Our clients consistently recognize the quality of our work. We listen closely to what our clients are asking and then we: 

  • Assist the sponsor to frame the primary and secondary hypotheses properly 
  • Help write sections of the clinical protocol
  • Draft and execute the statistical analysis plan
  • Develop code and perform statistical analyses
  • Assist in writing sections of the report for submission to regulatory agencies
  • Serve as the statistical representative at regulatory meetings. 


Clients often seek us out when their trials involve novel design and analytical issues that require careful thought and rigorous attention to detail. Our statisticians have applied recently developed and conventional statistical methods to a wide range of clinical trial study designs encountered in the development of new therapies.

Staff members conduct original research in statistics and have made significant contributions to scientific literature.

We at SCI envision statisticians as scientific partners working with scientists from other disciplines to develop interventions for the prevention and treatment of disease. By our nature, statisticians question data and design and sometimes challenge whether other possibilities lurk behind the obvious explanations. 

In addition to the common consulting arenas of trial design and regulatory strategy, we assist our clients with complex situations, including:

  • Sensitivity analyses
  • Simulation studies
  • Evaluation and verification of statistical analyses performed by others
  • Post-hoc assessment
  • Due diligence review
  • Expert witness testimony

We welcome new challenges and look forward to statistical problems we have never seen before. If you work with us, you will find us intellectually engaged in your projects. We do our best to interpret data in a way that conveys a story and, when necessary, we are constructively critical.

SCI has designed trials and helped develop protocols in many disease areas across all phases of drug development. While we focus on the statistical aspects of a protocol, these issues are integrally intertwined with other elements of the trial, including study outcomes, sample size calculations, randomization procedures, and the timing and method of data collection.

We frequently help clients navigate sample size and power calculations. Our clients often approach us when the method for obtaining a sample size is unclear or complex. Such computations are as much art as science, often relying on simulations. In calculating a sample size, SCI thoughtfully considers the timing, the frequency, and the method of analysis (including adjustment for multiple looks and multiple outcomes). 

SCI works closely with our clients to ensure that the sample sizes we calculate are appropriate to their specific goals and objectives. We discuss reasonable estimates of treatment effects and variability with the clinical team. When past clinical data are limited, we use input from historical data and from subject matter experts.

SCI recognizes that trial sponsors face real-world constraints on the design and implementation of their studies. Both financial resources and study participants may be in short supply. Small trials may be unavoidable in studies of rare diseases. Trials in certain areas, for example psychiatric diseases, are notorious for the high proportion of patients who discontinue study medication, thus leading to a high proportion of incomplete or missing data. SCI has experience with a variety of statistical methods to address missing data. We understand the differences between estimates, estimators, and estimands. We work with our clients to identify methods that address the issues at hand, writing and reviewing appropriate methodology in the protocol and statistical analysis plan.

Our statisticians at SCI have had considerable interaction with the FDA. We have met with groups at the Center for Drug Evaluation and Research, the Center for Biologics Evaluation and Research, and the Center for Devices and Radiological Health. SCI staff has participated in many regulatory meetings at the FDA, including early phase, End of Phase 2, special meetings, and Advisory Committees where SCI staff has presented on behalf of our clients. Dr. Janet Wittes has participated as a regular and as an ad hoc member on several FDA Advisory Committees.

In our work with clients preparing for regulatory submission and review, we provide an independent, critical eye for reviewing protocols, analytic plans, and submissions. We often participate in mock FDA panels where we play the role of FDA panelists. Companies use such panels to evaluate and modify the written submissions and verbal presentations they have prepared for FDA panels. Our experience with many FDA submissions and our service on FDA panels allow us to provide useful advice to our clients.

We have also provided advice to clients working with the other health authorities such as EMA and Health Canada and have participated in regulatory meetings seeking scientific advice and feedback on global submission planning.

The SCI staff has many years of experience with all aspects of data monitoring committees (DMCs), serving on DMCs as well as acting as the independent statistical group reporting to DMCs. SCI’s internal operating procedures conform to the FDA’s and the ICH’s guidelines for DMC reporting.

