Challenges that surveys are facing are increasing data collection costs and declining budgets. During the past years, many surveys at Statistics Netherlands were redesigned to reduce costs and to increase or maintain response rates. From 2018 onwards, adaptive survey design has been applied in several social surveys to produce more accurate statistics within the same budget. In previous years, research has been done into the effect on quality and costs of reducing the use of interviewers in mixed-mode surveys starting with internet observation, followed by telephone or face-to-face observation of internet nonrespondents. Reducing follow-ups can be done in different ways. By using stratified selection of people eligible for follow-up, nonresponse bias may be reduced. The main decisions to be made are how to divide the population into strata and how to compute the allocation probabilities for face-to-face and telephone observation in the different strata. Currently, adaptive survey design is an option in redesigns of social surveys at Statistics Netherlands. In 2018 it has been implemented in the Health Survey and the Public Opinion Survey, in 2019 in the Life Style Monitor and the Leisure Omnibus, in 2021 in the Labour Force Survey, and in 2022 it is planned for the Social Coherence Survey. This paper elaborates on the development of the adaptive survey design for the Labour Force Survey. Attention is paid to the survey design, in particular the sampling design, the data collection constraints, the choice of the strata for the adaptive design, the calculation of follow-up fractions by mode of observation and stratum, the practical implementation of the adaptive design, and the six-month parallel design with corresponding response results.
DOCUMENT
From the literature three types of predictors for factor scores are available. These are characterized by the constraints: linear, linear conditionally unbiased, and linear correlation preserving. Each of these constraints generates a class of predictors. Best predictors are defined in terms of L?wner's partial matrix order applied to matrices of mean square error of prediction. It is shown that within the first two classes a best predictor exists and that it does not exist in the third. Copyright ? 1996 by Marcel Dekker, Inc.
MULTIFILE
Density histograms can bridge the gap between histograms and continuous probability distributions, but research on how to learn and teach them is scarce. In this paper, we explore the learning of density histograms with the research question: How can a sequence of tasks designed from an embodied instrumentation perspective support students’ understanding of density histograms? Through a sequence of tasks based on students’ notions of area, students reinvented unequal bin widths and density in histograms. The results indicated that students had no difficulty choosing bin widths or using area in a histogram. Nevertheless, reinvention of the vertical density scale required intense teacher intervention suggesting that in future designs, this scale should be modified to align with students’ informal notions of area. This study contributes to a new genre of tasks in statistics education based on the design heuristics of embodied instrumentation.
DOCUMENT
BackgroundConfounding bias is a common concern in epidemiological research. Its presence is often determined by comparing exposure effects between univariable- and multivariable regression models, using an arbitrary threshold of a 10% difference to indicate confounding bias. However, many clinical researchers are not aware that the use of this change-in-estimate criterion may lead to wrong conclusions when applied to logistic regression coefficients. This is due to a statistical phenomenon called noncollapsibility, which manifests itself in logistic regression models. This paper aims to clarify the role of noncollapsibility in logistic regression and to provide guidance in determining the presence of confounding bias.MethodsA Monte Carlo simulation study was designed to uncover patterns of confounding bias and noncollapsibility effects in logistic regression. An empirical data example was used to illustrate the inability of the change-in-estimate criterion to distinguish confounding bias from noncollapsibility effects.ResultsThe simulation study showed that, depending on the sign and magnitude of the confounding bias and the noncollapsibility effect, the difference between the effect estimates from univariable- and multivariable regression models may underestimate or overestimate the magnitude of the confounding bias. Because of the noncollapsibility effect, multivariable regression analysis and inverse probability weighting provided different but valid estimates of the confounder-adjusted exposure effect. In our data example, confounding bias was underestimated by the change in estimate due to the presence of a noncollapsibility effect.ConclusionIn logistic regression, the difference between the univariable- and multivariable effect estimate might not only reflect confounding bias but also a noncollapsibility effect. Ideally, the set of confounders is determined at the study design phase and based on subject matter knowledge. To quantify confounding bias, one could compare the unadjusted exposure effect estimate and the estimate from an inverse probability weighted model.
MULTIFILE
Estimation of the factor model by unweighted least squares (ULS) is distribution free, yields consistent estimates, and is computationally fast if the Minimum Residuals (MinRes) algorithm is employed. MinRes algorithms produce a converging sequence of monotonically decreasing ULS function values. Various suggestions for algorithms of the MinRes type are made for confirmatory as well as for exploratory factor analysis. These suggestions include the implementation of inequality constraints and the prevention of Heywood cases. A simulation study, comparing the bootstrap standard deviations for the parameters with the standard errors from maximum likelihood, indicates that these are virtually equal when the score vectors are sampled from the normal distribution. Two empirical examples demonstrate the usefulness of constrained exploratory and confirmatory factor analysis by ULS used in conjunction with the bootstrap method.
