption of financial technologies: Implications for money demand and monetary policy

In this paper we argue that inventory models are probably not usefulmodels of household money demand because the majority of households does nothold any interest bearing assets. The relevant decision for most people is notthe fraction of assets to be held in interest bearing form, but whether to holdany of such assets at all. The implications of this realization are interesting and important. We find that(a) the elasticity of money demand is very small when the interest rate is small,(b) the probability that a household holds any amount of interest bearing assetsis positively related to the level of financial assets, and (c) the cost ofadopting financial technologies is positively related to age and negatively relatedto the level of education. Unlike the traditional methods of money demand estimation, our methodology allowsfor the estimation of the interest--elasticity at low values of the nominalinterest rate. The finding that the elasticity is very small for interest ratesbelow 5 percent suggests that the welfare costs of inflation are small. At interest rates of 6 percent, the elasticity is close to 0.5. We find thatroughly one half of this elasticity can be attributed to the Baumol--Tobin orintensive margin and half of it can be attributed to the new adopters or extensivemargin. The intensive margin is less important at lower interest rates and moreimportant at higher interest rates.

Una extensión de la regresión propuesta por Geweke y Porter-Hudak para la estimación del orden de diferenciación en modelos ARFIMA

Recientemente, ha aumentado mucho el interés por la aplicación de los modelos de memoria larga a variables económicas, sobre todo los modelos ARFIMA. Sin duda , el método más usado para la estimación de estos modelos en el ámbito del análisis económico es el propuesto por Geweke y Portero-Hudak (GPH) aun cuando en trabajos recientes se ha demostrado que, en ciertos casos, este estimador presenta un sesgo muy importante. De ahí que, se propone una extensión de este estimador a partir del modelo exponencial propuesto por Bloomfield, y que permite corregir este sesgo.A continuación, se analiza y compara el comportamiento de ambos estimadores en muestras no muy grandes y se comprueba como el estimador propuesto presenta un error cuadrático medio menor que el estimador GPH

Una extensión de la regresión propuesta por Geweke y Porter-Hudak para la estimación del orden de diferenciación en modelos ARFIMA

Recientemente, ha aumentado mucho el interés por la aplicación de los modelos de memoria larga a variables económicas, sobre todo los modelos ARFIMA. Sin duda , el método más usado para la estimación de estos modelos en el ámbito del análisis económico es el propuesto por Geweke y Portero-Hudak (GPH) aun cuando en trabajos recientes se ha demostrado que, en ciertos casos, este estimador presenta un sesgo muy importante. De ahí que, se propone una extensión de este estimador a partir del modelo exponencial propuesto por Bloomfield, y que permite corregir este sesgo.A continuación, se analiza y compara el comportamiento de ambos estimadores en muestras no muy grandes y se comprueba como el estimador propuesto presenta un error cuadrático medio menor que el estimador GPH

Forecasting tourism demand using consumer expectations

Abstract Purpose- There is a lack of studies on tourism demand forecasting that use non-linear models. The aim of this paper is to introduce consumer expectations in time-series models in order to analyse their usefulness to forecast tourism demand. Design/methodology/approach- The paper focuses on forecasting tourism demand in Catalonia for the four main visitor markets (France, the UK, Germany and Italy) combining qualitative information with quantitative models: autoregressive (AR), autoregressive integrated moving average (ARIMA), self-exciting threshold autoregressions (SETAR) and Markov switching regime (MKTAR) models. The forecasting performance of the different models is evaluated for different time horizons (one, two, three, six and 12 months). Findings- Although some differences are found between the results obtained for the different countries, when comparing the forecasting accuracy of the different techniques, ARIMA and Markov switching regime models outperform the rest of the models. In all cases, forecasts of arrivals show lower root mean square errors (RMSE) than forecasts of overnight stays. It is found that models with consumer expectations do not outperform benchmark models. These results are extensive to all time horizons analysed. Research limitations/implications- This study encourages the use of qualitative information and more advanced econometric techniques in order to improve tourism demand forecasting. Originality/value- This is the first study on tourism demand focusing specifically on Catalonia. To date, there have been no studies on tourism demand forecasting that use non-linear models such as self-exciting threshold autoregressions (SETAR) and Markov switching regime (MKTAR) models. This paper fills this gap and analyses forecasting performance at a regional level. Keywords Tourism, Forecasting, Consumers, Spain, Demand management Paper type Research paper

