Search

The cost of medical resources used is often recorded for each patient in clinical studies in order to inform decision-making. Although cost data are generally skewed to the right, interest is in making inferences about the population mean cost. Common methods for non-normal data, such as data transformation, assuming asymptotic normality of the sample mean or non-parametric bootstrapping, are not ideal. This paper describes possible parametric models for analysing cost data. Four example data sets are considered, which have different sample sizes and degrees of skewness. Normal, gamma, log-normal, and log-logistic distributions are fitted, together with three-parameter versions of the latter three distributions. Maximum likelihood estimates of the population mean are found; confidence intervals are derived by a parametric BCa bootstrap and checked by MCMC methods. Differences between model fits and inferences are explored. Skewed parametric distributions fit cost data better than the normal distribution, and should in principle be preferred for estimating the population mean cost. However for some data sets, we find that models that fit badly can give similar inferences to those that fit well. Conversely, particularly when sample sizes are not large, different parametric models that fit the data equally well can lead to substantially different inferences. We conclude that inferences are sensitive to choice of statistical model, which itself can remain uncertain unless there is enough data to model the tail of the distribution accurately. Investigating the sensitivity of conclusions to choice of model should thus be an essential component of analysing cost data in practice. Copyright © 2004 John Wiley & Sons, Ltd. [ABSTRACT FROM AUTHOR]

Objective – To examine whether the development of tardive dyskinesia (TD) is accompanied by a parallel process of worsening negative symptoms in a longitudinal study. Method – A sample of 708 psychotic patients were followed over a period of 2 years, using the Abnormal Involuntary Movement Scale and the Scale for the Assessment of Negative symptoms. Results – Of 361 individuals with no prior evidence of dyskinesia, 46 (13%) developed TD by year 2. Independent of the effects of male sex (odds ratio (OR)=2.18, 95% confidence interval: 1.00–4.74), age (OR per quartile group=1.39, 95% CI: 1.01–1.90), duration of exposure to antipsychotic medication (OR=2.35 per 8 months, 95% CI: 1.17–4.72) and average SANS score (OR per quartile group=1.38, 95% CI: 0.99–1.93), worsening of negative symptoms over the 2 previous years was associated with TD onset (OR per quartile group=1.46, 95% CI: 1.07–2.00). Conclusion – The development of TD is linked, independent of the effect of antipsychotics and older age, to an illness‐related pathological process, characterized by worsening negative symptoms. [ABSTRACT FROM AUTHOR]

Objective: To examine whether the development of tardive dyskinesia (TD) is accompanied by a parallel process of worsening negative symptoms in a longitudinal study., Method: A sample of 708 psychotic patients were followed over a period of 2 years, using the Abnormal Involuntary Movement Scale and the Scale for the Assessment of Negative Symptoms (SANS)., Results: Of 361 individuals with no prior evidence of dyskinesia, 46 (13%) developed TD by year 2. Independent of the effects of male sex (odds ratio (OR)=2.18, 95% confidence interval: 1.00-4.74), age (OR per quartile group = 1.39, 95% CI: 1.01-1.90), duration of exposure to antipsychotic medication (OR = 2.35 per 8 months, 95% CI: 1.17-4.72) and average SANS score (OR per quartile group = 1.38, 95% CI: 0.99-1.93), worsening of negative symptoms over the 2 previous years was associated with TD onset (OR per quartile group = 1.46, 95% CI: 1.07-2.00)., Conclusion: The development of TD is linked, independent of the effect of antipsychotics and older age, to an illness-related pathological process, characterized by worsening negative symptoms.

It is commonly held that women are more at risk of developing tardive dyskinesia (TD). However, recent evidence suggests that this may only be the case in samples of older patients, men being more at risk in the younger age groups. Abnormal movements were measured with the Abnormal Involuntary Movement Scale (AIMS) in a sample of 706 chronic psychotic patients aged not older than 65 years (median age 36 years). Female gender was associated with a lower risk of TD (OR, 0.5; 95% CI, 0.3-0.7). The effect of gender was independent of other risk factors such as older age, severity of negative symptoms and exposure to antipsychotic medication in the previous 2 years. There was no evidence that the effect of these risk factors differed between the sexes. In samples of relatively young patients with chronic psychotic illness, who typically represent the majority of patients in community programmes for the severely mentally ill, men are more at risk of TD than women.

Factor VII was assayed in healthy adults and pregnant women by a coagulation method (VIIc) and a procedure (VIIt) based upon activation of factor X. Although VIIc and VIIt were highly correlated (r 0.8) they apparently measured different aspects of VII activity. This difference was related to plasma lipid concentrations. Plasma VIIc showed independent positive associations in vivo with VIIt, cholesterol and triglyceride concentrations, but was unaffected by in vitro adjustment of plasma lipoprotein concentrations. The difference between assays might be due to differing reactivities of VII. The VIIc assay measures VII in its in vivo proportions as the single-chain protein and fully active double-chain form (alpha VIIa). In VIIt, all VII is converted to alpha VIIa before measurement. Thus an increase in VIIc but not VIIt with increasing lipid concentrations reflects an increased proportion of VII as alpha VIIa, possibly secondary to activation of the contact system. This effect may explain at least part of the increased VIIc and normal VIIt in pregnancy, and the increased VIIc of hyperlipidaemias in general. The relative values of VIIc and VIIt are proposed as a measure of flux within the coagulation system, and as a measure of coagulability in hyperlipidaemia and other states.