Estimate Carryover Effect in Clinical Trial Crossover Designs

Total Page:16

File Type:pdf, Size:1020Kb

Estimate Carryover Effect in Clinical Trial Crossover Designs Paper PO16 Estimate Carryover Effect in Clinical Trial Crossover Designs David Shen, WCI, Inc. Zaizai Lu, AstraZeneca Pharmaceuticals ABSTRACT The crossover design to study the differences in treatments yields a more efficient comparison of treatments than a parallel design. Subjects are on their own controls. The within-patient variation is less than between-patient variation. Crossover design requires a smaller sample size than a parallel design, but achieves same level of statistical power and precision. However, there might be a potential carryover effect in crossover design. The paper discusses how carryover effect may bias statistical results, and provides a method to test carryover effects. SAS procedures such as TTEST, GLM and MIXED are also included. INTRODUCTION A crossover trial is one in which individual subjects are given a sequence of treatments rather that one treatment at any time. The subjects cross over from one treatment to another treatment during the course of the trial. This is in contrast to a parallel design where subjects are randomized to a treatment and remain on that treatment throughout the whole trial. Crossover design is commonly used in the early phase trials such as: • Pharmacokinetic studies to establish concentration time profiles • Bioequivalence • Food interaction studies • Dose proportionality • Dose escalation studies for investigating maximum tolerated does (MTD) In clinical trials, the disease should be chronic and stable. Quickly reversible treatments are more suitable such as for asthma, arthritis, gastro-esophageal reflux and hypertension. The treatments should not be a complete cure but only alleviate the disease condition. If one treatment cures the patient disease in the first period, then the other treatment will have no chance to demonstrate its effectiveness in the second period. It’s not recommended for crossover design when either treatment is expected to be a cure or the condition disappears in a short period (e.g. common cold). The crossover design would increase the precision. Each patient serves his or her own control, so the comparisons are usually based on within-patient variability (which is usually less than the between-subject variability). The increased power with greater precision to estimate the treatment differences reduces the sample size. 1 MODEL AND DESIGN The order of drug treatment in a crossover study is called a sequence and the time of a treatment is called a period. The treatment are represented with capital letters, such as A, B, etc. The most common crossover design is AB/BA. Treatment A Treatment A Start Washout (Baseline) (Baseline) Treatment B Treatment B Subjects should be randomized to the sequence. If all subjects receive the two treatments in the same order, the difference between treatments would be confounded with any other changes, which may occur overtime. For example, in a study of treatment effect of cholesterol level, subjects may change their diet and exercise behavior for as a result of awareness of health issues. This would likely manifest itself as a decrease in cholesterol levels over the later portion of the study and might end up being attributed to the second treatment. In randomization, half of subjects are assigned to receive A/B while other half receive B/A. Any change that favors B over A in one sequence will favor A over B in the other sequence and cancel out of the treatment comparison. CARRYOVER EFFECTS Despite the appeal of having each subject serve as his own control, crossover studies have substantial weaknesses, as well. The potential problem in crossover design is that carryover effects may bias the direct treatment effects. Carryover (or residual) effect is defined as the effect of the treatment from the previous time period on the response at the current time period. It occurs when the effect of a treatment given in the first time period persists into the second period and distorts the effect of the second treatment. The incorporation of washout period in the design can diminish the impact of carryover effects. The washout period is defined as the time between treatment periods. In clinical trial studies, the length of the washout period usually id determined as some multiple of the half-life (t1/2) of the study medicine within the population of interest. Generally, a washout is at least 5 times of the t/12. If the carryover effects for A and B are equivalent in the AB|BA crossover design, then this carryover effect is not aliased with the treatment difference. While differential carryover effects may occur is in clinical trials where an active drug (A) is compared to placebo (B). The subjects in the AB sequence might experience a strong A carryover during the second period, whereas the subjects in BA sequence might experience a weak B carryover during the second period. A washout period should be long enough to minimize the carryover effects. Separate baseline is also helpful to eliminate the carryover effects. 