Film creditsMore readings. Or more evidence?
A replication design for distinguishing instrument repeats, independently prepared materials and application-relevant variation.
Proposed evidence-engineering direction | External sources and defined methods; scope, rights and delivery capacity to be agreed.
The row count is not the experimental design
Distinguish independent preparations from repeated readings before deciding whether the dataset can support the intended material or population comparison.
A spreadsheet may contain hundreds of readings from one sample. Those readings can describe a curve very well while providing little evidence about another preparation or production lot. The proposed replication map identifies what varies independently: instrument read, aliquot, preparation, lot, operator or laboratory. It then connects that variation to the decision the buyer needs to make. A repeatability question about one instrument may need a different design from an ingredient consistency question. Counting both as the same sample size can make an attractive comparison appear more certain than its material coverage justifies.
Examine the development decision
More readings. Or more evidence?
Open the sequence to examine what a development decision needs.
Identify the exact preparation, its source, and the properties a second laboratory must be able to reproduce.
Explanatory geometry · no simulated or measured performance
The new rheology dataset illustrates the distinction
Use the deposited sweeps to see how hundreds of observed coordinates can still represent only two specifically studied specimens.
Woodbridge et al. (2025) provide 392 acquired rows across flow, amplitude and frequency sweeps for two source specimens. Those rows are useful measurements along experimental axes; the files do not establish 392 independent preparations. The proposed record retains sweep identity, material description and reported conditions while leaving replicate and lot counts unreported where absent. A formulation team can inspect how a specimen behaves across the measured domain, then decide what independent preparation work is needed. The dataset cannot supply a general production-consistency claim simply because its graphs contain many well-resolved points.
Different repeat structures answer different questions
Match replication to the source of variation that matters, whether it arises during manufacturing, preparation, sampling or instrument reading.
A split preparation tested twice assesses a different source of variation from two separately manufactured batches. Repeated measurements across conditions also share their starting material and may share calibration. STRENDA asks authors to explain what changed between repetitions, including preparations, staff and laboratories (STRENDA Commission, 2021). The proposed study specification would adopt that explicitness for formulation work. It would identify which repeat layer addresses the intended uncertainty and avoid adding a costly independent-lot design when the immediate decision is only whether an instrument method can resolve the relevant difference under controlled conditions.
Keep the conditions attached to the result.
Make scientific records useful through source-linked comparisons, explicit units and a reproducible decision trail.
A hierarchical model is a hypothesis about variation
Explain what a hierarchical model assumes about preparation and reading variation before fitting parameters or interpreting its uncertainty.
A simple random-intercept formulation can describe repeated observations within independent preparations. The preparation term represents a shared deviation while the observation term represents remaining variation. This is a proposed statistical structure, not evidence that a particular dataset meets its assumptions. Bland and Altman’s repeated-data note explains why pooled observations can misrepresent dependence (Bland and Altman, 1994). Before fitting, the team would need enough identified preparations and a design that allows the components to be distinguished. If the source does not identify those units, a model cannot recover them from the number of rows alone.
Separate a preparation-level deviation from a within-preparation observation deviation.
- Observation j from preparation iSame unit as endpoint
- Population mean under stated conditionsSame unit as endpoint
- Preparation-level deviationSame unit as endpoint
- Within-preparation residualSame unit as endpoint
- Independent preparation identifierIndex
- Observation or read identifier within preparation iIndex
Model conditions. Identified independent preparations Appropriate random-effect and residual assumptions must be checked Not fitted here; no variance components inferred from anonymous rows
Change the conditions · examine the reference
More readings—or more evidence?
Change the independent preparations and repeat readings. See which source of variation the next measurement can actually reduce.
The data, equations and controls remain available below if 3D cannot load.
Defined model · illustrative conditions
Points are discrete design calculations, joined for comparison. No experimental observations or confidence intervals are shown.
Fund the preparation or repeat that addresses the uncertainty relevant to the development decision.
The defined comparison
Balanced random-intercept scenario with between-preparation SD 10 response AU and within-preparation SD 6 response AU. Preparations are independent; residual readings are independent with common variance. The naive estimate treats all BR readings as independent and ignores clustering. The 3D groups depict a design count, not measured sample values. No confidence interval, power or precision guarantee is calculated. Drift, pairing, operators, serial correlation and unequal group sizes need additional structure.
Inspect the calculated values
Calculation grid, not measured observations. Inputs and assumptions are stated above.
| Independent preparations / count | Hierarchical design | All readings treated as independent |
|---|
Match the replication to the comparator
Choose paired or independently prepared comparisons according to the buyer question, preserving the design that gives the contrast meaning.
A candidate and benchmark may be tested within the same session or across independently prepared batches. Pairing can help control a known source of variation, but it must remain visible in the record and analysis. The proposed protocol would specify sample allocation, session order and whether each comparison is paired. It would also identify which conditions are fixed and which are deliberately varied. This is particularly useful for an application scientist trying to choose between formulation routes: a difference created by session drift should not be confused with a consistent difference between materials, and a paired design should not be analysed as unrelated groups.
