Negative variance components and intercept-slope correlations greater than one in magnitude: How do such "non-regular" random intercept and slope models arise, and what should be done when they do?

Statistical models with random intercepts and slopes (RIAS models) are commonly used to analyze longitudinal data. Fitting such models sometimes results in negative estimates of variance components or estimates on parameter space boundaries. This can be an unlucky chance occurrence, but can also occur because certain marginal distributions are mathematically identical to those from RIAS models with negative intercept and/or slope variance components and/or intercept-slope correlations greater than one in magnitude. We term such parameters "pseudo-variances" and "pseudo-correlations," and the models "non-regular." We use eigenvalue theory to explore how and when such non-regular RIAS models arise, showing: (i) A small number of measurements, short follow-up, and large residual variance increase the parameter space for which data (with a positive semidefinite marginal variance-covariance matrix) are compatible with non-regular RIAS models. (ii) Non-regular RIAS models can arise from model misspecification, when non-linearity in fixed effects is ignored or when random effects are omitted. (iii) A non-regular RIAS model can sometimes be interpreted as a regular linear mixed model with one or more additional random effects, which may not be identifiable from the data. (iv) Particular parameterizations of non-regular RIAS models have no generality for all possible numbers of measurements over time. Because of this lack of generality, we conclude that non-regular RIAS models can only be regarded as plausible data-generating mechanisms in some situations. Nevertheless, fitting a non-regular RIAS model can be acceptable, allowing unbiased inference on fixed effects where commonly recommended alternatives such as dropping the random slope result in bias.

An indirect comparison of acalabrutinib with and without obinutuzumab vs zanubrutinib in treatment-naive CLL.

ABSTRACT: The efficacy and safety of acalabrutinib plus obinutuzumab and acalabrutinib monotherapy vs zanubrutinib in patients with treatment-naive chronic lymphocytic leukemia/small lymphocytic lymphoma without del(17p) were compared using an unanchored matching-adjusted indirect comparison. Individual patient-level data from ELEVATE-TN (acalabrutinib plus obinutuzumab, n = 162; acalabrutinib monotherapy, n = 163) were weighted to match published aggregate baseline data from SEQUOIA cohort 1, which excluded patients with del(17p) (zanubrutinib, n = 241), using variables that were prognostic/predictive of investigator-assessed progression-free survival (INV-PFS) in an exploratory Cox regression analysis of ELEVATE-TN. After matching, INV-PFS was longer with acalabrutinib plus obinutuzumab (hazard ratio [HR], 0.41; 95% confidence interval [CI], 0.23-0.74) and comparable with acalabrutinib monotherapy (HR, 0.91; 95% CI, 0.53-1.56) vs zanubrutinib. Acalabrutinib monotherapy had significantly lower odds of any grade hypertension vs zanubrutinib (odds ratio [OR], 0.44; 95% CI, 0.20-0.99), whereas acalabrutinib plus obinutuzumab had significantly higher odds of neutropenia (OR, 2.19; 95% CI, 1.33-3.60) and arthralgia (OR, 2.33; 95% CI, 1.37-3.96) vs zanubrutinib. No other significant differences in safety were observed. In summary, acalabrutinib plus obinutuzumab had longer INV-PFS with increased odds of neutropenia and arthralgia than zanubrutinib, whereas acalabrutinib monotherapy had similar INV-PFS with lower odds of any grade hypertension. These trials were registered at www.ClinicalTrials.gov as #NCT02475681 and #NCT03336333.

Effectiveness of Communication-specific Coping Intervention for adults with traumatic brain injury: preliminary results.

People with traumatic brain injury (TBI) describe everyday interactions as a long-term challenge frequently associated with ongoing stress. Communication-specific Coping Intervention (CommCope-I) is a new treatment developed to target coping in the context of communication breakdown. The intervention incorporates principles of cognitive behavioural therapy, self-coaching and context-sensitive social communication therapy. The purpose of this study was to examine the effectiveness of CommCope-I in a group of adults with severe TBI and ongoing functional communication difficulties. Participants were 13 adults with severe TBI (GCS = 3-8; mean age = 35.2 years; mean time post-injury = 7.6 years). The project involved three phases: (1) Control/pre-intervention wait phase (multiple assessments), (2) Treatment (6 weeks), and (3) Follow-up (12 weeks). Repeated measures ANOVA with planned pairwise comparisons were used to test the significance of change. Intervention elicited statistically significant improvements in communication-specific coping, functional communication and stress that were maintained for three months. Improved use of communication-specific coping strategies was evident in clinician blind ratings. Clients reported significant reduction in stress at the end of treatment and one and three months later. This intervention provides a promising means of improving communication-specific coping and reducing communication dysfunction and its negative consequences for people with TBI.