2 Carryover effects will cause the difference between the two treatments to be different in the two time periods, resulting in a significant TREATMENT*PERIOD interaction. Thus, TREATMENT*PERIOD interactions label carryover effect. When the interaction is significant, indicating the presence of carryover, a usual practice is to set aside the results of the second time period and analyze the first period only, because the first period is free of carryover effects. If the preliminary test for carryover is not significant, then the data from both periods are analyzed in the usual manner. STATISTICAL DETAILS Analysis is more complex than parallel group designs, possibility of carryover effects poses added concern in the analysis which is not present in the randomized parallel group design. The two-stage model Grizzle proposed is shown below. Yijk = µ + bij + πk + φm + λm + εijk where i = sequence, j = patient, k = period and m = treatment µ : overall mean th th 2 bij : effect of j patient with i sequence and is ~N(0, σb ) th πk : effect of k period th φm : direct effect of m drug treatment th λm : residual effect of m drug treatment 2 εijk : random error and is ~N(0, σb ) The table 1 lists al the effects in period 1 and period 2. Note this is no carryover effect in period 1. Table 1. Effects of AB| in both Period BA Period 1 Period 2 Sum Difference Sequence AB µ + π1 + φ1 µ + π2 + φ2 + λ1 Y1.1+ Y2.1 Y1.1 - Y2.1 (Y1.1) (Y2.1) Sequence BA µ + π1 + φ2 µ + π2 + φ1 + λ2 Y1.2+ Y2.2 Y1.2 - Y2.2 (Y1.2) (Y2.2) Step 1. Estimate the carryover effect H0: λ1 = λ2 The effect sum for each sequence can be used for the hypothesis test. H0 Y1.1+ Y2.1 = Y1.2+ Y2.2 that is µ + π1 + φ1 + µ + π2 + φ2 + λ1 = µ + π1 + φ2 + µ + π2 + φ1 + λ2 finally λ1 = λ2 If the null hypothesis can not be rejected, then go to step 2, otherwise go to step 3. Step 2. Estimate the treatment effect of 2 periods 3 H0: φ1 = φ2 The effect crossover difference for each sequence can be used for the hypothesis test. H0 ½ ( Y1.1- Y2.1 ) = ½( Y1.2 - Y2.2 ) that is ½ ( µ + π1 + φ1 - µ - π2 - φ2 - λ1 ) = ½( µ + π1 + φ2 - µ - π2 - φ1 - λ2) φ1 - ½ λ1 = φ2 - ½ λ2 assume λ1 = λ2 then φ1 = φ2 Step 3. Estimate the treatment effect of period 1 H0: φ1 = φ2 If carryover effect is significant, then data from period 1 only is used. H0: Y1.1 = Y2.1 µ + π1 + φ1 = µ + π1 + φ2 that is φ1 = φ2 DATA ANALYSIS The analysis of crossover studies is more complex than parallel group designs. The following is an example of AB/BA crossover study. data a; input subject sequence $ period regimen $ result ; cards; 1 AB 1 A 15 1 AB 2 B 10 2 AB 1 A 14 2 AB 2 B 11 3 AB 1 A 16 3 AB 2 B 10 4 AB 1 A 15 4 AB 2 B 9 5 AB 1 A 16 5 AB 2 B 9 6 BA 1 B 11 6 BA 2 A 15 7 BA 1 B 10 7 BA 2 A 14 8 BA 1 B 9 8 BA 2 A 16 9 BA 1 B 12 9 BA 2 A 15 10 BA 1 B 11 10 BA 2 A 14 ; run; PROC MEANS is used to calculate the descriptive statistics by SEQUENCE, PERIOD or REGIMEN PERIOD, then show the mean values graphically by PROC GPLOT. 4 Calculate the sum and difference of AB/BA sequences cross two periods. data b; set a; by subject; retain sum dif ; if first.subject then do; sum = result; dif = result; end; else do; sum = sum + result; dif = dif - result; end; if last.subject then output; run; Estimate the carryover effect using sum values by T-Test, proc ttest data= b; class sequence; var sum; run; T-Tests Variable Method Variances DF t Value Pr > |t| sum Pooled Equal 8 -0.67 0.5237 The p-value of 0.5237 shows the possible carryover effect is no significantly different between AB/BA sequences. Now estimate the effect of two treatments in 2 periods, proc ttest data= b; class sequence; var dif; run; 5 T-Tests Variable Method Variances DF t Value Pr > |t| dif Pooled Equal 8 9.60 <.0001 The result from T-test shows that effect of treatment A is significantly better than that of treatment B at <0.001 level. The statistical analysis can also be done by linear models. title “Grizzles Model by PROC GLM”; proc glm data=a; class subject sequence period regimen; model result = sequence subject(sequence) period regimen / ss3; lsmeans sequence regimen /pdiff stderr; estimate 'Regimen' regimen 1 -1; test h=sequence e=subject(sequence); run; quit; title “Grizzles Model Using PROC MIXED with a Random Effcet”; proc mixed data=a; class sequence subject regimen period; model result = sequence period regimen ; random subject (sequence); lsmeans sequence regimen /pdiff cl; run; quit; CONCLUSION The feature of crossover seems to make the design preferable to parallel group study.
