The effects of clustered data on standard error estimates in covariance structure analysis : a field data application

Purpose – The purpose of this article is to present an empirical analysis of complex sample data with regard to the biasing effect of non-independence of observations on standard error parameter estimates. Using field data structured in the form of repeated measurements it is to be shown, in a two-factor confirmatory factor analysis model, how the bias in SE can be derived when the non-independence is ignored.

Design/methodology/approach – Three estimation procedures are compared: normal asymptotic theory (maximum likelihood); non-parametric standard error estimation (naïve bootstrap); and sandwich (robust covariance matrix) estimation (pseudo-maximum likelihood).

Findings – The study reveals that, when using either normal asymptotic theory or non-parametric standard error estimation, the SE bias produced by the non-independence of observations can be noteworthy.

Research limitations/implications – Considering the methodological constraints in employing field data, the three analyses examined must be interpreted independently and as a result taxonomic generalisations are limited. However, the study still provides “case study” evidence suggesting the existence of the relationship between non-independence of observations and standard error bias estimates.

Originality/value – Given the increasing popularity of structural equation models in the social sciences and in particular in the marketing discipline, the paper provides a theoretical and practical insight into how to treat repeated measures and clustered data in general, adding to previous methodological research. Some conclusions and suggestions for researchers who make use of partial least squares modelling are also drawn.

Legal ethics is (just) normal ethics: towards a coherent system of legal ethics

The standards governing how lawyers ought to conduct themselves consist of a number disparate principles and rules, which are devoid of an overarching rationale. We argue that legal ethics is not a stand-alone social construct. Rather, it is the application of normal ethical principles so far as they relate to the law. Approached in this manner, legal ethics becomes a far more coherent and justifiable institution. In this paper we apply general moral theory to several key dilemmas facing lawyers. This results in outcomes which some may find counter-intuitive. We conclude that lawyers should not do pro bono work; that the first cab rank off the rank principle is unsound and that there is no relevant difference between expressly misleading the court and putting the other side to the proof of its case.

Stress-shielding as a cause of insertional tendinopathy: the operative technique of limited adductor tenotomy supports this theory

The aetiology of tendinopathy is poorly understood. A new hypothesis proposed argues that tendinopathy may not be purely a tensile injury, rather that altered mechanics such as compression or stress-shielding may be important. Both tendon compression and a decrease in tendon load (stress-shielding) will induce change in a tendon similar to that seen in an insertional tendinopathy.

Stress-shielding as a cause of tendinopathy is supported by the clinical success of operative release of adductor longus. This surgery releases the superficial section of the normal adductor longus tendon at a point distal to the insertion. This may have the effect of transferring stress from the superficial section of the tendon to the stress-shielded deeper portion, and the induction of normal loads in both the deeper and superficial portions of the tendon may assist in tendon recovery. This interesting hypothesis and clinical intervention require further investigation

Intervention efficacy among 'At Risk' adolescents: a test of subjective wellbeing homeostasis theory

 This study tests a number of theoretical predictions based on subjective wellbeing (SWB) Homeostasis Theory. This theory proposes that SWB is actively maintained and defended within a narrow, positive range of values around a 'set-point' for each person. Due to homeostatic control, it is predicted to be very difficult to substantially increase SWB in samples operating normally within their set-point-range. However, under conditions of homeostatic defeat, where SWB is lower than normal, successful interventions should be accompanied by a substantial increase as each person's SWB returns to lie within its normal range of values. This study tests these propositions using a sample of 4,243 participants in an Australian Federal Government Program for 'at-risk' adolescents. SWB was measured using the Personal Wellbeing Index and results are converted to a metric ranging from 0 to 100 points. The sample was divided into three sub-groups as 0-50, 51-69, and 70+ points. The theoretical prediction was confirmed. The largest post-intervention increase in SWB was in the 0-50 group and lowest in the 70+ group. However, a small increase in SWB was observed in the normal group, which was significant due to the large sample size. The implications of these findings for governments, schools and policy makers are discussed.

(Particularly) Burdensome prison time should reduce imprisonment length — and not merely in theory

Imprisonment is the harshest sanction in our system of law. It is a sanction that isincreasingly imposed by the courts. The severity of imprisonment as a sanction stemsprincipally from the considerable restrictions it imposes on an individual’s liberty.However, the deprivation experienced by a prisoner can vary considerably, depending onthe strictness of the prison regime in which the prisoner is confined and his or her state ofhealth. Prisoners subjected to non-mainstream conditions almost invariably suffer morethan those in normal conditions. There is no settled approach regarding the extent towhich prison conditions should impact on the length of a prison term. The jurisprudencein this area is inconsistent. It is particularly unsettled when the additional burden stemsfrom subjective matters relating to an accused, such as ill health. In this article we makerecommendations regarding the manner in which prison conditions should impact on thelength of a prison term. The main recommendation is that prisoners who spend time inparticularly burdensome conditions should have their sentence reduced by a factor of0.5 days for each day spent in such conditions. In this article we also recommend thatAustralia should adopt a model similar to those which exist in some Scandinaviancountries, whereby the only deprivation stemming from imprisonment is the loss ofliberty. This would mean that few prisoners would ever be subjected to particularlyburdensome conditions. This would make many of the recommendations in this paperobsolete. However, there is no evidence that Australian prison conditions are about tofundamentally alter. Hence, the recommendations will remain pragmatically relevant inthe foreseeable future.