Unobserved Measurement Research Articles

The economics of adaptations to evidence-based practices

BackgroundEvidence-based practices (EBPs) are frequently adapted in response to the dynamic contexts in which they are implemented. Adaptation is defined as the degree to which an EBP is altered to fit the setting or to improve fit to local context and can be planned or unplanned. Although adaptations are common and necessary to maximizing the marginal impact of EBPs, little attention has been given to the economic consequences and how adaptations affect marginal costs.DiscussionIn assessing the economic consequences of adaptation, one should consider its impact on core components, the planned adaptive periphery, and the unplanned adaptive periphery. Guided by implementation science frameworks, we examine how various economic evaluation approaches accommodate the influence of adaptations and discuss the pros and cons of these approaches. Using the Framework for Reporting Adaptations and Modifications to Evidence-based interventions (FRAME), mixed methods can elucidate the economic reasons driving the adaptations. Micro-costing approaches are applied in research that integrates the adaptation of EBPs at the planning stage using innovative, adaptive study designs. In contrast, evaluation of unplanned adaptation is subject to confounding and requires sensitivity analysis to address unobservable measures and other uncertainties. A case study is presented using the RE-AIM framework to illustrate the costing of adaptations. In addition to empirical approaches to evaluating adaptation, simulation modeling approaches can be used to overcome limited follow-up in implementation studies.ConclusionsAs implementation science evolves to improve our understanding of the mechanisms and implications of adaptations, it is increasingly important to understand the economic implications of such adaptations, in addition to their impact on clinical effectiveness. Therefore, explicit consideration is warranted of how costs can be evaluated as outcomes of adaptations to the delivery of EBPs.

Population Size Estimation using Zero-truncated Poisson Regression with Measurement Error.

Population size estimation is an important research field in biological sciences. In practice, covariates are often measured upon capture on individuals sampled from the population. However, some biological measurements, such as body weight may vary over time within a subject's capture history. This can be treated as a population size estimation problem in the presence of covariate measurement error. We show that if the unobserved true covariate and measurement error are both normally distributed, then a naïve estimator without taking into account measurement error will under-estimate the population size. We then develop new methods to correct for the effect of measurement errors. In particular, we present a conditional score and a nonparametric corrected score approach that are both consistent for population size estimation. Importantly, the proposed approaches do not require the distribution assumption on the true covariates, furthermore the latter does not require normality assumptions on the measurement errors. This is highly relevant in biological applications, as the distribution of covariates is often non-normal or unknown. We investigate finite sample performance of the new estimators via extensive simulated studies. The methods are applied to real data from a capture-recapture study.

Current Account Balances, External Debts and Exchange Rates in Selected African Countries

Most African countries had been bedeviled by the problem of deficits in their current account balances (World Bank, 2020). In a bid to overcome this challenge, they usually resorted to contracting external debts from institutions and countries that required them to repay these loans in the currencies of the creditors. Thus, the rate of exchange between the creditors and debtors should be of concern. Several studies have been carried out to examine the relationship between current account balances, external debts and the exchange rates. Some studies found a unidirectional relationship among these variables. In some other studies, the relationship knitting these variables was bi-directional. In most of these studies, the methods of analysis ranged from the ordinary least squares, panel data analysis and the vector error correction model. This study fills the gap in the literature by examining the relationship across these variables making use of the generalized methods of moments (GMM). The GMM estimation technique will correct for unobserved heterogeneity, endogeneity and measurement errors which were observed in the data. The study found that a 9.46% increase in external debts leads to a percentage increase in current account balances in the selected African countries. Also, there is a positive and significant relationship between the exchange rates and the current account balances in the group.

Experimental demonstration and optimization of X-ray StaticCodeCT.

As the use of X-ray computed tomography (CT) grows in medical diagnosis, so does the concern for the harm a radiation dose can cause and the biological risks it represents. StaticCodeCT is a new low-dose imaging architecture that uses a single-static coded aperture (CA) in a CT gantry. It exploits the highly correlated data in the projection domain to estimate the unobserved measurements on the detector. We previously analyzed the StaticCodeCT system by emulating the effect of the coded mask on experimental CT data. In contrast, this manuscript presents test-bed reconstructions using an experimental cone-beam X-ray CT system with a CA holder. We analyzed the reconstruction quality using three different techniques to manufacture the CAs: metal additive manufacturing, cold casting, and ceramic additive manufacturing. Furthermore, we propose an optimization method to design the CA pattern based on the algorithm developed for the measurement estimation. The obtained results point to the possibility of the real deployment of StaticCodeCT systems in practice.

