SEARCH · PubMed Health

Results for “measurement error”

Explore indexed PubMed citations for clinical trials, systematic reviews and public health research. Read source abstracts and follow each citation to its original PubMed record.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 91 records · Page 5Linked to original sources

PubMed1999

Flexible parametric measurement error models.

Inferences in measurement error models can be sensitive to modeling assumptions. Specifically, if the model is incorrect, the estimates can be inconsistent. To reduce sensitivity to modeling assumptions and yet still retain the efficiency of parametric inference, we propose using flexible parametric models that can accommodate departures from standard parametric models. We use mixtures of normals for this purpose. We study two cases in detail: a linear errors-in-variables model and a change-point Berkson model.

Biometry↗

PubMed2006

Measurement error in a random walk model with applications to population dynamics.

Population abundances are rarely, if ever, known. Instead, they are estimated with some amount of uncertainty. The resulting measurement error has its consequences on subsequent analyses that model population dynamics and estimate probabilities about abundances at future points in time. This article addresses some outstanding questions on the consequences of measurement error in one such dynamic model, the random walk with drift model, and proposes some new ways to correct for measurement error. We present a broad and realistic class of measurement error models that allows both heteroskedasticity and possible correlation in the measurement errors, and we provide analytical results about the biases of estimators that ignore the measurement error. Our new estimators include both method of moments estimators and "pseudo"-estimators that proceed from both observed estimates of population abundance and estimates of parameters in the measurement error model. We derive the asymptotic properties of our methods and existing methods, and we compare their finite-sample performance with a simulation experiment. We also examine the practical implications of the methods by using them to analyze two existing population dynamics data sets.

Animals↗

PubMedDate not supplied

Measurement error in functional balance and mobility tests for people with stroke: what are the sources of error and what is the best way to minimize error?

OBJECTIVE: To assess the degree and source of measurement error in functional balance and mobility tests for people with stroke, and to identify the most effective method of data collection to minimize error. DESIGN: To assess the degree and source of error, the total, systematic, and random error were calculated for within-session, test-retest, and interrater testing. To identify the most effective method of data collection, the total error was calculated for 4 data collection methods: 1 familiarization trial, then scoring a 2nd trial; 2 familiarization trials, then scoring a 3rd trial; averaging 2 trials, then averaging 3 trials. SETTING: Stroke services in National Health Service hospitals. PATIENTS: Thirty-five people with a poststroke hemiplegia. INTERVENTIONS: None. MAIN OUTCOME MEASURES: Five tests provided interval-level data: arm raise (sitting and standing), weight shift, tap, and step-up. Four tests provided ratio-level data: forward reach (sitting and standing) and 5-m timed walk (with and without an aid). RESULTS: Total measurement error ranged from zero for the step-up test to 55% for within-session error for the 5-m walk without an aid. Ratio data tests showed somewhat greater error than interval data tests (5%-55% vs. 0%-46%). A within-session practice effect for the standing forward reach, 5-m walk (with and without an aid), and weight shift tests was found. For the other tests, random error was greater than the systematic error. Interrater testing had the least error. For most tests, the average of 2 trials produced the least measurement error. For the 5-m walk, the mean obtained from 2 or 3 trials was equally effective. For the step-up test, the mean of 3 trials was slightly more effective. The overall error from all 3 sources was 3 lifts for sitting arm raise, 11 cm for sitting forward reach, 3 lifts for the standing arm raise, 7.5 cm for standing forward reach, 4.5 s for walking with an aid, 3 shifts on the weight shift test, 1.1 s for walking without an aid, 2 taps, and 1 step up. CONCLUSION: The tests using interval data showed less error than ratio-data tests and may be preferable measurement tools. Taking an average of 2 trials was the most accurate data collection method.

Aged↗

PubMed2003

Using measurement error models to assess effects of prenatal and postnatal methylmercury exposure in the Seychelles Child Development Study.

