Implications Of Measurement Error Research Articles

Valuing urban open space using the travel-cost method and the implications of measurement error

Urbanization has placed pressure on open space within and adjacent to cities. In recent decades, a greater awareness has developed to the fact that individuals derive multiple benefits from urban open space. Given the location, there is often a high opportunity cost to preserving urban open space, thus it is important for both public and private stakeholders to justify such investments. The goals of this study are twofold. First, we use detailed surveys and precise, accessible, mapping methods to demonstrate how travel-cost methods can be applied to the valuation of urban open space. Second, we assess the degree to which typical methods of estimating travel times, and thus travel costs, introduce bias to the estimates of welfare. The site we study is Taylor Mountain Regional Park, a 1100-acre space located immediately adjacent to Santa Rosa, California, which is the largest city (∼170,000 population) in Sonoma County and lies 50 miles north of San Francisco. We estimate that the average per trip access value (consumer surplus) is $13.70. We also demonstrate that typical methods of measuring travel costs significantly understate these welfare measures. Our study provides policy-relevant results and highlights the sensitivity of urban open space travel-cost studies to bias stemming from travel-cost measurement error.

Moisture content correction: Implications of measurement errors on tree- and site-based estimates of biomass

Accurate estimates of biomass are required for relating ecosystem functioning to atmospheric carbon regulation. Biomass may be directly measured through field sampling, which can then be used to calibrate biomass predictions from remote sensing and/or modelling. Field sampling generally entails measuring the fresh mass of individual trees or shrubs and then estimating the moisture contents of a representative sub-samples, which are then used to calculate dry mass. Because any errors in the estimation of the moisture content (MC) correction are translated proportionally to the biomass prediction of an individual tree or shrub, care is required to ensure MC estimates are unbiased and as precise as possible. There are numerous different protocols currently applied to attain MC, with these differing in accuracy (bias and precision) and cost of implementation. A dataset of MC of above-ground biomass (AGB) of 1396 individuals (trees or shrubs) was used to assess which protocols for within- and among-individual sampling are likely to provide the most cost-effective estimates of MC within acceptable bounds of accuracy. Monte-Carlo analysis was used to explore key sources of error in within-individual MC estimation. Results suggest these MC estimates may be based on at least the bole and crown components of AGB, with bias resulting if MC is based on stem wood only, particularly in young (or small) individuals. Little gain in accuracy was attained with more intensive sub-sampling (e.g. into foliage, twig, branches, bark, and stem wood components). Moreover, further efficiencies may be gained by applying existing empirical models to estimate the proportion of AGB that is crown based on easily measured variables such as stem diameter, thereby avoiding the resource-intensive process of partitioning to obtain fresh weights measurements of components. However to minimise bias, it is important to undertake MC sampling at each study site, and to stratify sampling among-individuals by both appropriate taxonomic grouping (e.g. plant functional type) and age-class. For a given plant functional type-by-size (or age) strata at a given site a precision of about 4% coefficient of variation of the average MC estimate can be achieved with intensive within- and among-individual sampling. However a precision of 8–10% is achievable using our recommended less intensive but more efficient protocol; derive an average MC for at least six individuals, and for each individual, intensively sub-sample bole and crown components for MC, which is then applied to the fresh weights of these components. This latter estimate may be obtained from partitioning of the AGB, or for the highest efficiency, from predictions obtained from the application of existing representative empirical relationships of partitioning based on the size of the individual.

Air Pollution and Autism Spectrum Disorders: Causal or Confounded?

In the last decade, several studies have examined the association between perinatal exposure to ambient air pollution and risk of autism spectrum disorder (ASD). These studies have largely been consistent, with associations seen with different aspects of air pollution, including hazardous air toxics, ozone, particulate, and traffic-related pollution. Confounding by socioeconomic status (SES) and place of residence are of particular concern, as these can be related to ASD case ascertainment and other potential causal risk factors for ASD. While all studies take steps to address this concern, residual confounding is difficult to rule out. Two recent studies of air pollution and ASD, however, present findings that strongly argue against residual confounding, especially for factors that do not vary over relatively short time intervals. These two studies, conducted in communities around the USA, found a specific association with air pollution exposure during the 3rd, but not the 1st, trimester, when both trimesters were modeled simultaneously. In this review, we discuss confounding possibilities and then explain-with the aid of directed acyclic graphs (DAGs)-why an association that is specific to a particular time window, when multiple exposure windows are simultaneously assessed, argues against residual confounding by (even unmeasured) non-time-varying factors. In addition, we discuss why examining ambient air pollution concentration as a proxy for personal exposure helps avoid confounding by personal behavior differences, and the implications of measurement error in using ambient concentrations as a proxy for personal exposures. Given the general consistency of findings across studies and the exposure-window-specific associations recently reported, the overall evidence for a causal association between air pollution and ASD is increasingly compelling.