Recommended publications
  • A Case-Crossover Study of Sleep and Childhood Injury
    A Case-Crossover Study of Sleep and Childhood Injury Francesca Valent, MD*; Silvio Brusaferro, MD*; and Fabio Barbone, MD, DrPH*‡ ABSTRACT. Objective. To evaluate the association n Italy (ϳ56 million inhabitants; 9 million chil- between sleep and wakefulness duration and childhood dren Ͻ15 years of age), ϳ500 children Ͻ15 years unintentional injury. of age are killed each year in unintentional inju- Study Design. Case-crossover study. I 1 ries. Homicides and suicides are much less frequent, Methods. Two hundred ninety-two injured children accounting for Ͻ10% of all fatal injuries among chil- who presented at the Children’s Emergency Center of dren.1 In Northern Italy, in 1995, injury mortality Udine, Italy, or their parents were interviewed after a rates (International Classification of Diseases, Ninth Re- structured questionnaire. Information was collected con- vision codes from 800 to 999) were 10 deaths/100 000 cerning sociodemographic variables, participant’s habits, and injury characteristics, including a brief description inhabitants under 1 year of age, 5/100 000 from 1 to of the accident dynamics. Sleep or wakefulness status of 4 years of age, and 6/100 000 from 5 to 14 years of the child was assessed retrospectively for each of the 48 age. Among infants, injury represented only 2% of hours before injury. For each child, we compared the 24 overall mortality, whereas in the 2 older age groups hours immediately before the injury (hours 1–24; case injuries accounted for 18% and 33% of all deaths, period) with hours 25 to 48 (control period). Nonparamet- respectively.2 Mortality, however, is just the tip of a ric tests were conducted to compare the difference of pyramid, where for each injury resulting in a death sleep duration between case and control periods.
    [Show full text]
  • A Phase I, Double Blind, Three-Way Crossover Study to Assess The
    A Phase I, Double Blind, Three-Way Crossover Study to Assess the Pharmacokinetic Profile of Cannabis Based Medicine Extract (CBME) Administered Sublingually in Variant Cannabinoid Ratios in Normal Healthy Male Volunteers (GWPK0215) G. W. Guy P. J. Robson SUMMARY. Primary objectives of this study were to assess the pharm- acokinetic characteristics of CBME when administered sublingually in different ratios, to determine if the pharmacokinetic profiles of THC and its metabolite 11-hydroxy-THC are different when administered sub- lingually in different formulations, and to characterise the pharmaco- kinetic profile of CBD when administered with THC in equal amounts. G. W. Guy and P. J. Robson are affiliated with GW Pharmaceuticals plc, Porton Down Science Park, Salisbury, Wiltshire, SP4 0JQ, UK. [Haworth co-indexing entry note]: “A Phase I, Double Blind, Three-Way Crossover Study to Assess the Pharmacokinetic Profile of Cannabis Based Medicine Extract (CBME) Administered Sublingually in Variant Cannabinoid Ratios in Normal Healthy Male Volunteers (GWPK0215).” Guy, G. W., and P. J. Robson. Co-published simultaneously in Journal of Cannabis Therapeutics (The Haworth Integrative Healing Press, an imprint of The Haworth Press, Inc.) Vol. 3, No. 4, 2003, pp. 121-152; and: Cannabis: From Pariah to Pre- scription (ed: Ethan Russo) The Haworth Integrative Healing Press, an imprint of The Haworth Press, Inc., 2003, pp. 121-152. Single or multiple copies of this article are available for a fee from The Haworth Document Delivery Service [1-800-HAWORTH, 9:00 a.m. - 5:00 p.m. (EST). E-mail address: docdelivery@ haworthpress.com]. http://www.haworthpress.com/store/product.asp?sku=J175 2003 by The Haworth Press, Inc.
