General Econometric Model Research Articles

Tail behavior of ACD models and consequences for likelihood-based estimation

We establish new results for estimation and inference in financial durations models, where events are observed over a given time span, such as a trading day, or a week. For the classical autoregressive conditional duration (ACD) models by Engle and Russell (1998), we show that the large sample behavior of likelihood estimators is highly sensitive to the tail behavior of the financial durations. In particular, even under stationarity, asymptotic normality breaks down for tail indices smaller than one or, equivalently, when the clustering behavior of the observed events is such that the unconditional distribution of the durations has no finite mean. Instead, we find that estimators are mixed Gaussian and have non-standard rates of convergence. The results are based on exploiting the crucial fact that for duration data the number of observations within any given time span is random. Our results apply to general econometric models where the number of observed events is random.

TIME SERIES FORECASTING WITH THE CIR# MODEL: FROM HECTIC MARKETS SENTIMENTS TO REGULAR SEASONAL TOURISM

This research aims to propose the so-called CIR#, which takes its cue from the well- known Cox-Ingersoll-Ross (CIR) model originally devised for pricing, as a general econometric model. To this end, we present the results on two very different time series such as Polish interest rates (subject to market sentiments) and seasonal tourism (subject to pandemic lock-down measures). For interest rates, as reference models, we consider an improved version of the CIR model (denoted CIRadj), the Hull and White model, the exponentially weighted moving average (EWMA) which is often adopted whenever no structure is assumed in the data and a popular machine learning model such as the short-term memory network (LSTM). For tourism, as a benchmark, we consider seasonal autoregressive integrated moving average (SARIMA) complemented by the generalized autoregressive conditional heteroskedasticity (GARCH) for modelling the variance, the classic Holt-Winters model and the aforementioned LSTM. Results support the claim that the CIR# performs better than the other models in all considered cases being able to deal with erratic behaviour in data.

Greece 2010–18: What Could Have Been Done Differently?

At the beginning of 2010, the fiscal situation of Greece was unsustainable, and an ambitious but costly adjustment plan had to be put in place under a consortium of the International Monetary Fund, the European Commission and the European Central Bank. It took three consecutive adjustment programmes, including debt-relief through private sector involvement, to restore confidence in the economy and achieve a budget surplus. In this paper, we provide a theoretical analysis of the Greek Crisis starting from 2010. We build a series of counterfactuals using the National Institute General Econometric Model (NIGEM) to analyse why the cost of the adjustment in terms of GDP loss and increase in debt-to-GDP ratio turned out to be much worse than expected. In doing so, we analyse three scenarios: (i) one in which we simulate a much more conservative cut in public investment by the Greek central government; (ii) a second scenario of a lower risk-premium, signalling, e.g., lower political and re-denomination risks, had the European Central Bank guaranteed its lending of last resort role earlier than 2012; (iii) finally, a similar financial envelope as the one adopted during the first Greek adjustment programme but over a longer period, moving beyond the standard IMF three-year duration programmes. We find that the mix of expenditure cuts and loss of confidence among households and firms explain a large part of the unanticipated costs of the adjustment in the Greek crisis.

A Markov regime switching model of crises and contagion: The case of the Iberian countries in the EMS

We develop a general econometric model of currency crises and contagion that integrates a number of important features appearing in many different models recently proposed in the literature. In particular, we consider a Markov regime switching vector autoregression conditional heteroskedastic model with time-varying transition probabilities allowing for shifting correlations. This model is used to study the case of the Portuguese escudo and the Spanish peseta during the EMS crisis. The results show that, in a crisis situation, the interest rate differential has different effects on the transition probability from the crisis state to the non-crisis state: a perverse effect for Portugal, and a positive effect for Spain. We also find strong evidence of contagion, mostly from the Spanish peseta to the Portuguese escudo, and to some extent from the Portuguese escudo to the Spanish peseta.

External bootstrap tests for parameter stability

Abstract This article considers tests for parameter stability over time in general econometric models, possibly nonlinear-in-variables. Existing test statistics are commonly not asymptotically pivotal under nonstandard conditions. In such cases, the external bootstrap tests proposed in this paper are appealing from a practical viewpoint. We propose to use bootstrap versions of the asymptotic critical values based on a first-order asymptotic expansion of the test statistics under the null hypothesis, which consists of a linear transformation of the unobserved “innovations” partial sum process. The nature of these transformations under nonstandard conditions is discussed for the main testing principles. Also, we investigate the small sample performance of the proposed bootstrap tests by means of a small Monte Carlo experiment.

