Statistics publications
Permanent URI for this collection
Browse
Browsing Statistics publications by Issue Date
Now showing 1 - 20 of 48
Results Per Page
Sort Options
Item Metadata only Statistical models for prevalent cohort data(International Biometrics Society, 1995) Ripley, B.; Solomon, P.Item Metadata only Effect of mistletoes, Amyema preissi, on host, acacia victoriae, survival(Blackwell Scientific Publications, 1995) Reid, N. C. H.; Stafford Smith, M.; Venables, William N.Item Metadata only A review of the technical features of breast cancer screening illustrated by a specific model using South Australian Cancer Registry data(Edward Arnold, 1995) O'Neill, Terence J.; Tallis, George M.; Leppard, Phillip I.Item Metadata only Measuring by citation: Dangerously misleading?(Brian Wexham, 1995) Carey, A.; Solomon, P.; Wilson, S.Item Metadata only REML estimation of multiplicative effects in multi-environment variety trials(International Biometrics Society, 1995) Verbyla, A.; Gogel, B.; Cullis, B.Item Metadata only The force-interval relationship of the left ventricle: a quantitative description in patients with ischemic heart disease(Elsevier BV, 1995) Ritchie, R.; Wuttke, R.; Hii, J.; Jarrett, R.; Carey, A.; Horowitz, J.Quantitative descriptions of the mechanical restitution curve as a description of variability in ventricular performance with coupling interval in isolated tissue preparations are widely available. In humans, however, in vivo examination of the force-interval relationship is restricted to test pulse intervals shorter than the sinus cycle length (i.e., incomplete mechanical restitution). The primary objectives in this investigation were therefore to examine this aspect of mechanical restitution in patients with ischemic heart disease and to develop a quantitative description of the phenomenon. Mechanical restitution curves were constructed in 40 patients, most of whom had well-preserved left ventricular (LV) systolic function, undergoing diagnostic cardiac catheterization for the investigation of chest pain, using a single premature test pulse interval during baseline atrial pacing. The mechanical restitution curve, the relationship between LV + dP/dtmax and test pulse interval, was fitted to a rectangular hyperbolic function. From this, the parameter c, the calculated proportional decrease in LV + dP/dtmax at 60% of the resting cycle length, was derived. The mechanical restitution curve-fitting model (involving determination of c) satisfactorily described the force-interval relationship in 37 of the 40 patients studied (as a rectangular hyperbola in 31 and with simple linear regression in 6 patients). The refractory period of the atria/atrioventricular node limited accurate use of the model in the remaining three patients. The parameter c was inversely proportional to both baseline atrial pacing cycle length (P < .001) and LV ejection fraction (P < .02) In patients with normal LV ejection fractions, the derived value of c at a cycle length of 800 ms (c800) was 29.0% baseline LV + dP/dtmax (95% confidence interval, 23.0, 35.0). The presence of hemodynamically significant ischemic heart disease was not a predictor of the parameters of the model. After intravenous injection of the beta-adrenoreceptor antagonist metoprolol in seven patients, there was a significant (P < .05) reduction in both c and LV + dP/dtmax at the baseline atrial pacing cycle length. Thus, the force-interval relationship can be quantitatively studied using incomplete mechanical restitution curves in humans in vivo. This quantitative description probably reflects relative intracellular calcium availability via slow channel activity and can be used to assess effects of cardioactive drugs on frequency-dependent inotropic mechanisms in humans. The predictive value of this mechanical restitution curve model for hemodynamic instability during tachycardia in patients with impaired LV function remains to be determined.Item Metadata only Parenteral magnesium sulfate versus amiodarone in the therapy of atrial tachyarhythmias: A prospective randomized study(Williams & Wilkins, 1995) Moran, J.; Gallagher, J.; Peake, S.; Cunningham, D.; Salagaras, M.; Leppard, P.Objective
To compare the efficacy of parenteral magnesium sulfate vs. amiodarone in the therapy of atrial tachyarrhythmias in critically ill patients.Design
Prospective, randomized study.Setting
Multidisciplinary intensive care unit (ICU) at a university teaching hospital.Patients
Forty-two patients, 21 medical and 21 surgical, of mean (SD) age 67 +/- 15 yrs and mean Acute Physiology and Chronic Health Evaluation II score of 22 +/- 6, with atrial tachyarrhythmias (ventricular response rate of > or = 120 beats/min) sustained for > or = 1 hr.Interventions
After correction of the plasma potassium concentration to > or = 4.0 mmol/L, patients were randomly allocated to treatment with either a) magnesium sulfate 0.037 g/kg (37 mg/kg) bolus followed by 0.025 g/kg/hr (25 mg/kg/hr); or b) amiodarone 5 mg/kg bolus and 10 mg/kg/24-hr infusion. Therapeutic plasma magnesium concentration in the magnesium sulfate group was 1.4 to 2.0 mmol/L. Therapeutic end point was conversion to sinus rhythm over 24 hrs.Measurements and main results
At study entry (time 0), initial mean ventricular response rate and systolic blood pressure were 151 +/- 16 (SD) beats/min and 127 +/- 30 mm Hg in the magnesium sulfate group vs. 153 +/- 23 beats/min and 123 +/- 23 mm Hg in the amiodarone group, respectively (p = .8 and .65). Plasma magnesium (time 0) was 0.84 +/- 0.20 vs. 1.02 +/- 0.22 mmol/L in the magnesium and amiodarone group, respectively (p = .1). Eight patients had chronic dysrhythmias (magnesium 3, amiodarone 5). Excluding the two patient deaths (amiodarone group, time 0 + 12 to 24 hrs), no significant change in systolic blood pressure subsequently occurred in either group. In the magnesium group, mean plasma magnesium concentrations were 1.48 +/- 0.36, 1.82 +/- 0.41, 2.16 +/- 0.45, and 1.92 +/- 0.49 mmol/L at time 0 + 1, 4, 12 and 24 hrs, respectively. By logistic regression, the probability of conversion to sinus rhythm was significantly better for magnesium than for amiodarone at time 0 + 4 (0.6 vs. 0.44), 12 (0.72 vs. 0.5), and 24 (0.78 vs. 0.5) hrs. In patients not converting to sinus rhythm, a significant decrease in ventricular response rate occurred at time 0 + to 0.5 hrs (mean decrease 19 beats/min, p = .0001), but there was no specific treatment effect between the magnesium and the amiodarone groups; thereafter, there was no significant reduction in ventricular response rate over time in either group.Conclusions
