Statistical analysis of fever interval data

Periodic fever syndromes usually do not show a clear fixed periodicity, and hence cannot be described by the mean and the standard deviation of the interval length. In those cases statistical tools must be used. Fever interval data can be described as a random point process; the renewal density function and its Fourier transform can be used to uncover hidden periodicities. In this report the estimation and evaluation of the renewal density function are described. The data of three patients with periodic fever were investigated. In one of these patients, suffering from periodic fever originating at the level of the hypothalamus, a 30-day periodicity was observed. In a female patient with hyperimmunoglobulinaemia D and periodic fever, menstruation often coincided with or was preceded by a fever episode. In the third patient with a Familial Hibernian Fever-like syndrome, an irregular fever pattern and no periodicity were found. The computerized analysis of the fever intervals may be useful in assessing various periodic fever syndromes.     

Alternative data treatment principles for categorical ADL data

Scaling methodology represents a problem in assessments of activities of daily living (ADL) and little is known about how the results of these assessments are affected by data treatment principles and statistical methods. The aims of this paper are to: (i) describe alternative ways of transforming a response pattern on ADL into a single number; and (ii) to present and compare different ways of analysing both changes in ADL capacity from one occasion to another and also differences in ADL between one group and another. Three datasets based on assessments with the ADL Staircase were used. Four different data treatment principles were described and the development of a novel principle to transform response patterns into ranks was put forward. Thereafter, different paired-data cases and two-sample cases were analysed, using different statistical standard methods to explore possible variations in results. The results demonstrated a few marked differences among P values, no matter which data treatment principle or statistical method was used. That is, different principles and methods yield similar results in terms of P values, although there are important differences as regards selection bias. Principles and methods respecting the ordinal character of ADL data encourage the use of non-parametric methods and the novel rank principle presented here is a useful alternative.     

Statistical presentation and analysis of ordinal data in nursing research

OBJECTIVES: The aim of this study was to review the presentation and analysis of ordinal data in three international nursing journals in 2003. METHOD: In total, 166 full-length articles from the 2003 editions of Cancer Nursing, Scandinavian Journal of Caring Sciences and Nursing Research were reviewed for their use of ordinal data. RESULTS: This review showed that ordinal scales were used in about a third of the articles. However, only about half of the articles that used ordinal data had appropriate data presentation and only about half of the analyses of the ordinal data were performed properly. CONCLUSIONS: Ordinal data are rather common in nursing research, but a large share of the studies do not present/analyse the result properly. Incorrect presentation and analysis of the data may lead to bias and reduced ability to detect statistical differences or effects, resulting in misleading information. This highlights the importance of knowledge about data level, and underlying assumptions for the statistical tests must be considered to ensure correct presentation and analyses of data.     

Body mass index estimates using a categorical body weight variable: A cross-sectional secondary data analysis

BackgroundSelf-reported weight data have been considered questionable because of under- or over-reporting trends and stigma, especially among females.ObjectivesThis study aimed to evaluate the quality of self-reported categorical weight information used to determine body mass index (BMI) groups among females.DesignCross-sectional secondary data analysis.SettingsThis study used two datasets: a nurse survey of the Nurses Worklife and Health Study (NWHS) in the 2 US states, and the 2003–2004 National Health and Nutrition Examination Survey (NHANES).ParticipantsThis analysis included 2203 female nurses in the NWHS and 606 female participants in the NHANES, all of whom aged 22–83 years and were currently employed with at least a college education.MethodsBMI groups created using self-reported categorical weight data were compared to those derived from continuous weight responses and to the gold standard: scale measured weight data.ResultsWhen using the median values of each weight category, similar distributions of BMI groups were found to those obtained from continuous self-reported responses and direct scaled measures of weight. The groupings derived from the BMI median estimates demonstrated good agreement with those obtained from the directly scaled BMI data and good criterion/construct validity.ConclusionsBMI-based weight groups derived from self-reported categorical weight responses demonstrated good psychometric properties when the median value was used to calculate the BMI, and may promote more complete responding, especially among women.     

Analyzing interrater agreement for categorical data using Cohen's kappa and alternative coefficients

Within rehabilitation research ratings are one of the most frequently used assessment procedures. For example, therapists frequently make categorical judgements aiming to get information whether specific patient characteristics prevail or not (dichotomous rating format) or which of several alternatives holds for a patient (polytomous rating format). Interrater agreement is an important prerequisite to ensure that reliable and meaningful information concerning patients' state can be inferred from the data obtained. Cohen's kappa (Cohen's kappa) is the most frequently used measure to quantify interrater agreement. The properties of Cohen's kappa are characterized and conditions for the appropriate application of kappa are clarified. Because sometimes specific properties of kappa are not appropriately considered, misleading interpretations of this measure may easily arise. This is the case because the value of Cohen's kappa is affected by information aspects that are independent of the quality of the rating process. In order to avoid such misconceptions, alternative evaluation strategies are described for dichotomous rating formats which enhance agreement analysis and thus ensure a more valid interpretation. In addition, it is shown how weighted Cohen's kappa (omega) may be used to analyze polytomous rating formats.     

Statistical analysis of population screening

Statistical techniques used for the evaluation and monitoring of screening tests and screening programmes are reviewed. Though many differences exist between screening to prevent congenital abnormalities, and screening to prevent death from chronic disease, the two are considered together. Analysis for other instances of medical screening will be conceptually similar to one or other of these.     