Studies of the effects of environmental exposures on human health typically require estimation of both exposure and outcome. Standard methods for the assessment of the association between exposure and outcome include multiple linear regression analysis, which assumes that the outcome variable is observed with error, while the levels of exposure and other explanatory variables are measured with complete accuracy, so that there is no deviation of the measured from the actual value. The term measurement error in this discussion refers to the difference between the actual or true level and the value that is actually observed. In the investigations of the effects of prenatal methylmercury (MeHg) exposure from fish consumption on child development, the only way to obtain a true exposure level (producing the toxic effect) is to ascertain the concentration in fetal brain, which is not possible. As is often the case in studies of environmental exposures, the measured exposure level is a biomarker, such as the average maternal hair level during gestation. Measurement of hair mercury is widely used as a biological indicator for exposure to MeHg and is the only indicator that has been calibrated against the target tissue, the developing brain. Variability between the measured and the true values in explanatory variables in a multiple regression analysis can produce bias, leading to either over or underestimation of regression parameters (slopes). Fortunately, statistical methods known as measurement error models (MEM) are available to account for measurement errors in explanatory variables in multiple regression analysis, and these methods can provide an (either "unbiased" or "bias-corrected") estimate of the unknown outcome/exposure relationship. In this paper, we illustrate MEM analysis by reanalyzing data from the 5.5-year test battery in the Seychelles Child Development Study, a longitudinal study of prenatal exposure to MeHg from maternal consumption of a diet high in fish. The use of the MEM approach was made possible by the existence of independent, calibration data on the magnitude of the variability of the measurement error deviations for the biomarker of prenatal exposure used in this study, the maternal hair level. Our reanalysis indicated that adjustment for measurement errors in explanatory variables had no appreciable effect on the original results.

Adult↗

PubMed1995

OOPSEG: a data smoothing program for quantitation and isolation of random measurement error.

We describe a data smoothing program, OOPSEG, which automatically quantitates and filters the random measurement error in a given data series. The measurement error is initially guessed, and the Optimal Segments technique is used to filter a corresponding amount of variation from the data, thus generating a relatively smooth curve. The residuals about this smooth curve are tested for serial correlation. If correlation is detected, a new measurement error is guessed, and the data are filtered again. This process continues until a smooth curve has been found for which the residuals do not exhibit serial correlation. Such residuals represent the random component of the data, i.e. (presumably) the measurement error. The corresponding smooth curve thus approximates the original, error-free curve. The smooth curve and the estimated coefficient of variation of the data are returned. OOPSEG handles end effects by performing an expansion of the data set, smoothing this expanded data set, then deleting the artificial points before assembling the final, smooth curve. Also, data may be smoothed as a sequence of independent regions to accommodate time courses with known changes in experimental conditions. We suggest that OOPSEG may have numerous applications in data analysis and experimental design.

Algorithms↗

PubMed1989

Correction of logistic regression relative risk estimates and confidence intervals for systematic within-person measurement error.

Errors in the measurement of exposure that are independent of disease status tend to bias relative risk estimates and other measures of effect in epidemiologic studies toward the null value. Two methods are provided to correct relative risk estimates obtained from logistic regression models for measurement errors in continuous exposures within cohort studies that may be due to either random (unbiased) within-person variation or to systematic errors for individual subjects. These methods require a separate validation study to estimate the regression coefficient lambda relating the surrogate measure to true exposure. In the linear approximation method, the true logistic regression coefficient beta* is estimated by beta/lambda, where beta is the observed logistic regression coefficient based on the surrogate measure. In the likelihood approximation method, a second-order Taylor series expansion is used to approximate the logistic function, enabling closed-form likelihood estimation of beta*. Confidence intervals for the corrected relative risks are provided that include a component representing error in the estimation of lambda. Based on simulation studies, both methods perform well for true odds ratios up to 3.0; for higher odds ratios the likelihood approximation method was superior with respect to both bias and coverage probability. An example is provided based on data from a prospective study of dietary fat intake and risk of breast cancer and a validation study of the questionnaire used to assess dietary fat intake.

Bias↗

PubMed2000

Effects of measurement error and sampling resolution on estimates of atrial tissue recovery parameters.