    [Show full text]
  • Randomized, Double-Blind, Placebo-Controlled, Crossover Study of the Efficacy and Safety of Lisdexamfetamine Dimesylate in Adult
    UC Irvine UC Irvine Previously Published Works Title Randomized, double-blind, placebo-controlled, crossover study of the efficacy and safety of lisdexamfetamine dimesylate in adults with attention-deficit/hyperactivity disorder: novel findings using a simulated adult workplace environment design Permalink https://escholarship.org/uc/item/4kq3z3hd Journal Behavioral and Brain Functions, 6(1) ISSN 1744-9081 Authors Wigal, Timothy Brams, Matthew Gasior, Maria et al. Publication Date 2010-06-24 DOI http://dx.doi.org/10.1186/1744-9081-6-34 Peer reviewed eScholarship.org Powered by the California Digital Library University of California Wigal et al. Behavioral and Brain Functions 2010, 6:34 http://www.behavioralandbrainfunctions.com/content/6/1/34 RESEARCH Open Access Randomized,Research double-blind, placebo-controlled, crossover study of the efficacy and safety of lisdexamfetamine dimesylate in adults with attention-deficit/hyperactivity disorder: novel findings using a simulated adult workplace environment design Timothy Wigal*1, Matthew Brams2, Maria Gasior3, Joseph Gao4, Liza Squires3, John Giblin5 for 316 Study Group Abstract Background: Duration of efficacy and safety of lisdexamfetamine dimesylate (LDX) was assessed in adults (18-55 years) with attention-deficit/hyperactivity disorder (ADHD) using the simulated adult workplace environment. Methods: After open-label dose optimization (4-week) with LDX, 30-70 mg/d, subjects entered a 2-week randomized, double-blind, placebo-controlled crossover phase. Efficacy assessments included the Permanent Product Measure of Performance (PERMP) total score (attempted+correct) measured predose and from 2 to 14 hours postdose, averaged across postdose sessions (primary) and at each time point vs placebo (secondary), and ADHD Rating Scale IV (ADHD- RS-IV) with adult prompts at baseline and crossover visits.
    [Show full text]
  • A Cross-Over Study to Evaluate the Effect of Glucagon-Like Peptide 1 on Women with Polycystic Ovarian Syndrome
    Volume 1- Issue 6 : 2017 DOI: 10.26717/BJSTR.2017.01.000534 Yu Liu. Biomed J Sci & Tech Res ISSN: 2574-1241 Review Article Open Access A Cross-Over Study to Evaluate the Effect of Glucagon-Like Peptide 1 on Women with Polycystic Ovarian Syndrome Yu Liu*1, Suyan Tian*2, Ming-Wen An3 and Lu Wang4 1Sir Run Run Hospital, Nanjing Medical University, Nanjing, Jiangsu, China 2Department of Endocrinology, Second Hospital of Jilin University, Changchun, Jilin, China 3Department of Mathematics, Vassar College, Poughkeepsie, New York, NY, USA 4Division of Clinical Research, First Hospital of Jilin University, Jilin, China Received: November 08, 2017; Published: November 15, 2017 *Corresponding author: Yu Liu, Sir Run Hospital, Nanjing Medical University, 109 Longman Avenue, Nanjing, Jiangsu, China, 211166, Email: Suyan Tian, Division of Clinical Research, First Hospital of Jilin University, 71 Xiamen Street, Changchun, Jilin, China, Email: Abstract Background: Crossover design is very popular for a study of new and developmental drugs. However this design tends to be misused regardless of whether it is suitable for underlying research questions. Method: Given that in clinical practice 2x2 cross over is the most commonly used design, the Hills- Arbitrage approach is suggested to with multiple time points within each stratum. analyze data. Furthermore, we propose fitting a linear mixed model and then conducting a likelihood ratio test to yield a single p-value on data Finding: Applying these methods to a real data, we evaluate effect of glucagon-like peptide 1 (GLP-1) on women with polycystic ovarian PCOS women is nevertheless clinically meaningful. Not only does it show a longer washout period is desired, but also it suggests GLP-1 may havesyndrome the same (PCOS).
