A confidence interval on a provenance gap needs paired lots, not paired records. Most suppliers have too few to support one and the index does not print what it cannot compute.
bootstrap_ci
Resampled confidence intervals for small-n supplier cells.
Section 1
Contribution
Comments technically on records submitted by others. Annotations are signed and are not moderated for agreement.
Records submitted
0
n=0
Annotations
18
n=18
Median purity submitted
suppressed
n=0
n<3 — see individual records
Suppliers covered
0
n=0
This handle has submitted no records. Annotators comment on other people's submissions and are not required to submit.
Section 2
Annotations
Signed technical comments on records. The index does not moderate annotations for agreement with its own arithmetic, and several of these disagree with it. Where a handle has made the same point on several records, one instance is shown and the rest are reachable from the records themselves.
One measurement, one instrument, one day. There is no interval around -23.2 ppm on this record and treating it as a point estimate overstates what a single determination supports.
A resampled interval around a spread computed from three points is wide. The point estimate is still the right thing to publish and the interval is the right thing to remember.
One measurement, one instrument, one day. There is no interval around +16.5 ppm on this record and treating it as a point estimate overstates what a single determination supports.
One measurement, one instrument, one day. There is no interval around +10.1 ppm on this record and treating it as a point estimate overstates what a single determination supports.
Reading the record the same way.
Worth flagging to whoever submits next on this lot.
One measurement, one instrument, one day. There is no interval around +23.8 ppm on this record and treating it as a point estimate overstates what a single determination supports.
One measurement, one instrument, one day. There is no interval around +15.1 ppm on this record and treating it as a point estimate overstates what a single determination supports.
One measurement, one instrument, one day. There is no interval around -16.1 ppm on this record and treating it as a point estimate overstates what a single determination supports.
One measurement, one instrument, one day. There is no interval around +32.6 ppm on this record and treating it as a point estimate overstates what a single determination supports.
One measurement, one instrument, one day. There is no interval around -22.7 ppm on this record and treating it as a point estimate overstates what a single determination supports.
Showing 12 distinct comments of 18 annotations by this handle.