DOCUMENT
Mycotoxins are small (MW approximately 700), toxic chemical products formed as secondary metabolites by a few fungal species that readily colonise crops and contaminate them with toxins in the field or after harvest. Ochratoxins and Aflatoxins are mycotoxins of major significance and hence there has been significant research on broad range of analytical and detection techniques that could be useful and practical. Due to the variety of structures of these toxins, it is impossible to use one standard technique for analysis and/or detection. Practical requirements for high-sensitivity analysis and the need for a specialist laboratory setting create challenges for routine analysis. Several existing analytical techniques, which offer flexible and broad-based methods of analysis and in some cases detection, have been discussed in this manuscript. There are a number of methods used, of which many are lab-based, but to our knowledge there seems to be no single technique that stands out above the rest, although analytical liquid chromatography, commonly linked with mass spectroscopy is likely to be popular. This review manuscript discusses (a) sample pre-treatment methods such as liquid-liquid extraction (LLE), supercritical fluid extraction (SFE), solid phase extraction (SPE), (b) separation methods such as (TLC), high performance liquid chromatography (HPLC), gas chromatography (GC), and capillary electrophoresis (CE) and (c) others such as ELISA. Further currents trends, advantages and disadvantages and future prospects of these methods have been discussed.
DOCUMENT
The subject of factor indeterminacy has a vast history in factor analysis (Guttman, 1955; Lederman, 1938; Wilson, 1928). It has lead to strong differences in opinion (Steiger, 1979). The current paper gives necessary and sufficient conditions for observability of factors in terms of the parameter matrices and a finite number of variables. Five conditions are given which rigorously define indeterminacy. It is shown that (un)observable factors are (in)determinate. Specifically, the indeterminacy proof by Guttman is extended to Heywood cases. The results are illustrated by two examples and implications for indeterminacy are discussed.
DOCUMENT
We present a simple analytical formalism based on the Lorentz-Scherrer equation and Bernoulli statistics for estimating the fraction of crystallites (and the associated uncertainty parameters) contributing to all finite Bragg peaks of a typical powder pattern obtained from a static polycrystalline sample. We test and validate this formalism using numerical simulations, and show that they can be applied to experiments using monochromatic or polychromatic (pink-beam) radiation. Our results show that enhancing the sampling efficiency of a given powder diffraction experiment for such samples requires optimizing the sum of the multiplicities of reflections included in the pattern along with the wavelength used in acquiring the pattern. Utilizing these equations in planning powder diffraction experiments for sampling efficiency is also discussed.
DOCUMENT
Several models in data analysis are estimated by minimizing the objective function defined as the residual sum of squares between the model and the data. A necessary and sufficient condition for the existence of a least squares estimator is that the objective function attains its infimum at a unique point. It is shown that the objective function for Parafac-2 need not attain its infimum, and that of DEDICOM, constrained Parafac-2, and, under a weak assumption, SCA and Dynamals do attain their infimum. Furthermore, the sequence of parameter vectors, generated by an alternating least squares algorithm, converges if it decreases the objective function to its infimum which is attained at one or finitely many points.
LINK
BACKGROUND: Blended physiotherapy, in which physiotherapy sessions and an online application are integrated, might support patients in taking an active role in the management of their chronic condition and may reduce disease related costs. The aim of this study was to evaluate the cost-effectiveness of a blended physiotherapy intervention (e-Exercise) compared to usual physiotherapy in patients with osteoarthritis of hip and/or knee, from the societal as well as the healthcare perspective.METHODS: This economic evaluation was conducted alongside a 12-month cluster randomized controlled trial, in which 108 patients received e-Exercise, consisting of physiotherapy sessions and a web-application, and 99 patients received usual physiotherapy. Clinical outcome measures were quality-adjusted life years (QALYs) according to the EuroQol (EQ-5D-3 L), physical functioning (HOOS/KOOS) and physical activity (Actigraph Accelerometer). Costs were measured using self-reported questionnaires. Missing data were multiply imputed and bootstrapping was used to estimate statistical uncertainty.RESULTS: Intervention costs and medication costs were significantly lower in e-Exercise compared to usual physiotherapy. Total societal costs and total healthcare costs did not significantly differ between groups. No significant differences in effectiveness were found between groups. For physical functioning and physical activity, the maximum probability of e-Exercise being cost-effective compared to usual physiotherapy was moderate (< 0.82) from both perspectives. For QALYs, the probability of e-Exercise being cost-effective compared to usual physiotherapy was 0.68/0.84 at a willingness to pay of 10,000 Euro and 0.70/0.80 at a willingness to pay of 80,000 Euro per gained QALY, from respectively the societal and the healthcare perspective.CONCLUSIONS: E-Exercise itself was significantly cheaper compared to usual physiotherapy in patients with hip and/or knee osteoarthritis, but not cost-effective from the societal- as well as healthcare perspective. The decision between both interventions can be based on the preferences of the patient and the physiotherapist.TRIAL REGISTRATION: NTR4224 (25 October 2013).
DOCUMENT
