SAS Code Research Articles

Extreme heat episodes and risk of preterm birth in California, 2005–2013

BackgroundPreterm birth is a leading cause of infant morbidity and mortality. Identifying potentially modifiable triggers toward the end of gestation, such as extreme heat, can improve understanding of the role of acute stress on early deliveries and inform warning systems. In this study we examined the association between extreme heat, variously defined during the last week of gestation, and risk of preterm birth among mothers in California. MethodsWe created a population-based cohort comprised of 1,967,300 mothers who had live, singleton births in California, from May through September 2005–2013. Daily temperature data estimated at the maternal zip code of residence was used to create 12 definitions of extreme heat with varying relative temperatures (75th, 90th, 95th, and 98th percentiles) and durations (at least 2, 3, or 4 consecutive days). We estimated risk of preterm birth (<37 gestational weeks) in relation to exposure to extreme heat during the last week of gestation with multi-level Cox proportional hazard regression models, adjusting for maternal characteristics, sex of neonate, and seasonality. We also included randomly generated data, SAS code, and estimates for reproducibility purposes. ResultsApproximately 7% of the cohort had a preterm birth. For all definitions of extreme heat, the risk of preterm birth was consistently higher among mothers who experienced an extreme heat episode during their last week of gestation. Hazard ratios ranged from 1.008 (95% CI: 0.997, 1.021) to 1.128 (95% CI: 1.052, 1.210), with increasing associations as the relative temperature and duration of extreme heat episode increased. ConclusionThis study adds to the previous literature by considering multiple definitions of extreme heat and applying a time-to-event framework. Findings suggest that acute exposure to extreme heat during the last week of gestation may trigger an earlier delivery. Implementing heat warning systems targeted toward pregnant women may improve birth outcomes.

A note on the bias of standard errors when orthogonality of mean and variance parameters is not satisfied in the mixed model for repeated measures analysis.

The mixed effect models for repeated measures (MMRM) analysis is sometimes used as a primary analysis in longitudinal randomized clinical trials. The SE for the treatment effect in the MMRM analysis is usually estimated by assuming the orthogonality of the fixed effect and variance-covariance parameters, which is the orthogonality property of a multivariate normal distribution, because of default settings of most standard statistical software. However, this property might be lost when analysis models are misspecified and/or data include missing values with the mechanism of being missing at random. In this study, we investigated the effect of the assumption of the orthogonality property on the estimation of the SE for the MMRM analysis. From simulation and case studies, it was shown that the SE with the assumption of orthogonality property had nonnegligible bias, especially when the analysis models assuming heteroscedasticity between treatment groups were applied. We also introduce the SAS code for the MMRM analysis without assuming the orthogonality property. Assuming the orthogonality property in the MMRM analysis would lead to invalid statistical inference, and it is necessary to be careful when applying the MMRM analysis with most standard software.

Inverse Probability of Treatment Weighting (Propensity Score) using the Military Health System Data Repository and National Death Index.

When randomized controlled trials are not feasible, retrospective studies using big data provide an efficient and cost-effective alternative, though they are at risk for treatment selection bias. Treatment selection bias occurs in a non-randomized study when treatment selection is based on pre-treatment characteristics that are also associated with the outcome. These pre-treatment characteristics, or confounders, can influence evaluation of a treatment's effect on the outcome. Propensity scores minimize this bias by balancing the known confounders between treatment groups. There are a few approaches to performing propensity score analyses, including stratifying by the propensity score, propensity matching, and inverse probability of treatment weighting (IPTW). Described here is the use of IPTW to balance baseline comorbidities in a cohort of patients within the US Military Health System Data Repository (MDR). The MDR is a relatively optimal data source, as it provides a contained cohort in which nearly complete information on inpatient and outpatient services is available for eligible beneficiaries. Outlined below is the use of the MDR supplemented with information from the national death index to provide robust mortality data. Also provided are suggestions for using administrative data. Finally, the protocol shares an SAS code for using IPTW to balance known confounders and plot the cumulative incidence function for the outcome of interest.

How to Clean Academic TRACE Data

This note updates the filter from the previous note How to clean Enhanced TRACE data to handle the Academic TRACE data. The Academic TRACE include masked dealer identifiers and allow for improved handling of inter-dealer transactions. We include SAS code for the new filter in the appendix.

%svy_logistic_regression: A generic SAS macro for simple and multiple logistic regression and creating quality publication-ready tables using survey or non-survey data.

