Assessing the Causal Effect of Binary Interventions from Observational Panel Data with Few Treated Units

Samartsidis, Pantelis; Seaman, Shaun R.; Presanis, Anne M.; Hickman, Matthew; Angelis, Daniela De

doi:10.1214/19-sts713

Cited by 31 publications

(26 citation statements)

References 104 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The reference zones of increasing distance from the MPAs considered important for estimating MPA impacts [ 135 ] were (1) the southern zone, (2) the northwest zone, and (3) the northeast zone. We then fit a Bayesian state-space or structural times series model [ 137 , 140 ] with weakly informative regularizing priors to the zone-specific data using the R package [ 137 ]. We focus only on the 2009 intervention since the 2014 MPA expansions are too recent to be evaluated using this approach.…”

Section: Methodsmentioning

confidence: 99%

“…Evaluating social, conservation or management policy interventions using observational data is challenging and can lead to ambiguous conclusions [139]-especially if the intervention is nonrandomized, there are few treatment units affected by the intervention and there are multiple time-dependent outcome measures [140]. In our case, the MPA expansions (interventions) were prescribed (not random) and also binary (all or nothing), there were few MPAs to assess, and the data series were time-dependent.…”

Section: Statistical Modeling Approaches For Counterfactual Predictionsmentioning

confidence: 99%

“…The importance of each reference and predictor contribution to the composite synthetic control series can be shown in an inclusion probability plot. Unlike the commonly used difference-in-differences approach [20,151], the synthetic control approach to counterfactual prediction makes no assumptions about the data generating mechanism and is especially applicable for sparse data settings (few treatment units), unlike the closely related covariate matching methods (see the review in [140]). When there are a large number of treatment units (hundreds or thousands) in a policy intervention analysis, then it can be informative to combine the synthetic control method with unit-specific covariate matching in a Bayesian counterfactual prediction modelling framework [146].…”

Section: Plos Onementioning

confidence: 99%

See 2 more Smart Citations

Ecological responses to blue water MPAs

et al. 2020

View full text Add to dashboard Cite

Marine protected areas (MPAs) can contribute to protecting biodiversity and managing ocean activities, including fishing. There is, however, limited evidence of ecological responses to blue water MPAs. We conducted the first comprehensive evaluation of impacts on fisheries production and ecological responses to pelagic MPAs of the Pacific Remote Islands Marine National Monument. A Bayesian time series-based counterfactual modelling approach using fishery-dependent data was used to compare the temporal response in the MPAs to three reference regions for standardized catch rates, lengths, trophic level of the catch and species diversity. Catch rates of bigeye tuna, the main target species (Kingman/Palmyra MPA, causal effect probability >99% of an 84% reduction; 95% credible interval:-143%,-25%), and blue shark (Johnston MPAs, causal effect probability >95%) were significantly lower and longnose lancetfish significantly higher (Johnston MPAs, causal effect probability >95%) than predicted had the MPAs not been established, possibly from closing areas near shallow features, which aggregate pelagic predators, and from 'fishing-the-line'. There were no apparent causal impacts of the MPAs on species diversity, lengths and trophic level of the catch, perhaps because the MPAs were young, were too small, did not contain critical habitat for specific life-history stages, had been lightly exploited or experienced fishing-the-line. We also assessed model-standardized catch rates for species of conservation concern and mean trophic level of the catch within and outside of MPAs. Displaced effort produced multi-species conflicts: MPAs protect bycatch hotspots and hotspots of bycatch-to-target catch ratios for some at-risk species, but coldspots for others. Mean trophic level of the catch was significantly higher around MPAs, likely due to the aggregating effect of the shallow features and there having been light fishing pressure within MPAs. These findings demonstrate how exploring a wide range of ecological responses supports evidence-based evaluations of blue water MPAs.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Statistical Modeling Approaches For Counterfactual Predictionsmentioning

confidence: 99%

Section: Plos Onementioning

confidence: 99%

See 1 more Smart Citation

Ecological responses to blue water MPAs

et al. 2020

View full text Add to dashboard Cite

show abstract

“…We do not consider the interaction of interventions, but merely their joint effect as mandated through the Tier system. In generating counterfactuals our model makes a “difference in differences” counterfactual assumption, which has previously been shown to have limitations [11] arising from the assumption of parallel trajectories. It is important to note that the effect sizes we model quantify the instantaneous and constant impact of the Tiers on R t , whereas the effects of Tiers may vary over time, perhaps with a lag before they take effect or with a waning of efficacy.…”