    [Show full text]
  • Inferences on Treatment and Carryover Effects in Two-Period Two-Sequence Crossover Designs
    Research Article Curr Trends Biomedical Eng & Biosci Volume 11 Issue 5 - February 2018 Copyright © All rights are reserved by Sam Weerahandi DOI: 10.19080/CTBEB.2018.11.555821 Inferences on Treatment and Carryover Effects in Two-Period Two-Sequence Crossover Designs Vladimir Geneus1, Chunming Li1, Sam Weerahandi1*, Ed Whalen1 and Ching Ray Yu2 1Department of Statistics, Florida State University, USA 2Department of Statistics, Pfizer Inc., USA Submission: January 13, 2018; Published: February 01, 2018 *Corresponding author: Sam Weerahandi, Department of Statistics, Florida State University, 23 Chestnut St, Edison, NJ 08817, USA, Email: Abstract It is well known that, in the absence of 4 sequences or a long washout period, it is not possible for classical methods to separate out the treatment effects and carryover effects of a crossover design involving two treatments. Motivated by self-contradictory, visually clear results from a standard mixed effects model repeated measures (MMRM) type analysis of a 2X2 crossover, we develop a method to take advantage of repeated measures in each period to make inferences on treatments and carryover effects. The proposed model applied to our data rectified the anomaly in our application. Results from a simulation study are also included to demonstrate the advantage of the proposed approach over the regular MMRM approach. Introduction and Background method failing to sort things out, in this article we propose how can see from the figure, and having seen the widely used MMRM one can separate out the treatment effects and carryover effects by taking advantage the repeated measures. In fact, the proposed method can be applied even if there is no washout period.
    [Show full text]
  • A Systematic Review of Quasi-Experimental Study Designs in the Fields of Infection Control and Antibiotic Resistance
    INVITED ARTICLE ANTIMICROBIAL RESISTANCE George M. Eliopoulos, Section Editor A Systematic Review of Quasi-Experimental Study Designs in the Fields of Infection Control and Antibiotic Resistance Anthony D. Harris,1,2 Ebbing Lautenbach,3,4 and Eli Perencevich1,2 1 2 Division of Health Care Outcomes Research, Department of Epidemiology and Preventive Medicine, University of Maryland School of Medicine, and Veterans Downloaded from https://academic.oup.com/cid/article/41/1/77/325424 by guest on 24 September 2021 Affairs Maryland Health Care System, Baltimore, Maryland; and 3Division of Infectious Diseases, Department of Medicine, and 4Department of Biostatistics and Epidemiology, Center for Clinical Epidemiology and Biostatistics, University of Pennsylvania School of Medicine, Philadelphia, Pennsylvania We performed a systematic review of articles published during a 2-year period in 4 journals in the field of infectious diseases to determine the extent to which the quasi-experimental study design is used to evaluate infection control and antibiotic resistance. We evaluated studies on the basis of the following criteria: type of quasi-experimental study design used, justification of the use of the design, use of correct nomenclature to describe the design, and recognition of potential limitations of the design. A total of 73 articles featured a quasi-experimental study design. Twelve (16%) were associated with a quasi-exper- imental design involving a control group. Three (4%) provided justification for the use of the quasi-experimental study design. Sixteen (22%) used correct nomenclature to describe the study. Seventeen (23%) mentioned at least 1 of the potential limitations of the use of a quasi-experimental study design.
    [Show full text]
  • STATISTICAL ANALYSES PLAN a Replicated Crossover Study to Explore Individual Variability of Appetite Responses to a Standardised
    STATISTICAL ANALYSES PLAN A replicated crossover study to explore individual variability of appetite responses to a standardised meal and any moderating influence of the FTO gene Version 1 Investigators Professor David Stensel Professor Greg Atkinson Ms Fernanda Reistenbach Goltz Address School of Sport, Exercise and Health Sciences Loughborough University Leicestershire LE11 3TU United Kingdom Correspondence Professor David Stensel: +44(0)1509 226344, [email protected] Statistical analyses plan Unique protocol ID: R17-P178 Date: 03-12-2018 Statistical analyses plan Between-genotype differences in participant characteristics will be quantified using linear mixed models with group (AA versus TT) modelled as a fixed factor. The presence of interindividual differences in blood marker and perceived appetite responses to a standardised meal will be examined according to three analytical approaches (Atkinson and Batterham, 2015; Senn et al., 2011; Senn, 2016). The three approaches, detailed recently by Goltz et al. (2018), will be as follows: (i) The association between the first and second replicate of control-adjusted treatment effect will be quantified for each outcome using Pearson’s correlation coefficients (Senn, 2016). The first meal condition in any participant’s sequence will be paired to the first control condition in the same individual’s sequence. Thresholds of 0.1, 0.3 and 0.5 will be used to label correlation coefficients as small, moderate and large, respectively (Cohen, 1988). This correlation coefficient quantifies the consistency of meal effect across the replicated experimental conditions. (ii) The following equation (Atkinson and Batterham, 2015) will be used to provide an overall estimate of the true (control condition adjusted) between-subject differences in treatment response: SD = SD SD 2 2 IR � M − C SDIR represents the true interindividual variation in treatment effect.
