Augmented Inverse Probability Weighting Research Articles

Are the current colonoscopy recommendations for interval surveillance in patients with polyps enough? Machine learning-augmented propensity score cohort analysis of 1840 patients.

Colonoscopy remains the gold standard for screening and surveillance of colorectal neoplasms, and is associated with a lower risk of colorectal cancer (CRC)-related mortality. The current interval surveillance recommendations in patients with previous adenomas lack sufficient evidence. The prevalence of subsequent adenomas, and especially high-risk adenomas, during surveillance is not well known. The primary outcome of this study was to determine the prevalence of polyps upon surveillance colonoscopy in patients who have a history of adenomas on initial average-risk-screening colonoscopy, but then have a normal initial surveillance (second) colonoscopy between 2003 and 2017. This is the first known retrospective cohort study of adenoma detection rate (ADR) with sub-group analysis of patients with serial surveillance colonoscopies by abnormal and high-risk surveillance findings separately by prior abnormal colonoscopies and correct surveillance strategies based on the recent March 2020 updated guidelines. After ADR calculation, machine learning-augmented propensity score adjusted multivariable regression with augmented inverse-probability weighting propensity (AIPW) score analysis was used to assess the relationship between guideline adherence, as well as abnormal and high-risk surveillance findings. A total of 1840 patients with pathologically confirmed adenomas or cancer on an initial average-risk-screening (first) colonoscopy met study criteria. 837 (45.5%) had confirmed adenomas on second colonoscopy, and 1003 (54.5%) had normal findings. Of 837 patients with polyps on both first and second colonoscopy, 423 (50.5%) had adenomas on third colonoscopy. Of the 1003 patients without polyps on second colonoscopy, 406 (40.5%) had confirmed adenomas on third colonoscopy. Guideline adherence was low at 9.18%, though was associated in propensity score adjusted multivariable regression with increased odds of an abnormal third (but not high-risk) colonoscopy, with comparable AIPW results. This 14-year study demonstrates the ADR to be > 40% on the third colonoscopy for patients with adenomas on initial screening colonoscopy, who then have a normal second colonoscopy. Through advanced machine learning and propensity score analysis, we showed that correct adherence is associated with higher odds of abnormal, but not high-risk abnormal 3rd colonoscopy, with evidence that high-risk surveillance findings are reduced by providers shortening the time between surveillance colonoscopies in contrast to the guidelines for those for whom there is presumed greater clinical suspicion of eventual cancer. Larger prospective trials are needed to guide optimal surveillance for these patients.

Comparing Parametric, Nonparametric, and Semiparametric Estimators: The Weibull Trials.

We use simple examples to show how the bias and standard error of an estimator depend in part on the type of estimator chosen from among parametric, nonparametric, and semiparametric candidates. We estimated the cumulative distribution function in the presence of missing data with and without an auxiliary variable. Simulation results mirrored theoretical expectations about the bias and precision of candidate estimators. Specifically, parametric maximum likelihood estimators performed best but must be "omnisciently" correctly specified. An augmented inverse probability-weighted (IPW) semiparametric estimator performed best among candidate estimators that were not omnisciently correct. In one setting, the augmented IPW estimator reduced the standard error by nearly 30%, compared with a standard Horvitz-Thompson IPW estimator; such a standard error reduction is equivalent to doubling the sample size. These results highlight the gains and losses that can be incurred when model assumptions are made in any analysis.

Machine Learning for Causal Inference: On the Use of Cross-fit Estimators.

