About
202
Publications
862,010
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
6,341
Citations
Introduction
Additional affiliations
September 2017 - present
November 2015 - July 2017
September 2011 - July 2017
Education
September 1994 - June 1997
University of California, Los Angeles
Field of study
- Heath Services Research
Publications
Publications (202)
This article introduces the ITSA command, which performs interrupted time series analysis for single and multiple group comparisons. In an interrupted time series analysis, an outcome variable is observed over multiple, equally spaced time periods before and after the introduction of an intervention which is expected to interrupt its level and/or t...
Diagnostic or predictive accuracy concerns are common in all phases of a disease management (DM) programme, and ultimately play an influential role in the assessment of programme effectiveness. Areas, such as the identification of diseased patients, predictive modelling of future health status and costs and risk stratification, are just a few of th...
Objectives: Medicare penalizes hospitals with 30-day readmissions above their expected rates. Hospitals have responded by implementing transitional care interventions; however, there is limited evidence to inform the development of a successful intervention.
Study Design: Parallel-group, stratified, randomized controlled trial.
Methods: A total of...
Interventions targeting individuals classified as "high-risk" have become common-place in health care. High-risk may represent outlier values on utilization, cost, or clinical measures. Typically, such individuals are invited to participate in an intervention intended to reduce their level of risk, and after a period of time, a follow-up measuremen...
Often, when conducting programme evaluations or studying the effects of policy changes, researchers may only have access to aggregated time series data, presented as observations spanning both the pre- and post-intervention periods. The most basic analytic model using these data requires only a single group and models the intervention effect using...
Importance
Multiple organ dysfunction (MOD) is a leading cause of in-hospital child mortality. For survivors, posthospitalization health care resource use and costs are unknown.
Objective
To evaluate longitudinal health care resource use and costs after hospitalization with MOD in infants (aged <1 year) and children (aged 1-18 years).
Design, Set...
Purpose
In the literature, the propriety of the meta-analytic treatment-effect produced by combining randomized controlled trials (RCT) and non-randomized studies (NRS) is questioned, given the inherent confounding in NRS that may bias the meta-analysis. The current study compared an implicitly principled pooled Bayesian meta-analytic treatment-eff...
Objective:
To use more precise measures of which hospitals are electronically connected to determine whether health information exchange (HIE) is associated with lower emergency department (ED)-related utilization.
Materials and methods:
We combined 2018 Medicare fee-for-service claims to identify beneficiaries with 2 ED encounters within 30 day...
Background
Intensive care unit (ICU) length of stay (LOS) and the risk adjusted equivalent (RALOS) have been used as quality metrics. The latter measures entail either ratio or difference formulations or ICU random effects (RE), which have not been previously compared.
Methods
From calendar year 2016 data of an adult ICU registry-database (Austral...
In prospective studies that evaluate the accuracy of diagnostic tests, participants' true disease status is unknown until after enrollment when the tests are performed. As such, the number of diseased and non-diseased participants cannot be fixed in advance as in retrospective studies. Furthermore, when the prevalence of the disease in the populati...
This paper demonstrates how ODA can be used to estimate treatment effects in longitudinal panel data using the oda Stata package.
In this article, I introduce two commands for computing the fragility index (FI): fragility, which is used for individual randomized controlled trials, and metafrag, which is used for meta-analyses. The FI for individual studies is defined as the minimum number of patients whose status would have to change from a nonevent to an event to nullify a s...
IMPORTANCE Policy makers envision synergistic benefits from primary care reform programs that advance infrastructure and processes in the context of a supportive payment environment.
However, these programs have been operationalized and implemented separately, raising the question of whether synergies are achieved.
OBJECTIVE To evaluate association...
This erratum fixes two formulas originally presented in: Linden, A. 2017. A comprehensive set of post‐estimation measures to enrich interrupted time series analysis. Stata Journal 17: 73‐88.
