Model selection and misspecification in discrete choice welfare analysis

This study extends the work by Herriges and Kling (1997) to further evaluate the impact of discrete choice modelling techniques on welfare measures. Particularly, we evaluate the performance of the increasingly popular mixed logit model and the computational strategy for deriving discrete choice welfare measures. Our simulation results show that model misspecification can have profound effects on welfare measures. In general, the flexible mixed logit model performs relatively well in the presence of misspecification. However, when the nesting structure can be appropriately identified (via statistical tests and a priori knowledge/experience), the nested logit model provides more reliable welfare measures than the mixed logit model.     

Macroeconomic impacts of fiscal policy shocks in the UK: A DSGE analysis

This paper develops and estimates a new-Keynesian dynamic stochastic general equilibrium (DSGE) model for the analysis of fiscal policy in the UK. We find that government consumption and investment yield the highest GDP multipliers in the short-run, whereas capital income tax and public investment have dominating effect on GDP in the long-run. When nominal interest rate is at the zero lower bound, consumption taxes and public consumption and investment are found to be the most effective fiscal instruments throughout the analysed horizon, and capital and labour income taxes are established to be the least effective. The paper also shows that the effectiveness of fiscal policy decreases in a small open-economy scenario and that nominal rigidities improve effectiveness of public spending and consumption taxes, whereas decrease that of income taxes.     

Yield curve and the macroeconomy: Evidence from a DSGE model with housing

The slope of the yield curve has long been found to be a useful predictor of future economic activities, but the relationship is unstable. One change we have identified in this paper is that, between the early 1990s and the collapse of the housing market in 2007, movements at the long end of the yield curve have an increase in predictive power. We use a medium-scale DSGE model with a housing sector and a yield curve as a guide to find out the sources of such change. The model implies that an increase in the short-term interest rate and a decrease in the long-term interest rate have different impacts on the economy, and to use the slope as a predictor one needs to distinguish movements at the two ends of the yield curve. Based on simulated data from the model, we find that nominal wage rigidities and the capital adjustment costs are closely related to the predictive power of the yield curve. This result is further confirmed with actual data.     

Structural heterogeneity or asymmetric shocks? Poland and the euro area through the lens of a two-country DSGE model

This paper presents a two-country model linking Poland and the euro area and applies it for assessment of heterogeneity across these two regions. Overall, our results can be seen as rather inconclusive about the differences in parameters describing agents' decision-making in Poland and in the euro area. On the contrary, we find strong evidence for heterogeneity in terms of volatility and synchronization of shocks hitting both economies. Our results may be viewed as a step towards estimating the costs of Poland's entry to the European Monetary Union, associated with giving up the monetary autonomy and losing benefits from stabilizing movements of the exchange rate.     

The post-crisis slump in the Euro Area and the US: Evidence from an estimated three-region DSGE model

The global financial crisis (2008–09) led to a sharp contraction in both Euro Area (EA) and US real activity, and was followed by a long-lasting slump. However, the post-crisis adjustment in the EA and the US shows striking differences—in particular, the EA slump has been markedly more protracted. We estimate a three-region (EA, US and Rest of World) New Keynesian DSGE model (using quarterly data for 1999–2014) to quantify the drivers of the divergent EA and US adjustment paths. Our results suggest that financial shocks were key drivers of the 2008–09 Great Recession, for both the EA and the US. The post-2009 slump in the EA mainly reflects a combination of adverse aggregate demand and supply shocks, in particular lower productivity growth, and persistent adverse shocks to capital investment, linked to the continuing poor health of the EA financial system. Adverse financial shocks were less persistent for the US. The financial shocks identified by the model are consistent with observed performance indicators of the EA and US banking systems.     