IntroductionReproducible research is increasingly gaining interest in the research community. Automating the production of research manuscript tables from statistical software can help increase the reproducibility of findings. Logistic regression is used in studying disease prevalence and associated factors in epidemiological studies and can be easily performed using widely available software including SAS, SUDAAN, Stata or R. However, output from these software must be processed further to make it readily presentable. There exists a number of procedures developed to organize regression output, though many of them suffer limitations of flexibility, complexity, lack of validation checks for input parameters, as well as inability to incorporate survey design.MethodsWe developed a SAS macro, %svy_logistic_regression, for fitting simple and multiple logistic regression models. The macro also creates quality publication-ready tables using survey or non-survey data which aims to increase transparency of data analyses. It further significantly reduces turn-around time for conducting analysis and preparing output tables while also addressing the limitations of existing procedures. In addition, the macro allows for user-specific actions to handle missing data as well as use of replication-based variance estimation methods.ResultsWe demonstrate the use of the macro in the analysis of the 2013–2014 National Health and Nutrition Examination Survey (NHANES), a complex survey designed to assess the health and nutritional status of adults and children in the United States. The output presented here is directly from the macro and is consistent with how regression results are often presented in the epidemiological and biomedical literature, with unadjusted and adjusted model results presented side by side.ConclusionsThe SAS code presented in this macro is comprehensive, easy to follow, manipulate and to extend to other areas of interest. It can also be incorporated quickly by the statistician for immediate use. It is an especially valuable tool for generating quality, easy to review tables which can be incorporated directly in a publication.

Sample size calculation for the Andersen-Gill model comparing rates of recurrent events.

Recurrent events arise frequently in biomedical research, where the subject may experience the same type of events more than once. The Andersen-Gill (AG) model has become increasingly popular in the analysis of recurrent events particularly when the event rate is not constant over time. We propose a procedure for calculating the power and sample size for the robust Wald test from the AG model in superiority, noninferiority, and equivalence clinical trials. Its performance is demonstrated by numerical examples. Sample SAS code is provided in the Supplementary Material.

Simple methods for the estimation and sensitivity analysis of principal strata effects using marginal structural models: Application to a bone fracture prevention trial.

In randomized clinical trials, it is often of interest to estimate the effect of treatment on quality of life (QOL), in addition to those on the event itself. When an event occurs in some patients prior to QOL score assessment, investigators may compare QOL scores between patient subgroups defined by the event after randomization. However, owing to postrandomization selection bias, this analysis can mislead investigators about treatment efficacy and result in paradoxical findings. The recent Japanese Osteoporosis Intervention Trial (JOINT-02), which compared the benefits of a combination therapy for fracture prevention with those of a monotherapy, exemplifies the case in point; the average QOL score was higher in the combination therapy arm for the unfractured subgroup but was lower for the fractured subgroup. To address this issue, principal strata effects (PSEs), which are treatment effects estimated within subgroups of individuals stratified by potential intermediate variable, have been discussed in the literature. In this paper, we describe a simple procedure for estimating the PSEs using marginal structural models. This procedure utilizes SAS code for the estimation. In addition, we present a simple sensitivity analysis method for examining the resulting estimates. The analyses of JOINT-02 data using these methods revealed that QOL scores were higher in the combination therapy arm than in the monotherapy arm for both subgroups.

Usage of the Healthy Eating Index-2015 (HEI-2015) (P13-031-19)

ObjectivesWith each iteration of the Dietary Guidelines for Americans (DGA) since 2005, scientists from the U.S. Department of Agriculture and the National Cancer Institute (NCI) have updated and released a Healthy Eating Index (HEI) to measure alignment with federal dietary guidance. The HEI-2015, which includes the 13 dietary components emphasized in the 2015–2020 DGA, was released in April 2017, and details about its development, evaluation, and applications were published in September 2018. Examination of research using the HEI-2015 and resources designed to facilitate its application are critical for researchers who study dietary quality and dietary patterns and can inform key stakeholders and scientists participating in the ongoing refinement of the index and its supporting resources. MethodsTo evaluate use of resources related to the HEI-2015, we reviewed Adobe Analytics reports on the NCI HEI-2015 webpages, the main website containing background and detailed information about the application HEI-2015. We searched PubMed and Google Scholar abstracts to determine the number publications (including abstracts, poster presentations, and dissertations) that used the HEI-2015. ResultsIn 2017–18, there were 87,130 page views of the NCI HEI webpages, of which 9244 were unique visitors to the HEI-2015 homepage. There were 3946 unique visitors to the “Calculating HEI Scores” webpage and 2502 unique visitors to the “SAS code” page. As of January 2019, there were 35 peer-reviewed publications utilizing the HEI-2015. A Google Scholar search yielded 20 abstracts, poster presentations, and dissertations that utilized the HEI-2015. ConclusionsUsage of the latest iteration of the Healthy Eating Index, HEI 2015, has been growing in the only 20 months since its release in 2017. Publications using it include a range of topics, such as economic research, epidemiology, surveillance, and sustainability. Given the relatively small number of publications, abstracts or posters that have used the HEI-2015, and the large number of unique visitors to the HEI website, especially the SAS code webpage, many more applications of the HEI-2015 are anticipated in the near future. Funding SourcesNone.