Modelling the conditional volatility of commodity index futures as a regime switching process

AbstractCommodity index futures offer a versatile tool for gaining different forms of exposure to commodity markets. Volatility is a critical input in many of these applications. This paper examines issues in modelling the conditional variance of futures returns based on the Goldman Sachs Commodity Index (GSCI). Given that commodity markets tend to be ‘choppy’ (Webb, 1987), a general econometric model is proposed that allows for abrupt changes or regime shifts in volatility, transition probabilities which vary explicitly with observable fundamentals such as the basis, GARCH dynamics, seasonal variations and conditional leptokurtosis. The model is applied to daily futures returns on the GSCI over 1992–1997. The results show clear evidence of regime shifts in conditional mean and volatility. Once regime shifts are accounted for, GARCH effects are minimal. Consistent with the theory of storage, returns are more likely to switch to the high‐variance state when the basis is negative than when the basis is positive. The regime switching model also performs well in forecasting the daily volatility compared to standard GARCH models without regime switches. The model should be of interest to sophisticated traders who base their trading strategies on short‐term volatility movements, managed commodity funds interested in hedging an underlying diversified portfolio of commodities and investors of options and other derivatives tied to GSCI futures contracts. Copyright © 2001 John Wiley & Sons, Ltd.

A composite model of macro-economic functioning of China

A composite model of macroeconomic variables was constructed to simulate the quantitative relationships among economic growth, money supply, and inflation, and to provide an evaluation tool for government economic decision-making. This model is a composite one in that it is combination of an Econometric Model and Neural Network Models. Simultaneous simulation of the composite model indicates that its accuracy is higher than a general Econometric Model. Results show that inflation had negative impact on money supply, and its impact on M2 is stronger than that on M1. Income and price elasticities of money supply bear the expected signs, and those of M2 are larger than those of M1, respectively. It also has been revealed that during the 1980 s inflation did not exert a significant impact on economic growth.

A General Econometric Model of the Determinants of Library Subscription Prices of Scholarly Journals: The Role of Exchange Rate Risk and Other Factors

This article provides regression-based empirical evidence of the effect of variations in exchange rate risk on 1985 library prices of the top-ranked ninety-nine journals in economics. When modeling for the other known factors that have an impact on journal prices, changes in exchange rate risk from continental European publishers account for about 3.7 percent of the mean library journal price from such publishers. In addition, econometric findings reveal that a $1.00 increase in individual journal prices results in a $1.29 increase in library journal prices, confirming that individuals do switch demands to the library as individual subscription rates rise, creating the effect known as the commons tragedy. Also, increases in library journal prices are associated with the existence of illustrations, number of pages printed, and journal quality based on a composite of various citation measures. Decreases in journal prices are related to increases in journal age, greater economies of scale as created by higher circulation, and the existence of nonprofit motivations of publishers. Moreover, standardized regression coefficient results reveal that the setting of individual journal prices is of the greatest relative importance to other factors in the model in determining variations in library journal prices, followed by journal age, total pages printed, and journal quality. Contrary to recent conclusions in the literature, changes in journal circulation are found to have a relatively less important impact in determining variations in library journal prices. Library administrators may wish to pursue policy implications from the empirical findings concerning the reduc1. We are grateful for financial support from the Council on Library Resources under the council's Cooperative Research Program (CLR grant 8048), which made this research possible. Special thanks go to research assistant Vivek Pandey for his data collection efforts. Appreciation also goes to John Tagler of Elsevier Science Publishers B.V. (North-Holland), Jan Peterson of Academic Press, Georg Siebeck of J. C. B. Mohr (Paul Siebeck), Tubingen, and Ree Sherer of EBSCO for insights into the workings of the academic journal market and vendor services to libraries. Last, thanks go to four anonymous referees and the editor for their constructive comments. All errors,

Minimum chi-square estimation and tests for model selection

This paper studies the problem of model selection based on Pearson chi-square type statistics. Such goodness-of-fit statistics have been considered by Moore (1978) and diagnostic tests based on them have recently been extended to general econometric models by Andrews (1988a, b). Here we consider another important use of these statistics. Specifically, we propose some convenient asymptotically standard normal tests for model selection based on chi-square type statistics. Following Vuong (1989), the null hypothesis is that the competing models are equally close to the data-generating process (DGP) vs. the alternative hypotheses that one model is closer to the DGP where closeness of a model is measured according to the discrepancy implicit in the Pearson type statistic used. Our model selection tests have the desirable feature that neither model needs to be correctly specified nor nested in each other. As a prerequisite, we study the corresponding class of minimum chi-square estimators.

Communication to the Editor—A General Planning Model

A general econometric model for allocation of a set of activities to a set of spaces is proposed. Potential applications include engineering and economic planning at various levels from national, regional and urban development to industrial and building layouts and chemical or electronic systems design. Scheduling problems may also be handled. Current applications are to urban planning, hospital layouts, and building design.