Section: Discussionmentioning

confidence: 99%

Impact of the Tier system on SARS-CoV-2 transmission in the UK between the first and second national lockdowns

Laydon

Mishra

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

Objective: Measure the effects of the Tier system on the COVID-19 pandemic in the UK between the first and second national lockdowns, before the emergence of the B.1.1.7 variant of concern. Design: Modelling study combining estimates of the real-time reproduction number Rt (derived from UK case, death and serological survey data) with publicly available data on regional non-pharmaceutical interventions. We fit a Bayesian hierarchical model with latent factors using these quantities, to account for broader national trends in addition to subnational effects from Tiers. Setting: The UK at Lower Tier Local Authority (LTLA) level. Primary and secondary outcome measures: Reduction in real-time reproduction number Rt. Results: Nationally, transmission increased between July and late September, regional differences notwithstanding. Immediately prior to the introduction of the tier system, Rt averaged 1.3 (0.9-1.6) across LTLAs, but declined to an average of 1.1 (0.86-1.42) two weeks later. Decline in transmission was not solely attributable to Tiers. Tier 1 had negligible effects. Tiers 2 and 3 respectively reduced transmission by 6% (5%-7%) and 23% (21%-25%). 93% of LTLAs would have begun to suppress their epidemics if every LTLA had gone into Tier 3 by the second national lockdown, whereas only 29% did so in reality. Conclusions: The relatively small effect sizes found in this analysis demonstrate that interventions at least as stringent as Tier 3 are required to suppress transmission, especially considering more transmissible variants, at least until effective vaccination is widespread or much greater population immunity has amassed.

show abstract

“…Ideally, the measurements would be taken frequently enough (say, daily or weekly) to enable the application of time-series methods (e.g. Granger causality or cointegration tests), which would help determine the causal structures of the time variation of exogenous factors on the SRB ( Samartsidis et al, 2018 ). On the other hand, only a small subset of US environmental quality measurements were available in Sweden.…”

Section: Discussionmentioning

confidence: 99%

Mythical and Observable Trends in Human Sex Ratio at Birth

Rzhetsky

Long

Chen

et al. 2020

Preprint

View full text Add to dashboard Cite

The human sex ratio at birth (SRB) is defined as the ratio between the number of 11 newborn boys to the total number of newborns per time unit. It is, typically, slightly greater than 1 2 12 (more boys than girls) and fluctuates over time. In this study, we sought to "myth-check" previously 13 reported associations (and test new hypotheses) using variants of mixed-effect regression analyses 14 and time-series models on two very large electronic health record datasets, representing the 15 populations in the United States and Sweden, respectively. Our results revealed that neither 16 dataset supported models in which the SRB changed seasonally or in response to variations in 17 ambient temperature, and that an increased level of a diverse array of pollutants were associated 18 with lower SRBs. Moreover, we found that increased levels of industrial and agricultural activity, 19 which served as proxies for water pollution, were also associated with lower SRBs. 20 21 42 215 We are grateful to E. Gannon and M. Rzhetsky for comments on earlier versions of this manuscript. References 221 Benjamini Y, Yekutieli D, et al. The control of the false discovery rate in multiple testing under dependency. The 222 annals of statistics. 2001; 29(4):1165-1188. 223 Box GE, Jenkins GM, Reinsel GC, Ljung GM. Time series analysis: forecasting and control. John Wiley & Sons; 224 2015. 225 Breusch TS. Testing for autocorrelation in dynamic linear models. Australian Economic Papers. 1978; 17(31):334-226 355. 227 Brodersen KH, Gallusser F, Koehler J, Remy N, Scott SL, et al. Inferring causal impact using Bayesian structural 228 time-series models. The Annals of Applied Statistics. 2015; 9(1):247-274. 229 Bruckner TA, Catalano R. Selection in utero and population health: theory and typology of research. SSM-230 population health. 2018; 5:101-113. 231 Bürkner PC. brms: An R package for Bayesian multilevel models using STAN. Journal of Statistical Software. 232 2017; 80(1):1-28. 233 Catalano R, Bruckner T, Smith KR. Ambient temperature predicts sex ratios and male longevity.

show abstract

Assessing the Causal Effect of Binary Interventions from Observational Panel Data with Few Treated Units

Cited by 31 publications

References 104 publications

Ecological responses to blue water MPAs

Ecological responses to blue water MPAs

Impact of the Tier system on SARS-CoV-2 transmission in the UK between the first and second national lockdowns

Mythical and Observable Trends in Human Sex Ratio at Birth

Contact Info

Product

Resources

About