We studied the effect of sampling resolution and measurement error on estimates of tissue recovery parameters using experimental and simulated data. Action potential duration (APD) was estimated from monophasic action potentials recorded at 250 sites (delta x = 3.5 mm) on the endocardium of the canine right atrium (n = 8) during control and acetylcholine perfusion. APD distributions were also simulated using a random number generator, then scaled and filtered to physiological values. The following parameters were estimated at increasing APD sampling interval and measurement error: mean APD, standard deviation of APD, mean APD gradient, standard deviation of APD gradient, APD wavelength, and APD correlation length. We found that large errors can result from APDs collected at inadequate sampling intervals and adequate sampling intervals may be 3-6 times less than the Nyquist interval. Large parameter errors also resulted from data with relatively low levels of measurement error. The effect of measurement error was dependent upon the standard deviation of APD, sampling resolution, and APD wavelength. Inadequate sampling resolution was the largest source of error in experimental parameter estimates. Estimates of mean and standard deviation of APD gradient decreased with spacing as estimates of correlation length and wavelength increased. Careful selection of spacing interval, taking into account the spatial complexity of recovery, as well as considerably low measurement errors will produce accurate estimates of gradients, correlation length, and wavelength.

Acetylcholine↗

PubMed2004

Measurement error in covariates in the marginal hazards model for multivariate failure time data.

We consider measurement error in covariates in the marginal hazards model for multivariate failure time data. We explore the bias implications of normal additive measurement error without assuming a distribution for the underlying true covariate. To correct measurement-error-induced bias in the regression coefficient of the marginal model, we propose to apply the SIMEX procedure and demonstrate its large and small sample properties for both known and estimated measurement error variance. We illustrate this method using the Lipid Research Clinics Coronary Primary Prevention Trial data with total cholesterol as the covariate measured with error and time until angina and time until nonfatal myocardial infarction as the correlated outcomes of interest.

Angina Pectoris↗

PubMed2004

Adjustment for baseline measurement error in randomized controlled trials induces bias.

When estimating the treatment effect in a randomized controlled trial, it is common to have a continuous outcome which is also observed at baseline. These observations are often prone to measurement error, for example due to within-patient variability. Controversy exists in the literature about whether baseline measurement error should be adjusted for in this context. Computer simulations were used to compare the biases in the estimated treatment effect, with and without adjusting for measurement error, and for different levels of observed baseline imbalance. The impacts of sample size (30 per group and 300 per group) and reliability coefficient (0.6, 0.8 and 1) were also assessed. The results show that in randomized controlled trials, the ordinary least squares (OLS) estimator without adjusting for measurement error is unbiased. On the contrary, adjusting for measurement error leads to bias, especially when sample sizes are small and/or measurement error is large. The treatment effect adjusting for measurement error is on average overestimated when the baseline mean of the control group is larger than that of the treated group. It is underestimated when the control group has a smaller baseline mean.

Analysis of Variance↗

PubMed2002

The performance of methods for correcting measurement error in case-control studies.

BACKGROUND: It is generally agreed that adjustment for measurement error (when feasible) can substantially increase the validity of epidemiologic analyses. Although a broad variety of methods for measurement error correction has been developed, application in practice is rare. One reason may be that little is known about the robustness of these methods against violations of their restrictive assumptions. METHODS: We carried out a simulation study to assess the performance of two error correction methods (a regression calibration method and a semiparametric approach) as compared with standard analyses without measurement error correction in case-control studies with internal validation data. Performance was assessed over a wide range of model parameters including varying degrees of violations of assumptions. RESULTS: In nearly all the settings assessed, the semiparametric estimate performed better than all alternatives under investigation. The regression calibration method is sensitive to violations of the assumptions of nondifferential error and small error variance. CONCLUSIONS: The semiparametric method is a very robust method to correct for measurement error in case-control studies, but lack of functional software hinders widespread use. If the assumptions for the regression calibration method are fulfilled, application of this method, originally developed for cohort studies, in case-control studies may be a useful alternative that is easy to implement.

Bias↗

PubMed1995

Effect of measurement errors on cardiac output calculated with O2 and modified CO2 Fick methods.

