134 research outputs found
Scoring and estimating score precision using multidimensional IRT
No full textThe ultimate goal of measurement is to produce a score by which individuals can be assessed and differentiated. Item response theory (IRT) modeling views responses to test items as indicators of a respondent’s standing on some underlying psychological attributes (van der Linden & Hambleton, 1997) – we often call them latent traits – and devises special algorithms for estimating this standing. This chapter gives an overview of methods for estimating person attribute scores using one-dimensional and multi-dimensional IRT models, focusing on those that are particularly useful with patient-reported outcome (PRO) measures.
To be useful in applications, a test score has to approximate the latent trait well, and importantly, the precision level must be known in order to produce information for decision-making purposes. Unlike classical test theory (CTT), which assumes the precision with which a test measures the same for all trait levels, IRT methods assess the precision with which a test measures at different trait levels. In the context of patient-reported outcomes measurement, this enables assessment of the measurement precision for an individual patient. Knowing error bands around the patient’s score is important for informing clinical judgments, such as deciding upon significance of any change, for instance in response to treatment etc. (Reise & Haviland, 2005). At the same time, summary indices are often needed to summarize the overall precision of measurement in a research sample, population group, or in the population as a whole. Much of this chapter is devoted to methods for estimating measurement precision, including the score-dependent standard error of measurement and appropriate sample-level or population-level marginal reliability coefficients.
Patient-reported outcome measures often capture several related constructs, the feature that may make the use of multi-dimensional IRT models appropriate and beneficial (Gibbons, Immekus & Bock, 2007). Several such models are described, including a model with multiple correlated constructs, a model where multiple constructs are underlain by a general common factor (second-order model), and a model where each item is influenced by one general and one group factor (bifactor model). To make the use of these models more easily accessible for applied researchers, we provide specialized formulae for computing test information, standard errors and reliability. We show how to translate a multitude of numbers and graphs conditioned on several dimensions into easy-to-use indices that can be understood by applied researchers and test users alike. All described methods and techniques are illustrated with a single data analysis example involving a popular PRO measure, the 28-item version of the General Health Questionnaire (GHQ28; Goldberg & Williams, 1988), completed in mid-life by a large community sample as a part of a major UK cohort study
Comparing Growth Trajectories of Risk Behaviors From Late Adolescence Through Young Adulthood: An Accelerated Design.
No full textRisk behaviors such as substance use or deviance are often limited to the early stages of the life course. Whereas the onset of risk behavior is well studied, less is currently known about the decline and timing of cessation of risk behaviors of different domains during young adulthood. Prevalence and longitudinal developmental patterning of alcohol use, drinking to the point of drunkenness, smoking, cannabis use, deviance, and HIV-related sexual risk behavior were compared in a Swiss community sample (N = 2,843). Using a longitudinal cohort-sequential approach to link multiple assessments with 3 waves of data for each individual, the studied period spanned the ages of 16 to 29 years. Although smoking had a higher prevalence, both smoking and drinking up to the point of drunkenness followed an inverted U-shaped curve. Alcohol consumption was also best described by a quadratic model, though largely stable at a high level through the late 20s. Sexual risk behavior increased slowly from age 16 to age 22 and then remained largely stable. In contrast, cannabis use and deviance linearly declined from age 16 to age 29. Young men were at higher risk for all behaviors than were young women, but apart from deviance, patterning over time was similar for both sexes. Results about the timing of increase and decline as well as differences between risk behaviors may inform tailored prevention programs during the transition from late adolescence to adulthood
Computerized adaptive testing of population psychological distress:simulation-based evaluation of GHQ-30
