Alternative Estimation Methods Research Articles

The effect of employer tenure on wages in Japan

We estimate the effects of employer tenure on wages using the instrumental variable (IV) methodology by analyzing data from the Japan Household Panel Survey and Keio Household Panel Survey from 2004 to 2014. We find that the estimates based on the IV method, which corrects for omitted variable bias due to individuals’ unobserved abilities and unobserved matching qualities, are significantly lower than those found using the ordinary least squares methodology. These results are robust across subsamples and specifications and cannot be rejected using an alternative estimation method. Our findings suggest that the recent returns on employer tenure in the Japanese labor market are likely to be lower than those discussed in previous studies.

Robust estimation of the distributed lag model with multicollinearity and outliers

The use of Almon technique is encouraged for estimation of the distributed lag model (DLM) to avoid some serious problems associated with the direct application of the ordinary least squares (OLS) method. In Almon technique, the OLS procedure is applied on the transformed regressors which may be correlated themselves. To tackle this issue, the use of ordinary ridge regression estimator (ORRE) combined with the Almon technique has been considered as an alternative approach in the literature. However, the ORRE may be sensitive to outliers in the y-direction and thus, its use combined with the Almon technique may raise doubts on the estimated lag coefficients. The present work addresses this issue and suggests an alternative estimation method for the DLM, which is robust in the presence of multicollinearity and outliers. The performance of the proposed estimator has been evaluated through an extensive Monte Carlo simulation study and empirical findings are presented using the mean squared error criterion. The results reveal an attractive performance of the proposed estimator in the presence of outliers.

Using an Alternative Method to Estimate Overcount for Census 2021.

ObjectivesThe project aimed to test an alternative method to estimate the number of duplicate responses in the 2021 England and Wales Census. The method utilises information from all census records instead of relying on samples. It requires less clerical review than the original inverse sampling method used for overcount estimation. ApproachWe used the Splink implementation of Fellegi-Sunter to match the 2021 Census to itself. The resulting linked dataset was filtered to retain only the top scoring record pair for each unique census record, giving a final dataset of around 71.5 million record pairs. These pairs were divided by score into 13 homogeneous buckets. Random samples of 1000 pairs per bucket were clerically reviewed to determine whether each pair was a true duplicate or not. The clerical results were used to assign an estimated probability of being a duplicate to each bucket and hence to every census record within the bucket. ResultsA dashboard was created which contained percentages of duplicates by region and ‘overcount group’ for the original and alternative methods. This enabled us to view the data side by side and create visualisations to aid analysis. The alternative method had higher average duplicate percentages in overcount groups for communal establishments and was also higher for 9 out of 10 regions in the armed forces overcount group. We found that both the original and alternative methods of overcount estimation followed the same pattern in terms of minimum and maximum duplicate percentages except for those in communal establishments where minimum and maximums were both higher than the original method. Additionally, the minimum was marginally higher for the student and armed forces overcount groups for the alternative method. ConclusionOn initial comparison, estimated rates of duplication resulting from the different methods are comparable. We plan to conduct further analysis on the similarities and differences of the two methods, and research whether the new method could be applied to estimate the duplication rate in other large datasets including administrative data.

Cultural norms and women’s health: Implications of the practice of menstrual restrictions in Nepal

We study the association between the ritual of menstrual restrictions and maternal healthcare access in Nepal as similar restrictions are also practised around the time of childbirth. These restrictions are based on the assumption that women are ritually impure during both menstruation and childbirth. Our outcomes of interest include the likelihood of giving birth at home and receiving no trained medical assistance at childbirth. We use a rich set of controls as well as assess the sensitivity of our results to alternative estimation methods. We find that women who face any menstrual restriction are also more likely to give birth at home and receive assistance only from untrained individuals during childbirth, which potentially increases the risk of maternal mortality. These findings indicate that menstrual restriction related rituals can have persistent negative implications on women’s physical health that is not just limited to the time of menstruation.