Intravenous magnesium sulfate is superior to amiodarone in the conversion of acute atrial tachyarrhythmias, while initial slowing of ventricular response rate in nonconverters appears equally efficacious with both agents.Item Metadata only Response to discussion of `AIDS: modelling and predicting' by N.E. Day.(Cambridge University Press., 1996) Solomon, P.Item Metadata only A conditional likelihood approach to residual maximum likelihood estimation in generalized linear models(Wiley, 1996) Smyth, G.; Verbyla, A.Residual maximum likelihood (REML) estimation is often preferred to maximum likelihood estimation as a method of estimating covariance parameters in linear models because it takes account of the loss of degrees of freedom in estimating the mean and produces unbiased estimating equations for the variance parameters. In this paper it is shown that REML has an exact conditional likelihood interpretation, where the conditioning is on an appropriate sufficient statistic to remove dependence on the nuisance parameters. This interpretation clarifies the motivation for REML and generalizes directly to non-normal models in which there is a low dimensional sufficient statistic for the fitted values. The conditional likelihood is shown to be well defined and to satisfy the properties of a likelihood function, even though this is not generally true when conditioning on statistics which depend on parameters of interest. Using the conditional likelihood representation, the concept of REML is extended to generalized linear models with varying dispersion and canonical link. Explicit calculation of the conditional likelihood is given for the one-way lay-out. A saddlepoint approximation for the conditional likelihood is also derived.Item Metadata only Acute physiology and chronic health evaluation (APACHE II) scoring system recalculated and reconsidered(1996) Moran, J.; Leppard, P.; Finnis, M.; Peisach, R.Item Metadata only Oxygen uptake at various levels of pressure support in mechanically ventilated patients suitable for extubation.(1996) John, G.; Moran, John L.; Leppard, Phillip I.Item Metadata only AIDS: Modelling and Predicting.(Cambridge University Press., 1996) Solomon, P.Item Metadata only Predicting patient outcome in an adult intensive care unit: an evaluation of the Mortality Probability Model II.(1996) Moran, J.; Leppard, P.; Finnis, M.; Grealy, B.; Peisach, R.Item Metadata only Comparative performance of oxygenation indices in ICU patients.(1996) Finnis, M.; Moran, J.; Leppard, P.Item Metadata only Is Length of Life Predictable?(1997) Tallis, George M.; Leppard, Phillip I.Item Metadata only Accounting for natural and extraneous variation in the analysis of field experiments(Springer Verlag, 1997) Gilmour, A.; Cullis, B.; Verbyla, A.We identify three major components of spatial variation in plot errors from field experiments and extend the two-dimensional spatial procedures of Cullis and Gleeson (1991) to account for them. The components are nonstationary, large-scale (global) variation across the field, stationary variation within the trial (natural variation or local trend), and extraneous variation that is often induced by experimental procedures and is predominantly aligned with rows and columns. We present a strategy for identifying a model for the plot errors that uses a trellis plot of residuals, a perspective plot of the sample variogram and, where possible, likelihood ratio tests to identify which components are present. We demonstrate the strategy using two illustrative examples. We conclude that although there is no one model that adequately fits all field experiments, the separable autoregressive model is dominant. However, there is often additional identifiable variation present.Item Metadata only Efficient Two-Replicate Resolvable Row-Column Designs(1997) Jarrett, Richard Gentry; Piper, F. C.; Wild, Peter R.Item Metadata only Genotype by Environment Variance Heterogeneity in a Two-Stage Analysis(1997) Frensham, A.; Cullis, B.; Verbyla, A.Item Metadata only Parameter orthogonality in mixed regression models for survival data(Royal Statistical Society, 1997) Hutton, J.; Solomon, P.The implications of parameter orthogonality for the robustness of survival regression models are considered. The question of which of the proportional hazards or the accelerated life families of models would be more appropriate for analysis is usually ignored, and the proportional hazards family is applied, particularly in medicine, for convenience. Accelerated life models have conventionally been used in reliability applications. We propose a one-parameter family mixture survival model which includes both the accelerated life and the proportional hazards models. By orthogonalizing relative to the mixture parameter, we can show that, for small effects of the covariates, the regression parameters under the alternative families agree to within a constant. This recovers a known misspecification result. We use notions of parameter orthogonality to explore robustness to other types of misspecification including misspecified base-line hazards. The results hold in the presence of censoring. We also study the important question of when proportionality matters.
- «
- 1 (current)
- 2
- 3
- »