Two-step Estimation Research Articles

On Band Stitching for Wideband Vector Measurements With Vector Signal Analyzers

As the bandwidth of radio signals increases significantly over the evolution of communication systems, the analysis bandwidth of many current instruments becomes insufficient. In this article, we study analysis bandwidth extension using the so-called band stitching. Specifically, we propose a two-step delay estimation method, which combines the cross correlation and an additional refining step to resolve the timing impairment between different sampling branches in postprocessing. We verify the method with a sequential measurement setup, using vector signal analyzers (VSAs). The result shows the necessity of conducting the refining step for getting a more accurate delay estimate to successfully recover the original wideband signal. Besides, a good agreement is found between the stitched data and the reference data in terms of the waveforms and error vector magnitude (EVM), which shows the effectiveness and robustness of the proposed calibration method in practice.

Does energy-efficiency label affect appliance price? Empirical analysis of the new national standard air conditioners in China

A new national standard (NS) for energy-efficiency labels has been released in China to improve the energy-efficiency requirements of household appliances. However, the impacts of the newly revised NS for air conditioners (ACs) on consumer preference and willingness to pay (WTP) remain unclear. Using data from a large e-commerce website in China, this study explores users’ preferences and WTP for the attributes of online stores, comments, and products pertaining to new NS ACs based on the hedonic price model (HPM), and uses the Heckman two-step estimation to correct for selection bias. The results show that the premium of the new NS energy-efficiency label estimated by the Heckman model is 6.24%, which is 23.71% lower than that estimated directly by the HPM. Online store attributes and comment attributes also affect the prices of new NS ACs. Furthermore, product attributes have effects on the prices of both new and old NS ACs, while online store attributes and comment attributes have greater effects on the old NS ACs. Finally, after the implementation of the new NS, the premium for the new NS energy-efficiency label is lower than that of the old one.

Two-step conditional least squares estimation for the bivariate Z -valued INAR(1) model with bivariate Skellam innovations

This article studies the two-step conditional least squares (CLS) estimation for the bivariate Z -valued INAR(1) model with bivariate Skellam innovations. For readers’ convenience, we first give a brief review of the bivariate Skellam distribution, bivariate signed thinning operator and the definition of the bivariate Z -valued INAR(1) model with bivariate Skellam innovations (denoted as the BSK-BINARS(1) model). Then, we discuss the stationarity and ergodicity of the BSK-BINARS(1) model, give some stochastic properties. Second, we discuss the two-step CLS estimate of the parameters and establish their large-sample properties. Third, we conduct a simulation study to illustrate the finite sample performances of the two-step CLS estimators, which are compared with those obtained by the plug-in method. Last but not least, we apply the BSK-BINARS(1) model on the zonal annual means temperature (*100).

Productivity determinants in the service industry: differences between high and low knowledge intensive sectors

PropósitoLa industria de servicios se ha convertido en un sector importante para el crecimiento económico, particularmente en los países en desarrollo. En este contexto, el objetivo de este artículo es comparar los determinantes de la productividad entre empresas que operan en sectores de servicios de baja y alta intensidad de conocimiento (LKIS y HKIS) en Ecuador.Diseño/metodología/enfoqueUtilizamos un método de estimación de dos pasos. En primer lugar, estimamos la productividad de las empresas y, en segundo lugar, los determinantes de la productividad. Para esto, utilizamos una base de datos de panel no balanceado sobre los estados financieros de las empresas formales ecuatorianas de los años 2007 a 2018.HallazgosNuestros resultados muestran que las empresas LKIS son ligeramente más intensivas en mano de obra en comparación con las empresas HKIS. Los determinantes de la productividad son similares entre las empresas HKIS y LKIS, excepto por las exportaciones y la concentración del mercado. Las empresas HKIS son más productivas cuando el nivel de competencia es bajo, lo que indica que un mayor poder de mercado está asociado con una mayor productividad. La influencia de los impuestos sobre la productividad depende del tamaño de la empresa. Las pequeñas y medianas empresas se ven más negativamente afectadas que las grandes empresas.Implicaciones prácticasLos impuestos deben diseñarse considerando el tamaño de las empresas, ya que podrían afectar su productividad. Por lo tanto, impuestos más bajos para las pequeñas y medianas empresas pueden reducir la desigualdad entre el tamaño de las empresas. Además, el conocimiento que tienen las HKIS debe extenderse a otras empresas convirtiéndose en una externalidad positiva en lugar de una barrera de entrada.Originalidad/valorA pesar de que los determinantes de la productividad del sector servicios se han explorado recientemente, en contraste con el sector manufacturero, los determinantes individuales y contextuales están menos identificados. En este artículo utilizamos un amplio conjunto de características de las empresas que podrían afectar la productividad en las empresas de servicios.