Digital Module 06: Bayesian Psychometrics—Posterior Predictive Model Checking https://ncme.elevate.commpartners.com

AbstractDrawing valid inferences from modern measurement models is contingent upon a good fit of the data to the model. Violations of model‐data fit have numerous consequences, limiting the usefulness and applicability of the model. As Bayesian estimation is becoming more common, understanding the Bayesian approaches for evaluating model‐data fit models is critical. In this instructional module, Allison Ames and Aaron Myers provide an overview of Posterior Predictive Model Checking (PPMC), the most common Bayesian model‐data fit approach. Specifically, they review the conceptual foundation of Bayesian inference as well as PPMC and walk through the computational steps of PPMC using real‐life data examples from simple linear regression and item response theory analysis. They provide guidance for how to interpret PPMC results and discuss how to implement PPMC for other model(s) and data. The digital module contains sample data, SAS code, diagnostic quiz questions, data‐based activities, curated resources, and a glossary.

Sequential trials in the context of competing risks: Concepts and case study, with R and SAS code.

Sequential designs and competing risks methodology are both well established. Their combined use has recently received some attention from a theoretical perspective, but their joint application in practice has been discussed less. The aim of this paper is to provide the applied statistician with a basic understanding of both sequential design theory and competing risks methodology and how to combine them in practice. Relevant references to more detailed theoretical discussions are provided, and all discussions are illustrated using a real case study. Extensive R and SAS code is provided in the online Supplementary Material.

Corrigendum

Corrigendum

Improved strategy to collect sensitive data by using geometric distribution as a randomization device

In this article, we improvise Singh and Grewal (2013) and Hussain et al. (2016) techniques by introducing a new two-stage randomization response process. Using the proposed new technique, we achieve better efficiency and increasing protection of privacy of respondents than the Kuk (1990), Singh and Grewal (2013) and Hussain et al. (2016) models. The relative efficiency and protection of the respondents of the proposed two-stage randomization device have been investigated through simulation study, and the situations are reported where the proposed estimator performs better than its competitors. The SAS code used to investigate the performance of the proposed strategy are also provided.

A monotone data augmentation algorithm for multivariate nonnormal data: With applications to controlled imputations for longitudinal trials.

An efficient monotone data augmentation (MDA) algorithm is proposed for missing data imputation for incomplete multivariate nonnormal data that may contain variables of different types and are modeled by a sequence of regression models including the linear, binary logistic, multinomial logistic, proportional odds, Poisson, negative binomial, skew-normal, skew-t regressions, or a mixture of these models. The MDA algorithm is applied to the sensitivity analyses of longitudinal trials with nonignorable dropout using the controlled pattern imputations that assume the treatment effect reduces or disappears after subjects in the experimental arm discontinue the treatment. We also describe a heuristic approach to implement the controlled imputation, in which the fully conditional specification method is used to impute the intermediate missing data to create a monotone missing pattern, and the missing data after dropout are then imputed according to the assumed nonignorable mechanisms. The proposed methods are illustrated by simulation and real data analyses. Sample SAS code for the analyses is provided in the supporting information.

Miscodings in Compustat's auditor variable: issues, identification, and correction

Using an easily implementable methodology for identifying potential data errors, I identify and correct cases where Compustat miscodes its auditor variable. In this paper, I present the methodology and provide SAS code that implements the methodology, enabling researchers to easily identify and correct auditor variable miscodings. Further, I provide a list of corrections for a sample of Compustat firms from 2001 to 2014. Auditor variable miscodings have implications for both audit-specific research as well as general capital markets research. I find that some of the miscodings arise from the fact that, following an auditor change, the previous auditor's report remains in a firm's 10-K, and Compustat occasionally codes the previous auditor as the current auditor. Aside from identifying and correcting miscodings, I also find that a non-zero number of firms change to a new auditor and then, after only one year with the new auditor, switch back to the prior auditor.