Imputation to predict height to crown base for trees with predicted heights

Height-to-crown-base (HTCB) measurements are frequently used as inputs for growth and yield models. They are essential for reliable projections of stand structure over time required for sustainable forest management. Often, HTCB is measured alongside total height (HT) for only a subsample of trees and must be imputed for unobserved measurements in the sample. Typically, HTCB models require HT as a covariate, requiring a “double” imputation for missing HTCB measurements, leading to potentially substantial error propagation issues. We compared the effects of subsample size, imputation method, and use of imputed rather than measured HT on the accuracy of HTCB predictions. HT and HTCB were imputed using a nonlinear fixed-effects model (NFEM), a NFEM with a correction factor estimated using an ordinary least squares (OLS) regression on the subsampled measurements, and a nonlinear mixed-effects model (NMEM) with stand- and plot-level random parameters. Using cross-validated bias and root mean squared error (RMSE), our results indicated that NMEM obtained the smallest RMSE at subsample sizes greater than one, with RMSEs ranging between 2.19 and 2.51 m. However, while NMEM provided generally smaller RMSEs, biases ranging between −0.92 and −0.29 m existed at subsample sizes less than three trees per plot, and −2.86 m when no subsample was available. We observed negative bias when using imputed rather than measured HT for both the correction factor and mixed-effects model that is mitigated to a range of −0.51 m to −0.08 m with subsample sizes of at least two trees. Following this, we recommend using NMEMs for HTCB imputation with at least four trees per plot.

Multi-sensor Optimal Linear Estimation With Unobservable Measurement Losses

For a multiple-channel system with sensor measurement losses, if the loss of sensor measurements can be observed by the estimator, the system is called a system with observable measurement losses; otherwise, it is called a system with unobservable measurement losses (a UML system). We first obtain the optimal linear estimator (OLE) for multiple-channel UML systems and then establish a necessary and sufficient condition for the stability and convergence of the OLE. We give a tight bound of the estimation performance loss caused by the unobservability of measurement losses. We show that the estimation performance is a monotonically increasing function of the measurement-loss rate and then analytically characterize the relation between the OLE-performance-loss rate and the measurement-loss rate. Finally, numerical examples are provided to show the effectiveness of the proposed OLE, when the measurement-loss status, that is, the private information of measurement losses, cannot be observed.

Is There Really a Foreign Ownership Productivity Advantage? Evidence from Nigerian Manufacturing Firms

ABSTRACT The role of foreign ownership of an enterprise in impacting their performance is a vital policy issue for Africa. In this paper, panel data for manufacturing firms is used to investigate that role in Nigeria. After controlling for unobserved firm heterogeneity, inputs simultaneity, measurement errors and possible selection bias, I find that foreign ownership has a positive, but statistically insignificant, effect on total factor productivity (TFP). However, foreign-owned firms operate on a far larger scale than domestic ones, with much higher levels of employment, capital intensity and labour productivity. As it is labour productivity that determines the ability of firms to pay higher wages, the evidence presented in this paper suggests it is their ability to operate at higher scale, rather than having higher TFP, is what characterises foreign-owned firms in Nigeria.

Quantum state smoothing: why the types of observed and unobserved measurements matter

We investigate the estimation technique called quantum state smoothing introduced in (Guevara and Wiseman 2015 Phys. Rev. Lett. 115 180407), which offers a valid quantum state estimate for a partially monitored system, conditioned on the observed record both prior and posterior to an estimation time. The technique was shown to give a better estimate of the underlying true quantum states than the usual quantum filtering approach. However, the improvement in estimation fidelity, originally examined for a resonantly driven qubit coupled to two vacuum baths, was also shown to vary depending on the types of detection used for the qubit’s fluorescence. In this work, we analyse this variation in a systematic way for the first time. We first define smoothing power using an average purity recovery and a relative average purity recovery, of smoothing over filtering. Then, we explore the power for various combinations of fluorescence detection for both observed and unobserved channels. We next propose a method to explain the variation of the smoothing power, based on multi-time correlation strength between fluorescence detection records. The method gives a prediction of smoothing power for different combinations, which is remarkably successful in comparison with numerically simulated qubit trajectories.