SCI provides a full range of services for DMCs:

Management and operations

  • Developing a DMC charter
  • Recommending experts to sit on a DMC
  • Managing DMC meetings: scheduling, planning logistics of meetings, creating agendas, preparing minutes
  • Facilitating communication between the sponsor and the DMC
  • Facilitating the DMC’s recommendation to the sponsor
  • Archiving DMC materials until the study is unblinded


  • Writing interim analysis plans, including statistical methods and table shells
  • Developing statistical stopping guidelines for efficacy, futility, and safety
  • Proposing the appropriate analyses for ad hoc DMC analysis requests


  • Programming analysis datasets with interim data
  • Creating planned and ad hoc presentations for the DMC


  • Preparing and presenting unblinded safety and efficacy reports
  • Preparing blinded sponsor reports

Our approach to DMCs

SCI takes an active role when we report to a DMC. We provide the DMC with clearly written reports that assist the members in assessing the risks and benefits of the interventions being studied. We tailor each report to the study at hand. We consider the data being collected, the disease under study, and the emerging pattern of risks observed in the study or suspected for the class of agent. DMC members find our tables, figures, and text readily interpretable. We aim for completeness, clarity, and succinctness. We come to meetings prepared to answer questions from the DMC.

We have experience reporting to program level DMCs and DMCs responsible for monitoring multiple studies simultaneously. We also have experience working with different database sources and formats.

Liaison between the sponsor and the DMC

Because of the highly confidential nature of DMC reports and decisions, SCI takes exquisite care in all its interactions with DMCs. We are practiced in securely transferring study materials, managing DMC requests while keeping the sponsor blinded, and managing communications among the sponsor, the data provider, and the DMC. For members who prefer to receive hard copy reports, we bind DMC reports and number them to maintain accountability of confidential information. For those who prefer electronic reports, we use secure transmission methods for distribution of electronic materials and train DMC members on best practices for maintaining confidentiality.

We serve as an intermediary to facilitate communication between the sponsor and the DMC members. Our goal is to ensure the safety of participants; maintain the integrity of the trial and data confidentiality; and respect the interests of the sponsor, the investigators, IRBs and Ethics Committees, and regulatory agencies.

Programming for interim reports

The approach to programming final study results based on clean, locked data is often not ideally suited to programming for DMC reports while a study is ongoing. At SCI we have decades of experience programming with interim data, using defensive programming techniques to anticipate possible variations in future transfers of interim data. We work with the data provider to choose a course of action that will effectively present a clear snapshot of the interim data.

Interim analyses and group sequential design

A trial may be discontinued at a pre-specified timepoint before its originally planned conclusion when interim data provide strong evidence of either efficacy or futility of the experimental agent. SCI has many years of experience reporting interim results to DMCs that allow for early stopping of the study. We work with clients and DMCs to analyze and present the data necessary for the DMC to make an informed recommendation at a pre-specified interim data review, and we anticipate the pertinent questions DMC members may ask. We have experience with conditional power, predictive power, and sample-size recalculation. We help clients establish trial monitoring boundaries and alpha spending functions and calculate stopping boundaries based on data accumulated at the time of the interim analysis.

Preparing clinical study data and conducting statistical analyses are essential components of SCI’s activities. Our programmers and statisticians have many years of experience using commercially validated software, ranging from sample size calculations at the beginning of a study to sensitivity analyses following a regulatory submission, and all stages in between.

We use SAS® for much of our programming, employing our proprietary macros for version control and archiving of log and output files for each run. A senior staff member independently reviews our programs using validation approaches customized to reflect the complexity of each program. Beyond SAS®, our programmers are also familiar with R, PASS®, CART®, and other specialized statistical packages. We routinely use industry-standard coding dictionaries (e.g., MedDRA, ATC Classification, WHODrug) to summarize adverse events and concomitant medications.