We have investigated the effect of measurement errors on cardiac output, calculated via three different Fick methods. In method 1, the classic O2 Fick equation is expressed in terms of oxygen uptake (VO2), arterial pulse (SaO2) and venous oximetry (SVO2) saturations. The second method, a modified CO2 Fick method, is obtained by replacing VO2 in method 1 with carbon dioxide production (VCO2) divided by the respiratory quotient. In method 3, cardiac output is expressed as VCO2 divided by the product of the SaO2-SVO2 difference and a constant. This constant is determined from initial measurements of VCO2, SaO2, SVO2, and thermodilution cardiac output (Qth). This determination of the constant results in equality of the initial cardiac output of method 3 with the simultaneously determined Qth and, therefore, is similar to performing an autocalibration. For each of the three preceding Fick methods, we derive general expressions that explicitly show how measurement errors (random and systematic) in the Fick variables (VO2, VCO2, SaO2, and SVO2) propagate into errors in calculated cardiac output. The errors in theoretically calculated cardiac output decrease as the SaO2-SVO2 difference increases, except for the systematic error in method 3. The systematic error of method 3 is constant and depends only upon the accuracy of the initial Qth. Analytic expressions for the sensitivity of calculated cardiac output to errors in individual Fick variables are also obtained. Using estimates from the literature for typical systematic and random measurement errors in the Fick variables, the resultant errors in cardiac output are numerically calculated. The effect of random measurement errors on errors in calculated cardiac output was comparable among the three methods. However, the systematic error was least with method 3. Total errors (random and systematic) were comparable among the three methods. Using these numerical measurement errors, we conclude that continuous cardiac output may be calculated with comparable accuracy with each of these methods.

Bias↗

PubMed2000

Assessing the impact of differential measurement error on estimates of fine particle mortality.

In air pollution epidemiology, error in measurements of correlated pollutants has been advanced as a reason to distrust regressions that find statistically significant weak associations. Much of the related debate in the literature and elsewhere has been qualitative. To promote quantitative evaluation of such errors, this paper develops an air pollution time-series model based on correlations among unit-normal variables. Assuming there are no other sources of bias present, the model shows the expected amount of relative bias in the regression coefficients of a bivariate regression of coarse and fine particulate matter measurements on daily mortality. The model only requires information on instrumental error and spatial variability, along with the observed regression coefficients and information on the true fine-course correlation. Analytical results show that if one pollutant is truly more harmful than the other, then it must be measured more precisely than the other in order not to bias the ratio of the fine and course regression coefficients. Utilizing published data, a case study of the Harvard Six-Cities study illustrates use of the model and emphasizes the need for data on spatial variability across the study area. Current epidemiology time-series regressions can use this model to address the general concern of correlated pollutants with differing measurement errors.

Air Pollutants↗

PubMed2005

Isoflurane measurement error using short wavelength infrared techniques in horses: influence of fresh gas flow and pre-anaesthetic food deprivation.

OBJECTIVE: To quantify the isoflurane measurement error arising from the use of short wavelength infrared (IR) anaesthetic gas analysis during low flow anaesthesia in horses. STUDY DESIGN: Prospective clinical study. ANIMAL POPULATION: Sixty-four client-owned horses referred for elective or emergency surgery (age 1-16 years, body mass 400-650 kg). MATERIALS AND METHODS: Horses were divided into four groups based on duration of pre-anaesthetic food deprivation period (FDP) and fresh gas flow during anaesthesia: a high flow group with normal FDP (n = 16) and three groups with low flow and normal (n = 29), long (n = 5) or no (n = 14) FDP, respectively. Circuit isoflurane concentrations were measured simultaneously using a short wavelength (methane-sensitive) analyser (Datex Capnomac Ultima) and a long wavelength (methane-insensitive) analyser (Hewlett Packard M 1025 B) for at least 60 minutes. The difference between the readings of both analysers gave the isoflurane measurement error of short wavelength IR analysis, from which the circuit methane concentration was calculated. RESULTS: In the low flow groups, isoflurane measurement error increased over time, whereas in the high flow group, error remained constant after an initial rise in the first 15 minutes. The isoflurane measurement error was significantly lower (p < 0.005) in the high flow group compared with the low flow-normal FDP group from 15 to 60 minutes. Compared to the low flow - normal FDP group, isoflurane measurement error was significantly smaller (p < 0.001, from 15 to 60 minutes) in the low flow-long FDP group and significantly larger (p = 0.016, at 60 minutes) in the low flow-no FDP group. Within the low flow-no FDP group, values in colic cases did not differ from those in noncolic cases (p > 0.7). CONCLUSIONS: Isoflurane measurement using short wavelength IR absorption is inaccurate. The fresh gas flow and duration of pre-anaesthetic food deprivation influence the isoflurane measurement error during anaesthesia in horses. CLINICAL RELEVANCE: Short wavelength IR analysers are not reliable for isoflurane measurement during (low flow) anaesthesia in horses.