An Examination of the Quality and Utility of Interviewer Observations in the National Survey of Family Growth

SummarySurvey agencies have started to use interviewer observations collected on all sample units to adjust survey estimates for non-response. Ideally, these observations should be related to both response indicators and key survey variables. However, these observations are typically judgements that are made by the interviewers, making them potentially prone to measurement error. Presenting analyses of data from the National Survey of Family Growth in the USA, this study examines the quality and utility of these interviewer observations and considers the implications of measurement errors in these observations for the effectiveness of non-response adjustments.

No Such Effect? The Implications of Measurement Error in Self-Report Measures of Mobile Communication Use

Research on the social and psychological effects of mobile phone communication primarily is conducted using self-report measures of use. However, recent studies have suggested such measures of mobile phone communication use contain a significant amount of measurement error. This study compares the frequency of mobile phone use measured by self-report questions with error-free log data automatically collected through an Android smartphone application. Using data from 310 Android phone users in Japan, we investigate the extent to which nonrandom measurement error exists in self-report responses to questions about mobile phone use and predictors of this error. Our analysis shows that users generally overreport their frequency of mobile communication and that overestimation is better predicted by proxy measures of social activity than demographic variables. We further show an example of how overreporting can result in an overestimation of the effects of mediated communication on civic engagement. Finally, the value of behavioral log data in mediated communication research is discussed.

MEASUREMENT ERROR IN RESEARCH ON HUMAN RESOURCES AND FIRM PERFORMANCE: ADDITIONAL DATA AND SUGGESTIONS FOR FUTURE RESEARCH

Gerhart and colleagues (2000) and Huselid and Becker (2000) recently debated the presence and implications of measurement error in measures of human resource practices. This paper presents data from 3 more studies, 1 of large organizations from different industries at the corporate level, 1 from commercial banks, and the other of autonomous business units at the level of the job. Results of all 3 studies provide additional evidence that single respondent measures of HR practices contain large amounts of measurement error. Implications for future research into the HR firm performance relationship are discussed.

Implications of measurement error in exposure for the sample sizes of case-control studies.

In this paper, recent results describing the effects of measurement error on estimation of the association between an exposure and a disease are applied to sample size calculation in case-control studies. Models of the relation between true exposure and a surrogate exposure measure assessed with error are used to derive equations for sample size determination. The results show that the sample size of a study based on an exposure variable which is measured with error must be larger by a factor of 1/rho 2 than if exposure were measured without error, where rho is the correlation between the true exposure and the surrogate exposure measure. Review of the magnitude of measurement error in dietary assessments suggests that failure to account for measurement error in sample size determination for case-control studies of diet and disease could lead to marked underestimation of the required sample size.

Sexual assessment and the epidemiology of AIDS

Research on the transmission dynamics of AIDS necessitates an extraordinarily rigorous sexual science. Thus, the purpose of the present paper is to isolate sexual parameters which are crucial to the epidemiology of AIDS. Several representative mathematical models of the proliferation of HIV are described. From these models, three consistent sexual parameters emerge (sexual orientation, anal intercourse, and selection of sexual partners). Consequently, each parameter is examined for the feasibility of assessment and the reliability of existing data. However, as the present review suggests, the relevant data on sexual parameters are either marginal or nonexistent. Therefore, alternatives are described, and the broader implications of measurement error on epidemiological predictions is developed.

Teaching concepts of clinical measurement variation to medical students.

An exercise in clinical epidemiology was developed for medical students to demonstrate the process and limitations of scientific measurement using models that simulate common clinical experiences. All scales of measurement (nominal, ordinal and interval) were used to illustrate concepts of intra- and interobserver variation, systematic error, recording error, and procedural error. In a laboratory, students a) determined blood pressures on six videotaped subjects, b) graded sugar content of unknown solutions from 0 to 4+ using Clinitest tablets, c) measured papules that simulated PPD reactions, d) measured heart and kidney size on X-rays and, e) described a model skin lesion (melanoma). Traditionally, measurement variation is taught in biostatistics or epidemiology courses using previously collected data. Use of these models enables students to produce their own data using measurements commonly employed by the clinician. The exercise provided material for a meaningful discussion of the implications of measurement error in clinical decision-making.