Policies and Guidelines for Including Biostatistics Support on Grants

Introduction

This document lays out policies and guidelines for inclusion of Biostatistics personnel in grant applications. The guidelines lay out common scenarios and are meant to serve as a starting point for discussion for planning and budgeting purposes. In all cases, discussion with Biostatistics faculty early in the grant preparation process is necessary to ensure that the appropriate level of support is provided.

PhD faculty and master’s statisticians can participate in grant development in numerous ways including

• assisting with the development of a research team;
• assisting the investigators in defining and refining study aims and measures;
• developing study designs;
• writing statistical analysis plans;
• computing the power or sample sizes necessary to achieve the study aims;

If Biostatistics effort in proposal development is not covered by funded projects, time spent on proposal development will be billed at the current hourly rate or MOU.

Inclusion of Biostatistics Personnel in Project Budgets

PhD faculty effort

Biostatistics faculty should be included as named co-investigators (typically as key personnel) on collaborative applications. While effort may vary from year to year, an average of 10% effort (1.2 calendar months per year) over the project period is suggested as a guideline for most clinical projects and more complex basic science projects (see effort allocation guidelines below). Faculty may not be included on budgets for less than 5% effort without the approval of the Chair of the Department of Biostatistics.

For projects with limited statistical needs or limited budgets (e.g., R03 applications), provision for support of faculty time on a fee for service basis may be made through CCORDA. In these cases, the CCORDA will provide a letter of support, but no biosketch will be provided.

Master’s statistician effort

Master’s statisticians and data management personnel provide assistance with data management, statistical programming, and preparation of reports and manuscripts. Master’s statisticians have experience developing REDCap and Access databases and using SAS, R, Stata, and other statistical packages. 

For most funded projects, master’s statistician should be coupled with PhD faculty effort. Master’s statisticians are not named, but support is included as a percentage of charge per FTE.

Effort Allocation Guidelines

These guidelines provide suggested levels of support for projects of varying complexity and need of statistical expertise.

Large or complex projects (e.g. multi-site clinical trials, cores for program projects or SPORES): Total biostatistics annual effort 50–100+% per year, such as 20% or more of PhD faculty time plus 30–100%  master’s statistician FTE:

• High level of involvement in the development and implementation of the research project and communication of study results, including:
• Development and/or implementation of complex study designs.
• Assembly of datasets from large, complex or poorly documented sources (e.g. administrative or survey databases).
• Development and/or implementation of interim data analyses during data collection phase of prospective studies.
• Coordination of analyses for multi-site projects.
• Development of and/or use and interpretation of novel or complex statistical methods.
• Active participation in publications, with opportunity for first authored papers. 

Regular Projects (e.g., R01 involving clinical data, basic science project with complex analysis (eg. Omics data)): Total biostatistics annual effort 20–50%, such as 10–15% PhD faculty time plus 10–35% master’s statistician FTE.

This effort profile is suitable for straightforward projects with uncomplicated analyses and includes:

• Collaboration and involvement of biostatisticians through all phases of the study, including regular meeting attendance.
• Involvement of biostatisticians in routine study design, implementation, and data collection.
• Well-documented primary datasets provided for statistical analysis.
• Analyses carried out using standard procedures available in statistical software packages.
• Active participation of biostatisticians in publications, with opportunity for first authored papers.

Simple Projects (e.g., project under 250K direct per year): Total biostatistics effort 5–20% per year, such as 5-10% PhD faculty time plus 5-10% master’s statistician FTE.

This effort profile is suitable for simple projects requiring minimal PhD faculty collaboration and straightforward statistical analyses performed by the biostatisticians (for about one manuscript per year).

• Ongoing occasional consultations with PI about study issues, such as choice of statistical methods to use. Support at the lower end of the range (i.e., 5%) is typically too low for a PhD faculty to carry out analyses.
• This level of effort commitment and support for the PhD faculty is generally not compatible with smooth workflows and readily available consultation support, unless adequate biostatistical support through CCORDA is included on the project as well.

Limited Scope projects: Total biostatistics effort <5% per year

In rare occasions, a limited amount of funding may be justified, for example, for assistance with small-scale Phase I trials, straightforward animal studies, or simple cell-based experiments. In these cases, some statistical analysis will be needed, but the scope is limited. Such small projects may budget for faculty biostatistics services through CCORDA using the hourly rate in place of effort.

Other Budgetary Considerations

• There are some grant mechanisms that do not support funded effort by biostatisticians; this may include some K awards. In this case, the PI should discuss the proposal with the biostatistics departmental chair.
• Statistical effort has been reserved through the great plains IDeA-CTR program in support of grant applications submitted to the great plains IDeA-CTR program. The PI should contact the biostatistics, epidemiology and research design (BERD) KCA coordinator on questions regarding their great plains IDeA-CTR applications.
• PhD faculty effort usually will not be supported by the internal pilot grant. We recommend the internal pilot project application reserve support to master’s statistician for the data analyses and other statistical support after funded.
• Any changes in percent support made during proposal writing or after research has been funded must be made jointly between the PI and biostatisticians. If biostatistics percent efforts are reduced to be lower than 5% FTE per year, the approval of the Chair of the Department of Biostatistics will be needed. Simply reducing sample sizes does not reduce the amount of work to do the analysis. On rare occasions, investigators will re-budget upon the grant being awarded to eliminate statistical support. As one can imagine, this will considerably reduce our enthusiasm for future collaboration with such investigators.
• Sometimes additional resources are required, such as computer hardware, specifically required software and off-site meeting travel. Please discuss this in advance.
• Please notify us about the funding decision on the proposal, whether positive or negative.
• We do not allow an investigator to use the name of a PhD faculty or master’s statistician on a grant or contract proposal unless the biostatistician has fully participated in the development of the proposal and can vouch for the study design and analysis plan.

Acknowledgements

Effort allocation guidelines were modified from those of the University of California Davis School of Medicine, Jefferson University and University of Kansas Medical Center.