Anesthetics, Inhalation↗

PubMedDate not supplied

Nonsampling measurement error in administrative data: implications for economic evaluations.

Administrative databases are increasingly being used to measure resource use in economic evaluations. Traditionally, it is assumed that any measurement error within the resource data source is stochastic and uncorrelated with group assignment. If the error is correlated with characteristics of the service delivery system and/or correlated by group, the estimated differences in consumption between groups may be reflecting errors in measurement rather than treatment effects. This paper is concerned with the effect of nonsampling measurement error on the internal and external validity of cost estimates based on data drawn from administrative record systems. Two service delivery characteristics, ownership form and financial incentives, are likely to influence systemically an agency's data collection effort. Using data from three community mental health centres located in three different states, evidence of systematic differences in data quality was found; private agencies with reimbursement property rights had higher quality data than public agencies without property rights. Simple tests for detecting variation in service use and costs data and cost-effective solutions for managing these problems are proposed.

Bias↗

PubMed1998

Measurement error, biases, and the validation of complex models for blood lead levels in children.

Measurement error causes biases in regression fits. If one could accurately measure exposure to environmental lead media, the line obtained would differ in important ways from the line obtained when one measures exposure with error. The effects of measurement error vary from study to study. It is dangerous to take measurement error corrections derived from one study and apply them to data from entirely different studies or populations. Measurement error can falsely invalidate a correct (complex mechanistic) model. If one builds a model such as the integrated exposure uptake biokinetic model carefully, using essentially error-free lead exposure data, and applies this model in a different data set with error-prone exposures, the complex mechanistic model will almost certainly do a poor job of prediction, especially of extremes. Although mean blood lead levels from such a process may be accurately predicted, in most cases one would expect serious underestimates or overestimates of the proportion of the population whose blood lead level exceeds certain standards.

Algorithms↗

PubMed2003

Effects of exposure measurement error when an exposure variable is constrained by a lower limit.

Epidemiologic studies routinely suffer from bias due to exposure measurement error. In this paper, the authors examine the effect of measurement error when the exposure variable of interest is constrained by a lower limit. This is an important consideration, since often in epidemiologic studies an exposure variable is constrained by a lower limit such as zero or a nonzero detection limit. In this paper, attenuation of exposure-disease associations is defined within the framework of a classical model of uncorrelated additive error. Then, the special case of nonlinearity due to the effect of a lower threshold is examined. A general model is developed to characterize the effect of random measurement error when there is a lower threshold for recorded values. Findings are illustrated under the assumption that the true exposure follows the lognormal and gamma distributions. The authors show that the direction and magnitude of bias in estimated exposure-response associations depends on the population distribution of the exposure, the magnitude of the recording threshold, the value assigned to below-threshold measurement results, and the variance in the measured exposure due to random measurement error.

Bias↗

PubMed2001

Correcting for measurement error in binary and continuous variables using replicates.

Measurement error in exposures and confounders leads to bias in regression coefficients. It is possible to adjust for this bias if true values or independent replicates are observed on a subsample. We extend a method suitable for quantitative variables to the situation where both binary and quantitative variables are present. Binary variables with independent replicates introduce two extra problems: (i) the error is correlated with the true value, and (ii) the measurement error probabilities are unidentified if only two replicates are available. We show that - under plausible assumptions - adjustment for error in binary confounders does not need to address these problems. The regression coefficient for a binary exposure is overadjusted if methods for continuous variables are used. Correct adjustment is possible either if three replicates are available, or if further assumptions can be made; otherwise, bounds can be put on the correctly adjusted value, and these bounds are reasonably close together if the exposure has prevalence near 0.5.

Bias↗

PubMed1995

Prediction in the presence of measurement error: general discussion and an example predicting defoliation.

Motivated by the particular problem of predicting defoliation based on a measure of gypsy moth egg mass density, prediction in the presence of measurement error is discussed. The measurement error variances and covariances are allowed to vary from unit to unit and are estimated by some type of within unit sampling. A general discussion is given as to when one should correct for the measurement error, and a method of estimating the prediction standard deviation is given when a correction is needed. The results are illustrated with the defoliation example.

Animals↗