The harvest plot: a method for synthesising evidence about the differential effects of interventions.
BMC Medical Research Methodology 2007 ; 8: 8.
DOI : 10.1186/1471-2288-8-8
PubMed ID : 18298827
PMCID : PMC2270283
One attraction of meta-analysis is the forest plot, a compact overview of the essential data included in a systematic review and the overall 'result'. However, meta-analysis is not always suitable for synthesising evidence about the effects of interventions which may influence the wider determinants of health. As part of a systematic review of the effects of population-level tobacco control interventions on social inequalities in smoking, we designed a novel approach to synthesis intended to bring aspects of the graphical directness of a forest plot to bear on the problem of synthesising evidence from a complex and diverse group of studies.
We coded the included studies (n = 85) on two methodological dimensions (suitability of study design and quality of execution) and extracted data on effects stratified by up to six different dimensions of inequality (income, occupation, education, gender, race or ethnicity, and age), distinguishing between 'hard' (behavioural) and 'intermediate' (process or attitudinal) outcomes. Adopting a hypothesis-testing approach, we then assessed which of three competing hypotheses (positive social gradient, negative social gradient, or no gradient) was best supported by each study for each dimension of inequality.
We plotted the results on a matrix ('harvest plot') for each category of intervention, weighting studies by the methodological criteria and distributing them between the competing hypotheses. These matrices formed part of the analytical process and helped to encapsulate the output, for example by drawing attention to the finding that increasing the price of tobacco products may be more effective in discouraging smoking among people with lower incomes and in lower occupational groups.
The harvest plot is a novel and useful method for synthesising evidence about the differential effects of population-level interventions. It contributes to the challenge of making best use of all available evidence by incorporating all relevant data. The visual display assists both the process of synthesis and the assimilation of the findings. The method is suitable for adaptation to a variety of questions in evidence synthesis and may be particularly useful for systematic reviews addressing the broader type of research question which may be most relevant to policymakers.