Discrete time Non-homogeneous Semi-Markov Processes applied to Models for Disability Insurance

In this paper, we present a stochastic model for disability insurance contracts. The model is based on a discrete time non-homogeneous semi-Markov process (DTNHSMP) to which the backward recurrence time process is introduced. This permits a more exhaustive study of disability evolution and a more efficient approach to the duration problem. The use of semi-Markov reward processes facilitates the possibility of deriving equations of the prospective and retrospective mathematical reserves. The model is applied to a sample of contracts drawn at random from a mutual insurance company.

Time-series regression models to study the short-term effects of environmental factors on health

Time series regression models are especially suitable in epidemiology for evaluating short-term effects of time-varying exposures on health. The problem is that potential for confounding in time series regression is very high. Thus, it is important that trend and seasonality are properly accounted for. Our paper reviews the statistical models commonly used in time-series regression methods, specially allowing for serial correlation, make them potentially useful for selected epidemiological purposes. In particular, we discuss the use of time-series regression for counts using a wide range Generalised Linear Models as well as Generalised Additive Models. In addition, recently critical points in using statistical software for GAM were stressed, and reanalyses of time series data on air pollution and health were performed in order to update already published. Applications are offered through an example on the relationship between asthma emergency admissions and photochemical air pollutants

Incorporating waiting time in competitive location models: formulations and heuristics

In this paper we propose a metaheuristic to solve a new version of the Maximum Capture Problem. In the original MCP, market capture is obtained by lower traveling distances or lower traveling time, in this new version not only the traveling time but also the waiting time will affect the market share. This problem is hard to solve using standard optimization techniques. Metaheuristics are shown to offer accurate results within acceptable computing times.

Probabilistic maximal covering location-allocation models with constrained waiting time or queue length for congested systems

When dealing with the design of service networks, such as healthand EMS services, banking or distributed ticket selling services, thelocation of service centers has a strong influence on the congestion ateach of them, and consequently, on the quality of service. In this paper,several models are presented to consider service congestion. The firstmodel addresses the issue of the location of the least number of single--servercenters such that all the population is served within a standard distance,and nobody stands in line for a time longer than a given time--limit, or withmore than a predetermined number of other clients. We then formulateseveral maximal coverage models, with one or more servers per service center.A new heuristic is developed to solve the models and tested in a 30--nodesnetwork.

A test of the predictive validity of non-linear QALY models using time trade-off utilities

This paper presents a test of the predictive validity of various classes ofQALY models (i.e., linear, power and exponential models). We first estimatedTTO utilities for 43 EQ-5D chronic health states and next these states wereembedded in health profiles. The chronic TTO utilities were then used topredict the responses to TTO questions with health profiles. We find that thepower QALY model clearly outperforms linear and exponential QALY models.Optimal power coefficient is 0.65. Our results suggest that TTO-based QALYcalculations may be biased. This bias can be avoided using a power QALY model.

On the short-time behavior of the implied volatility for jump-diffusion models with stochastic volatility

In this paper we use Malliavin calculus techniques to obtain an expression for the short-time behavior of the at-the-money implied volatility skew for a generalization of the Bates model, where the volatility does not need to be neither a difussion, nor a Markov process as the examples in section 7 show. This expression depends on the derivative of the volatility in the sense of Malliavin calculus.

Incorporating waiting time in competitive location models: Formulations and heuristics

In this paper we propose a metaheuristic to solve a new version of the Maximum CaptureProblem. In the original MCP, market capture is obtained by lower traveling distances or lowertraveling time, in this new version not only the traveling time but also the waiting time willaffect the market share. This problem is hard to solve using standard optimization techniques.Metaheuristics are shown to offer accurate results within acceptable computing times.