Bootstrapping structural VARs: Avoiding a potential bias in confidence intervals for impulse response functions

Constructing bootstrap confidence intervals for impulse response functions (IRFs) from structural vector autoregression (SVAR) models has become standard practice in empirical macroeconomic research. The accuracy of such confidence intervals can deteriorate severely, however, if the bootstrap IRFs are biased. We document an apparently common source of bias in the estimation of the VAR error covariance matrix which can be easily reduced by a scale adjustment. This bias is generally unrecognized because it only affects the bootstrap estimates of the error variance, not the original OLS estimates. Nevertheless, as we illustrate here, analytically, with sampling experiments, and in an example from the literature, the bootstrap error variance bias can have significant distorting effects on bootstrap IRF confidence intervals. We also show that scale-adjusted bootstrap confidence intervals can be expected to exhibit improved coverage accuracy.     

Forecasting with preliminary data: a comparison of two methods

This study examines two alternate methods, a vector autoregression error correction model and a state space model, to forecast revised United States trade balance figures. Both these methods incorporate preliminary and revised trade data. The results obtained from these methods were compared to the benchmark forecasts generated by revised-data-only models. This Study finds that the state space model performs worse than the benchmark. The vector autoregression model performs better than the benchmark only in the one-step forecast. These results indicate that incorporating preliminary data may not be useful in forecasting the revised data.     

The transmission of financial shocks in an estimated DSGE model with housing and banking

We develop a dynamic stochastic general equilibrium (DSGE) model with housing and banking to study the transmission of financial shocks between the financial and real sectors. A deterioration in the bank's balance sheet induced by financial shocks could have amplified and persistent impacts on real activities. The amplification of the shocks are originated from financial frictions tied to households and banks. We find that a disruption in bank net worth initiated by capital quality shocks generates a decline in household loans, house prices and output. Bank liquidity shocks also have negative effects on these variables. Housing preference shocks could generate a positive comovement between house prices and output. All these findings are qualitatively consistent with empirical evidence, suggesting that these financial shocks are critical to the dynamics of house prices and other macroeconomic variables.     

The EAGLE. A model for policy analysis of macroeconomic interdependence in the euro area

We develop a 4-region macroeconomic model of the euro area and the world economy. The model (EAGLE, Euro Area and Global Economy model) is microfounded and designed for conducting quantitative policy analysis of macroeconomic interdependence across regions in the euro area and between the euro area and the world economy. Specifically, we simulate a permanent reduction in labor tax rates in the euro area. The effects on real activity are expansionary in both the short run and long run. Implementing reforms simultaneously across regions would produce extra benefits and make the macroeconomic performance in the euro area more even.     

The effects of wind generation capacity on electricity prices and generation costs: a Monte Carlo analysis

We use Monte Carlo analysis to examine the potential of increased renewable generation to provide a hedge against variability in energy prices and costs. Fuel costs, electricity demand and wind generation are allowed to vary and a unit commitment and economic dispatch algorithm is employed to produce cost-minimizing generation schedules under different levels of installed wind capacity. Increased wind capacity reduces the mean and the variance of production costs but only the variance of electricity prices. Wind generators see their market revenues increase while consumer payments and fossil generator profits do not considerably vary as wind capacity increases. Risk aversion is captured by considering the conditional value-at-risk for both consumers and producers. The optimal level of wind generation increases as risk aversion increases due to the potential of wind to act as a hedge against very high electricity prices in high fuel price scenarios.     

Forecasting the output of integrated circuit industry using a grey model improved by the Bayesian analysis

The production values of the integrated circuit industry has the following attributes, short product life cycle, numerous influencing factors on the market, and rapid changing of technology. These features obstruct the precision of forecasting the outputs of integrated circuit industry using the traditional statistical methods. The grey forecast model can obviously conquer these difficulties with a small sample set and ambiguity of available information. This study evaluates original and Bayesian grey forecast models for the integrated circuit industry. Bayesian method uses the technique of Markov Chain Monte Carlo to estimate the parameters for grey differential function. The predictive value of integrated circuit in Taiwan was evaluated along with mean absolute percentage error. Various parameters and efficiency of three forecast models were compared and summary outcomes were reported. Meanwhile, the Bayesian grey model was the most accurate one among these models.     