    [Show full text]
  • Exact Calculation of Power and Sample Size in Bioequivalence Studies Using Two One-Sided TestsŽ Meiyu Shen,A* Estelle Russek-Cohen,B and Eric V
    MAIN PAPER (wileyonlinelibrary.com) DOI: 10.1002/pst.1666 Published online 5 December 2014 in Wiley Online Library Exact calculation of power and sample size in bioequivalence studies using two one-sided tests Meiyu Shen,a* Estelle Russek-Cohen,b and Eric V. Sludc,d The number of subjects in a pharmacokinetic two-period two-treatment crossover bioequivalence study is typically small, most often less than 60. The most common approach to testing for bioequivalence is the two one-sided tests procedure. No explicit mathematical formula for the power function in the context of the two one-sided tests procedure exists in the statistical literature, although the exact power based on Owen’s special case of bivariate noncentral t-distribution has been tabulated and graphed. Several approximations have previously been published for the probability of rejection in the two one-sided tests procedure for crossover bioequivalence studies. These approximations and associated sample size formulas are reviewed in this article and compared for various parameter combinations with exact power formulas derived here, which are computed analytically as univariate integrals and which have been validated by Monte Carlo simulations. The exact formulas for power and sample size are shown to improve markedly in realistic parameter settings over the previous approximations. Copyright © 2014 John Wiley&Sons,Ltd. Keywords: bioequivalence; single endpoint; sample size; power; crossover; pharmacokinetic study 1. INTRODUCTION The null hypothesis, H0,statesthatT and R are not equivalent. The alternative hypothesis representing equivalence, In a typical pharmacokinetic two-period two-treatment crossover Ha, is the intersection of the two one-sided parameter regions, bioequivalence study, subjects are randomized to one group f1 <T Rg and fT R <2g.
    [Show full text]
  • Statistical Review(S)
    CENTER FOR DRUG EVALUATION AND RESEARCH APPLICATION NUMBER: 21-977 STATISTICAL REVIEW(S) DEPARTMENT OF HEALTH AND HUMAN SERVICES PUBLIC HEALTH SERVICE FOOD AND DRUG ADMINISTRATION CENTER FOR DRUG EVALUATION AND RESEARCH STATISTICAL REVIEW AND EVALUATION Clinical Studies NDA/Serial Number: 21-977 (N000) Drug Name: Lisdexamfetamine Caps Indication: ADHD in Pediatric Population (Ages 6-12) Applicant: New River Pharmaceuticals, Inc Dates: Date of Document: 12/06/2005 PDUFA Due Date: 10/06/2006 Review Priority: Standard Biometrics Division: Biometrics I, HFD-710 Statistical Reviewer: Yeh-Fong Chen, Ph.D. Concurring Reviewers: Peiling Yang, Ph.D. Kooros Mahjoob, Ph.D. Medical Division: Division of Psychiatry Drug Products, HFD-130 Clinical Team: Clinical Reviewer: Michelle Chuen, M.D. Clinical Team Leader: Ni Aye Khin, M.D. Project Manager: Susan Player 1 Table of Contents 1. EXECUTIVE SUMMARY ...................................................................................................................... 3 1.1 CONCLUSIONS AND RECOMMENDATIONS............................................................................... 3 1.2 BRIEF OVERVIEW OF CLINICAL STUDIES.................................................................................. 3 1.3 STATISTICAL ISSUES AND FINDINGS .......................................................................................... 3 2. INTRODUCTION .................................................................................................................................... 4 2.1 OVERVIEW........................................................................................................................................