No full textPurpose: Goldberg’s General Health Questionnaire (GHQ) items are frequently used to assess psychological distress but no study to date has investigated the GHQ-30’s potential for adaptive administration. In computerized adaptive testing (CAT) items are matched optimally to the targeted distress level of respondents instead of relying on fixed-length versions of instruments. We therefore calibrate GHQ-30 items and report a simulation study exploring the potential of this instrument for adaptive administration in a longitudinal setting.Methods: GHQ-30 responses of 3445 participants with 2 completed assessments (baseline, 7-year follow-up) in the UK Health and Lifestyle Survey were calibrated using item response theory. Our simulation study evaluated the efficiency of CAT administration of the items, cross-sectionally and longitudinally, with different estimators, item selection methods, and measurement precision criteria.Results: To yield accurate distress measurements (marginal reliability at least 0.90) nearly all GHQ-30 items need to be administered to most survey respondents in general population samples. When lower accuracy is permissible (marginal reliability of 0.80), adaptive administration saves approximately 2/3 of the items. For longitudinal applications, change scores based on the complete set of GHQ-30 items correlate highly with change scores from adaptive administrations.Conclusions: The rationale for CAT-GHQ-30 is only supported when the required marginal reliability is lower than 0.9, which is most likely to be the case in cross-sectional and longitudinal studies assessing mean changes in populations. Precise measurement of psychological distress at the individual level can be achieved, but requires the deployment of all 30 items
Erratum: Human settlement of East Polynesia earlier, incremental, and coincident with prolonged South Pacific drought (Proceedings of the National Academy of Sciences of the United States of America(2020)117(8813-8819)DOI: 10.1073/pnas.1920975117)
No full textCorrection for "Human settlement of East Polynesia earlier, incremental, and coincident with prolonged South Pacific drought," byDavid A. Sear,Melinda S. Allen, JonathanD. Hassall, Ashley E. Maloney, Peter G. Langdon, Alex E. Morrison, Andrew C. G. Henderson, Helen Mackay, Ian W. Croudace, Charlotte Clarke, Julian P. Sachs, Georgiana Macdonald, Richard C. Chiverrell, Melanie J. Leng, L. M. Cisneros-Dozal, and Thierry Fonville, which was first published April 6, 2020; 10.1073/pnas.1920975117 (Proc. Natl. Acad. Sci. U.S.A. 117, 8813-8819). The authors note that Emma Pearson should be added to the author list after Thierry Fonville. Emma Pearson should be credited with performing research and analyzing data. The corrected author line, affiliation line, and author contributions appear below. The author line, affiliations, and contributions sections have been corrected online. The authors note that the following statement should be added to the Acknowledgments: "E.P. acknowledges NERC grant BRIS/ 81/0415"
Correction for Sear et al., Human settlement of East Polynesia earlier, incremental, and coincident with prolonged South Pacific drought.
No full textCorrection for "Human settlement of East Polynesia earlier, incremental, and coincident with prolonged South Pacific drought," byDavid A. Sear,Melinda S. Allen, JonathanD. Hassall, Ashley E. Maloney, Peter G. Langdon, Alex E. Morrison, Andrew C. G. Henderson, Helen Mackay, Ian W. Croudace, Charlotte Clarke, Julian P. Sachs, Georgiana Macdonald, Richard C. Chiverrell, Melanie J. Leng, L. M. Cisneros-Dozal, and Thierry Fonville, which was first published April 6, 2020; 10.1073/pnas.1920975117 (Proc. Natl. Acad. Sci. U.S.A. 117, 8813-8819). The authors note that Emma Pearson should be added to the author list after Thierry Fonville. Emma Pearson should be credited with performing research and analyzing data. The corrected author line, affiliation line, and author contributions appear below. The author line, affiliations, and contributions sections have been corrected online. The authors note that the following statement should be added to the Acknowledgments: "E.P. acknowledges NERC grant BRIS/ 81/0415"
General and specific components of depression and anxiety in an adolescent population
No full textAbstract Background Depressive and anxiety symptoms often co-occur resulting in a debate about common and distinct features of depression and anxiety. Methods An exploratory factor analysis (EFA) and a bifactor modelling approach were used to separate a general distress continuum from more specific sub-domains of depression and anxiety in an adolescent community sample (n = 1159, age 14). The Mood and Feelings Questionnaire and the Revised Children's Manifest Anxiety Scale were used. Results A three-factor confirmatory factor analysis is reported which identified a) mood and social-cognitive symptoms of depression, b) worrying symptoms, and c) somatic and information-processing symptoms as distinct yet closely related constructs. Subsequent bifactor modelling supported a general distress factor which accounted for the communality of the depression and anxiety items. Specific factors for hopelessness-suicidal thoughts and restlessness-fatigue indicated distinct psychopathological constructs which account for unique information over and above the general distress factor. The general distress factor and the hopelessness-suicidal factor were more severe in females but the restlessness-fatigue factor worse in males. Measurement precision of the general distress factor was higher and spanned a wider range of the population than any of the three first-order factors. Conclusions The general distress factor provides the most reliable target for epidemiological analysis but specific factors may help to refine valid phenotype dimensions for aetiological research and assist in prognostic modelling of future psychiatric episodes.</p