Discrete-time autoregressive model for unequally spaced time-series observations

Most time-series models assume that the data come from observations that are equally spaced in time. However, this assumption does not hold in many diverse scientific fields, such as astronomy, finance, and climatology, among others. There are some techniques that fit unequally spaced time series, such as the continuous-time autoregressive moving average (CARMA) processes. These models are defined as the solution of a stochastic differential equation. It is not uncommon in astronomical time series, that the time gaps between observations are large. Therefore, an alternative suitable approach to modeling astronomical time series with large gaps between observations should be based on the solution of a difference equation of a discrete process. In this work we propose a novel model to fit irregular time series called the complex irregular autoregressive (CIAR) model that is represented directly as a discrete-time process. We show that the model is weakly stationary and that it can be represented as a state-space system, allowing efficient maximum likelihood estimation based on the Kalman recursions. Furthermore, we show via Monte Carlo simulations that the finite sample performance of the parameter estimation is accurate. The proposed methodology is applied to light curves from periodic variable stars, illustrating how the model can be implemented to detect poor adjustment of the harmonic model. This can occur when the period has not been accurately estimated or when the variable stars are multiperiodic. Last, we show how the CIAR model, through its state space representation, allows unobserved measurements to be forecast.

A Modeling Method of Stochastic Parameters’ Inverse Gauss Process Considering Measurement Error under Accelerated Degradation Test

To solve the problem that the individual differences and the measurement errors affect the accuracy of life estimation in accelerated degradation test, the inverse Gauss process with stochastic parameters is applied in the accelerated degradation test with the consideration of the influence of individual differences, and the analysis of measurement uncertainty is carried out. An inverse Gauss accelerated degradation model considering both individual differences and measurement errors is established. In the maximum likelihood estimation of parameters, Genetic Algorithm and Monte Carlo integral are used to solve the problems caused by complex integral and the unobservable measurement errors in the calculation process. Finally, the proposed method is verified by the Monte Carlo simulation under the constant accelerated stress and step accelerated stress and the illustrative example of electrical connectors under the constant acceleration stress, respectively. The results show that the modeling tool is useful for improving the accuracy of the life prediction and the reliability evaluation.

Smoothed quantum-classical states in time-irreversible hybrid dynamics

We consider a quantum system continuously monitored in time which in turn is coupled to an arbitrary dissipative classical system (diagonal reduced density matrix). The quantum and classical dynamics can modify each other, being described by an arbitrary time-irreversible hybrid Lindblad equation. Given a measurement trajectory, a conditional bipartite stochastic state can be inferred by taking into account all previous recording information (filtering). Here, we demonstrate that the joint quantum-classical state can also be inferred by taking into account both past and future measurement results (smoothing). The smoothed hybrid state is estimated without involving information from unobserved measurement channels. Its average over recording realizations recovers the joint time-irreversible behavior. As an application we consider a fluorescent system monitored by an inefficient photon detector. This feature is taken into account through a fictitious classical two-level system. The average purity of the smoothed quantum state increases over that of the (mixed) state obtained from the standard quantum jump approach.

Matrix and Tensor Completion on a Human Activity Recognition Framework.

Sensor-based activity recognition is encountered in innumerable applications of the arena of pervasive healthcare and plays a crucial role in biomedical research. Nonetheless, the frequent situation of unobserved measurements impairs the ability of machine learning algorithms to efficiently extract context from raw streams of data. In this paper, we study the problem of accurate estimation of missing multimodal inertial data and we propose a classification framework that considers the reconstruction of subsampled data during the test phase. We introduce the concept of forming the available data streams into low-rank two-dimensional (2-D) and 3-D Hankel structures, and we exploit data redundancies using sophisticated imputation techniques, namely matrix and tensor completion. Moreover, we examine the impact of reconstruction on the classification performance by experimenting with several state-of-the-art classifiers. The system is evaluated with respect to different data structuring scenarios, the volume of data available for reconstruction, and various levels of missing values per device. Finally, the tradeoff between subsampling accuracy and energy conservation in wearable platforms is examined. Our analysis relies on two public datasets containing inertial data, which extend to numerous activities, multiple sensing parameters, and body locations. The results highlight that robust classification accuracy can be achieved through recovery, even for extremely subsampled data streams.

