MMR: the facts in the case of Dr Andrew Wakefield This 15-page cartoon explains the events surrounding the MMR controversy, and provides links to the relevant evidence. | 5 Comments World without bias Overcoming biases is difficult but important. Treatment comparisons must be fair. | 0 Comments You may also like MMR: the facts in the case of Dr Andrew Wakefield This 15-page cartoon explains the events surrounding the MMR controversy, and provides links to the relevant evidence. | 5 Comments World without bias Overcoming biases is difficult but important. Treatment comparisons must be fair. | 0 Comments Browse Key Concepts Back to Library Claims: are they justified? 1-1 Treatments can harm 1-2 Anecdotes are unreliable evidence 1-3 Association is not the same as causation 1-4 Common practice is not always evidence-based 1-5 Newer is not necessarily better 1-6 Expert opinion is not always right 1-7 Beware of conflicting interests 1-8 More is not necessarily better 1-9 Earlier is not necessarily better 1-10 Hope may lead to unrealistic expectations 1-11 Explanations about how treatments work can be wrong 1-12 Dramatic treatment effects are rare Comparisons: are they fair and reliable? 2-1 Comparisons are needed to identify treatment effects 2-2 Comparison groups should be similar 2-3 Peoples’ outcomes should be analyzed in their original groups 2-4 Comparison groups should be treated equally 2-5 People should not know which treatment they get 2-6 Peoples’ outcomes should be assessed similarly 2-7 All should be followed up 2-8 Consider all of the relevant fair comparisons 2-9 Reviews of fair comparisons should be systematic 2-10 Peer-review and publication does not guarantee reliable information 2-11 All fair comparisons and outcomes should be reported 2-12 Subgroup analyses may be misleading 2-13 Relative measures of effects can be misleading 2-14 Average measures of effects can be misleading 2-15 Fair comparisons with few people or outcome events can be misleading 2-16 Confidence intervals should be reported 2-17 Don’t confuse “statistical significance” with “importance” 2-18 Don’t confuse “no evidence” with “no effect” Choices: making informed choices 3-1 Do the outcomes measured matter to you? 3-2 Are you very different from the people studied? 3-3 Are the treatments practical in your setting? 3-4 Do treatment comparisons reflect your circumstances? 3-5 How certain is the evidence? 3-6 Do the advantages outweigh the disadvantages? GET-IT Jargon Buster Select a termacceptability adherence adverse effect adverse event allocation allocation bias allocation schedule allocation schedule concealment applicability association attrition bias average average difference baseline characteristics before-after study benefit bias blinding burden case report case series case-control study causal association certainty of the evidence change in cost cluster cluster randomized study cohort study comparative study comparing like with like confidence interval confidence region confirmation bias conflicts of interests confounders contamination controlled before-after study controlled study cost cost-effectiveness critical assessment cross-sectional study crossover study cut-off value data collection data fishing diagnosis diagnostic algorithm diagnostic odds ratio diagnostic test diagnostic test accuracy difference direct comparison disease progression bias disease stage disease status double blinding double dummy dramatic treatment effect drug effect estimate effectiveness efficiency eligibility criteria enrolment estimate evidence evidence profile evidence to decision framework explanatory trial exploratory analysis extrapolated evidence factorial study fair comparisons of treatments false negative test result false negative test result (duplicate) false positive test result false positive test result (duplicate) follow-up forest plot GRADE guideline high certainty of the evidence important imprecision incidence inconsistency incremental cost-effectiveness ratio indeterminate diagnostic test result index test indicator indirect comparison indirectness informed consent intention-to-treat analysis interim analysis interrupted time series study lead-time bias length-time bias level of evidence likelihood likelihood ratio loss to follow-up low certainty of the evidence low risk of bias measurement bias meta-analysis minimization moderate certainty of the evidence modified intention-to-treat analysis monitoring multicentre study multiple statistical comparisons natural course of health problems negative predictive value nocebo effect non-random allocation non-randomized study number needed to harm number needed to screen number needed to treat objective outcome odds odds ratio outcome outcome measured on a scale overdiagnosis overtreatment p-value paired study design for diagnostic tests parallel group study peer review performance bias perspective phase 1 trial phase 2 trial phase 3 trial phase 4 trial PICO placebo placebo effect planned analysis play of chance positive predictive value pragmatic trail pre-test probability precision prevalence primary outcome prognosis prognostic variable protocol or study plan qualitative study quality-adjusted life years quantitative study random random allocation randomized study reference standard test regulation of research relative effect reliability repeated measures study reporting bias reproducibility research research data research evidence research methods research priorities resource use risk of bias risk ratio sample sample size scale screening screening test secondary outcome selection criteria sensitivity shared decision making single blinding single participant trial smallest important difference specificity spin sponsor bias statistical power statistically significant stratified randomization strength of recommendation study study participants study population subgroup subgroup analysis summary of findings surrogate outcome systematic review target condition theory time horizon treatment treatment comparison treatment comparison group treatment effect treatment effect trial phases triple blinding true negative test result true positive test result type of study uncertainty under-reporting undesirable effect unfairness unit of analysis error utility value value variables very low certainty of the evidence yes/no outcomes About GET-IT GET-IT provides plain language definitions of health research terms
