%0 Figure %A Carroll, Robert %A Metcalfe, Chris %A Steeg, Sarah %A M. Davies, Neil %A Cooper, Jayne %A Kapur, Nav %A Gunnell, David %D 2016 %T Instrumental variable estimates* of the risk difference in repeat self-harm between those who did, and did not receive a psychosocial assessment.* %U https://plos.figshare.com/articles/figure/Instrumental_variable_estimates_of_the_risk_difference_in_repeat_self_harm_between_those_who_did_and_did_not_receive_a_psychosocial_assessment_/3024871 %R 10.1371/journal.pone.0149713.g002 %2 https://ndownloader.figshare.com/files/4727107 %K Hospital Presentation BackgroundClinical guidelines %K RD %K hospital presentation %K IV effect estimate %K indication.ResultsConventional regression analysis %K UK %K assessment %K CI %K Instrumental Variable Analysis %X

The overall estimate in this figure is the overall instrumental variable estimate, not the pooled estimate from a meta-analysis of the three individual centre estimates.

%I PLOS ONE