Most statistical questions that matter are really measurement questions. Whether a single passing test proves compliance. Whether the assay is drifting or the product is. Whether a study design can answer the question it was built to answer. MRP Group exists to answer them, and to say plainly when the data cannot.
A statistical consulting practice working across federal regulatory, industrial, clinical and academic programs — for organizations whose results have to survive a regulator, an auditor or a peer reviewer.
Engagements almost always start with a specific problem rather than a capability search.
The first question is whether the process moved or the measurement did — and that is answerable from records you already have.
Most statistical IRs ask you to make an existing decision auditable, not to replace it. A reply that generates a follow-up costs a full review cycle.
A single measurement carries test-to-test variability. Converting that into a guard band is what makes the compliance decision defensible.
Sometimes the design cannot answer the question and no analysis will rescue it. Being told that early is the deliverable.
Catching an underpowered design or a mis-specified endpoint beforehand costs a fraction of discovering it afterwards.
GSA Schedule 47QRAA25D000P with an awarded Statistician labor category — no rate crosswalk, no separate negotiation.
Federal work reaches end clients through prime contractor relationships; commercial clients are served directly. Client names are withheld where the work remains under contract.
Engagements are led and delivered by the principal. Clients work directly with the statistician doing the analysis, from the first scoping conversation through to defending the method.
This is work where judgment is the deliverable: deciding whether a design can support a claim, whether a model has failed quietly, whether an anomaly is the product or the instrument.
Robert J. Parody, Ph.D. — Principal Statistician. Ph.D. in Statistics, University of South Carolina; Associate Professor of Applied Statistics at Rochester Institute of Technology, where he teaches graduate design of experiments, statistical quality control, applied linear models, categorical data analysis and time series. Twenty years across federal regulatory, industrial, clinical and academic programs, with peer-reviewed publications as statistician and a current NIH Phase 2 trial co-investigator appointment.
A regulator needed to know what one passing certification test established about a product's compliance. We quantified how much a product's measured emission rate varies between tests, then converted that variability into a guard band — how far below the limit a product must measure to be genuinely likely to comply. Delivered as regulator-risk and producer-risk curves rather than a single threshold.
A challenge study designed to estimate a lethal dose produced an estimate that was not usable — mortality ran essentially flat across every dose, the slope was barely identifiable, and confidence limits could not be computed at all. The deliverable was to say so plainly, and to identify dose placement rather than a different model as the remedy.
Before asking how often certified units exceed an emissions limit, the certification test itself was characterized as a measurement system through a nested Gage R&R — nested rather than crossed, because laboratories do not test a common set of units. Capability against method-specific limits was then estimated on the log scale, reported separately for a single test and for the population distribution.
Detection limits and minimum detectable concentration, guard bands, compliance demonstration, decision-error and data quality objectives frameworks.
Capability and performance indices, statistical process control, gauge R&R and measurement system analysis, method and assay validation, root cause investigation.
Dose–response and lethal dose estimation, potency assays and lot release, statistical analysis plans, CDISC SDTM and ADaM datasets, tables listings and figures.
Sample size and power determination, design of experiments and response surface methods, monitoring network design, stratified and multistage sampling.
MRP Group works with prime contractors as a named statistical subcontractor. Because the labor category is already awarded and priced, there is no crosswalk and no separate rate negotiation.
MRP Group is a statistical consulting practice led by Robert J. Parody, Ph.D. Most engagements come down to establishing what a measurement can and cannot support, then designing the study or sampling scheme that makes the resulting decision defensible. Work spans regulatory decision-making, preclinical and clinical biostatistics, medical device validation, and process capability and measurement systems.
Yes. MRP Group holds GSA Multiple Award Schedule contract 47QRAA25D000P under SINs 541990 and 54151S, with an awarded Statistician (Ph.D., 10 years) labor category, so the firm can be added to a prime contractor's team without a rate crosswalk or separate negotiation. UEI RPKJGEB3QKL8, CAGE 9AWW3, small business.
A rejected Gage R&R usually means one of three things: the study design did not match the measurement process, the acceptance criterion applied was the wrong one for the application, or the measurement system genuinely cannot resolve the tolerance. These call for different responses, and determining which applies can often be done from the data already collected.
Send the problem, not the data. A short call will establish whether the question is answerable with what you have, roughly what it would take, and whether you need a statistician at all.
