Search results

When there are few treated clusters in a pure treatment or difference-in-differences setting, t tests based on a cluster-robust variance estimator can severely over-reject. Although procedures based on the wild cluster bootstrap often work well when the number of treated clusters is not too small, they can either over-reject or under-reject seriously when it is. In a previous paper, we showed that procedures based on randomization inference (RI) can work well in such cases. However, RI can be impractical when the number of possible randomizations is small. We propose a bootstrap-based alternative to RI, which mitigates the discrete nature of RI p values in the few-clusters case. We also compare it to two other procedures. None of them works perfectly when the number of clusters is very small, but they can work surprisingly well.

Classical unit root tests are known to suffer from potentially crippling size distortions, and a range of procedures have been proposed to attenuate this problem, including the use of bootstrap procedures. It is also known that the estimating equation’s functional form can affect the outcome of the test, and various model selection procedures have been proposed to overcome this limitation. In this chapter, the authors adopt a model averaging procedure to deal with model uncertainty at the testing stage. In addition, the authors leverage an automatic model-free dependent bootstrap procedure where the null is imposed by simple differencing (the block length is automatically determined using recent developments for bootstrapping dependent processes). Monte Carlo simulations indicate that this approach exhibits the lowest size distortions among its peers in settings that confound existing approaches, while it has superior power relative to those peers whose size distortions do not preclude their general use. The proposed approach is fully automatic, and there are no nuisance parameters that have to be set by the user, which ought to appeal to practitioners.

The main purpose of this paper is to determine the bias-corrected efficiencies and rankings of the selected hotels and restaurants (H&Rs) in India.

The data for the Indian H&R sector are collected from the Prowess database. The bootstrap data envelopment analysis (DEA) based on a constant return to scale (CRS), variable return to scale-input oriented (VRS-IP) and variable return to scale-output oriented (VRS-OP) are applied on H&Rs to obtain the bias-corrected efficiencies.

It is found that relative efficiencies using basic DEA methods of all the 45 H&Rs of India are overestimated. These efficiencies are corrected using bias correction through bootstrap DEA methods. The bounds for the efficiencies of each H&R are computed using all the adopted methods. All H&Rs are ranked using bias-corrected efficiencies, and the linear trend between ranks suggests that the H&Rs are ranked almost similarly by all the adopted methods.

To improve efficiency, Indian H&R companies must rethink their personnel needs by enhancing their workforce management capabilities. The government needs to extend more support to this sector by introducing a liberal legislation framework and supporting infrastructure policies.

There is a paucity of studies on H&Rs in India. The current study focused on measuring bias-corrected efficiencies of the selected H&Rs of India. This study is one of the few initiatives to explore bias-corrected efficiencies extensively using the bootstrap DEA method.

The aim of this paper is to make sense of the “funding gap” by exploring how and why informal entrepreneurial finance is made available to entrepreneurs. By challenging the epistemological and ontological assumptions of the “funding gap”, an enactment perspective of entrepreneurial finance, supported by a social constructionist stance, is proposed in this paper.

The study on which this paper reports was conducted through a longitudinal fieldwork process. Networks in two Chinese cities, Shanghai and Hong Kong, were chosen because of their differences in institutional context yet exceptionally high level of entrepreneurial activities.

This paper highlights the active role entrepreneurs play in managing their financial needs in the process of new venture creation. The results show that entrepreneurs are actively managing the demand as well as supply of entrepreneurial finance to narrow the “funding gap”. Furthermore, individuals work to fill the funding gap by creating required start‐up capital. In other words, the “funding gap” is not static or concrete; rather it is dynamic, manageable and in many cases is within individuals' power and ability to overcome.

The findings of this paper are particularly important to all stakeholders, including policy makers, educators, researchers, entrepreneurs and nascent entrepreneurs.

This paper contributes to the conceptual, methodological and practical knowledge in advancing understanding of the “funding gap”. First, it provides insight into the relationship between entrepreneurs and their environment that shapes the “funding gap”. Second, the findings suggested that a positive, supportive enterprise culture can be particularly useful in driving individuals towards entrepreneurship. Third, in terms of methodology, the author argues that an “inside‐looking‐lout”, interpretive, multi‐stage fieldwork and network as unit of analysis is particularly distinctive in revealing the complex process of managing entrepreneurial finance in the process of new venture creation.

Quality function deployment (QFD) is a planning methodology to improve products, services and their associated processes by ensuring that the voice of the customer has been effectively deployed through specified and prioritised technical attributes (TAs). The purpose of this paper is two ways: to enhance the prioritisation of TAs: computer simulation significance test; and computer simulation confidence interval. Both are based on permutation sampling, bootstrap sampling and parametric bootstrap sampling of given empirical data.

The authors present a theoretical case for the use permutation sampling, bootstrap sampling and parametric bootstrap sampling. Using a published case study the authors demonstrate how these can be applied on given empirical data to generate a theoretical population. From this the authors describe a procedure to decide upon which TAs have significantly different priority, and also estimate confidence intervals from the theoretical simulated populations.

First, the authors demonstrate not only parametric bootstrap is useful to simulate theoretical populations. The authors can also employ permutation sampling and bootstrap sampling to generate theoretical populations. Then the authors obtain the results from these three approaches. qThe authors describe why there is a difference in results of permutation sampling, bootstrap and parametric bootstrap sampling. Practitioners can employ any approach, it depends how much variation in FWs is required by quality assurance division.

Using these methods provides QFD practitioners with a robust and reliable method for determining which TAs should be selected for attention in product and service design. The explicit selection of TAs will help to achieve maximum customer satisfaction, and save time and money, which are the ultimate objectives of QFD.