Overviews of optimal discriminant analysis (ODA) and novometric theory are presented. Discussion addresses the role of accuracy in translational and precision forecasting research, and of parsimony in theoretical research; the structure of maximum-accuracy univariable and multivariable models; underlying theoretical axioms; assessing statistical si...
This article introduces two commands for computing the fragility index (FI); fragility which is used for individual randomized controlled trials and metafrag which is used for meta-analyses. The FI for individual studies is defined as the minimum number of patients whose status would have to change from a nonevent to an event to nullify a statistic...
Interrupted time‐series analysis (ITSA) is a popular study design when conducting a randomized experiment is not feasible. The design is called an interrupted time series because the intervention is expected to “interrupt” the level and/or trend of the outcome variable —measured at equal intervals over time—subsequent to its introduction. The ITSA...
This paper introduces the getregstats command which computes all the statistics reported in a standard regression table when the user specifies the point estimate and only one other statistic (e.g., standard error, test statistic, P value, or upper/lower confidence limit). This is useful in situations when a minimal amount of information is availab...
In this article, we introduce the rwrmed package, which performs mediation analysis using the methods proposed by Wodtke and Zhou (2020, Epidemiology 31: 369–375). Specifically, rwrmed estimates interventional direct and indirect effects in the presence of treatment-induced confounding by fitting models for 1) the conditional mean of the mediator g...
We demonstrate the use of optimal data analysis to obtain a hierarchically optimal classification tree-based propensity score model for an application with three (treatment) groups, and to assess outcome differences between treatment groups after weighting observations by propensity scores to reduce threats to causal inference.
This paper illustrates testing directional hypotheses for test-retest Likert ratings of positive and negative emotional states and personality traits for males and females, using the Stata package for implementing ODA.
This paper demonstrates how the random forest algorithm can be used in conjunction with ODA to estimate treatment effects for multivalued treatments using the new Stata package for implementing ODA.
This paper illustrates testing a directional (i.e., confirmatory) hypotheses for a split-half reliability study using a polychotomous attribute having four categories, via the Stata package for implementing ODA.
This paper illustrates testing a directional (i.e., confirmatory) hypotheses for a parallel-forms reliability study using a binary and an ordered measure, via the Stata package for implementing ODA.
This paper illustrates testing directional (confirmatory) and non-directional (exploratory) hypotheses for an inter-rater reliability study using a three-category ordinal measure, via the Stata package for implementing ODA.
This paper describes how to test a non-directional (exploratory) hypothesis for a design relating a three-category class (“dependent”) variable and a continuous attribute vis-à-vis the Stata package for implementing ODA.
Objective: To assess longitudinal primary care organization participation patterns in
large-scale reform programs and identify organizational characteristics associated
with multiprogram participation.
Data Sources: Secondary data analysis of national program participation data over an
eight-year period (2009-2016).
Study Design: We conducted a ret...
This article introduces the rwrmed package, which performs mediation analysis using the methods proposed by Wodtke and Zhou (2020, Epidemiology, 31: 369-375). Specifically, rwrmed estimates interventional direct and indirect effects in the presence of treatment-induced confounding by fitting models for (1) the conditional mean of the mediator given...
Boosted regression (BR) has been recommended as a machine learning alternative to logistic regression for estimating the propensity score because of its greater accuracy. Commonly known as multiple additive regression trees, BR is a general, automated, data-adaptive modelling algorithm which can estimate the non-linear relationship between treatmen...
Data from the National Supported Work (NSW) randomized experiment have been used frequently over the past 30 years to demonstrate the imple-mentation of various non-experimental methods for drawing causal inferences about treatment effects. The present paper reassesses the approach used by Dehejia and Wahba (2002) for estimating propensity scores a...
Data from the National Supported Work (NSW) randomized experiment have been used frequently over the past 30 years to demonstrate implementation of various non-experimental methods for drawing causal inferences about treatment effects. In this paper we reanalyze these data using the new Stata package for implementing ODA.