The effect of financial distress on capital structure: The case of Brazilian banks

This study investigates the effect of financial distress on capital structure, considering banking performance variables and the economic environment. The analysis is based on balanced panel data for Brazilian listed banks, using accounting and non-accounting information on a quarterly basis from September 2009 to December 2016. This study uncovers evidence that the effect of financial distress on capital structure is context-dependent. During normal times, the findings support the argument for higher bank capital in times of financial distress. However, in periods of economic recession, the effect of bank distress on capital was found to be negative, indicating that the impact of banks’ risk on capital is especially important during such periods of market uncertainty. The findings are robust to alternative estimation methods and to alternative measures of risk. This study provides insights for the design of prudent regulation and the supervision of banks, especially for emerging markets economies, considering their highly uncertain environment with widely varying rates of growth and inflation.

Real-time sinusoidal parameter estimation for damage growth monitoring during ultrasonic very high cycle fatigue tests

Ultrasonic fatigue tests (UFT) are used to study the fatigue life behavior of metallic components undergoing a very high number of cycles (typically ≥107−109 cycles) under relatively low mechanical loads. By soliciting fatigue specimens at 20 kHz, ultrasonic fatigue machines are indispensable for monitoring damage growth and fatigue failures in a reasonable amount of time. As fatigue damage accumulates in the specimen, the specimen’s free-end exhibits a nonlinear dynamic response. The resulting quasi-stationary, harmonic signals have sinusoidal parameters (frequency and amplitude) which are slowly time-varying with respect to the excitation frequency. The discrete Fourier transform (DFT) is typically used to extract these evolving sinusoidal parameters from a window of finite data of the vibration signal. Alternative spectral estimation methods, specifically line spectra estimators (LSEs), exploit a priori information of the signal via their modeling basis and overcome limitations seen by the DFT. Many LSEs are known to have state-of-the-art results when benchmarked on purely stationary signals with unit amplitudes. However, their performances are unknown in the context of slowly time-varying signals typical of UFT, leading to a widespread use of the DFT. Thus, this paper benchmarks classical and modern LSEs against specific synthetic signals which arise in UFTs. Adequate algorithms are then recommended and made publicly available to process experimental data coming from ultrasonic fatigue tests depending on performance metrics and experimental restraints.

Comparing the Robustness of the Structural after Measurement (SAM) Approach to Structural Equation Modeling (SEM) against Local Model Misspecifications with Alternative Estimation Approaches

Structural equation models (SEM), or confirmatory factor analysis as a special case, contain model parameters at the measurement part and the structural part. In most social-science SEM applications, all parameters are simultaneously estimated in a one-step approach (e.g., with maximum likelihood estimation). In a recent article, Rosseel and Loh (2022, Psychol. Methods) proposed a two-step structural after measurement (SAM) approach to SEM that estimates the parameters of the measurement model in the first step and the parameters of the structural model in the second step. Rosseel and Loh claimed that SAM is more robust to local model misspecifications (i.e., cross loadings and residual correlations) than one-step maximum likelihood estimation. In this article, it is demonstrated with analytical derivations and simulation studies that SAM is generally not more robust to misspecifications than one-step estimation approaches. Alternative estimation methods are proposed that provide more robustness to misspecifications. SAM suffers from finite-sample bias that depends on the size of factor reliability and factor correlations. A bootstrap-bias-corrected LSAM estimate provides less biased estimates in finite samples. Nevertheless, we argue in the discussion section that applied researchers should nevertheless adopt SAM because robustness to local misspecifications is an irrelevant property when applying SAM. Parameter estimates in a structural model are of interest because intentionally misspecified SEMs frequently offer clearly interpretable factors. In contrast, SEMs with some empirically driven model modifications will result in biased estimates of the structural parameters because the meaning of factors is unintentionally changed.

Validation of heliospheric modeling algorithms through pulsar observations II: Simulations with EUHFORIA

In space weather studies and forecasting we employ magnetohydrodynamic (MHD) simulations which can provide rather accurate reconstruction of the solar wind dynamics and its evolution. However, all MHD simulations are restricted by the input data and the modelled solar wind characteristics need to be validated with different types of observations. That is very difficult, in particular for the solar wind characteristics close to the Sun, since the majority of in situ observations are taken in the vicinity of the Earth. This is why all alternative methods for estimation of solar wind plasma characteristics are very important. In this study we utilise low radio frequency observations of pulsars to probe the total electron content along the line of sight. For the first time, we compare density estimates from pulsars with predictions from the 3D MHD modelling code; the EUropean Heliospheric FORecasting Information Asset (EUHFORIA). We find a very good correlation for the solar wind density along a given line of sight obtained by EUHFORIA and pulsar observations. We demonstrate that pulsar observations can be very useful not only for the model validation but also for understanding its limitations.