World without bias Overcoming biases is difficult but important. Treatment comparisons must be fair. | 0 Comments You may also like MMR: the facts in the case of Dr Andrew Wakefield This 15-page cartoon explains the events surrounding the MMR controversy, and provides links to the relevant evidence. | 5 Comments World without bias Overcoming biases is difficult but important. Treatment comparisons must be fair. | 0 Comments Browse Key Concepts Back to Library Claims: are they justified? 1-1 Treatments can harm 1-2 Anecdotes are unreliable evidence 1-3 Association is not the same as causation 1-4 Common practice is not always evidence-based 1-5 Newer is not necessarily better 1-6 Expert opinion is not always right 1-7 Beware of conflicting interests 1-8 More is not necessarily better 1-9 Earlier is not necessarily better 1-10 Hope may lead to unrealistic expectations 1-11 Explanations about how treatments work can be wrong 1-12 Dramatic treatment effects are rare Comparisons: are they fair and reliable? 2-1 Comparisons are needed to identify treatment effects 2-2 Comparison groups should be similar 2-3 Peoples’ outcomes should be analyzed in their original groups 2-4 Comparison groups should be treated equally 2-5 People should not know which treatment they get 2-6 Peoples’ outcomes should be assessed similarly 2-7 All should be followed up 2-8 Consider all of the relevant fair comparisons 2-9 Reviews of fair comparisons should be systematic 2-10 Peer-review and publication does not guarantee reliable information 2-11 All fair comparisons and outcomes should be reported 2-12 Subgroup analyses may be misleading 2-13 Relative measures of effects can be misleading 2-14 Average measures of effects can be misleading 2-15 Fair comparisons with few people or outcome events can be misleading 2-16 Confidence intervals should be reported 2-17 Don’t confuse “statistical significance” with “importance” 2-18 Don’t confuse “no evidence” with “no effect” Choices: making informed choices 3-1 Do the outcomes measured matter to you? 3-2 Are you very different from the people studied? 3-3 Are the treatments practical in your setting? 3-4 Do treatment comparisons reflect your circumstances? 3-5 How certain is the evidence? 3-6 Do the advantages outweigh the disadvantages? GET-IT Jargon Buster Select a termacceptability adherence adverse effect adverse event allocation allocation bias allocation schedule allocation schedule concealment applicability association attrition bias average average difference baseline characteristics before-after study benefit bias blinding burden case report case series case-control study causal association certainty of the evidence change in cost cluster cluster randomized study cohort study comparative study comparing like with like confidence interval confidence region confirmation bias conflicts of interests confounders contamination controlled before-after study controlled study cost cost-effectiveness critical assessment cross-sectional study crossover study cut-off value data collection data fishing diagnosis diagnostic algorithm diagnostic odds ratio diagnostic test diagnostic test accuracy difference direct comparison disease progression bias disease stage disease status double blinding double dummy dramatic treatment effect drug effect estimate effectiveness efficiency eligibility criteria enrolment estimate evidence evidence profile evidence to decision framework explanatory trial exploratory analysis extrapolated evidence factorial study fair comparisons of treatments false negative test result false negative test result (duplicate) false positive test result false positive test result (duplicate) follow-up forest plot GRADE guideline high certainty of the evidence important imprecision incidence inconsistency incremental cost-effectiveness ratio indeterminate diagnostic test result index test indicator indirect comparison indirectness informed consent intention-to-treat analysis interim analysis interrupted time series study lead-time bias length-time bias level of evidence likelihood likelihood ratio loss to follow-up low certainty of the evidence low risk of bias measurement bias meta-analysis minimization moderate certainty of the evidence modified intention-to-treat analysis monitoring multicentre study multiple statistical comparisons natural course of health problems negative predictive value nocebo effect non-random allocation non-randomized study number needed to harm number needed to screen number needed to treat objective outcome odds odds ratio outcome outcome measured on a scale overdiagnosis overtreatment p-value paired study design for diagnostic tests parallel group study peer review performance bias perspective phase 1 trial phase 2 trial phase 3 trial phase 4 trial PICO placebo placebo effect planned analysis play of chance positive predictive value pragmatic trail pre-test probability precision prevalence primary outcome prognosis prognostic variable protocol or study plan qualitative study quality-adjusted life years quantitative study random random allocation randomized study reference standard test regulation of research relative effect reliability repeated measures study reporting bias reproducibility research research data research evidence research methods research priorities resource use risk of bias risk ratio sample sample size scale screening screening test secondary outcome selection criteria sensitivity shared decision making single blinding single participant trial smallest important difference specificity spin sponsor bias statistical power statistically significant stratified randomization strength of recommendation study study participants study population subgroup subgroup analysis summary of findings surrogate outcome systematic review target condition theory time horizon treatment treatment comparison treatment comparison group treatment effect treatment effect trial phases triple blinding true negative test result true positive test result type of study uncertainty under-reporting undesirable effect unfairness unit of analysis error utility value value variables very low certainty of the evidence yes/no outcomes About GET-IT GET-IT provides plain language definitions of health research terms
MMR: the facts in the case of Dr Andrew Wakefield This 15-page cartoon explains the events surrounding the MMR controversy, and provides links to the relevant evidence. | 5 Comments World without bias Overcoming biases is difficult but important. Treatment comparisons must be fair. | 0 Comments
World without bias Overcoming biases is difficult but important. Treatment comparisons must be fair. | 0 Comments