Bootstrapping Financial Time Series

It is well known that time series of returns are characterized by volatility clustering and excess kurtosis. Therefore, when modelling the dynamic behavior of returns, inference and prediction methods, based on independent and/or Gaussian observations may be inadequate. As bootstrap methods are not, in general, based on any particular assumption on the distribution of the data, they are well suited for the analysis of returns. This paper reviews the application of bootstrap procedures for inference and prediction of financial time series. In relation to inference, bootstrap techniques have been applied to obtain the sample distribution of statistics for testing, for example, autoregressive dynamics in the conditional mean and variance, unit roots in the mean, fractional integration in volatility and the predictive ability of technical trading rules. On the other hand, bootstrap procedures have been used to estimate the distribution of returns which is of interest, for example, for Value at Risk (VaR) models or for prediction purposes. Although the application of bootstrap techniques to the empirical analysis of financial time series is very broad, there are few analytical results on the statistical properties of these techniques when applied to heteroscedastic time series. Furthermore, there are quite a few papers where the bootstrap procedures used are not adequate.     

Funding a PAYG pension system: the case of Italy

Italy is characterised by a mature pay‐as‐you‐go social security system and by particularly adverse population projections. Given these trends, the social security contribution rate is expected to increase above its current high level. This hinders the development of employer‐provided pension funds and introduces a significant wedge between labour cost and earnings that discourages both labour demand and labour supply. Any proposal to reduce payroll taxes and to reform the system in the direction of partial funding has to cope with the state of Italian public finances. Italy has to comply with the Stability and Growth Pact that imposes constraints on budget deficit and debt trends. Using micro data from the Bank of Italy's Survey of Household Income and Wealth and official population projections, we estimate future employment trends under different demographic and macroeconomic scenarios and compute the cost of the transition. We show that it would be substantially reduced if positive effects on employment were induced by the payroll tax reduction.     

Tax Discounting in a High‐debt Economy*

This paper estimates a consumption function for Belgium that allows for government debt discounting and for the overall discounting of the future (reflecting the consumers’ planning horizon or precautionary savings). It also allows for substitutability or complementarity effects from government expenditures. Results suggest that consumers do take into account (future) government activity. Ricardian Equivalence is rejected however, since we cannot reject a relatively short planning horizon or a precautionary savings motive for the consumers. We use bootstrapped distributions for inference since the instrumental variables estimators used may have non‐standard distributions. This procedure also helps to tackle potential endogeneity and sample size problems.     

Preliminary negotiations as an indicator of the context and the utilization of research: A case study

According to Komter, the consultations necessary to get permission to investigate a certain group can provide information as to the research subject and the prospects that the people to be examined believe to have in their circumstances. In this paper it will be made clear that these ‘preliminary investigations’ can provide more than these two kinds of information. On the basis of a case study it will be demonstrated that: (1) the reasons provided by the people involved for not being able to participate in the research as such, or in its proposed form, at least provide some information about the context in which the empirical research will have to take place; (2) this context may suggest in what way the results of the research will possibly be utilized by the people examined. I am grateful to Pieter Bak for presenting me with the necessary information for this article and to Sara Delamont and Paul Atkinson for their helpful comments and suggestions.     

Explaining the US–EU productivity growth gap: Structural change vs. intra-sectoral effect

This paper proposes a decomposition of labour productivity growth in the EU15 and the the US since the mid 1990s. The results suggest that the EU's relative slowdown is due to modest “pure” gains of productivity within sectors.     

Sources of crime in the state of Veracruz: The role of female labor force participation and wage inequality

Abstract

In recent years, crime has become a serious concern in Mexico as its increase has detrimentally affected government institutions and economic growth. There is considerable speculation among policy analysts about the causes of the increase in crime. Whereas some analysts attribute the increase to a rise in income inequality, others believe internal migration and a loss of morals are the roots of criminal behavior. This research shows that at least for the Mexican state of Veracruz, wage inequality and labor force participation have an important impact on crime. When gender is considered, however, the impact is more complicated than it seems. An increase in women's labor force participation decreases the overall number of alleged violent offenders. However, the number of alleged rapists and grievous bodily harm offenders increases as women's wage distribution improves. The results shed light on the gender dimensions of the economics of crime.     