FLAT LIKELIHOODS: THE SKEW NORMAL DISTRIBUTION CASE

Several references argue in favor of alternative estimation methods, rather than the likelihood one, when the likelihood function exhibits flat regions. However, in the case of the skew normal distribution we present a discussion describing the interpretation of those flat likelihoods. This distribution is widely used in several interesting applications and contains the normal distribution as a nested model and the half-normal as an embedded model. Here, we show that flat likelihoods provide relevant information that should be carefully analyzed before discarding its use and proposing other estimation methods. Two well-known examples, that have been reported as troublesome, are analyzed here, including also an exhaustive computational study. The analysis of different scenarios allows to understand not only the reason of this likelihood function shape, but also to discover the information this behavior provides.

Addressing Non-response Bias in Urban Forest Inventories: An Estimation Approach

When conducting urban forest inventories, complete or partial inaccessibility of sample plots results in non-response for a portion of the selected sample. Unfortunately, the non-response is rarely random and thus a potential bias may be imparted in the sample and associated data analyses. In this study, results from an alternative estimation method that employs response homogeneity groups (RHGs) appeared to be more robust to non-random non-response when compared to those of a standard estimation method. Across the six cities studied, the total non-response rates varied from 8.0 to 20.4%. Percent differences between the two methods in estimated number of trees ranged from −0.7 to 12.6%; whereas 1.4 to 14.8% differences were found for tree biomass density. While these differences only approximate the amount of non-response bias present under standard estimation methods, there is a clear indication that misleading results may be obtained if non-response bias is not adequately addressed. By implementing methods that mitigate potential non-response bias, urban forest inventory practitioners would increase the reliability of information used by city planners to make effective management and policy decisions.

Alternative methods for disaggregating Sustainable Development Goal indicators using survey data

Samples used in most surveys are either not large enough to guarantee reliable direct estimates for all relevant sub-populations, or do not cover all possible disaggregation domains. After having described a holistic strategy for producing disaggregated estimates of Sustainable Development Goal (SDG) indicators, this paper discusses alternative sampling and estimation methods that can be applied when sample surveys are the primary data source. In particular, the paper focuses on strategies that can be implemented at different stages of the statistical production process. At the design stage, the paper describes a series of sampling approaches that ensure a “sufficient” sampling size for each disaggregation domain. In this context, the article highlights the main limitations of traditional sampling approaches and shows how ad-hoc techniques could overcome some of their key constraints. At the analysis stage, it discusses an indirect model-assisted estimation approach to integrate data from independent surveys and censuses, eliminating costs deriving from redesigning data collection instruments, and ensuring a greater accuracy of the final disaggregated estimates. A case study applying the abovementioned method on the production of disaggregated estimates of SDG Indicator 2.1.2 (Prevalence of Moderate and Severe Food Insecurity) is then presented along with its main results.

Land Suitability Analysis for Agricultural Land Use using Hyperscale DEM Data

Cropland suitability analysis is a crucial process for achieving the optimum utilization of land use. It is frequently used today and continues to develop, especially in the methods. Digital soil mapping is a new technique that can generate spatial predictions of soil attributes obtained from digital soil covariates, reducing the cost, time, and land-use suitability evaluation accuracy. This study aims to determine the land suitability for agriculture commodities based on a hyperscale soil texture predictive model and compare it with the conventional land-use suitability evaluation based on determining soil texture. The target agricultural commodities in this study are leafy vegetables, carrots, apples, and coffee. This study finds that the Hyperscale Soil Texture estimation model can be used as a parameter for land suitability assessment for agricultural commodities. The prediction obtained by this model is not significantly different from that obtained by the traditional approach. This research discovers that the two procedures produced similar outcomes. The hyperscale approach can be an alternative method for land suitability estimation and reduce the time and cost compared to traditional techniques.