This paper describes how to test a directional (confirmatory) hypothesis for a design relating a three-category class (“dependent”) variable and a four-level categorical ordinal attribute (“Likert-type independent variable”) vis-à-vis the new Stata package for implementing ODA.
This paper describes how to assess a confirmatory (directional) hypothesis for a design involving a multicategorical class (“dependent”) variable and an ordinal attribute (“independent variable”) using the new Stata package for implementing ODA.
This paper describes how to evaluate an exploratory (nondirectional) hypothesis for a design involving a multicategorical class (“dependent”) variable and a multicategorical attribute (“independent variable”) using the new Stata package for implementing ODA.
This paper demonstrates how to evaluate a confirmatory (directional) hypothesis for a design involving a multicategorical class (“dependent”) variable and a multicategorical attribute (“independent variable”) using the new Stata package for implementing ODA.
This paper describes how a confirmatory (a priori, directional, one-tailed) hypothesis involving a binary (dichotomous) class variable and continuous (interval or ratio) attribute is evaluated via MegaODA software using the new Stata package implementing ODA analysis.
This paper describes how a confirmatory (a priori, directional, one-tailed) hypothesis involving a binary (dichotomous) class variable and an ordinal (quintiles) attribute is evaluated using MegaODA software using the new Stata package implementing ODA analysis.
This paper describes how an exploratory (post hoc, nondirectional, two-tailed) hypothesis involving a binary (dichotomous) class variable and a categorical ordinal (three-level) attribute is evaluated using MegaODA software using the new Stata package implementing ODA analysis.
This paper describes how an exploratory (post hoc, nondirectional, two-tailed) hypothesis involving a binary (dichotomous) class variable and a categorical ordinal (three-level) attribute is evaluated using MegaODA software using the new Stata package implementing ODA analysis.
This paper describes how a confirmatory (a priori, directional, one-tailed) hypothesis involving a binary (dichotomous) class variable and a five-level ordinal attribute is evaluated using MegaODA software via the new Stata package implementing ODA analysis.
This paper describes how an exploratory (i.e., post hoc, nondirectional, two-tailed) hypothesis involving a binary (i.e., dichotomous) class variable and an ordinal (rank) attribute is evaluated using MegaODA software vis-à-vis the new Stata package implementing ODA analysis.
This paper describes how an exploratory (i.e., post hoc, nondirectional, two-tailed) hypothesis involving a binary (i.e., dichotomous) class variable and a multicategorical attribute with three or more categorical levels is evaluated using MegaODA software vis-à-vis the new Stata package implementing ODA analysis.
This paper describes how an exploratory (i.e., post hoc, nondirectional, or two-tailed) hypothesis involving a binary (i.e., dichotomous) class variable and a binary attribute can be evaluated using MegaODA software vis-à-vis the new Stata package for implementing ODA analysis.
This paper describes how a confirmatory (i.e., a priori, directional, or one-tailed) hypothesis involving a binary (i.e., dichotomous) class variable and a binary attribute can be evaluated using MegaODA software vis-à-vis the new Stata package for implementing ODA analysis.
Randomization ensures that treatment groups do not differ systematically in their characteristics, thereby reducing threats to validity that may otherwise explain differences in outcomes. Large observed imbalances in patient characteristics may indicate that selection bias is being introduced into the treatment allocation process. In this paper, I...
Health researchers frequently generate predictive models of time-to-event outcomes (e.g., death, onset of disease, hospital readmission) to assist clinicians to better understand the disease process and manage their patients. In this paper, I describe how the new Stata package for implementing CTA can be used to generate predictive models with time...
Mediation analysis identifies causal pathways by testing the relationships between the treatment, the outcome, and an intermediate variable that mediates the relationship between the treatment and the outcome. In this paper, I describe how the new Stata package for implementing CTA can be used to assess mediation effects.