A within-trial cost-effectiveness analysis of panitumumab compared with bevacizumab in the first-line treatment of patients with wild-type RAS metastatic colorectal cancer in the US

Abstract

Aims: This analysis investigated the cost-effectiveness of panitumumab plus mFOLFOX6 (oxaliplatin, 5-fluorouracil, and leucovorin) compared with bevacizumab plus mFOLFOX6 in the first-line treatment of patients with wild-type RAS metastatic colorectal cancer (mCRC).

Materials and methods: The cost-effectiveness analysis was developed from a third-party payer perspective in the US and was implemented using a partitioned survival model with health states for first-line treatment (progression-free), disease progression with and without subsequent active treatment, and death. Survival analyses of patients with wild-type RAS mCRC from the PEAK head-to-head clinical trial of panitumumab vs bevacizumab were performed to estimate time in the model health states. Additional data from PEAK informed the amount of each drug consumed, duration of therapy, subsequent therapy use, and toxicities related to mCRC treatment. Literature and US public data sources were used to estimate unit costs associated with treatment and duration of subsequent active therapies. Utility weights were calculated from patient-level data from panitumumab trials in the first-, second-, and third-line settings. A life-time perspective was taken with future costs and outcomes discounted at 3% per annum. Scenario, one-way, and probabilistic sensitivity analyses were performed.

Results: Compared with bevacizumab, the use of panitumumab resulted in an incremental cost of US $60,286, and an incremental quality-adjusted life-year (QALY) of 0.445, translating into a cost per QALY gained of US $135,391 in favor of panitumumab. Results were sensitive to wastage and dose rounding assumptions modeled.

Limitations: Progression-free and overall survival were extrapolated beyond the follow-up of the primary analysis using fitted parametric curves. Costs and quality of life were estimated from multiple and different data sources.

Conclusions: The efficacy of panitumumab in extending progression-free and overall survival and improving quality of life makes it a cost-effective option for first-line treatment of patients with wild-type RAS mCRC compared with bevacizumab.     

On bootstrapping panel factor series

This paper studies the asymptotic validity of sieve bootstrap for nonstationary panel factor series. Two main results are shown. Firstly, a bootstrap Invariance Principle is derived pointwise in i$i$, obtaining an upper bound for the order of truncation of the AR polynomial that depends on n$n$ and T$T$. Consistent estimation of the long run variances is also studied for (n,T)→∞$(n,T)\to \infty$. Secondly, joint bootstrap asymptotics is also studied, investigating the conditions under which the bootstrap is valid. In particular, the extent of cross sectional dependence which can be allowed for is investigated. Whilst we show that, for general forms of cross dependence, consistent estimation of the long run variance (and therefore validity of the bootstrap) is fraught with difficulties, however we show that “one-cross-sectional-unit-at-a-time” resampling schemes yield valid bootstrap based inference under weak forms of cross-sectional dependence.     

Short-run forecasting of the euro-dollar exchange rate with economic fundamentals

We propose a fundamentals-based econometric model for the weekly changes in the euro-dollar rate with the distinctive feature of mixing economic variables quoted at different frequencies. The model obtains good in-sample fit and, more importantly, encouraging out-of-sample forecasting results at horizons ranging from one-week to one month. Specifically, we obtain statistically significant improvements upon the hard-to-beat random-walk model using traditional statistical measures of forecasting error at all horizons. Moreover, our model obtains a great improvement when we use the direction of change metric, which has more economic relevance than other loss measures. With this measure, our model performs much better at all forecasting horizons than a naive model that predicts the exchange rate as an equal chance to go up or down, with statistically significant improvements.