Diesel cetane number estimation from NIR spectra of hydrocracking total effluent

The work shown in this paper offers a fast and efficient alternative for estimating the cetane number of the diesel obtained from the distillation of the hydrocracking total effluent. In this study, the estimation of this diesel property was achieved through a partial least squares regression (PLSR) model using only the NIR spectrum of the hydrocracking total effluent. For calibrating and validating the PLS model, it was used a database containing the NIR spectra acquired on 98 total effluent samples and the cetane number measured on the 98 diesel fractions recovered from each total effluent sample distillation. The database was divided into the calibration and test data sets using the Kennard-Stone algorithm. The regression model developed exhibited good performance in estimating the studied property with errors of calibration (1.3), cross-validation (2.2), and prediction (2.0), close to the reproducibility of the reference method (±3.6). The alternative method for diesel cetane number estimation discussed in this article evidences its feasibility in optimizing diesel fuel characterization by reducing the necessity of the total effluent distillation. Furthermore, the results also show the potential of the alternative proposed to be applied in predicting other properties of fuels obtained from the hydrocracking process.

Empirical likelihood and uniform convergence rates for dyadic kernel density estimation

This paper studies the asymptotic properties of and alternative inference methods for kernel density estimation (KDE) for dyadic data. We first establish uniform convergence rates for dyadic KDE. Secondly, we propose a modified jackknife empirical likelihood procedure for inference. The proposed test statistic is asymptotically pivotal regardless of presence of dyadic clustering. The results are further extended to cover the practically relevant case of incomplete dyadic data. Simulations show that this modified jackknife empirical likelihood-based inference procedure delivers precise coverage probabilities even with modest sample sizes and with incomplete dyadic data. Finally, we illustrate the method by studying airport congestion in the United States.

Medium-run local economic effects of a major earthquake

AbstractExisting research is inconclusive regarding the longer-term economic effects of earthquakes. We examine the medium-run impacts of the 2010 earthquake in Chile, the sixth-largest ever recorded, using value-added tax collection as a proxy for economic activity at the municipal level and a measure of local ground-shaking intensity. We find that the affected municipalities suffered a relevant and persistent drop in their economic activity of about 10%, 8–9 years after the event. We discuss the plausibility of the assumption of conditional parallel trends and show that the overall results are robust to using alternative estimation methods.

Are Islamic banks more resilient to the crises vis-à-vis conventional banks? Evidence from the COVID-19 shock using stock market data

The debate regarding the performance of Islamic banks vis-à-vis conventional counterparts has attracted growing attention recently. Exploiting the Covid-19 health and economic crisis as an exogenous shock, we extend this debate by examining the resilience of Islamic banks vis-à-vis conventional banks during this shock. Using data from the Gulf Cooperation Council member states, we find stock market investors have not assessed the Islamic banks to be superior to conventional ones during the Covid-19 market meltdown. Specifically, our findings show Covid-19 confirmed cases, government social distancing policies and feverish period (i.e., 24 February to 17 March 2020) have had negative impact on stock returns of both Islamic and conventional banks alike. Interestingly, the adverse impact of social distancing policies is stronger on Islamic banks due to their inherent higher cost structure. Additionally, we find the marginal adverse impact of Covid-19 shock is weaker on banks with higher liquid assets holdings on the onset of the Covid-19 shock. Moreover, larger banks were hit harder during the first quarter of 2020, however, they also recovered more quickly during the second quarter. Results are robust with alternative estimation methods, matched sample of Islamic and conventional banks, cross-sectional analysis with fever period and extended sample period.

Alternative methods for skeletal maturity estimation with the EOS scanner-Experience from 934 patients.

