Generate a declared fractional factorial execution plan
Declare basic factors, signed products and physical levels; export every replicated run, defining relation and alias term with the original JSON and settings.
Declare the complete factor specification
Declare factors, independentFactors and generators. A factor is a name or {name, low, high}; omitted levels use -1 and +1. A generator uses {factor, product, sign}; sign defaults to +1. Product factors must be distinct basic factors.
{
"factors": [
"A",
"B",
"C",
"D",
"E",
"F",
"G"
],
"independentFactors": [
"A",
"B",
"C",
"D"
],
"generators": [
{
"factor": "E",
"product": [
"A",
"B",
"C"
]
},
{
"factor": "F",
"product": [
"A",
"B",
"D"
]
},
{
"factor": "G",
"product": [
"A",
"C",
"D"
]
}
]
}- A low or high level can contain commas, quotes, Unicode or line breaks. It remains a string; no numeric conversion is applied.
- Only basic factors may appear in a generator product. Unknown fields, duplicated factor names and accessors are refused.
Set run count, repetitions and order
Random order: xorshift32 (13, 17, 5), continuous state across replications; Fisher–Yates draws use rejection sampling below floor(2^32 / bound) × bound. The supplied nonzero uint32 seed is saved even when randomization is off. This sequence does not claim to match R.
| Field | Meaning |
|---|---|
| standardRun | One-based standard design row; the first row has all basic factors low. |
| executeRun | One-based order across all repetitions. |
| replicationIndex | One-based repetition; every standard row appears exactly once in each repetition. |
Read signed defining relations and resolution
For E=ABC, F=ABD and G=ACD, multiplying each equation by its dependent factor gives the defining generators ABCE, ABDF and ACDG. Their complete group has eight words including I; the shortest nonidentity word has four factors, so the resolution is IV. Negative generators retain negative signs in the group and all alias classes.
- The minimum resolution is a check on the shortest word, not a search for a better design.
- With no dependent factors, the defining group contains only I and resolution is null: no defining confounding.
Keep every result, including originals
aliases.csv names every term; aliases.json records every mask and sign. Bit i selects factorOrder[i], zero is I, and each sign is relative to its class representative.
| File | Contents |
|---|---|
| coded-design.csv / physical-design.csv | Every factor and every execution row, with all three identity columns. |
| run-order.csv / generators.csv / defining-group.csv | Complete execution mapping, signed equations and full defining group. |
| aliases.csv / aliases.json | Every one of 2^factorCount terms, with masks and signs relative to the representative. |
| plan.json / settings.json / original-input.json | Complete typed plan, frozen settings and byte-exact source JSON; source name, MIME, length and SHA-256 are saved. |
| full-run-plan.html / LICENSE.txt | All physical runs in standalone HTML; JSON-escaped level attributes preserve control characters. Owned-code license status and reference boundary. |
Respect joint budgets and recover atomically
1–1024 replications; at most 32,768 total runs and 655,360 run cells. Random order uses a nonzero uint32 seed and the published rejection-sampled xorshift32 shuffle.
Joint budgets: 100,000,000 charged work units; files plus complete copy text 64 MiB; compact typed data 8 MiB; aggregate 72 MiB; transport 96 MiB; conservative owned allocation envelope 1,024 MiB. Names, escaping, encoding, alias members and copies count. Axis ceilings do not promise simultaneous maximum capacity.
One 120-second absolute deadline starts before source capture and includes metadata, reading, Worker startup, computation, encoding, full validation, cleanup and first publication. Failure or cancellation clears all prior outputs.
- The visible view is paged; full copy and downloads never truncate runs, labels or aliases.
- Correct fields, levels, generators or base-run count. For a joint-budget failure, reduce the complete task and retry. After cancellation or Worker failure, keep the same original input and settings and start a fresh run.
References
- Complete original public discussion
All four saved posts were read. The author requested seven factors, 16 runs, E=ABC, F=ABD, G=ACD and resolution IV. The five-factor reply does not complete that task; no author completion is present and the thread was automatically closed. Online preference, region, market volume and willingness to pay are unknown.
- FrF2 API reference
API/reference only. The owned GF(2) implementation does not bundle GPL >=2 FrF2, WebR or R, and makes no executed mature-R comparison claim.
Tools in this category
Expand a tool to see its steps, options and supported formats, then open its workspace.
Fractional factorial planTurn factor names, signed generators and physical levels into a complete execution plan, every defining relation and every alias term.
Declare the design you intend to execute. The original author’s seven factors and 16 runs use E=ABC, F=ABD and G=ACD and have resolution IV; a five-factor reply example does not replace that request.
Steps
- Declare all factors, two levels, basic factors and signed generators in the editor or one JSON file.
- Set base runs, replication count, randomization, seed and optional minimum resolution.
- Inspect paged physical runs and actual resolution; download all coded/physical runs, order, generators, defining group, aliases, original, settings and standalone HTML.
Available options
- Base runs
- 16
Must equal 2^basicFactors; repetitions are additional.
- Replications
- 1
1–1024, jointly limited to 32,768 total runs.
- Randomize each replication
- Off by default
Random order: xorshift32 (13, 17, 5), continuous state across replications; Fisher–Yates draws use rejection sampling below floor(2^32 / bound) × bound. The supplied nonzero uint32 seed is saved even when randomization is off. This sequence does not claim to match R.
- Nonzero uint32 seed
- 1
1–4,294,967,295, saved for all runs.
- Minimum resolution
- 4
Optional. Clear it to check no minimum; full factorial reports no confounding.
Capabilities and limits
- Safe JSON or the visible JSON editor: at most 1 MiB, 2–20 factors, 1–15 basic factors, unique ASCII names up to 64 characters, two distinct physical level strings of at most 128 UTF-8 bytes each.
- Exactly one signed product for each dependent factor, using distinct basic factors. Base runs equal 2^basicCount. At most 16 generators, 65,536 defining relations and 1,048,576 alias terms; every term is included.
- 1–1024 replications; at most 32,768 total runs and 655,360 run cells. Random order uses a nonzero uint32 seed and the published rejection-sampled xorshift32 shuffle.
- Joint budgets: 100,000,000 charged work units; files plus complete copy text 64 MiB; compact typed data 8 MiB; aggregate 72 MiB; transport 96 MiB; conservative owned allocation envelope 1,024 MiB. Names, escaping, encoding, alias members and copies count. Axis ceilings do not promise simultaneous maximum capacity.
- One 120-second absolute deadline starts before source capture and includes metadata, reading, Worker startup, computation, encoding, full validation, cleanup and first publication. Failure or cancellation clears all prior outputs.
- Only user-declared regular two-level designs. No design catalogue search, optimum selection, estimability, blocking, split plots or centre points. Full factorial resolution is null, meaning no defining confounding.