Meta-analysis of randomised controlled trials testing behavioural interventions to promote household action on climate change

Abstract

No consensus exists regarding which are the most effective mechanisms to promote household action on climate change. We present a meta-analysis of randomised controlled trials comprising 3,092,678 observations, which estimates the effects of behavioural interventions holding other factors constant. Here we show that behavioural interventions promote climate change mitigation to a very small degree while the intervention lasts (d = -0.093 95% CI -0.160, -0.055), with no evidence of sustained positive effects once the intervention ends. With the exception of recycling, most household mitigation behaviours show a low behavioural plasticity. The intervention with the highest average effect size is choice architecture (nudges) but this strategy has been tested in a limited number of behaviours. Our results do not imply behavioural interventions are less effective than alternative strategies such as financial incentives or regulations, nor exclude the possibility that behavioural interventions could have stronger effects when used in combination with alternative strategies.

Fig. 1

Duration of the behavioural interventions in weeks. Shows the distribution of intervention duration according to the number of weeks from the beginning to the conclusion of the experimental period

Fig. 2

Funnel plot displaying the relationship between estimate quality and effect size. Each dot represents a study (e.g. measuring the effect of a certain behavioural intervention); the y-axis represents study precision (standard error) and the x-axis shows the study’s result (effect estimate). This scatterplot is used for the visual detection of systematic heterogeneity between studies. It assumes that studies with high precision will be plotted near the average (red line), and studies with low precision will be spread evenly on both sides of the average, creating a roughly funnel-shaped distribution. Deviation from this shape suggest small-study bias, which is the case here, with lower precision studies reporting stronger effects

Fig. 3

Cumulative meta-analysis. In cumulative meta-analysis, the pooled estimate of the treatment effect is updated each time the result from a new study is included. The circles in the plot represent the cumulative effect size at any given moment, that is, the average effect size resulting from the inclusion of studies up to a certain point. This allows tracking the accumulation of evidence on the effect of behavioural interventions over time

Fig. 4

Sample size per experimental group in behavioural interventions targeting different types of behaviour. Shows how different household mitigation behaviours have been tested with interventions with a distinct number of observations

Fig. 5

Sample size per experimental group in behavioural interventions using different strategies. Shows how different behavioural stimuli have been tested in interventions with a distinct number of observations

Fig. 6

Type of intervention tested per mitigation behaviour. Shows how different mitigation behaviours have been targeted by distinct behavioural stimuli