Two-Step Unbiased Estimation on Small-Delay Multipath of GNSS Signals Based on S-Curve Bias

Multipath error is among the main error sources of global navigation satellite systems (GNSSs). The traditional estimation method represented by the multipath estimating delay-locked loop (MEDLL) has difficulty in distinguishing small-delay multipath signals and noise during iterations, which leads to a bias in the estimation of small-delay multipath signals. To mitigate this small-delay multipath estimation bias, a two-step unbiased estimation method based on the S-curve bias (SCB) is proposed. First, the relationship among SCB, multipath parameters, and correlation spacing is derived. Second, a search approach based on the least squares is designed to obtain the turning point position of the SCB results with different correlation spacings. Third, the multipath delay can be estimated through the turning point of the SCB results. Finally, the phase and amplitude ratio of the direct signal and multipath signals is estimated by the SCB results of local carrier signal replicas with different phases. The proposed method does not contain iteration steps, which minimizes the accuracy influence introduced by the iterations. Simulations using the Spirent simulator and real signal experiment results show that the proposed algorithm can reduce the small-delay multipath error effectively with low computational complexity. Compared with MEDLL, Teager and Kaiser-MEDLL (TK-MEDLL), and high-resolution correlator (HRC) algorithms, the small-delay multipath mitigation performance of the proposed algorithm was improved by approximately 82.9%, 74.5%, and 91.7%, respectively. Therefore, the proposed algorithm can mitigate estimation bias in small-delay multipath signals effectively. This method provides a new strategy for the parametric estimation of the multipath signals of GNSS.

A unified inferring framework of multiplex epidemic networks under multiple interlayer interaction modes

Different epidemic transmissions on multiplex networks may interact and display intertwined effects, leading to a challenge and urgently needed problem of the inference of multiplex epidemic network structures under multiple interlayer interaction modes (IIMs). However, in reality, few existing studies have focused on multiplex epidemic network inference responding to the intertwined IIMs, much less the corresponding consistency analysis. To fill these two gaps, we first propose an inference framework of multiplex epidemic networks under a unified form of IIMs. In particular, we develop a Hamming distance-based two-step estimator for an intricate IIM called infection-probability-dependent interaction (IPDI). The proposed two-step estimator overcomes the problems of unobservable and time-varying variable inference in the IPDI mode. Second, we solve the theoretical difficulty of consistency analysis for the network inference under multiple IIMs and obtain sufficient conditions for exponentially decaying inferring error. Under the guarantee of consistently sufficient conditions, the sample size scale enables our framework's high-dimensional inferring ability. The synthetic network simulations show the validity of the proposed algorithm and consistency analysis. In addition, the analysis of real data of Twitter and Foursquare indicates the effectiveness and practicality of the proposed inferring framework.

