Home » Research

Biostatistics & Bioinformatics Shared Resource

Services

New projects should be discussed with the Director or a member of BBSR depending upon the area of application. It is helpful when an abstract or description of the project is submitted in advance to facilitate informed discussion.

For grants and contracts that expect to use the BBSR, the investigator must fill in a Shared Resource transmittal form.

Consultation should begin in the planning stage of a project and can consist of advice concerning some or all of the following elements:

Planning Stage:

1. Background, rationale and especially the major objectives
2. Endpoints: primary and secondary
3. Design of study: type of design (e.g., phase of clinical trial, factorial design), sample size
4. Need and plans for interim analyses: type, frequency
5. Data management needs: primary observations, plans for acquisition, storage, and retrieval
6. Statistical considerations sections for research projects

During the conduct of the study:

1. Monitor the progress of the study
2. Provide advice and assistance concerning quality control
3. Perform interim analyses (e.g. sequential or Bayesian analyses)
4. Assist with making a decision to continue or stop a trial

At the completion of the study:

1. Recommend appropriate statistical methodologies
2. Perform data analyses
3. Prepare reports of analysis and provide interpretation of findings
4. Contribute to plans for write-up of the results for publication
5. Write the statistical methods and results sections of manuscripts

Bioinformatics resources are available to :

1. Preprocess the raw data
2. Perform high-level analyses such as differential expression and clustering
3. Relate the inferences to public-domain information.

Statistical Software

A variety of specialized statistical software is available to meet the broad range of needs of research investigators. Below is a list of the software programs used by the staff:

Microsoft Access, Excel and Scientific Word. Microsoft Access and Excel are data organization software. These two Microsoft Office products can be used to organize data for analyses with the specialized statistical software on the list. Access can be used to organize data in a relational database. Excel can be used to organize data in a spreadsheet. Scientific Word is convenient software for writing scientific reports. It has many of the features of Tex and Latex.

SAS-The Statistical Analysis System. SAS is a large computer software system for data processing and analysis. It has extensive data management, file handling and graphics facilities, and can be used for most types of statistical analysis, including Cox and logistic regression analysis, log linear models and principal components analysis.

Simon's Plans for Phase II Studies is a program that gives plans for Phase II cancer clinical trials including those for response rates not given in Simon (1989). (Optimal two stage designs for Phase II clinical trials, Controlled Clinical Trials, 10:1-10.)

S-Plus performs virtually all types of statistical analysis including ANOVA, linear regression, generalized linear, and nonlinear mixed effects models and survival analysis. It is also a powerful tool for graphical presentation and scientific research, in addition to its flexibility for self-programming.

SPSS, the Statistical Package for Social Sciences can be used to calculate a comprehensive range of statistical procedures and also has facilities for file manipulation and recoding or transforming data.

StatXact performs exact hypothesis tests for contingency tables and other applications, especially when the sample size is small in some units of the study.

StPlan performs sample size, power, and related calculations needed to plan studies.

R is a language and environment for statistical computing and graphics. R provides a wide variety of statistical (linear and nonlinear modeling, classical statistical tests, time-series analysis, classification, clustering, ...) and graphical techniques, and is highly extensible. The S language is often the vehicle of choice for research in statistical methodology, and R provides an Open Source route to participation in that activity.

MATLAB offers an integrated programming environment for design and implementation of various computational methods. It offers powerful numeric computation and visualization tools. It consists of application-specific functions grouped into Toolboxes, each extending the core MATLAB language. The Toolboxes can be easily viewed and are customizable. MATLAB Toolboxes such as the Statistics Toolbox, Bioinformatics Toolbox, and Neural Network Toolbox provide various functions that can be used for data analysis.

MATHEMATICA is a numeric and symbolic computational engine, which includes graphics and a programming language. It can be used to solve difficult integrals and create complex mathematical pictures.

GAUSS is programming language software for statistical manipulation that is very efficient for working with matrices, with macros for maximum likelihood testing.

STATISTICA is a comprehensive statistical analysis package for both the simplicity of menu-driven analysis choices as well as complex programming flexibility.

Bioconductor is an open source and open development software project for the analysis and comprehension of genomic data.

BRB-ArrayTools is an integrated package for the visualization and statistical analysis of DNA microarray gene expression data.

Eligibility/Fees

Eligibility: All Lombardi members are eligible to use the Biostatistics Resource.

Fees:

• Short-term consultations for biostatistical services for Lombardi members are provided without charge.
• For collaborations involving 5 percent or more of a biostatistician's time, investigators are encouraged to request support for the level of effort in grant or contract applications.
• For consultations of less than 5 percent time of a biostatistician, a fee for service consistent with the effort may be required. A written report of all consultations is provided.

Acknowledgements

Staff members of the Biostatistics & Bioinformatics Shared Resource should be acknowledged on publications consistent with the input provided, either by co-authorship when there have been major contributions to the design, analysis, and reporting of the project, or a brief acknowledgment for a simple and straightforward analysis.