Impact of the ICD-10 Primary Health Care (PHC) diagnostic and management guidelines for mental disorders on detection and outcome in primary care
No full textBackground The World Health Organization (WHO) ICD-10 Primary Health Care (PHC) Guidelines for Diagnosis and Management of Mental Disorders (1996) have not been evaluated in a pragmatic randomised controlled trial (RCT). Aims: To evaluate the effect of local adaptation and dissemination of the guidelines. Method: Pragmatic, pair-matched, cluster RCT involving 30 practices. Results: Guideline practices were less sensitive but more specific in identifying morbidity, but these differences were not significant. Guideline patients did not differ from usual-care patients on 12-item General Health Questionnaire scores at 3-month follow-up or in the proportion who were still cases. There were no significant differences in secondary outcomes. Conclusions: Attempts to influence clinician behaviour through a process of adaptation and extension of guidelines are unlikely to change detection rates or outcomes
Mokken scaling analysis of Revised Clinical Interview Schedule (CIS-R) psychiatric status rating scales in a nationally representative sample:the 2007 Adult Psychiatric Morbidity Survey of England
No full textThis study aims to investigate double monotonicity of Revised Clinical InterviewSchedule (CIS-R) psychiatric status rating scales data from 2007 Adult PsychiatricMorbidity Survey (APMS) within the framework of Mokken models. Results show that the items of the scale are sufficiently unidimensional in the general population for the CIS-R responses to be scalable according to broad Mokken principles. These do not require recourse to the parametric models for item response function curves typical of most applications of IRT in patient reported outcome measures research (PROMs). Our illustrative results provide an exemplar of the method. The methods are however more widely relevant for phenotype work in clinical and behavioural research, and so should appeal to those who work on addictions or in clinical medicine
Mokken scaling analysis of Revised Clinical Interview Schedule (CIS-R) psychiatric status rating scales in a nationally representative sample:the 2007 Adult Psychiatric Morbidity Survey of England
No full textThis study aims to investigate double monotonicity of Revised Clinical InterviewSchedule (CIS-R) psychiatric status rating scales data from 2007 Adult PsychiatricMorbidity Survey (APMS) within the framework of Mokken models. Results show that the items of the scale are sufficiently unidimensional in the general population for the CIS-R responses to be scalable according to broad Mokken principles. These do not require recourse to the parametric models for item response function curves typical of most applications of IRT in patient reported outcome measures research (PROMs). Our illustrative results provide an exemplar of the method. The methods are however more widely relevant for phenotype work in clinical and behavioural research, and so should appeal to those who work on addictions or in clinical medicine
Biased mentalizing in children aged seven to 11:Latent class confirmation of response styles to social scenarios and associations with psychopathology
No full textA new approach to the measurement of mentalizing is introduced. Instead of measuring the presence or absence of mentalizing capacity, the current study aimed at developing a mentalizing task that focuses on investigating biases in mentalizing through the use of ambiguous peer-related social scenarios. The response consistency of 659 children was investigated in a community sample of children aged seven to 11. Confirmatory latent class analysis allocated children to three groups on the basis of their responses: an overly positive style (OP), a rational/neutral style (R) or an overly negative style (ON). Children classed as OP showed a greater likelihood of being above cut-off on a population screen for externalizing disorder. Over a two-year follow-up period, the children who were classified as R were most likely to remain so whereas the OP and ON children were found to change group. The results are discussed in the context of social-cognitive research in this age group. Further studies should examine the external validity of the mentalizing task because the results reported here concern only internal construct validity.</p
- …