In contrast to randomized studies in which individuals have no control over their treatment assignment, participants in observational studies self-select into the treatment arm and are therefore likely to differ in their characteristics compared to those who elect not to participate. Analytic approaches using the propensity score to adjust for diff...
Maximizing the discriminatory accuracy of a diagnostic or screening test is paramount to ensuring that individuals with or without the disease (or disease marker) are correctly identified as such. In this paper, I describe how the new Stata package for implementing ODA can be used to determine the optimal cut-point along the continuum of test value...
In contrast to randomized studies where individuals have no control over their treatment assignment, participants in observational studies self-select into the treatment arm and are therefore likely to differ in their characteristics from those who elect not to participate. These differences may explain part, or all, of the difference in the observ...
In randomized controlled trials (RCT) of sufficient size, we expect the treatment and control groups to be balanced on both observed and unobserved characteristics, and any imbalances are considered to be due to chance. CTA can be used to determine whether treatment assignment can be predicted by observed pre-intervention covariates–separately or i...
In this paper, I describe how to determine if any structural breaks exist in a time series prior to the introduction of an intervention using the new Stata package for implementing ODA. Given that the internal validity of the design rests on the premise that the interruption in the time series is associated with the introduction of the intervention...
In this paper, I describe how to evaluate treatment effects in interrupted time-series studies in which the treated unit is contrasted with one or more comparable control groups, using the new Stata package for implementing ODA.
In this paper, I describe how to evaluate treatment effects in non-randomized studies with a time-to-event outcome using the new Stata package for implementing ODA.
In this article, we introduce the evalue package, which performs sensitivity analyses for unmeasured confounding in observational studies using the methodology proposed by VanderWeele and Ding (2017, Annals of Internal Medicine 167: 268–274). evalue reports E-values, defined as the minimum strength of association on the risk-ratio scale that an unm...
In this paper, I describe how to assess whether treatment groups are comparable on observed baseline covariates (balance) in non-randomized studies using the new Stata package for implementing ODA.
This paper describes how dose-response relationships can be evaluated using the new Stata package for implementing ODA.
In this paper, I demonstrate how treatment effects in observational data can be estimated for both binary and multivalued treatments using the new Stata package for implementing ODA. Matching and weighting techniques are implemented and ODA results are compared to those using conventional regression approaches.
In this paper, the new Stata package for implementing ODA is intro-duced by reanalyzing data from a study by Linden and Butterworth (2014) that investigated the effect of a comprehensive hospital-based intervention in reducing readmissions for chronically ill patients. In the original analysis, negative binomial regression was used to evaluate read...
Different weighting schemes in optimal survival analysis are considered.
In this article, I introduce the medadhere command, which computes medication adherence rates for two commonly used measures in research and practice: the medication possession ratio and the proportion of days covered. medadhere computes adherence rates for a single medication or multiple medications, and its options provide great flexibility to su...
This study extends recent research assessing the use of relative thresholds in matched-pairs designs, for a randomized blocks design in which four treatments are randomly assigned to blood samples drawn from each of eight people (each person treated as a block). Both raw and ipsatively standardized plasma clotting times are compared between treatme...
In this article I introduce the medadhere package, which computes medication adherence rates for two commonly-used measures in research and practice-the medication possession ratio (MPR) and proportion of days covered (PDC). medadhere computes adherence rates for a single medication or multiple medications, and its options provide great flexibility...
Optimal discriminant analysis (ODA) is often used to compare values of one (or more) attributes between two (or more) groups of observations with respect to a fixed discriminant threshold that maximizes accuracy normed against chance for the sample. However, a recent study using a matched-pairs design found that using a relative discriminant thresh...
Recent research compared the ability of various classification algorithms [logistic regression (LR), random forests (RF), support vector machines (SVM), boosted regression (BR), multi-layer perceptron neural net model (MLP), and classification tree analysis (CTA)] to correctly fail to identify a relationship between a binary class (dependent) varia...