The Impact of Health on Wages: Evidence from Europe Before and During the Great Recession

This paper adds to the empirical literature of health as a potential endogenous explanatory variable in wage equations by addressing problems such as unobserved heterogeneity, sample selection and measurement error (in the health variable) in one comprehensive framework. Moreover, by using European individual-level panel data from before and during the Great Recession (GR) — which started in Europe in 2008 — we gain insights into whether and how the current crisis has altered the relationship between health and wages. Our results provide empirical evidence of measurement error in the self-reported health variable when estimating its impact on wages for men, and of selectivity bias in wages for both men and women. We also show that in the period prior to the GR, working-age men (20-64 years old) who are in relatively better health (measured by a one-unit increase in a health index) have, on average, a 9 percent higher hourly wage rate. This effect is concentrated (and largest) among older workers (50-64 years old). Instead, during the GR the positive impact of health on wages disappears. One possible explanation for these findings is that presenteeism (i.e. attending work even though being sick) — which has become more common during the GR — may have reduced the impact of (poor) health on wages. With regard to working-age women (20-59 years old), we do not find evidence of an effect of health on wages, both before and during the GR.

Pieces of the immigrant paradox puzzle: measurement, level, and predictive differences in precursors to academic achievement

The “immigrant paradox” indicates that the academic attitudes and outcomes of 1st-generation youth exceed those of the 2nd- and 3rd-generation. This paper examines a) whether unobserved measurement bias contributes to these generational differences, b) generational differences in levels of behavioral school engagement (BSE) and perceived supportive school relations (SSR), and c) to what extent BSE mediates the relations between SSR and academic achievement and whether these relations differ across generations. New York City Social and Academic Engagement Study (NYCASES) data were analyzed. Strong measurement invariance for BSE and SSR suggests that unobserved measurement bias does not contribute to the immigrant paradox. 1st generation youth evinced higher latent means for BSE and SSR than 2nd or 3rd-generation youth. 1st generation youth responded to SSR by exerting effort while 2nd and 3rd generation youth responded to SSR by complying with rules. Because effort engendered achievement more than compliance, this study identifies a mediating mechanism that contributes to the immigrant paradox.

Estimating performance degradation using intervals between upcrossings of a threshold

We consider the problem of estimating the rate of degradation of a system when only limited data is available. Specifically, we consider the problem of deriving a consistent estimator of degradation when we can only observe the sequence of times when an unobserved performance measurement exceeds a given threshold. Such problems arise, for example, in the operation of complex systems where exceeding a predefined level multiple times drives repair actions, in security applications for which only entry into a secured facility is recorded, and in sensor networks where data acquisition and transmission are limited. We consider the relative efficiency of the resulting estimator when compared to the MLE estimators derived from the full unobserved continuous process and from unobserved binary high-low data.

Cross country differences in job reallocation: The role of industry, firm size and regulations

Somewhat surprisingly, cross-country empirical evidence (at least in the cross section) does not seem to support the predictions of standard models that economies with stricter regulations on hiring and firing should have a lower pace of job reallocation. One problem in exploring these issues empirically has been the difficulty of comparing countries on the basis of harmonized measures of job reallocation. A related problem is that there may be unobserved measurement errors or other factors accounting for differences in job reallocation across countries. This paper overcomes these challenges by using harmonized measures of job creation and destruction in a sample of 16 industrial and emerging economies, exploiting the country, industry and firm size dimensions. The analysis of variance in the paper shows that firm size effects are a dominant factor in accounting for the variation in the pace of job reallocation across country, industry and size cells. However, even after controlling for industry and size effects there remain significant differences in job flows across countries that could reflect differences in labor market regulations. We use the harmonized data to explore this hypothesis with a difference-in-difference approach. We find strong and robust evidence that stringent hiring and firing regulations tend to reduce the pace of job reallocation.