Optimal Micro-PMU Placement for Improving State Estimation Accuracy via Mixed-integer Semidefinite Programming

Micro-phasor measurement units (µPMUs) with a micro-second resolution and milli-degree accuracy capability are expected to play an important role in improving the state estimation accuracy in the distribution network with increasing penetration of distributed generations. Therefore, this paper investigates the problem of how to place a limited number of µPMUs to improve the state estimation accuracy. Combined with pseudo-measurements and supervisory control and data acquisition (SCADA) measurements, an optimal µPMU placement model is proposed based on a two-step state estimation method. The E-optimal experimental criterion is utilized to measure the state estimation accuracy. The nonlinear optimization problem is transformed into a mixed-integer semidefinite programming (MISDP) problem, whose optimal solution can be obtained by using the improved Benders decomposition method. Simulations on several systems are carried out to evaluate the effective performance of the proposed model.

Exchange Rates and Macroeconomic Fundamentals: Evidence of Instabilities from Time-Varying Factor Loadings

We examine the relationship between exchange rates and macroeconomic fundamentals using a two-step maximum likelihood estimator through which we compute time-varying factor loadings. Factors are obtained as principal components, extracted from a large macro-dataset. Using 14 currencies over 1995–2018, we show that the loadings on the factors vary considerably over time with frequent sign changes. Allowing for time-varying loadings increases the percentage of explained variation in exchanges rates by an order of magnitude. Accounting for instabilities improves the predictive ability of the model globally and locally during crises, and yields better forecast of sign changes in exchange rates.

The effect of remittance inflows on inflation in developing economies

Inflation is a topic of great debate among economists due to its positive and negative effects on the economy. Remittance inflow is a crucial source of capital that is always welcomed by developing economies for its contribution to economic development and growth. However, remittance flows can increase inflation, resulting in negative effects on the economy. Therefore, the research question is: does remittance inflow increase inflation in developing economies? For the answer, the paper employs a two-step difference GMM Arellano-Bond estimator to study the effect of remittance inflow on inflation in 88 developing economies between 2002 and 2021. The robustness of estimates is tested by the defactored instrumental variables estimation. The results report that remittance inflow reduces inflation in developing economies. Furthermore, money supply and trade openness boost inflation, while economic growth decreases it. These findings suggest some policy implications for governments in developing economies in attracting remittance inflows as a channel to control inflation, thus contributing significantly to promoting economic activities in the country.

Confidence intervals for high-dimensional multi-task regression

Regression problems among multiple responses and predictors have been widely employed in many applications, such as biomedical sciences and economics. In this paper, we focus on statistical inference for the unknown coefficient matrix in high-dimensional multi-task learning problems. The new statistic is constructed in a row-wise manner based on a two-step projection technique, which improves the inference efficiency by removing the impacts of important signals. Based on the established asymptotic normality for the proposed two-step projection estimator (TPE), we generate corresponding confidence intervals for all components of the unknown coefficient matrix. The performance of the proposed method is presented through simulation studies and a real data analysis.

A Two-Step Estimation of GPS Differential Code Biases and Local Ionospheric TEC Based on Orthogonal Transformation

A Two-Step Estimation of GPS Differential Code Biases and Local Ionospheric TEC Based on Orthogonal Transformation

Data-driven varying state-space model based on thermal network for transient temperature field prediction of motorized spindles

• 1) Rapid prediction of the transient temperature distribution. • 2) Parameter estimation driven by FE simulation and experimental data. • 3) Accuracy validated by thermal images of undetectable regions. • 4) Real-time correction of temperature prediction bias. Analyzing and modeling the thermal characteristics of the spindle is crucial to improving the thermal stability and intelligence of CNC machine tools. However, there is a lack of accurate real-time prediction methods for the transient temperature distribution inside the spindle. In this study, a thermal network consisting of thermal capacitances and resistors is constructed based on the thermal structure of a motorized spindle, and a varying state-space (VSS) model varying with node temperature and rotational speed is proposed to solve the thermal network. The parameters of this model are determined by a two-step estimation process, driven by simulation data of a finite element (FE) model under specific boundary conditions and experimental sensor data obtained from a series of thermal tests. The validation based on thermal experiment shows that the VSS model has high prediction accuracy with the average root mean square (RMS) bias of 0.5141°C. Thermal images of the rotating shaft also show that the proposed VSS model maintains high accuracy in predicting the temperature of the undetectable regions. In addition, a temperature prediction system (TPS) with bias correction is constructed based on two built-in temperature sensors in the spindle to further improve prediction accuracy, with the RMS bias reduced by 10.4% to 0.4606°C. All the results show that the real-time temperature field distribution of motorized spindles can be rapidly, accurately, and completely inferred based on the rotational speed and a few temperature sensors. The proposed modeling approach has the potential to be integrated into edge computing devices of intelligent spindles.

