Research output: Contribution to Journal/Magazine › Meeting abstract › peer-review
Research output: Contribution to Journal/Magazine › Meeting abstract › peer-review
}
TY - JOUR
T1 - MORECare research methods guidance development
T2 - recommendations for statistical methods in palliative and end of life care research
AU - Preston, Nancy
AU - Grande, Gunn
AU - Fayers, P.
AU - Pilling, M.
AU - Higginson, I. J.
AU - Short, V.
AU - Anscombe, E.
AU - Evans, C.
AU - Benalia, H.
PY - 2012/6
Y1 - 2012/6
N2 - Aims: To identify agreed best practice for statistical methodsin palliative and end of life (P&EoLC) research.Background: Carrying out statistical analysis in P&EoLCresearch can be problematic due to high levels of missingdata and attrition as patients’ disease progresses.Methods: We used the MORECare Transparent ExpertConsultation approach to conduct consultation workshopswith experts in statistical methods in P&EoLC research.Prior to workshops participants were sent overviews of pertinentissues in statistical methods in P&EoLC. Followingworkshop presentations and discussion, nominal grouptechniques were used to produce candidate recommendations.These were subsequently rated online by participatingexperts. Descriptive statistics were employed to permitanalysis of consensus and rated importance. Narrative commentswere collated.Results: The statistical methods expert workshop comprised20 participants making 19 recommendations. Therewas broad agreement across most recommendations, thetop 5 recommendations were:1. Types and amount of missing data should be reportedalong with imputation methods.2. Pattern of missing data should be investigated to informimputation method.3. A statistical analysis plan should be in place.4. A taxonomy should be devised to define types ofattrition.5. Use of transition questions and minimally important differenceapproach provides insight into response shift.Conclusions: When designing studies in P&EoLC it is recommendedthat high rates of attrition should not be seen asindicative of poor design and that a clear statistical analysisplan is in place to account for missing data and attrition. Moreresearch is required in statistical methods to assess theseareas but also develop the emerging area of response shift.
AB - Aims: To identify agreed best practice for statistical methodsin palliative and end of life (P&EoLC) research.Background: Carrying out statistical analysis in P&EoLCresearch can be problematic due to high levels of missingdata and attrition as patients’ disease progresses.Methods: We used the MORECare Transparent ExpertConsultation approach to conduct consultation workshopswith experts in statistical methods in P&EoLC research.Prior to workshops participants were sent overviews of pertinentissues in statistical methods in P&EoLC. Followingworkshop presentations and discussion, nominal grouptechniques were used to produce candidate recommendations.These were subsequently rated online by participatingexperts. Descriptive statistics were employed to permitanalysis of consensus and rated importance. Narrative commentswere collated.Results: The statistical methods expert workshop comprised20 participants making 19 recommendations. Therewas broad agreement across most recommendations, thetop 5 recommendations were:1. Types and amount of missing data should be reportedalong with imputation methods.2. Pattern of missing data should be investigated to informimputation method.3. A statistical analysis plan should be in place.4. A taxonomy should be devised to define types ofattrition.5. Use of transition questions and minimally important differenceapproach provides insight into response shift.Conclusions: When designing studies in P&EoLC it is recommendedthat high rates of attrition should not be seen asindicative of poor design and that a clear statistical analysisplan is in place to account for missing data and attrition. Moreresearch is required in statistical methods to assess theseareas but also develop the emerging area of response shift.
KW - research methods
U2 - 10.1177/0269216312446391
DO - 10.1177/0269216312446391
M3 - Meeting abstract
VL - 26
SP - 416
EP - 417
JO - Palliative Medicine
JF - Palliative Medicine
SN - 0269-2163
IS - 4
M1 - OA42
ER -