Randomised and Non-Randomised Studies: Threats to Internal and External Validity

Sanderson, Christine; McKee, Margaret; Britton, Ashley Joi; Black, Neil D.; McPherson, Kim; Bain, Chris

doi:10.4135/9781848608344.n6

Cited by 3 publications

(2 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…(Many critics of EBP have little problem with this.) Many of those who undertake and develop such approaches know only too well about their hazards and shortfalls and try to address or avoid them, or at least be aware of them: for example, the problems of applying the findings of a trial involving patients with certain characteristics to a patient with a different clinical background (McKee et al 1998), or the advantages of non‐randomised designs over randomised (Reeves et al 1998; Sanderson et al 2001). It also seems likely that all but the most hard‐nosed trialists would acknowledge that clinical efficacy is only one aspect of healthcare delivery.…”

Section: Evidence‐based Nursingmentioning

confidence: 99%

The oil crisis, risk and evidence‐based practice

Traynor

2002

Nursing Inquiry

View full text Add to dashboard Cite

Evidence-based practice has risen to prominence over the last 20 years. Different professions have taken it up in different ways and for different purposes. It has been seen as holding both threats and advantages to professionalising endeavours and professional identity. It has engendered controversy but some criticisms of it have been unconvincing. It is possible to account for its rise as a response to tightening financial constraints on state spending in the west, as a sign of a culture increasingly concerned with risk, distrust of professionals and experts, as well as a way for professionals themselves to maintain control over their activity in the face of growing managerialism. This paper reviews the literature of some of the movement's proponents as well as criticism from various professional groups. It concludes that more useful than either arguing for or against it, is to understand the policy background and sociological reasons for its emergence and spread.

show abstract

Section: Evidence‐based Nursingmentioning

confidence: 99%

The oil crisis, risk and evidence‐based practice

Traynor

2002

Nursing Inquiry

View full text Add to dashboard Cite

show abstract

“…Many examples exist in which non-randomised studies indicate a substantial "treatment" benefit that is subsequently refuted once all confounding has been eliminated by randomisation. 5 In this paper we will argue that, just as nonrandomised studies may provide unreliable evidence of eVect unless very strict conditions are met, 6 so RCTs that are not "blinded" are also diYcult to interpret. There are many large RCTs evaluating new treatments in cancer or heart disease that are, of necessity, unblinded and hence cannot-by the arguments to follow-provide reliable evidence for a treatment eVect as we understand it.…”

mentioning

confidence: 99%

Preferences and understanding their effects on health

McPherson¹,

Britton²

2001

Quality and Safety in Health Care

View full text Add to dashboard Cite

Preference for a particular intervention may, possibly via complicated pathways, itself confer an outcome advantage which will be subsumed in unblind randomised trials as part of the measured eVectiveness of the intervention. Where more attractive interventions are compared with less attractive ones, any diVerence could therefore be a consequence of attractiveness and not its intrinsic worth. For health promotion interventions this is clearly important, but we cannot tell how important it is for therapeutic interventions without special studies to measure or refute such eVects. These are diYcult to do and are complex. Until the therapeutic eVects of preference itself are more clearly understood, understanding the true therapeutic eVects will be compromised, at least in principle.(Quality in Health Care 2001;10(Suppl I):i61-i66)

show abstract

Incorporating Bayesian Ideas into Health-Care Evaluation

Spiegelhalter¹

2004

Statist. Sci.

131

View full text Add to dashboard Cite

Randomised and Non-Randomised Studies: Threats to Internal and External Validity

Cited by 3 publications

References 0 publications

The oil crisis, risk and evidence‐based practice

The oil crisis, risk and evidence‐based practice

Preferences and understanding their effects on health

Incorporating Bayesian Ideas into Health-Care Evaluation

Contact Info

Product

Resources

About