Determinants of bank stability in Ethiopia: A two-step system GMM estimation

Determinants of bank stability in Ethiopia: A two-step system GMM estimation

Two-step estimation in linear regressions with adaptive learning

Weak consistency and asymptotic normality of the ordinary least squares estimator in a linear regression with adaptive learning is derived when the crucial, so-called, ‘gain’ parameter is estimated in a first step by nonlinear least squares from an auxiliary model.

Machine learning-assisted ensemble analysis for the prediction of urinary tract infection in elderly patients with ovarian cancer after cytoreductive surgery

Urinary tract infection (UTI) is a common type of postoperative infection following cytoreductive surgery for ovarian cancer, which severely impacts the prognosis and quality of life of patients. To develop a machine learning assistant model for the prevention and control of nosocomial infection. A total of 674 elderly patients with ovarian cancer who were treated at the Department of Gynaecology at Jingzhou Central Hospital between January 31, 2016 and January 31, 2022 and met the inclusion criteria of the study were selected as the research subjects. A retrospective analysis of the postoperative UTI and related factors was performed by reviewing the medical records. Five machine learning-assisted models were developed using two-step estimation methods from the candidate predictive variables. The robustness and clinical applicability of each model were assessed using the receiver operating characteristic curve, decision curve analysis and clinical impact curve. A total of 12 candidate variables were eventually included in the UTI prediction model. Models constructed using the random forest classifier, support vector machine, extreme gradient boosting, and artificial neural network and decision tree had areas under the receiver operating characteristic curve ranging from 0.776 to 0.925. The random forest classifier model, which incorporated factors such as age, body mass index, catheter, catheter intubation times, blood loss, diabetes and hypoproteinaemia, had the highest predictive accuracy. These findings demonstrate that the machine learning-based prediction model developed using the random forest classifier can be used to identify elderly patients with ovarian cancer who may have postoperative UTI. This can help with treatment decisions and enhance clinical outcomes.

Inference in regression discontinuity designs with high-dimensional covariates

Summary We study regression discontinuity designs in which many predetermined covariates, possibly much more than the number of observations, can be used to increase the precision of treatment effect estimates. We consider a two-step estimator which first selects a small number of ‘important’ covariates through a localised lasso-type procedure, and then, in a second step, estimates the treatment effect by including the selected covariates linearly into the usual local linear estimator. We provide an in-depth analysis of the algorithm’s theoretical properties, showing that, under an approximate sparsity condition, the resulting estimator is asymptotically normal, with asymptotic bias and variance that are conceptually similar to those obtained in low-dimensional settings. Bandwidth selection and inference can be carried out using standard methods. We also provide simulations and an empirical application.

Job prospects and labour mobility in China

China's structural changes have brought new challenges to its regional employment structures, entailing labour redistribution. Until now, Chinese migration research with a forward-looking perspective and on bilateral longitudinal determinants at the prefecture city level is almost non-existent. This paper investigates the effects of job prospects on individual migration decisions across prefecture boundaries. To this end, we created proxy variables for wage and employment prospects, introduced reference-dependence to a dynamic discrete choice model, and estimated corresponding empirical specifications with a unique quasi-panel of 66,427 individuals from 283 cities during 1997–2017. To address multilateral resistance to migration resulting from the future attractiveness, we exploited various monadic and dyadic fixed effects. Multilevel logit models and two-step system GMM estimation were adopted for the robustness check. Our primary findings are that a 10% increase in the ratio of sector-based employment prospects in cities of destination to cities of origin raises the probability of migration by 1.281–2.185 percentage points, and the effects tend to be stronger when the scale of the ratio is larger. Having a family migration network causes an increase of approximately 6 percentage points in migratory probabilities. Further, labour migrants are more likely to be male, unmarried, younger, or more educated. Our results suggest that the ongoing industrial reform in China influences labour mobility between cities, providing important insights for regional policymakers to prevent brain drain and to attract relevant talent.