Examples of our programming capabilities and practices include:

  • Macros: Using SAS®, we have developed in-house, validated macros for a variety of tabular and graphical presentations. We ensure analytic tables and figures are comprehensible to statisticians and non-statisticians alike, regardless of the complexity of the methods. Recipients of SCI’s reports have commended us on our ability to display safety and efficacy data in a concise, complete, and unbiased way.
  • Graphics: SCI has developed innovative graphs to display data. We annotate our figures with relevant summary statistics. Our traffic light plots depict changes over time in a variable, sorted by subject within treatment group according to the magnitude of the variable of interest. Our patient profile plots display adverse events to show their temporal relationship to each other, to receiving study therapy, or to another relevant intervention. Our volcano plots graph the risk difference of AEs in two treatment groups and associated p-values.
  • Randomization: Our programmers are experienced in generating randomization schedules and in auditing the randomization processes of ongoing trials that implement either static or dynamic allocation methods.
  • Defensive programming: Interim data are by their nature “messy” and quite different from the final, locked databases used to generate clinical study reports. Our programming staff understands the unique issues posed by such data and is skilled at examining multiple sources in a clinical database to prepare thorough and complete interim monitoring reports.
  • External review: We have worked with code prepared by other programmers to serve as an “independent” reviewer or double-programmer to verify and validate results.

Some of our specialized programming capabilities include simulations for study design, bootstrapping, randomization tests, and other non-standard statistical analyses.

SCI writes and reviews protocols, statistical analysis plans (SAPs), clinical study reports (CSRs), and publications for a variety of trial types, analysis settings, and therapeutic areas. We synthesize information into a concise yet thorough document that conveys the information relevant to the intended audience. We design our carefully selected presentations and accompanying interpretation tell the full story of a trial’s conduct and results.

A trial’s SAP serves as a complete set of instructions for those who program the trial’s analyses. We tailor our SAPs to convey thoughtful, appropriate, and comprehensive analysis of the data. Our plans include justification for trial design and outcomes, methods for analysis, and sensitivity analyses to account for different conventions, as well as other potential problems with study data or conduct. Analysis plans contain text explaining the pre-planned methods; some plans include table and figure mock-ups with defined conventions, populations, and exceptions. The breadth of analysis plans that we prepare reflects the range of statistics and design with which we are familiar.

SCI has experience both in preparing the statistical section for clinical study reports (CSRs) and in participating in the writing of entire CSRs. Our clients and our peers have consistently recognized the quality of our work. We apply a “less is more” approach, recognizing that a well-crafted, succinct presentation of results can paint a clear picture of a product’s safety and efficacy. Rather than presenting a large volume of output, the reports resulting from our analysis plans are concise. We tailor each analysis to the problem at hand.

Our statisticians have authored hundreds of articles published in peer-reviewed scientific journals. We have experience working with clients to publish study results. Our staff has published papers on statistical methodology. Some of our senior statisticians have served as editors of peer-reviewed journals and many of us routinely serve as reviewers of manuscripts submitted for publication.

Meta-analysis involves combining data from different sources in a statistically sound way in order to arrive at an overall estimate of an outcome of interest. SCI helps clients gain a thorough understanding of the clinical and statistical issues that might arise when combining data from various sources. We work with clients to conduct a systematic literature review identifying articles reporting the results of relevant studies. We abstract the data from the relevant articles and analyze the abstracted data, addressing heterogeneity and the appropriate way to combine the data statistically.

Some of the statistical components of meta-analysis that SCI will address with the client include:

  • whether a fixed or random-effects model is more appropriate in the circumstances at hand for combining data from various studies;
  • whether an odds ratio or relative risk is the more appropriate statistic to generate from the meta-analysis;
  • how to estimate the effect robustly when only a small number of studies are available for inclusion in the meta-analysis; and
  • how to assess the size and impact of the variability of the data within and across studies.


Get in touch

To contact SCI about a potential project, please call us at 202.247.9700 or click below.

Emergency Message

Statistics Collaborative is experencing a business interruption due to circumstances beyond our control. Please call our main company phone number for details and updates.


Add Your Heading Text Here