Here are commonly used effort levels for a biostatistics budget on a grant proposal.

These numbers are extracted from the UC Davis Biostatistics group which provides helpful language on the level of support an investigator may expect for each “size”. See details https://health.ucdavis.edu/ctsc/area/biostatistics/Documents/ucdavis-biostat-effort-guidelines.pdf

A. Large or complex projects

• 20% or more of a PhD biostatistician
• 30-100% of an MS biostatistician

B. Regular Projects

• 10-15% of a PhD biostatistician
• 20-50% of an MS biostatistician

C. Simple Projects

• 5-10% of a PhD biostatistician
• 10-25% of an MS biostatistician

D. Limited Scope

• <10% of a biostatistician
• Hourly recharge rates

Notes:

This does not include data management such as building data entry forms, REDCap database, etc,  Data Management is a service provided by BCC which can be budgeted separately.

As we all continue to work on increased Rigor, Reproducibility, and Transparency (RRT) in scientific work, one service that we are providing with increased frequency at BCC is replicating analyses for manuscripts before they are submitted.

We recommend that all projects have two statisticians: a primary statistician to perform all data analyses, and a second statistician to review and replicate everything.

We perform 3 tasks when we review and replicate a paper.

1. Verify that we can precisely replicate every number in the text, tables, and figures by running the final analysis code on the data. (Reproducibility)
2. Verify that the methods used to produce those numbers are accurately described in the paper (Transparency)
3. Verify whether we believe the methods used are appropriate or could be improved (Rigor)

What is the process, and what files should I send to facilitate this review and replication?

Data. Best case is to have 1 (or 2-3) clean final analysis dataset(s) (.csv, .xlsx) with all the variables needed to replicate the analyses in the paper.

• Data will usually have 1 row of data per person/subject and 1 column for each variable.
• Longitudinal (repeated measures) data will usually have multiple rows of data per person/subject
• Sometimes 2-3 datasets are needed if data are represented in different data structures. For example, longitudinal data often has multiple rows of data for the same person, while the demographic data is only one per person.
• If more than 1 file is used, a unique ID should be used to link them together.
• NOTE: Please de-identify data before sending to BCC or anyone else.

Code. Please provide the syntax code that reads in this 1 (or 2-3) final analysis dataset and performs all data analysis, tables, and figures.

• Please add comments in the syntax file to indicate where each table and figure is being created.
• SAS, R, SPSS, or Stata are best.

Manuscript. Please provide a draft of the manuscript or report including methods, study design, analysis description, results, interpretations, tables and figures.

We will then perform the 3 RRT steps described above.

Data sharing. A related service we provide is to advise researchers on how to publish their data along with their publication. We recommend publishing this same analysis data file, and possibly the syntax file as well. The goal is that any reasonable statistician could reproduce all results using just the data provided and methods described in the paper. (We note that this is not always 100% possible if random numbers are involved, or if there are small details that couldn’t be included in the paper. But this is the goal.)

Box at IU is great for storing data in the cloud. It has unlimited storage and you can access it from the computer labs, your laptop, or IUanyware.

IUanyware is way to run stats software (and lots of others) for free streaming online.

Cloudstorage.iu.edu let’s you link your Box, Dropbox, or other file servers to your cloud account at IU so that these drives show up in your File Explorer using the computer labs or from IUanyware.

Box Sync is also helpful to sync your Box files to your laptop (like Dropbox). (Although, I heard there is a new “Box Drive” that doesn’t require syncing the files, but it’s still in beta at IU.)

IUware is the website to download SPSS and JMP (among others). SAS needs to be installed by Research Analytics. More info and license fees are listed here. As of today: SAS is $125, SPSS is $100, JMP is $50.

R is free, powerful, and flexible: https://www.r-project.org/, and R-studio is a nice interface for using R.

Stata is available on IUanyware and computer labs, but must be purchased separately for download.

Research Analytics is the branch of UITS who sell and support statistical software. Ask them questions about technical support and how to run procedures in different software.

IT training at UITS has workshop materials for learning SAS and SPSS.

Our mission is to support health-related research by providing advice and services for high quality study design and data analysis.

Services include study design, randomization, data management and cleaning, modeling and analysis, diagnostics, interpretations, tables and graphs, and written results for publications.

We can help on your project anywhere from advice on quick questions to being long-term members of your team.

Based in Bloomington, Indiana, we primarily support faculty research at IU School of Public Health – Bloomington, as well as IU School of Medicine, and any health-related research, including projects outside of the University.

See our official webpage at http://biostats.indiana.edu