A study budget should buy the right independence
Spend the study budget on the independence needed for the decision rather than simply increasing readings from one favourable specimen.
The proposed deliverable would separate the number of preparations from the number of readings required to characterise each one. It would identify the smallest design capable of answering the current decision and the larger design needed for later lot or application claims. An early feasibility comparison may justify a narrow controlled test; a supply-consistency proposition requires broader preparation coverage. These are different commitments with different sample, time and analysis requirements. Any commissioned work would need a practical delivery route and agreed scope. A large reading count should never be sold as a substitute for the independence the buyer’s question requires.
The next proposed comparison.
A replication map and a proportionate study specification
What would be repeated next
Name the result that must survive repetition, then choose the preparation or measurement step that a useful follow-up would repeat.
A useful next-step discussion begins by naming the result that needs to survive repetition. If the material’s curve is promising, the next unit may be another independently prepared batch rather than another hundred points on the same curve. If the method is unstable, technical repeat work may deserve priority before making new material. The proposed replication map makes this trade-off inspectable and ties it to a continue, narrow or stop decision. The aim is an experiment whose interpretation is clear enough to support the next development commitment, with its scope of generalisation stated from the outset.
Evidence engineering · Proposed development discussion
A development path
for this research.
The experimental unit needed to support a material comparison
The people this could serve.Formulation, application-science and research-data teams.
The decision behind the project.
Your intended application, present alternative and the constraint behind “Independent preparations and repeats”. A useful starting point is the change that would justify another development step.
A proposed scope centred on a replication map and a proportionate study specification.
Agree the comparison, acceptance basis and responsible expertise before discussing a paid package.
Specialist methods and a defined contribution.
Bring relevant analytical or experimental expertise, a comparator suggestion, and the conditions under which your method could resolve this question.
A jointly scoped proposal could connect your contribution with a replication map and a proportionate study specification.
Define contributions, required access, independent preparations and permitted outputs before work or protected information is shared.
The commercial purpose of the next milestone.
Bring the application or asset thesis, the buyer you expect to value it, and the scientific or commercial uncertainty that must be resolved before another commitment.
The proposed decision record would connect the buyer question with a replication map and a proportionate study specification. It would identify what a subsequent comparison needs to demonstrate.
Demand, development cost, resources, rights and a decision-changing milestone would need examination. No financing terms or investment outcome are represented here.
What a useful comparison
would record.
- Identify source lots, independently prepared specimens and repeated instrument readings separately.
- Record the chosen endpoint and method under matched comparison conditions.
- Locate variation at the lot, preparation and reading levels before setting a repeat-study scope.
What the proposed
brief could leave behind.
- A replication map and a proportionate study specification
- A preparation, comparator and endpoint record tied to this question.
- A source-linked account of the evidence gaps, study assumptions and next review point.
The proposed discussion brief
A brief you
can take away.
Use non-confidential notes to connect this topic with your own decision. Entries stay in this browser tab; saving creates a text file on your device. Nothing is submitted.
A scoped evidence/data decision brief or qualified comparison programme; recurring or API access only after delivery capacity and repeat buyer value are established.
Notes are optional. The brief includes this page’s proposed question and public source links.
Proposed scope; resources, methods, rights and delivery terms would be agreed before work. Begin with non-confidential information.
Sources and reading notes.
External work is identified below. Access notes describe the material inspected for this page; company research questions and proposed work are not presented as findings from these sources.
Woodbridge et al, 2025Woodbridge et al. (2025) Rheological Characterisation of a Carbopol Microgel and a Commercial Body Lotion: Steady, Oscillatory, and Parallel Superposition Measurements
Acquired six source CSVs: 392 flow, amplitude and frequency rows for two source specimens; source units and README conditions.
Scope and limitations: CC BY 4.0 version 1; two studied specimens, not independent lots or a current commercial product specification. No parallel-superposition or slip data analysed.
Open original sourceSTRENDA Commission, 2021STRENDA Commission (2021) Guidelines Lists Level 1A and 1B, version 1.8
Catalyst identity, assay conditions, activity units, replicate definitions and model reporting.
Scope and limitations: Reporting guidance, not assay approval or a probabilistic quality score.
Open original sourceBland and Altman, 1994Bland and Altman (1994) Correlation, regression, and repeated data
Separates within- and between-subject questions; repeated measurements are dependent.
Scope and limitations: Statistical note, not evidence of a Bio effect or licence to republish its tables.
Open original sourceJCGM, 2008JCGM (2008) Evaluation of measurement data—Guide to the expression of uncertainty in measurement
Measurement models, uncertainty components and covariance in propagation.
Scope and limitations: Does not provide application tolerances or missing source covariance.
Open original source