Modern causal inference methods allow machine learning to be used to weaken parametric modeling assumptions. However, the use of machine learning may result in complications for inference. Doubly robust cross-fit estimators have been proposed to yield better statistical properties. We conducted a simulation study to assess the performance of several different estimators for the average causal effect. The data generating mechanisms for the simulated treatment and outcome included log-transforms, polynomial terms, and discontinuities. We compared singly robust estimators (g-computation, inverse probability weighting) and doubly robust estimators (augmented inverse probability weighting, targeted maximum likelihood estimation). We estimated nuisance functions with parametric models and ensemble machine learning separately. We further assessed doubly robust cross-fit estimators. With correctly specified parametric models, all of the estimators were unbiased and confidence intervals achieved nominal coverage. When used with machine learning, the doubly robust cross-fit estimators substantially outperformed all of the other estimators in terms of bias, variance, and confidence interval coverage. Due to the difficulty of properly specifying parametric models in high-dimensional data, doubly robust estimators with ensemble learning and cross-fitting may be the preferred approach for estimation of the average causal effect in most epidemiologic studies. However, these approaches may require larger sample sizes to avoid finite-sample issues.

An Efficient Multiple Imputation Approach for Estimating Equations with Response Missing at Random and High-Dimensional Covariates

Empirical-likelihood-based inference for parameters defined by the general estimating equations of Qin and Lawless (1994) remains an active research topic. When the response is missing at random (MAR) and the dimension of covariate is not low, the authors propose a two-stage estimation procedure by using the dimension-reduced kernel estimators in conjunction with an unbiased estimating function based on augmented inverse probability weighting and multiple imputation (AIPW-MI) methods. The authors show that the resulting estimator achieves consistency and asymptotic normality. In addition, the corresponding empirical likelihood ratio statistics asymptotically follow central chi-square distributions when evaluated at the true parameter. The finite-sample performance of the proposed estimator is studied through simulation, and an application to HIV-CD4 data set is also presented.

Associations between Apgar scores and children's educational outcomes at eight years of age.

Low Apgar scores are associated with neonatal morbidity and mortality, but effects of Apgar scores of 0-5, 6, 7, 8 and 9 (compared with 10) on longer-term neurodevelopmental outcomes are less clear. To examine the associations between Apgar scores of 0-5, 6, 7, 8 and 9 (compared with 10) and children's educational outcomes as measured by the Australian National Assessment Program-Literacy and Numeracy (NAPLAN) tests at age eight. We merged perinatal data including all children born in South Australia from 1999 to 2008 with school assessment data (NAPLAN). School assessments included five learning areas (domains)-reading, writing, spelling, grammar and numeracy. Each domain was categorised according to performing at or below National Minimum Standards (≤NMS). Effects were estimated using Augmented Inverse Probability Weighting (AIPW) accounting for a range of maternal, perinatal and sociodemographic characteristics. Risk differences comparing five-minute Apgar scores of 0-5 with Apgar scores of 10 for children performing≤NMS for each domain were: reading (0.07 (95% CI -0.16 to 0.29)), writing (0.27 (95% CI -0.14 to 0.68)), spelling (0.15 (95% CI -0.10 to 0.40)), grammar (0.04 (95% CI -0.21 to 0.29)) and numeracy (0.21 (95% CI -0.04 to 0.45)). Risk differences for children performing ≤NMS were also evident when Apgar score of 6 was compared with Apgar score of 10. Children with five-minute Apgar scores of 0-5 and 6, compared with Apgar score of 10, are at higher risk of scoring at/below the NMS on the NAPLAN assessments at eightyears.

Statistical inference for missing data mechanisms.

In the literature of statistical analysis with missing data there is a significant gap in statistical inference for missing data mechanisms especially for nonmonotone missing data, which has essentially restricted the use of the estimation methods which require estimating the missing data mechanisms. For example, the inverse probability weighting methods (Horvitz & Thompson, 1952; Little & Rubin, 2002), including the popular augmented inverse probability weighting (Robins et al, 1994), depend on sufficient models for the missing data mechanisms to reduce estimation bias while improving estimation efficiency. This research proposes a semiparametric likelihood method for estimating missing data mechanisms where an EM algorithm with closed form expressions for both E-step and M-step is used in evaluating the estimate (Zhao et al, 2009; Zhao, 2020). The asymptotic variance of the proposed estimator is estimated from the profile score function. The methods are general and robust. Simulation studies in various missing data settings are performed to examine the finite sample performance of the proposed method. Finally, we analysis the missing data mechanism of Duke cardiac catheterization coronary artery disease diagnostic data to illustrate the method.

