BS ISO 5725-3:1994

Foreword
Introduction
1 Scope
2 Normative references
3 Definitions
4 General requirement
5 Important factors
6 Statistical model
   6.1 Basic model
   6.2 General mean, m
   6.3 Term B
   6.4 Terms B[0], B[1], B[2], etc.
   6.5 Error term, e
7 Choice of measurement conditions
8 Within-laboratory study and analysis of intermediate
   precision measures
   8.1 Simplest approach
   8.2 An alternative method
   8.3 Effect of the measurement conditions on the final
        quoted result
9 Interlaboratory study and analysis of intermediate
   precision measures
   9.1 Underlying assumptions
   9.2 Simplest approach
   9.3 Nested experiments
   9.4 Fully-nested experiment
   9.5 Staggered-nested experiment
   9.6 Allocation of factors in a nested experimental
        design
   9.7 Comparison of the nested design with the procedure
        given in ISO 5725-2
   9.8 Comparison of fully-nested and staggered-nested
        experimental designs
Annex A (normative) Symbols and abbreviations used in ISO
        5725
Annex B (normative) Analysis of variance for fully-nested
        experiments
   B.1 Three-factor fully-nested experiment
   B.2 Four-factor fully-nested experiment
Annex C (normative) Analysis of variance for
        staggered-nested experiments
   C.1 Three-factor staggered-nested experiment
   C.2 Four-factor staggered-nested experiment
   C.3 Five-factor staggered-nested experiment
   C.4 Six-factor staggered-nested experiment
Annex D (informative) Examples of the statistical
        analysis of intermediate precision experiments
   D.1 Example 1 - Obtaining the [time + operator]-different
        intermediate precision standard deviation, s[I(TO)],
        within a specific laboratory at a particular level
        of the test
   D.2 Example 2 - Obtaining the time-different intermediate
        precision standard deviation by interlaboratory
        experiment
Annex E (informative) Bibliography
Figures
Tables

Defines four intermediate precision measures due to changes in observation conditions within a laboratory. It deals exclusively with methods of measurement which yield measurements on a continuous scale and give a single value as the test result.

1.1 This part of ISO5725 specifies four intermediate precision measures due to changes in observation conditions (time, calibration, operator and equipment) within a laboratory. These intermediate measures can be established by an experiment within a specific laboratory or by an interlaboratory experiment. Furthermore, this part of ISO5725 discusses the implications of the definitions of intermediate precision measures;presents guidance on the interpretation and application of the estimates of intermediate precision measures in practical situations;does not provide any measure of the errors in estimating intermediate precision measures;does not concern itself with determining the trueness of the measurement method itself, but does discuss the connections between trueness and measurement conditions. 1.2 This part of ISO5725 is concerned exclusively with measurement methods which yield measurements on a continuous scale and give a single value as the test result, although the single value may be the outcome of a calculation from a set of observations. 1.3 The essence of the determination of these intermediate precision measures is that they measure the ability of the measurement method to repeat test results under the defined conditions. 1.4 The statistical methods developed in this part of ISO5725 rely on the premise that one can pool information from “similar” measurement conditions to obtain more accurate information on the intermediate precision measures. This premise is a powerful one as long as what is claimed as “similar” is indeed “similar”. But it is very difficult for this premise to hold when intermediate precision measures are estimated from an interlaboratory study. For example, controlling the effect of “time” or of “operator” across laboratories in such a way that they are “similar”, so that pooling information from different laboratories makes sense, is very difficult. Thus, using results from interlaboratory studies on intermediate precision measures requires caution. Within-laboratory studies also rely on this premise, but in such studies it is more likely to be realistic, because the control and knowledge of the actual effect of a factor is then more within reach of the analyst. 1.5 There exist other techniques besides the ones described in this part of ISO5725 to estimate and to verify intermediate precision measures within a laboratory, for example, control charts (see ISO5725‑6). This part of ISO5725 does not claim to describe the only approach to the estimation of intermediate precision measures within a specific laboratory. NOTE1 This part of ISO5725 refers to designs of experiments such as nested designs. Some basic information is given in AnnexB and AnnexC. Other references in this area are given in AnnexE.