Treatment comparisons for decision making: facing the problems of sparse and few data

Marta O Soares; Jo C. Dumville; A E  Ades; Nicky J.  Welton

doi:10.1111/rssa.12010

Treatment comparisons for decision making: facing the problems of sparse and few data

Marta O Soares, Jo C. Dumville, A E Ades, Nicky J. Welton

Research output: Contribution to journal › Article › peer-review

Abstract

Advanced evidence synthesis techniques such as indirect or mixed treatment comparisons (MTCs) provide powerful analytic tools to inform decision making. In some cases, however, existing research is limited in quantity and/or existing research data is ‘sparse’. In this paper we demonstrate how modelling assumptions in evidence synthesis can be explored in the face of limited and sparse data using an example where estimates of relative treatment effects were required in a synthesis of the available evidence regarding treatments for grade 3 or 4 pressure ulcers.

Original language	English
Pages (from-to)	259-279
Number of pages	21
Journal	Journal of the Royal Statistical Society: Series A (Statistics in Society)
Volume	177
Issue number	1
Early online date	23 Apr 2013
DOIs	https://doi.org/10.1111/rssa.12010
Publication status	Published - Jan 2014

Keywords

evidence synthesis
elicited evidence
MIXED TREATMENT COMPARISONS
Network meta-analysis
observational studies
RCT evidence
Sparse data

Access to Document

10.1111/rssa.12010

http://onlinelibrary.wiley.com/doi/10.1111/rssa.12010/abstract

Cite this

@article{94c92b6643fe4d9fbcf83af8c4d3e986,

title = "Treatment comparisons for decision making: facing the problems of sparse and few data",

abstract = "Advanced evidence synthesis techniques such as indirect or mixed treatment comparisons (MTCs) provide powerful analytic tools to inform decision making. In some cases, however, existing research is limited in quantity and/or existing research data is {\textquoteleft}sparse{\textquoteright}. In this paper we demonstrate how modelling assumptions in evidence synthesis can be explored in the face of limited and sparse data using an example where estimates of relative treatment effects were required in a synthesis of the available evidence regarding treatments for grade 3 or 4 pressure ulcers.",

keywords = "evidence synthesis, elicited evidence, MIXED TREATMENT COMPARISONS, Network meta-analysis, observational studies, RCT evidence, Sparse data",

author = "{O Soares}, Marta and Dumville, {Jo C.} and Ades, {A E} and Welton, {Nicky J.}",

year = "2014",

month = jan,

doi = "10.1111/rssa.12010",

language = "English",

volume = "177",

pages = "259--279",

journal = "Journal of the Royal Statistical Society: Series A (Statistics in Society)",

issn = "0964-1998",

publisher = "Wiley-Blackwell",

number = "1",

}

TY - JOUR

T1 - Treatment comparisons for decision making

T2 - facing the problems of sparse and few data

AU - O Soares, Marta

AU - Dumville, Jo C.

AU - Ades, A E

AU - Welton, Nicky J.

PY - 2014/1

Y1 - 2014/1

N2 - Advanced evidence synthesis techniques such as indirect or mixed treatment comparisons (MTCs) provide powerful analytic tools to inform decision making. In some cases, however, existing research is limited in quantity and/or existing research data is ‘sparse’. In this paper we demonstrate how modelling assumptions in evidence synthesis can be explored in the face of limited and sparse data using an example where estimates of relative treatment effects were required in a synthesis of the available evidence regarding treatments for grade 3 or 4 pressure ulcers.

AB - Advanced evidence synthesis techniques such as indirect or mixed treatment comparisons (MTCs) provide powerful analytic tools to inform decision making. In some cases, however, existing research is limited in quantity and/or existing research data is ‘sparse’. In this paper we demonstrate how modelling assumptions in evidence synthesis can be explored in the face of limited and sparse data using an example where estimates of relative treatment effects were required in a synthesis of the available evidence regarding treatments for grade 3 or 4 pressure ulcers.

KW - evidence synthesis

KW - elicited evidence

KW - MIXED TREATMENT COMPARISONS

KW - Network meta-analysis

KW - observational studies

KW - RCT evidence

KW - Sparse data

U2 - 10.1111/rssa.12010

DO - 10.1111/rssa.12010

M3 - Article

SN - 0964-1998

VL - 177

SP - 259

EP - 279

JO - Journal of the Royal Statistical Society: Series A (Statistics in Society)

JF - Journal of the Royal Statistical Society: Series A (Statistics in Society)

IS - 1

ER -