The aim of this work is to implement bootstrapping methods into software tools, based on Java.

This paper presents a category of software e‐tools aimed at simulating laboratory works and experiments.

Both students and teaching staff use traditional statistical methods to infer the truth from sample data gathered in laboratory experiments. However, the repeated laboratory experiments mean the consumption of a great deal of substances and reactants. At the same time, there are some ethically motivated reasons to reduce the number of animals used in experimentation. Using a bootstrapping tool and computer power, the experimenter can repeat the original experiment on computer, obtaining pseudo‐data as plausible as those obtained from the original experiment.

Provides data on implementing bootstrapping methods into software e‐tools, simulating laboratory experiments in didactic and research activities.

The aim of this paper is to test the existence of bubbles for the daily prices of cryptocurrencies Bitcoin and Ethereum and verify if there is a relationship between bubbles and volatility regimes.

The authors test the presence of bubbles with the generalized supremum augmented Dickey–Fuller (GSADF) test using critical values simulated by the bootstrap procedures of Gutierrez (2011), Harvey et al. (2016) and Pedersen and Schütte (2020). Also, the authors estimate Markov regime switching generalized autoregressive conditional heteroskedasticity model for these cryptocurrencies.

The GSADF test result indicates the presence of bubbles for both cryptocurrencies. Simulating critical values by wild-bootstrap, which is robust to non-stationary volatility, leads to the highest number of bubbles in both cryptocurrencies. In addition, based on the estimates of conditional variance models with regime changes, the authors find that the bubbles identified are associated with a regime of low returns volatility, indicating a change in the trade-off between risk and return when the prices of cryptocurrencies differ from their fundamental values.

To the best of the authors knowledge, there are no studies that test the explosive behavior for cryptocurrencies by the GSADF test using the bootstrap method to simulate critical values from the procedures of Harvey et al. (2016) or Pedersen and Schütte (2020). These bootstrapping procedures are robust to heteroscedasticity and avoid the detection of false bubbles. Further, the advantage of Harvey et al. (2016) procedure is the robustness to non-stationary volatility.

In all existing theoretical papers on causality it is assumed that the lag length is known a priori. However, in applied research the lag length has to be selected before testing for causality. The purpose of this paper is to suggest that in investigating the effectiveness of various Granger causality testing methodologies, including those using bootstrapping, the lag length choice should be endogenized, by which we mean the data‐driven preselection of lag length should be taken into account.

The size and power of a bootstrap test with endogenized lag‐length choice are investigated by simulation methods. A statistical software component is produced to implement the test, which is available online.

The simulation results show that this test performs well. An application of the test provides empirical support for the hypothesis that the UAE financial market is integrated with the US market.

The empirical results based on this test are expected to be more precise.

This paper considers a bootstrap test for causality with endogenous lag order. This test has superior properties compared to existing causality tests in terms of size, with similar if not better power and it is robust to ARCH effects that usually characterize financial data. Practitioners interested in causal inference based on time series data might find the test valuable.

The purpose of this paper is to develop a more robust methodology for asset allocation for the property investment market which takes into account inherent valuation and data issues.

The methodology applied is that of a bootstrap, borrowed from Carlstein, and is applied to an investment universe consisting of UK equities, gilts and property. The bootstrap selectively re‐samples the return time series by maintaining the economic cycle. The resulting return series is then used in the standard mean‐variance optimisation (MVO) on an unconstrained basis. Finally, a “sanity” test is applied on the correlation matrix to ensure that spurious instances do not skew the results.

The bootstrapped optimisation provides a range within which the portfolio weights can be manoeuvred instead of a static point under the standard MVO. It provides a more robust methodology for asset allocation and without giving any undue significance to one year of extreme result.

The current analysis is based on unconstrained portfolio optimisation, with a very limited investment universe. Additionally, by conforming with the MVO methodology, normality of asset returns is implicitly assumed, which is clearly not the case in the data used. Future work will also focus on an all‐property portfolio.

The proposed methodology will prove to be useful for making asset allocation decisions, particularly in turbulent financial markets.

The paper focuses solely on bootstrapping with the IPD UK annual index and is particularly significant after one year of extremely poor performance of UK property. The results will be of use to fund managers and portfolio analysts.

There are many types of the ADCs implemented in the mobile and wireless devices. Most of these devices are battery operated and operational at low input voltage. SAR ADC is popular for its low power operations and simple architecture. Scientists are still working to make its working faster under the same low power area. There are many SAR-ADC implemented in the past two decades, but still, there is a big room for dual SAR-ADC.

The authors are presenting a dual SAR-ADC with a smaller number of components and blocks. The proposed ultra-low-power circuit of the SAR-ADC consists of four major blocks, which include Bee-bootstrap, Spider-Latch dual comparator, dual SAR-logic and dual digital to analog converter. The authors have used the 90-nm CMOS library for the construction of the design.

The power breaks down of the comparator are dramatically improved from 0.006 to 0.003 uW. The ultimate design has 5 MHz operating frequency with 25 KS/s sampling frequency. The supply voltage is 1.2 V with 35.724 uW power consumption. Signal-to-noise and distortion ratio and spurious-free dynamic range are 65 and 84 dB, respectively. The Walden's figure of merits calculated 7.08 fj/step.

The authors are proposing two-in-one circuit for SAR-ADC named as “dual SAR-ADC”, which obeys the basic equation of duality, derived and proved under the heading of proposed solution. It shows a clear difference between the performance of two circuit-based ADC and one dual circuit ADC. The number of components is reduced by sharing the work load of some key components.