BackgroundHand-wrist bone age assessment methods are not possible on typical EOS 2D/3D images without body position modifications that may affect spinal position. We aimed to identify and assess lesser known bone age assessment alternatives that may be applied retrospectively and without the need for extra imaging.Materials and methodsAfter review of 2857 articles, nine bone age methods were selected and applied retrospectively in pilot study (thirteen individuals), followed by evaluation of EOS images of 934 4-24-year-olds. Difficulty of assessment and time taken were recorded, and reliability calculated.ResultsFive methods proved promising after pilot study. Risser ‘plus’ could be applied with no difficulty in 89.5% of scans (836/934) followed by the Oxford hip method (78.6%, 734/934), cervical (79.0%, 738/934), calcaneus (70.8%, 669/934) and the knee (68.2%, 667/934). Calcaneus and cervical methods proved to be fastest at 17.7s (95% confidence interval, 16.0s to 19.38s & 26.5s (95% CI, 22.16s to 30.75s), respectively, with Oxford hip the slowest at 82.0 s (95% CI, 76.12 to 87.88s). Difficulties included: regions lying outside of the image—assessment was difficult or impossible in upper cervical vertebrae (46/934 images 4.9%) and calcaneus methods (144/934 images, 15.4%); position: lower step length was associated with difficult lateral knee assessment & head/hand position with cervical evaluation; and resolution: in the higher stages of the hip, calcaneal and knee methods.ConclusionsHip, iliac crest and cervical regions can be assessed on the majority of EOS scans and may be useful for retrospective application. Calcaneus evaluation is a simple and rapidly applicable method that may be appropriate if consideration is given to include full imaging of the foot.

Burden or Blessing? CEO Early-Life Adversity Experience and Firm Internationalization Performance.

Firm internationalization is a great challenge that needs a strong leader because of the uncertainty involved. Previous research has examined the antecedents of firm internationalization from the perspective of upper echelons theory, including chief executive officer (CEO) or top management team (TMT) characteristics, yet little research has examined the role of CEO early-life adversity experiences. Based on the imprinting theory and upper echelons theory, this study explores the relationship between CEO early-life adversity experience and firm internationalization. Using data from Chinese listed companies during the period 2007–2017, we demonstrate that CEO early-life adversity experiences have a significantly positive effect on firm internationalization; the effect is stronger when the CEO with early-life adversity has a higher level of organization discretion and institutional discretion. The findings are robust to a battery of alternative variable definitions and estimation methods. We contribute to upper echelons theory and the research on internationalization antecedents by showing that CEO early-life adversity has a positive effect on firm internationalization. The findings suggest boards aspiring to expand internationally place weight on candidates’ early-life experiences while selecting and hiring CEOs and confer them managerial discretion to better play their strength after CEO’s appointment decision is made.

Interlocking complementarities between job design and labour contracts

In this paper, we study the existence of interlocking complementarities between job design and labour contract at the firm level. Using a formal model, we show that firms face two organizational equilibria: one in which job designs with high routine task intensity are matched with a large use of non-standard contracts; and the other in which low routine task intensity combines with a small use of non-standard contracts. These complementarities exist because while non-standard contracts allow firm to adjust to external shocks, they also provide little incentive to invest in firm-specific knowledge. We test this prediction using linked-employer-employee data from the Emilia-Romagna region. The evidence is consistent with our theory: the use of non-standard contracts is positively associated with routine task intensity at the firm level. This result holds controlling for a wide range of firm-specific and contextual covariates and it is robust to alternative estimation methods (OLS, panel and IV).

Lorenz Interpolation: A Method for Estimating Income Inequality from Grouped Income Data

To understand how income inequality affects individuals and communities, researchers must have accurate measures of income inequality at lower geographic levels, such as counties, school districts, and census tracts. Studies of income inequality, however, are constrained by the tabular format in which censuses publish income data. In this article, the author proposes a new method, Lorenz interpolation, for estimating income inequality from binned income data. Using public microsample data from the American Community Survey (ACS), the author shows that Lorenz interpolation produces more accurate and reliable income inequality estimates than do alternative estimation methods. Then, using restricted ACS income data obtained through a Federal Statistical Research Data Center, the author evaluates the accuracy of Lorenz interpolation at the census tract and school district levels. Lorenz interpolation produces reliable school district–level estimates, but the method produces less reliable estimates for some income inequality measures at the tract level. These findings indicate that researchers should refrain from estimating tract-level income inequality measures from tabular data. They also show that aggregating tract income distributions to higher geographic levels can produce valid estimates of income inequality.