Multilevel Latent Gaussian Process Model for Mixed Discrete and Continuous Multivariate Response Data

We propose a Bayesian model for mixed ordinal and continuous multivariate data to evaluate a latent spatial Gaussian process. Our proposed model can be used in many contexts where mixed continuous and discrete multivariate responses are observed in an effort to quantify an unobservable continuous measurement. In our example, the latent, or unobservable measurement is wetland condition. While predicted values of the latent wetland condition variable produced by the model at each location do not hold any intrinsic value, the relative magnitudes of the wetland condition values are of interest. In addition, by including point-referenced covariates in the model, we are able to make predictions at new locations for both the latent random variable and the multivariate response. Lastly, the model produces ranks of the multivariate responses in relation to the unobserved latent random field. This is an important result as it allows us to determine which response variables are most closely correlated with the latent variable. Our approach offers an alternative to traditional indices based on best professional judgment that are frequently used in ecology. We apply our model to assess wetland condition in the North Platte and Rio Grande River Basins in Colorado. The model facilitates a comparison of wetland condition at multiple locations and ranks the importance of in-field measurements.

Longevity Risk in Fair Valuing Level 3 Assets in Securitised Portfolios

Fair value accounting aims to establish a three-level hierarchy that distinguishes (1) readily observable measurement inputs from (2) less readily observable measurement inputs and (3) unobservable measurement inputs. Level 3 longevity valued assets will pose unique valuation risks once securitised pools of these alternative asset classes come to market as investment vehicles for pension plans and individual retirement accounts. No uniform framework is available to assure consistent fair market valuation and transparency for investor decision-making. Applying existing international auditing standards and analytical procedures (IFRS 13) will offer a platform upon which fund managers, their auditors and actuaries can agree upon uniform valuation and presentation guidelines. Application of these quasi-governmental standards will bring future liquidity to otherwise illiquid capital market instruments. This paper presents a valuation methodology consistent with fair value accounting and auditing standards. The methodology incorporates the longevity predictive modelling of Stallard in a form that is compatible with Bayes Factor weighted average valuation techniques based on the study by Kass and Raftery. The methodology is applicable to fair valuation of life settlement portfolios where the combination of too few large death benefit policies and large variances in individual life expectancy estimates currently challenge accurate valuation and periodic re-valuation.

A Sensitivity Analysis for Shared‐Parameter Models for Incomplete Longitudinal Outcomes

All models for incomplete data either explicitly make assumptions about aspects of the distribution of the unobserved outcomes, given the observed ones, or at least implicitly imply such. One consequence is that there routinely exist a whole class of models, coinciding in their description of the observed portion of the data but differing with respect to their "predictions" of what is unobserved. Within such a class, there always is a single model corresponding to so-called random missingness, in the sense that the mechanism governing missingness depends on covariates and observed outcomes, but given these not further on unobserved outcomes. We employ these results in the context of so-called shared-parameter models where outcome and missingness models are connected by means of common latent variables or random effects, to devise a sensitivity analysis framework. Precisely, the impact of varying unverifiable assumptions about unobserved measurements on parameters of interest is studied. Apart from analytic considerations, the proposed methodology is applied to assess treatment effect in data from a clinical trial in toenail dermatophyte onychomycosis. While our focus is on longitudinal outcomes with incomplete outcome data, the ideas developed in this paper are of use whenever a shared-parameter model could be considered.

Cross Country Differences in Job Reallocation: The Role of Industry, Firm Size and Regulations

Somewhat surprisingly, cross-country empirical evidence (at least in the cross section) does not seem to support the predictions of standard models that economies with stricter regulations on hiring and firing should have a lower pace of job reallocation. One problem in exploring these issues empirically has been the difficulty of comparing countries on the basis of harmonised measures of job reallocation. A related problem is that there may be unobserved measurement or other factors accounting for differences in job reallocation across countries. This paper overcomes these challenges by using harmonised measures of job creation and destruction in a sample of 16 developed and emerging economies (including four transition economies), exploiting the country, industry and firm size dimensions. The analysis of variance in the paper shows that firm size effects are a dominant factor in accounting for the variation in the pace of job reallocation across country, industry and size cells. However, even after controlling for industry and size effects there remain significant differences in job flows across countries that could reflect differences in labour market regulations. We use the harmonised data to explore this hypothesis with a difference-in-difference approach. We find strong and robust evidence that stringent hiring and firing regulations tend to reduce the pace of job reallocation.