Statistical methods for assessing agreement for ordinal data

Evaluation of various methods in clinical practice is often based on interpretations by two or more observers. Such data need to be analysed with correct statistics, or the results and conclusions may be misleading. In this study, the use of measures of agreement for ordinal data in five international nursing journals is reviewed and various methods for measuring agreement are presented and discussed. Analyses of agreement did not seem to be very common in nursing research, but a great variation was found regarding the choice of method for analysing agreement. Both acceptable and unacceptable methods were found in the articles reviewed. When choosing among various methods for agreement the weighted kappa-coefficient is probably the most useful for ordinal data, but several issues of concern arise and need to be taken into consideration when using these types of analyses.     

Statistical shape analysis using non-Euclidean metrics

The contribution of this paper is the adaptation of data driven methods for non-Euclidean metric decomposition of tangent space shape coordinates. The basic idea is to extend principal component analysis (PCA) to take into account the noise variance at different landmarks and at different shapes. We show examples where these non-Euclidean metric methods allow for easier interpretation by decomposition into meaningful modes of variation. The extensions to PCA are based on adaptation of maximum autocorrelation factors and the minimum noise fraction transform to shape decomposition. A common basis of the methods applied is the assessment of the annotation noise variance at individual landmarks. These assessments are based on local models or repeated annotations by independent operators. We show that the Molgedey-Schuster independent component analysis is equivalent to the maximum autocorrelation factors. Finally, the different subspace methods are compared using a probabilistic formulation based on their ability to represent the data.     

Complexity and categorical analysis may improve the interpretation of agreement studies using continuous variables

Rationale Complex clinical scenarios involving a high degree of uncertainty frequently lead to a poor agreement over diagnosis and management. However, inconsistent results can be found with the most widely used measures of agreement for continuous variables – the limits of agreement and the intraclass correlation coefficient. Aims and objectives We aim to improve the interpretation of agreement studies using continues variables. Methods and results Evaluation of agreement may be improved by complexity analysis and by categorization of variables, followed by the use of the proportions of agreement. Conclusions The average never characterizes a complex phenomenon and the methods used to access agreement in continuous variables are based on the mean. For future agreement studies, involving complex continuous variables, we recommend a complexity and categorical analysis.     

Statistical analysis of hippocampal asymmetry in schizophrenia

The asymmetry of brain structures has been studied in schizophrenia to better understand its underlying neurobiology. Brain regions of interest have previously been characterized by volumes, cross-sectional and surface areas, and lengths. Using high-dimensional brain mapping, we have developed a statistical method for analyzing patterns of left-right asymmetry of the human hippocampus taken from high-resolution MR scans. We introduce asymmetry measures that capture differences in the patterns of high-dimensional vector fields between the left and right hippocampus surfaces. In 15 pairs of subjects previously studied (J. G. Csernansky et al., 1998, Proc. Natl. Acad. Sci. USA 95, 11406-11411). we define the difference in hippocampal asymmetry patterns between the groups. Volume analysis indicated a large normative asymmetry between left and right hippocampus (R > L), and shape analysis allowed us to visualize the normative asymmetry pattern of the hippocampal surfaces. We observed that the right hippocampus was wider along its lateral side in both schizophrenia and control subjects. Also, while patterns of hippocampal asymmetry were generally similar in the schizophrenia and control groups, a principal component analysis based on left-right asymmetry vector fields detected a statistically significant difference between the two groups, specifically related to the subiculum.     

Statistical considerations for analysis of microarray experiments

Microarray technologies enable the simultaneous interrogation of expressions from thousands of genes from a biospecimen sample taken from a patient. This large set of expressions generates a genetic profile of the patient that may be used to identify potential prognostic or predictive genes or genetic models for clinical outcomes. The aim of this article is to provide a broad overview of some of the major statistical considerations for the design and analysis of microarrays experiments conducted as correlative science studies to clinical trials. An emphasis will be placed on how the lack of understanding and improper use of statistical concepts and methods will lead to noise discovery and misinterpretation of experimental results.     

Statistical mapping analysis of lesion location and neurological disability in multiple sclerosis: application to 452 patient data sets

In multiple sclerosis (MS), the correlation between disability and the volume of white matter lesions on magnetic resonance imaging (MRI) is usually weak. This may be because lesion location also influences the extent and type of functional disability. We applied an automatic lesion-detection algorithm to 452 MRI scans of patients with relapsing-remitting MS to identify the regions preferentially responsible for different types of clinical deficits. Statistical parametric maps were generated by performing voxel-wise linear regressions between lesion probability and different clinical disability scores. There was a clear distinction between lesion locations causing physical and cognitive disability. Lesion likelihood correlated with the Expanded Disability Status Scale (EDSS) in the left internal capsule and in periventricular white matter mostly in the left hemisphere. Pyramidal deficits correlated with only one area in the left internal capsule that was also present in the EDSS correlation. Cognitive dysfunction correlated with lesion location at the grey-white junction of associative, limbic, and prefrontal cortex. Coordination impairment correlated with areas in interhemispheric and pyramidal periventricular white matter tracts, and in the inferior and superior longitudinal fascicles. Bowel and bladder scores correlated with lesions in the medial frontal lobes, cerebellum, insula, dorsal midbrain, and pons, areas known to be involved in the control of micturition. This study demonstrates for the first time a relationship between the site of lesions and the type of disability in large scale MRI data set in MS.     

Qualitative data analysis using data displays

The amount of data generated in qualitative research can be difficult to manage. In this paper Tracey Williamson and Andrew Long discuss how the use of data displays can improve data management and also how the process can help to make the routes from raw data to research findings in qualitative research more transparent. Data displays can take several forms but share the benefit of helping to condense large amounts of data into more manageable forms. They can also help to convey information in a visually stimulating format where presentation time or column space may be limited.