Multinomial logistic regression with missing outcome data: An application to cancer subtypes

Many diseases such as cancer and heart diseases are heterogeneous and it is of great interest to study the disease risk specific to the subtypes in relation to genetic and environmental risk factors. However, due to logistic and cost reasons, the subtype information for the disease is missing for some subjects. In this article, we investigate methods for multinomial logistic regression with missing outcome data, including a bootstrap hot deck multiple imputation (BHMI), simple inverse probability weighted (SIPW), augmented inverse probability weighted (AIPW), and expected estimating equation (EEE) estimators. These methods are important approaches for missing data regression. The BHMI modifies the standard hot deck multiple imputation method such that it can provide valid confidence interval estimation. Under the situation when the covariates are discrete, the SIPW, AIPW, and EEE estimators are numerically identical. When the covariates are continuous, nonparametric smoothers can be applied to estimate the selection probabilities and the estimating scores. These methods perform similarly. Extensive simulations show that all of these methods yield unbiased estimators while the complete-case (CC) analysis can be biased if the missingness depends on the observed data. Our simulations also demonstrate that these methods can gain substantial efficiency compared with the CC analysis. The methods are applied to a colorectal cancer study in which cancer subtype data are missing among some study individuals.

The association of Helicobacter pylori infection with serum lipid profiles: An evaluation based on a combination of meta-analysis and a propensity score-based observational approach.

Several previous studies have suggested that Helicobacter pylori (H. pylori) infection affects the serum lipid profile. However, it remains controversial and the mechanism has not been elucidated. The purpose of this study is to use an epidemiological perspective to evaluate the association between H. pylori infection and the serum lipid profile. Multivariate analysis was performed using the data of serum lipid profile, infection status of H. pylori, fitness/lifestyle habits, and various subjects' characteristics which were derived from the 15,679 generally healthy individuals in Japan. The average treatment effects (ATEs) of H. pylori infection on the serum lipid profile were estimated using augmented inverse probability weighting (AIPW). A meta-analysis was also performed using the 27 studies worldwide in which the status of H. pylori infection and at least one serum examination value (high-density lipoprotein cholesterol (HDL-C), low-density lipoprotein cholesterol (LDL-C), total cholesterol (TC), or triglyceride (TG)) were described. The ATEs determined with AIPW showed that H. pylori infection has significant positive effects on LDL-C and TC (ATE (95% confidence interval [95%CI]) = 3.4 (2.36-4.49) and 1.7 (0.58-2.88), respectively) but has significant negative effects on HDL-C and TG (ATE (95%CI) = -1.2 (-1.74 to -0.72) and -3.5 (-5.92 to -1.06), respectively). The meta-analysis to estimate the association between H. pylori infection and the serum lipid profile revealed that H. pylori infection is positively associated with LDL-C, TC, and TG (standardized mean difference [SMD] (95%CI) = 0.11 (0.09-0.12), 0.09 (0.07-0.10) and 0.06 (0.05-0.08), respectively) and negatively associated with HDL-C (SMD = -0.13 (-0.14 to -0.12)). Both our multivariate analyses and meta-analysis showed that H. pylori infection significantly affects the serum lipid profile, which might lead to various dyslipidemia-induced severe diseases like coronary thrombosis or cerebral infarction.

A Hybrid Approach for the Stratified Mark-Specific Proportional Hazards Model with Missing Covariates and Missing Marks, with Application to Vaccine Efficacy Trials.