Tax provision by international subsidiaries of Indian extractive industry multinationals: Do environmental pollution and corruption matter?

Outward foreign direct investment in the extractive industry increases the availability of metals and minerals that run the economic engine in the home country. It is unclear, however, whether tax provision by subsidiaries of emerging multinationals in extractive sectors respond to environmental pollution and corruption in the host country. In this paper we examine the tax provision in the host countries by subsidiaries of private sector based emerging multinationals in the extractive resources (metals and mining) sector. The analysis is carried out through a two-step system dynamic panel data GMM estimation, using data from 86 international subsidiaries of 15 Indian multinationals in 31 host countries for the period 2010 to 2019. Tax provisioning is found to be lesser in countries with higher environmental pollution. Tax provision is higher in countries with greater prevalence of corruption. However, the interactive effect suggests that in the presence of environmental pollution the subsidiary tax provisioning is higher in host countries if there is better control of corruption. This indicates that low corruption will offset a decline in tax provision from higher pollution. Furthermore, subsidiaries are found to have lesser tax provisioning when the parent firm has a tax dispute in the home country, implying the role of firm behaviour in shaping tax contribution by subsidiaries. The results are robust to the organization of subsidiaries through offshore financial centres.

Tensor response quantile regression with neuroimaging data.

Collecting neuroimaging data in the form of tensors (i.e. multidimensional arrays) has become more common in mental health studies, driven by an increasing interest in studying the associations between neuroimaging phenotypes and clinical disease manifestation. Motivated by a neuroimaging study of post-traumatic stress disorder (PTSD) from the Grady Trauma Project, we study a tensor response quantile regression framework, which enables novel analyses that confer a detailed view of the potentially heterogeneous association between a neuroimaging phenotype and relevant clinical predictors. We adopt a sensible low-rank structure to represent the association of interest, and propose a simple two-step estimation procedure which is easy to implement with existing software. We provide rigorous theoretical justifications for the intuitive two-step procedure. Simulation studies demonstrate good performance of the proposed method with realistic sample sizes in neuroimaging studies. We conduct the proposed tensor response quantile regression analysis of the motivating PTSD study to investigate the association between fMRI resting-state functional connectivity and PTSD symptom severity. Our results uncover non-homogeneous effects of PTSD symptoms on brain functional connectivity, which cannot be captured by existing tensor responsemethods.

Influence of internet and mobile usage on the institutional quality: An environmental perspective

Internet and mobile usages require digital tools that became familiar to all of us but whose industries create significant amount of CO2 emissions. The growing importance of communication channels usually enhances the institutional quality but it also generates a gradual increase in activities producing CO2 that, in turn, negatively affect the institutional quality – This embedded relationship led us to study conjointly these aspects in our empirical study. In this context, this article examines the influences of Internet usage, Mobile usage, and CO2 emissions on the institutional quality for a global sample of 87 economies. Through a two-step system GMM estimator, we show that Internet and mobile usage have a significant positive impact on the institutional quality while the CO2 emissions has a significant negative influence. The results are robust across six different institutional indicators and three subsamples including Low and Lower-Middle Income, Upper-Middle Income, and High-Income Economies. Our empirical research explores and discusses the complex influence of Internet and mobile usages on institutional quality through their environmental impacts suggesting that the latter jeopardizes the initial positive impact of Internet/mobile usage on institutional quality.