The effect of observables,functional specifications,model features and shocks on identification in linearized DSGE models

The decisions a researcher makes at the model building stage are crucial for parameter identification. This paper contains a number of applied tips for solving identifiability problems and improving the strength of DSGE model parameter identification by fine-tuning the (1) choice of observables, (2) functional specifications, (3) model features and (4) choice of structural shocks. We offer a formal approach based on well-established diagnostics and indicators to uncover and address both theoretical (yes/no) identifiability issues and weak identification from a Bayesian perspective. The concepts are illustrated by two exemplary models that demonstrate the identification properties of different investment adjustment cost specifications and output-gap definitions. Our results provide theoretical support for the use of growth adjustment costs, investment-specific technology, and partial inflation indexation.     

Monetary policy in Germany: A cointegration analysis on the relevance of interest rate rules

The paper attempts to identify an empirical relationship that characterizes the way the Bundesbank adjusted its short-term rate with respect to various objectives. By building on a careful exploration of the properties of the variables involved, it is established that interest rate rules —often remarkably similar to the Taylor rule— remain valid and relevant in a Vector Error Correction framework, and thereby proposing a distinctive interpretation of German monetary policy during the period 1975–1998.     

A cost-benefit analysis of the random assignment UK Employment Retention and Advancement Demonstration

This article presents a cost-benefit analysis of Britain’s Employment Retention and Advancement (ERA) demonstration, which was evaluated through the first large-scale randomized control trial in the UK. ERA used a combination of job coaching and financial incentives in attempting to help long-term unemployed men and low-income lone parents sustain employment and progress in work once they were employed. Using both administrative and survey data, ERA’s effects on benefits and costs were estimated through impact analyses, which exploited the experimental design. The findings indicated that ERA was cost beneficial for long-term unemployed adult men, but not for lone parents. The key findings appear robust to sensitivity tests. Uncertainty, as implied by the SEs of the estimated impacts, was addressed through a Monte Carlo analysis, an approach seldom previously used in cost-benefit analyses of social programs.     

Financial development shocks and contemporaneous feedback effect on key macroeconomic indicators: A post Keynesian time series analysis

In this paper we take into account the role of the banking system, credit and stock market in stimulating aggregate demand in post Keynesian tradition. According to the results of impulse response analysis; it appears all three financial development indicators contributed as expected in improving macroeconomic performance of South Korean economy. Stock market capitalisation and domestic credit availability are strongly responsible for stimulation of investment, saving and productivity Growth in Hong Kong. The UK financial system seems vulnerable to future shocks, whether by shocks in the credit markets or stock markets.     

Knowledge flows and the geography of networks: A strategic model of small world formation

This paper aims to demonstrate that the strategic approach to link formation can generate networks that share some of the main structural properties of most real social networks. For this purpose, we introduce a spatialized variation of the Connections model [Jackson, M.O., Wolinsky, A., 1996. A strategic model of social and economic networks. Journal of Economic Theory 71, 44–74] to describe the strategic formation of links by agents who balance the benefits of forming links resulting from imperfect knowledge flows against their costs, which increase with geographic distance. We show, for intermediate levels of knowledge transferability, clustering occurs in geographical space and a few agents sustain distant connections. Such networks exhibit the small world property (high clustering and short average relational distances). When the costs of link formation are normally distributed across agents, asymmetric degree distributions are also obtained.     