Deployment of the recently licensed CYD-TDV dengue vaccine requires understanding of how the risk of dengue disease in vaccine recipients depends jointly on a host biomarker measured after vaccination (neutralization titer - NAb) and on a "mark" feature of the dengue disease failure event (the amino acid sequence distance of the dengue virus to the dengue sequence represented in the vaccine). The CYD14 phase 3 trial of CYD-TDV measured NAb via case-cohort sampling and the mark in dengue disease failure events, with about a third missing marks. We addressed the question of interest by developing inferential procedures for the stratified mark-specific proportional hazards model with missing covariates and missing marks. Two hybrid approaches are investigated that leverage both augmented inverse probability weighting and nearest neighborhood hot deck multiple imputation. The two approaches differ in how the imputed marks are pooled in estimation. Our investigation shows that NNHD imputation can lead to biased estimation without properly selected neighborhood. Simulations show that the developed hybrid methods perform well with unbiased NNHD imputations from proper neighborhood selection. The new methods applied to CYD14 show that NAb is strongly inversely associated with risk of dengue disease in vaccine recipients, more strongly against dengue viruses with shorter distances.

Assessing the accuracy of predictive models with interval-censored data.

SummaryWe develop methods for assessing the predictive accuracy of a given event time model when the validation sample is comprised of case n}{}K interval-censored data. An imputation-based, an inverse probability weighted (IPW), and an augmented inverse probability weighted (AIPW) estimator are developed and evaluated for the mean prediction error and the area under the receiver operating characteristic curve when the goal is to predict event status at a landmark time. The weights used for the IPW and AIPW estimators are obtained by fitting a multistate model which jointly considers the event process, the recurrent assessment process, and loss to follow-up. We empirically investigate the performance of the proposed methods and illustrate their application in the context of a motivating rheumatology study in which human leukocyte antigen markers are used to predict disease progression status in patients with psoriatic arthritis.

Empirical likelihood for nonlinear regression models with nonignorable missing responses

AbstractThis article develops three empirical likelihood (EL) approaches to estimate parameters in nonlinear regression models in the presence of nonignorable missing responses. These are based on the inverse probability weighted (IPW) method, the augmented IPW (AIPW) method and the imputation technique. A logistic regression model is adopted to specify the propensity score. Maximum likelihood estimation is used to estimate parameters in the propensity score by combining the idea of importance sampling and imputing estimating equations. Under some regularity conditions, we obtain the asymptotic properties of the maximum EL estimators of these unknown parameters. Simulation studies are conducted to investigate the finite sample performance of our proposed estimation procedures. Empirical results provide evidence that the AIPW procedure exhibits better performance than the other two procedures. Data from a survey conducted in 2002 are used to illustrate the proposed estimation procedure. The Canadian Journal of Statistics 48: 386–416; 2020 © 2020 Statistical Society of Canada

Abstract WP114: Effect of Prestroke Aspirin on Infarct Volume

Objective: To investigate if prestroke aspirin use affects infarct volume, generally and by subtype. Background: Prestroke aspirin use may reduce initial stroke severity and improve functional outcome at discharge, especially in the large artery atherosclerosis (LAA) stroke. We investigated whether prestroke aspirin use is associated with infarct volume and the effect of prestroke aspirin on infarct volume is different between LAA versus non-LAA strokes. Methods: A total of 4427 patients were included. The association between infarct volume on DWI and prior aspirin use was assessed by multiple linear regression analysis. To adjust a significant imbalance between aspirin users vs. non-aspirin users, the augmented inverse-probability weighting (AIPW) and propensity score matching were used. Results: Mean age was 67.7(SD 12.4) years and 58.7% were male. 19.6% (n=869) took aspirin before stroke. Prestroke aspirin had an inverse relation with log-infarct volume (P = 0.007) and the effect was significantly modified by LAA versus non-LAA strokes (P for interaction = 0.02). In LAA stroke (n=2336), prestroke aspirin use was independently associated with log-infarct volume (standardized beta = -0.047; P = 0.032). In non-LAA stroke (n=2091), prestroke aspirin was not associated with infarct volume (P = 0.27). Using AIPW and propensity score matching, the mean difference of log-infarct volume between prestroke aspirin user versus non-aspirin uses was -0.28 (95% CI -0.52 to -0.04, P = 0.009) and -0.39 (95% CI -0.67 to -0.11, P = 0.02) in LAA strokes. In non-LAA strokes, AIPW and propensity score matching showed that prestroke aspirin use was not associated with infarct volume (P = 0.27 and P = 0.85, respectively). Conclusions: Our results showed that prestroke aspirin use is negatively associated with initial infarct volume on DWI in LAA strokes but not in non-LAA strokes.