    [Show full text]
  • Selection Bias and Confounding in Case-Crossover Analyses of Environmental Time-Series Data Thomas F
    Selection Bias and Confounding in Case-Crossover Analyses of Environmental Time-Series Data Thomas F. Bateson1 and Joel Schwartz2 The case-crossover study design is a popular analytic tool for hazard periods, even when the distribution of exposure is estimating the effects of triggers of acute outcomes by envi- stationary. This bias can be estimated and removed. Selection ronmental exposures. Although this approach controls for bias also occurs when the distribution of exposure is nonsta- time-invariant confounders by design, it may allow for selec- tionary, but the adjusted symmetric bidirectional case-cross- tion bias and confounding by time-varying factors. We con- over methodology substantially controls for this. Confounding ducted a simulation study of the sensitivity of the symmetric results from a common temporal pattern in the exposure and bidirectional case-crossover design to time-varying patterns in the outcome time series, but can also be the result of patterns exposure and outcome. We identified the effects of selection in exposure and outcome that, although asymptotically uncor- bias and confounding on symmetric bidirectional case-cross- related, are correlated at finite series lengths. All three biases over results and offer strategies to eliminate or reduce these are reduced by choosing shorter referent-spacing lengths. This biases. Selection bias results when exposure in the reference effect is illustrated using data on air pollution and daily deaths periods is not identically representative of exposure in the in Chicago. (EPIDEMIOLOGY 2001;12:654–661) Keywords: epidemiologic research designs, epidemiologic methods, case-crossover studies, case-referent studies, environmental epidemiology, epidemiologic biases, selection bias, confounding variables The case-crossover design of Maclure1 represents an rectional (SBI) referent sampling with close referents attractive approach to examining the impact of time- reduced that bias.
    [Show full text]
  • Statistical Review and Evaluation
    U.S. Department of Health and Human Services Food and Drug Administration Center for Drug Evaluation and Research Office of Translational Sciences Office of Biostatistics S TATISTICAL R EVIEW AND E VA L U AT I O N CLINICAL STUDIES NDA/Serial Number: 22-210 / 000 Drug Name: Zentase Pancreatic Enzyme Product Delayed-Release Capsules (EUR-1008) Indication(s): Exocrine Pancreatic Insufficiency (EPI) Applicant: Eurand Pharmaceuticals Limited (EPL) Date(s): Letter Date: 12/14/2007 Stamp Date: 12/17/2007 Date Forwarded to DDR: 12/19/2007 Date Received by Reviewer: 4/21/2008 PDUFA Date: 6/17/2008 Review Priority: Priority Biometrics Division: Division of Biometrics 3 Statistical Reviewer: Freda W. Cooner, Ph.D. Concurring Reviewers: Mike Welch, Ph.D. Medical Division: Division of Gastroenterology Products Clinical Team: Marjorie F. Dannis, M.D., Medical Reviewer Anne Pariser, M.D., Team Leader Project Manager: Maureen Dewey Keywords: Clinical studies, NDA review, Crossover design, Repeated measure ANOVA, Subgroup analyses Table of Contents 1. EXECUTIVE SUMMARY ..................................................................................................................................3 1.1 CONCLUSIONS AND RECOMMENDATIONS .......................................................................................................3 1.2 BRIEF OVERVIEW OF CLINICAL STUDIES ........................................................................................................3 1.3 STATISTICAL ISSUES AND FINDINGS ...............................................................................................................4
    [Show full text]
  • I. Introduction
    I. Introduction The case-crossover design was proposed as a method for estimating the association between a short-term exposure and the risk of a rare event.1 Only cases are required for such a study. For each case, exposure at the “index” time (the hazard or at-risk period prior to the event) is compared to exposure at comparable control, or “referent” times. The design can be viewed as a hybrid of the case-control and the crossover designs: selection is based on the outcome, similar to the case-control design, but the case serves as his/her own control, as in a crossover study. By making within-person comparisons, confounding due to time-independent factors is eliminated and, with proper selection of referents, time-dependent confounders can also be controlled. The case-crossover design has been widely used to study the effect of air pollution exposure on the risk of an adverse health event. A variety of different referent selection strategies have been used in implementing this design (see, for example 2-8). However, the choice of a referent scheme is of particular importance with air pollution exposure data. Representative referents are more difficult to define in an exposure series with substantial structure; air pollution often has a long term time trend, and varies with season and day of the week. These factors are also often associated with the outcome of interest, and hence confounding is a major issue. In addition, the design relies on the assumption of a constant distribution of exposure across referent times.6;9 Yet the choice of referent selection strategy is important for a more fundamental reason.
    [Show full text]