Development of a Concept Dictionary to Standardize Definitions and Classifications While Working With a Common Repository of Linked Administrative Data

IntroductionSupporting standardized approaches to common tasks is an important component of quality research using linked administrative data. Standard concept definitions and classifications are vital for ensuring accuracy and consistency in definitions between projects, and improving efficiency and quality. Other leading organizations have published online standard definitions of concepts and classifications.&#x0D; Objectives and ApproachWe developed a comprehensive concept dictionary using a standardized definition template of key components including data sources, codes, scale or range of values, validation details, limitations, SAS code and formats, related concepts, and MeSH terms. A web-based application (built on the Microsoft SharePoint platform) was developed to offer the latest web content authoring capabilities, and advanced search mechanisms enabling the user to search concepts by MeSH terms and key words. It also allowed for navigating concepts through category navigation including clickable categories and sub-categories. Entries will be reviewed annually to ensure the content remains up-to-date.&#x0D; ResultsTo date, ten concepts, with accompanying codes, have been published on the concept dictionary with another ten currently undergoing editorial review. These concepts span a variety of topics such as injuries, mental health and addictions-related outpatient services, and annual physical exams. New concepts written by content experts and reviewed by an editorial committee will be added on an on-going basis; thirty concepts are currently under development.&#x0D; Conclusion/ImplicationsDevelopment of a concept dictionary provides standardized definitions, algorithms and codes to ensure consistency and quality of research and analysis across multiple projects. Future aims include expansion of the internal organizational site to an external site through collaboration with key stakeholders.

Miscodings in Compustat's Auditor Variable: Issues, Identification, and Correction

Using an easily implementable methodology for identifying potential data errors, I identify and correct cases where Compustat miscodes its auditor variable. In this paper, I present the methodology and provide SAS code that implements the methodology, enabling researchers to easily identify and correct auditor miscodings. Further, I provide a list of corrections for a sample of Compustat firms from 2001 to 2014. Auditor variable miscodings have implications for both audit-specific research as well as general capital markets research. I find that in some cases, miscodings arise from the fact that, following an auditor change, the previous auditor’s report remains in a firm’s 10-K, and Compustat occasionally codes the previous auditor as the current auditor. Aside from identifying and correcting miscodings, I also find that a non-zero number of firms change to a new auditor and then, after only one year with the new auditor, switch back to the prior auditor.

A Practical Guide to Analyzing Time-Varying Associations between Physical Activity and Affect Using Multilevel Modeling.

There is growing interest in within-person associations of objectively measured physical and physiological variables with psychological states in daily life. Here we provide a practical guide with SAS code of multilevel modeling for analyzing physical activity data obtained by accelerometer and self-report data from intensive and repeated measures using ecological momentary assessments (EMA). We review previous applications of EMA in research and clinical settings and the analytical tools that are useful for EMA research. We exemplify the analyses of EMA data with cases on physical activity data and affect and discuss the future challenges in the field.

The Wilcoxon–Mann–Whitney Procedure Fails as a Test of Medians

ABSTRACTTo illustrate and document the tenuous connection between the Wilcoxon–Mann–Whitney (WMW) procedure and medians, its relationship to mean ranks is first contrasted with the relationship of a t-test to means. The quantity actually tested: is then described and recommended as the basis for an alternative summary statistic that can be employed instead of medians. In order to graphically represent an estimate of the quantity: Pr(X1 < X2) + Pr(X1 = X2)/2, use of a bubble plot, an ROC curve and a dominance diagram are illustrated. Several counter-examples (real and constructed) are presented, all demonstrating that the WMW procedure fails to be a test of medians. The discussion also addresses another, less common and perhaps less clear cut, but potentially even more important misconception: that the WMW procedure requires continuous data in order to be valid. Discussion of other issues surrounding the question of the WMW procedure and medians is presented, along with the authors' teaching experience with the topic. SAS code used for the examples is included as supplementary material.

Statistical methodological review for time-to-event data

For Time-To-Event (TTE) data, various statistical methods have been discussed in the literature. In this article we give a review of the TTE data analysis methods. The review includes descriptive methods, such as Kaplan-Meier estimator and Life Table, as well as inferential methods, such as the Log-Rank test and the Cox (Proportional Hazard) model. We provide a roadmap in a figure or diagram format to which methods are practically available to use in the literature. In addition, the implementation of these methods in popular statistical software packages such as SAS is also presented. This article will be very helpful for practitioners, investigators, and researchers to determine which TTE data analysis method (along with the corresponding SAS code) are available to use in various fields of study such as clinical trials, epidemiology, etc., both for the design phase of a study in prospective study or retrospective study analysis.

Financial Ratios for Accounting Research

This paper provides guidance on the appropriate estimation of financial ratios for empirical research corporate finance, corporate governance and accounting. Practical examples are provided employing the widely-used Compustat database, and all calculated ratios are made available for download in a dataset. A companion Github repository of the associated SAS code is offered to assist researchers in estimating key financial ratios consistently.