Improved Doubly Robust Estimation in Marginal Mean Models for Dynamic Regimes

Abstract Doubly robust (DR) estimators are an important class of statistics derived from a theory of semiparametric efficiency. They have become a popular tool in causal inference, including applications to dynamic treatment regimes. The doubly robust estimators for the mean response to a dynamic treatment regime may be conceived through the augmented inverse probability weighted (AIPW) estimating function, defined as the sum of the inverse probability weighted (IPW) estimating function and an augmentation term. The IPW estimating function of the causal estimand via marginal structural model is defined as the complete-case score function for those subjects whose treatment sequence is consistent with the dynamic regime in question divided by the probability of observing the treatment sequence given the subject's treatment and covariate histories. The augmentation term is derived by projecting the IPW estimating function onto the nuisance tangent space and has mean-zero under the truth. The IPW estimator of the causal estimand is consistent if (i) the treatment assignment mechanism is correctly modeled and the AIPW estimator is consistent if either (i) is true or (ii) nested functions of intermediate and final outcomes are correctly modeled. Hence, the AIPW estimator is doubly robust and, moreover, the AIPW is semiparametric efficient if both (i) and (ii) are true simultaneously. Unfortunately, DR estimators can be inferior when either (i) or (ii) is true and the other false. In this case, the misspecified parts of the model can have a detrimental effect on the variance of the DR estimator. We propose an improved DR estimator of causal estimand in dynamic treatment regimes through a technique originally developed by [4] which aims to mitigate the ill-effects of model misspecification through a constrained optimization. In addition to solving a doubly robust system of equations, the improved DR estimator simultaneously minimizes the asymptotic variance of the estimator under a correctly specified treatment assignment mechanism but misspecification of intermediate and final outcome models. We illustrate the desirable operating characteristics of the estimator through Monte Carlo studies and apply the methods to data from a randomized study of integrilin therapy for patients undergoing coronary stent implantation. The methods proposed here are new and may be used to further improve personalized medicine, in general.

Improved methods for moment restriction models with data combination and an application to two‐sample instrumental variable estimation

AbstractCombining‐100 information from multiple samples is often needed in biomedical and economic studies, but differences between these samples must be appropriately taken into account in the analysis of the combined data. We study the estimation for moment restriction models with data combined from two samples under an ignorability‐type assumption while allowing for different marginal distributions of variables common to both samples. Suppose that an outcome regression (OR) model and a propensity score (PS) model are specified. By leveraging semi‐parametric efficiency theory, we derive an augmented inverse probability‐weighted (AIPW) estimator that is locally efficient and doubly robust with respect to these models. Furthermore, we develop calibrated regression and likelihood estimators that are not only locally efficient and doubly robust but also intrinsically efficient in achieving smaller variances than the AIPW estimator when the PS model is correctly specified but the OR model may be mispecified. As an important application, we study the two‐sample instrumental variable problem and derive the corresponding estimators while allowing for incompatible distributions of variables common to the two samples. Finally, we provide a simulation study and an econometric application on public housing projects to demonstrate the superior performance of our improved estimators. The Canadian Journal of Statistics 48: 259–284; 2020 © 2019 Statistical Society of Canada

Comparison of Hospital Outcomes of Transcarotid Artery Revascularization with Flow Reversal (TCAR) Vs. Carotid Endarterectomy (CEA)