Prior research contrasted the ability of different classification algorithms [logistic regression (LR), random forests (RF), boosted regression (BR), support vector machines (SVM), classification tree analysis (CTA)] to correctly fail to identify a relationship between a binary class (dependent) variable and ten randomly generated attributes (covar...
After any algorithm which controls the growth of a classification tree model has completed, the resulting model must be pruned in order to explicitly maximize predictive accuracy normed against chance. This article illustrates manually-conducted maximum-accuracy pruning of a classification and regression tree (CART) model that was developed to pred...
In a recent paper, we assessed the ability of several classification algorithms (logistic regression, random forests, boosted regression, support vector machines, and classification tree analysis [CTA]) to correctly not identify a relationship between the dependent variable and ten covariates generated completely at random. Only classification tree...
The adaptability of novometric analysis is illustrated for an example involving three class categories and two ordered attributes.
Automated machine learning algorithms are widely promoted as the best approach for estimating propensity scores, because these methods detect patterns in the data which manual efforts fail to identify. If classification algorithms are indeed ideal for identifying relationships between treatment group participation and covariates which predict parti...
Low-value care worsens patient-centered outcomes and imparts a negative economic effect, which has prompted the Choosing Wisely campaign to promote a national dialogue on the judicious use of services that are deemed to be nonbeneficial. One recommendation is “avoid routine multiple daily self-glucose monitoring in adults with stable type 2 diabete...
Difference-in-differences (DID) analysis is used widely to estimate the causal effects of health policies and interventions. A critical assumption in DID is "parallel trends": that pre-intervention trends in outcomes are the same between treated and comparison groups. To date, little guidance has been available to researchers who wish to use DID wh...
Diagnostic screening tests are used to predict an individual's graduated disease status which is measured on an ordered scale assessing disease progression (severity of illness). Maximizing the predictive accuracy of the diagnostic or screening test is paramount to correctly identifying an individual's actual score along the ordered continuum. The...
Maximizing the discriminatory accuracy of a diagnostic or screening test is paramount to correctly identifying individuals with vs. without the disease or disease marker. In this paper we demonstrate the use of ODA to identify the optimal cut-point which best discriminates between those with vs. without the disease (or marker) under study, for any...
Background:
Improving primary care for patients with chronic illness is critical to advancing healthcare quality and value. Yet, little is known about what strategies are successful in helping primary care practices deliver high-quality care for this population under value-based payment models.
Methods:
Double-blind interviews in 14 primary care...
Data from the National Supported Work (NSW) randomized experiment
have been used frequently over the past 30 years to demonstrate the implementation
of various non-experimental methods for drawing causal
inferences about treatment effects. In the present study we reanalyze the
NSW data using ODA and compare results with those estimated using ttests...
In a recent series of papers, ODA has been applied to observational data to draw causal inferences about treatment effects. Presently, ODA is applied to survival outcomes from a randomized controlled trial, with a reanalysis of a study by Linden and Butterworth [2014] that investigated (as a secondary outcome) the effect of a comprehensive hospital...
In a recent series of papers, ODA has been applied to observational data to draw causal inferences about treatment effects. In this article ODA is applied to data from a randomized controlled trial, with a reanalysis of a study by Linden and Butterworth [2014] that investigated the effect of a comprehensive hospital-based intervention in reducing r...
Rationale, aims, and objectives
Interrupted time series analysis (ITSA) is a popular evaluation methodology in which a single treatment unit's outcome is studied over time and the intervention is expected to “interrupt” the level and/or trend of the outcome, subsequent to its introduction. The internal validity of this analysis is strengthened cons...
In this article, I review A Course in Item Response Theory and Modeling with Stata by Tenko Raykov and George A. Marcoulides (2018 [Stata Press]).