Determinants of violent and property crimes in England and Wales: a panel data analysis

We examine various determinants of property and violent crimes by using police force area level (PFA) data on England and Wales over the period of 1992–2008. Our list of potential determinants includes two law enforcement variables namely crime-specific detection rate and prison population, and various socio-economic variables such as unemployment rate, real earnings, proportion of young people and the Gini Coefficient. By adopting a fixed effect dynamic GMM estimation methodology we attempt to address the potential bias that arises from the presence of time-invariant unobserved characteristics of a PFA and the endogeneity of several regressors. There is a significant positive effect of own-lagged crime rate. The own-lagged effect is stronger for property crime, on an average, than violent crime. We find that, on an average, higher detection rate and prison population leads to lower property and violent crimes. This is robust to various specifications. However, socio-economic variables with the exception of real earnings play a limited role in explaining different crime types.     

Nonlinearities in the real exchange rates: new evidence from developed and developing countries

This paper investigates nonlinearities in the dynamics of real exchange rates. We use Monte Carlo simulations to establish the size properties of the Teräsvirta-Anderson test, when the dynamics of the real exchange rate is influenced by an exogenous process. In addition, we show that a modified nonlinearity test, which includes additional right-hand-side variables, performs much better than the original in both Monte Carlo exercises and in the actual data on 1431 bilateral real exchange rate series. Finally, we investigate the dynamics of the real exchange rate for both developed and developing countries using the modified test for the recent floating period. In general, the results find a greater incidence of nonlinear dynamics for developing country real exchange rates.     

Hospital costs associated with intraoperative hypotension among non-cardiac surgical patients in the US: a simulation model

Objective: Recent studies indicate intraoperative hypotension, common in non-cardiac surgical patients, is associated with myocardial injury, acute kidney injury, and mortality. This study extends on these findings by quantifying the association between intraoperative hypotension and hospital expenditures in the US.

Methods: Monte Carlo simulations (10,000 trial per simulation) based on current epidemiological and cost outcomes literature were developed for both acute kidney injury (AKI) and myocardial injury in non-cardiac surgery (MINS). For AKI, three models with different epidemiological assumptions (two models based on observational studies and one model based on a randomized control trial [RCT]) estimate the marginal probability of AKI conditional on intraoperative hypotension status. Similar models are also developed for MINS (except for the RCT case). Marginal probabilities of AKI and MINS sequelae (myocardial infarction, congestive heart failure, stroke, cardiac catheterization, and percutaneous coronary intervention) are multiplied by marginal cost estimates for each outcome to evaluate costs associated with intraoperative hypotension.

Results: The unadjusted (adjusted) model found hypotension control lowers the absolute probability of AKI by 2.2% (0.7%). Multiplying these probabilities by the marginal cost of AKI, the unadjusted (adjusted) AKI model estimated a cost reduction of $272 [95% CI?=?$223–$321] ($86 [95% CI?=?$47–$127]) per patient. The AKI model based on relative risks from the RCT had a mean cost reduction estimate of $281 (95% CI?=?–$346–$750). The unadjusted (adjusted) MINS model yielded a cost reduction of $186 [95% CI?=?$73–$393] ($33 [95% CI?=?$10–$77]) per patient.

Conclusions: The model results suggest improved intraoperative hypotension control in a hospital with an annual volume of 10,000 non-cardiac surgical patients is associated with mean cost reductions ranging from $1.2–$4.6 million per year. Since the magnitude of the RCT mean estimate is similar to the unadjusted observational model, the institutional costs are likely at the upper end of this range.     

Student-t distribution based VAR-MGARCH: an application of the DCC model on international portfolio risk management

Significant second-moment transmission effects and obvious time-varying patterns of correlation coefficients among major equity and currency markets in the US, Japan and the UK are found to exist. Such observations inspire the time-varying setting of dynamic conditional correlation coefficients in MGARCH models. On the other hand, the multivariate Student-t distribution is suitable for analysing the visible leptokurtosis that is common in financial markets. Both are important for international portfolio risk management. Thus, a comparison on the hedging efficiency of hypothetical portfolios consisting of stock and currency future positions is conducted in order to justify the multivariate Student-t distribution based on the DCC-MGARCH model.