Introduction - TransCarotid Artery Revascularization with flow reversal (TCAR) offers a less invasive option to carotid endarterectomy (CEA) in high risk patients and has the lowest reported overall stroke rate for any prospective trial of carotid artery stenting (CAS). This study compares initial in-hospital outcomes of CEA and TCAR using the Society for Vascular Surgery (SVS) Vascular Quality Initiative (VQI) TCAR Surveillance Project (TSP) done in collaboration with the Centers for Medicare & Medicaid Services (CMS) to create more information for future coverage decisions. Methods - The SVS TSP isdesigned to evaluate the safety and efficacy of TCAR in real world practice, using a contemporary comparison to CEA.Patients enrolled in this project were compared to those undergoing CEA during the same time period (2016-2017). The primary outcome was a composite of in-hospital stroke and death. Average treatment effects were estimated via augmented inverse-probability weighting (AIPW). Additional analysis was performed using multivariable logistic regression as well as various matching techniques such as propensity score matching and coarsened exact matching (CEM).Adjusted analysis accounted for age, gender, race, insurance status, CAD, CHF, CKD, COPD, symptomatic status, restenosis, prior vascular procedures, degree of ipsilateral stenosis and preoperative medication use. Results - A total of 637 patients underwent TCAR compared to 12,049 patients who underwent CEA. Patients undergoing TCAR were older (median age 74 vs.71 years), more likely to be symptomatic (33.6% vs. 27.9%),and had more medical comorbidities such as CAD (47.3% vs.26.6%), CHF (19.8% vs.11.1%), COPD (26.5% vs. 22.3%), CKD (39.9% vs. 33.6%), and prior vascular procedures compared to CEA patients (All p<0.01). The majority of TCAR procedures were done under general anesthesia (79.0% vs.90.3% in CEA, p<0.001). On average, TCAR was 36.7 minutes shorter than CEA (78.0±33.9 vs. 114.7±42.5, p<0.001). On univariate analysis, there were no differences in the rates of in-hospital stroke/death (1.3% vs. 1.7%, p=0.42), overall neurological events (2.0% vs.1.9%, p=0.83), in-hospital MI (0.7% vs.1.1%, p=0.31) and 30-day mortality (0.5% vs. 0.9%, p=0.08) between CEA and TCAR, respectively. Patients undergoing CEA had higher rates of cranial nerve injury (2.8% v.0.8%, p<0.01) and postoperative hypertension (18.3% vs. 11.6%, p<0.001) compared to TCAR patients. On multivariable analysis and using different matching methods, there were no differences in overall stroke, stroke/death or overall neurologic events (Figure 1). The absolute difference in adjusted stroke/death rates between the two groups was 0.3% [95%CI: -1.7%, 1.0%, p=0.64]. Conclusion - Despite a substantially higher medical risk in patients undergoing TCAR, preliminary analysis of the SVS-VQI TCAR Surveillance Project showed similar in-hospital stroke/death rates between TCAR and CEA after multivariable adjustment and rigorous matching. Further studies with larger sample sizes and longer follow will be needed to establish the equivalence of TCAR compared to CEA.

Conditional probability estimation based classification with class label missing at random

For binary classification, it is common that class labels of some subjects are missing. Generally, the complete case analysis and the two stage procedure can be used to extend existing full data classification methods to deal with classification with missing class labels. Nevertheless, these two approaches cannot take full advantage of unlabeled subjects. In this paper, binary classification with the class label missing at random (MAR) is considered. Based on the inverse probability weighting (IPW) method and the augmented inverse probability weighting (AIPW) method, two new methods called IPW–CPC and AIPW–CPC are proposed to construct powerful classifiers by estimating the conditional probability in a reproducing kernel Hilbert space (RKHS). Compared with the complete case analysis and the two stage procedure, the proposed IPW–CPC and AIPW–CPC methods can make the best use of unlabeled subjects, which contributes a lot to improving classification accuracy. Theoretically, we show that conditional misclassification rates of the proposed classifiers converge to the Bayes misclassification rate in probability and rates of convergence are also obtained. Finally, simulations and the real data analysis well demonstrate good performances of the proposed IPW–CPC and AIPW–CPC methods in comparison with existing methods.