Rationale, aims, and objectives
Interrupted time series analysis (ITSA) is a popular evaluation methodology in which a single treatment unit's outcome is studied over time, and the intervention is expected to “interrupt” the level and/or trend of the outcome, subsequent to its introduction. The internal validity of this analysis is strengthened con...
Rationale, aims, and objectives
Interrupted time series analysis (ITSA) is an evaluation methodology in which a single treatment unit's outcome is studied serially over time and the intervention is expected to “interrupt” the level and/or trend of that outcome. ITSA is commonly evaluated using methods which may produce biased results if model assum...
Rationale, aims, and objectives
Several enhancements have been proposed for interrupted time series analysis (ITSA) to improve causal inference. Presently, group‐based trajectory modelling (GBTM) is introduced as a complement to ITSA. GBTM assumes a certain number of discrete groups in the sample have unique trajectories of the outcome. GBTM is use...
In 1997, Australia implemented a gun buyback program that reduced the stock of firearms by around one-fifth, and nearly halved the number of gun-owning households. Leigh and Neill evaluated if the reduction in firearms availability affected homicide and suicide rates, and reported that the buyback led to a drop in the firearm suicide rates of almos...
Rationale, aims and objectives: Interrupted time series analysis (ITSA) is an evaluation methodology in which a single treatment unit's outcome is studied serially over time and the intervention is expected to “interrupt” the level and/or trend of that outcome. The internal validity is strengthened considerably when the treated unit is contrasted w...
Rationale, aims and objectives: Interrupted time series analysis (ITSA) is an evaluation methodology in which a single treatment unit's outcome is studied over time and the intervention is expected to “interrupt” the level and/or trend of the outcome. The internal validity is strengthened considerably when the treated unit is contrasted with a comp...
Rationale, aims and objectives: Interrupted time series analysis (ITSA) is a popular evaluation methodology in which a single treatment unit’s outcome is studied over time and the intervention is expected to “interrupt” the level and/or trend of the outcome, subsequent to its introduction. When ITSA is implemented without a comparison group, the in...
Rationale, aims and objectives:
A common approach to assessing treatment effects in nonrandomized studies with time-to-event outcomes is to estimate propensity scores and compute weights using logistic regression, test for covariate balance, and then estimate treatment effects using Cox regression. A machine-learning alternative-classification tre...
Rationale, aims, and objectives: Mediation analysis identifies causal pathways by testing the relationships between the treatment, the outcome, and an intermediate variable that mediates the relationship between the treatment and outcome. This paper introduces classification tree analysis (CTA), a machine‐learning procedure, as an alternative to co...
Background: Little is known about how to discourage clinicians from ordering low-value services. Our objective
was to test whether clinicians committing their future selves (ie, precommitting) to follow Choosing Wisely
recommendations with decision supports could decrease potentially low-value orders.
Methods: We conducted a 12-month stepped wedge...
Rationale, aims, and objectives: Randomization ensures that treatment groups do not differ systematically in their characteristics, thereby reducing threats to validity that may otherwise explain differences in outcomes. Large observed imbalances in patient characteristics may indicate that selection bias is being introduced into the treatment allo...
Rationale, aims, and objectives: Time to the occurrence of an event is often studied in health research. Survival analysis differs from other designs in that follow‐up times for individuals who do not experience the event by the end of the study (called censored) are accounted for in the analysis. Cox regression is the standard method for analysing...
The use of CTA to construct propensity score weights is complicated by division by zero in models having any perfectly predicted endpoints: omitting undefined propensity scores yields a degenerate solution. This note presents an algorithmic remedy to this situation.
Rationale, aims and objectives: In evaluating non‐randomized interventions, propensity scores (PS) estimate the probability of assignment to the treatment group given observed characteristics. Machine learning algorithms have been proposed as an alternative to conventional logistic regression for modelling PS in order to avoid limitations of linear...
Questions
Questions (3)