부패경험이 인식된 공직부패수준에 미치는 영향의 크기: 확장 역확률 가중치 접근을 이용한 준비모수적 접근을 중심으로

부패경험이 인식된 공직부패수준에 미치는 영향의 크기: 확장 역확률 가중치 접근을 이용한 준비모수적 접근을 중심으로

“Robust-Squared” Imputation Models Using Bart

AbstractExamples of “doubly robust” estimators for missing data include augmented inverse probability weighting (AIPWT) and penalized splines of propensity prediction (PSPP). Doubly robust estimators have the property that, if either the response propensity or the mean is modeled correctly, a consistent estimator of the population mean is obtained. However, doubly robust estimators can perform poorly when modest misspecification is present in both models. Here we consider extensions of the AIPWT and PSPP that use Bayesian additive regression trees (BART) to provide highly robust propensity and mean model estimation. We term these “robust-squared” in the sense that the propensity score, the means, or both can be estimated with minimal model misspecification, and applied to the doubly robust estimator. We consider their behavior via simulations where propensities and/or mean models are misspecified. We apply our proposed method to impute missing instantaneous velocity (delta-v) values from the 2014 National Automotive Sampling System Crashworthiness Data System dataset and missing Blood Alcohol Concentration values from the 2015 Fatality Analysis Reporting System dataset. We found that BART, applied to PSPP and AIPWT, provides a more robust estimate compared with PSPP and AIPWT.

Implications of vaginal instrumental delivery for children's school achievement: A population‐based linked administrative data study

Vaginal instrumental delivery is a common obstetrical intervention, but its effect on children's later development is not well known. To determine if vaginal instrumental delivery is associated with adverse neurodevelopment as measured by school achievement. We performed a whole-of-population study involving linkage of routinely collected perinatal data with school assessments among children born in South Australia from 1999 to 2008. Participants were singleton children born by forceps (n=5494), ventouse (n=6988), or normal delivery (n=80803). School achievement was measured through performance on the National Assessment Program in Literacy and Numeracy (NAPLAN), at around eight years of age. This assessment involved five domains and scores were categorised according to performing at or above National Minimum Standards (NMS). Effects of instrumental versus normal vaginal delivery were analysed via augmented inverse probability weighting (AIPW), taking into account a variety of maternal, perinatal and sociodemographic characteristics. In unadjusted analyses, instrumental delivery was not associated with poor NAPLAN scores. AIPW analyses also suggested that instrumental delivery had minimal adverse effect on NAPLAN scores, with the largest difference being lower spelling scores among forceps-delivered children (-0.022 (95% CI -0.0053-0.009)) compared with spontaneous vaginal births. The findings were consistent among exploratory subgroup analyses involving births in the absence of prolonged labour, with APGAR≥9, and among normotensive and non-diabetic mothers. In singleton children born at term, instrumental delivery does not have an adverse effect on neurodevelopment as measured by NAPLAN performance at age eight.

Medium Term Treatment and Side Effects of Quantitative Easing: International Evidence

We use a cross-country sample of monthly observations for quantitative easing (QE) treatments in order to study the causal effect of such policies on a large set of economic and financial outcome variables. We address potential endogeneity by re-randomising the sample and applying the augmented inverse probability weighting (AIPW) estimator. Our results show that QE policies do affect the central bank balance sheet and asset prices, in particular long term yields, equity prices and exchange rates in the expected direction. Most importantly, we find that QE policies lead to a sustained rise in the CPI and in inflation expectations. However, our findings suggest that the main transmission channel does not appear to be stronger aggregate demand impacting inflation through the Phillips curve, but rather exchange rate depreciation. Finally, we do not find any evidence for side effects and increases in risk taking following QE, with real house prices and real credit not increasing or falling, and no downward effect on stock market volatility. JEL Classification: E5, F3