ASTM D2904-97
(Practice)Standard Practice for Interlaboratory Testing of a Textile Test Method that Produces Normally Distributed Data
Standard Practice for Interlaboratory Testing of a Textile Test Method that Produces Normally Distributed Data
SCOPE
1.1 This practice serves as a guide for planning interlaboratory tests in preparation for the calculation of the number of tests to determine the average quality of a textile material as discussed in Practice D2905 and for the development of statements on precision as required in Practice D2906.
1.2 The planning of interlaboratory tests requires a general knowledge of statistical principles including the use of variance components estimated from an analysis of variance. Interlaboratory tests should be planned, conducted, and analyzed after consultation with statisticians who are experienced in the design and analysis of experiments and who have some knowledge of the nature of the variability likely to be encountered in the test method.
1.3 The instructions in this practice are specifically applicable to design and analysis of:
1.3.1 Single laboratory preliminary trial,
1.3.2 Pilot-scale interlaboratory tests, and
1.3.3 Full-scale interlaboratory tests.
1.4 Guides for decisions pertaining to data transformations prior to analysis, the handling of missing data, and handling of outlying observations are provided.
1.5 Procedures given in this practice are applicable to test methods based on the measurement of continuous variates from normal distributions or from distributions which can be made normal by a transformation. Get qualified statistical help to ( ) decide if the data are from another known distribution, such as the Poisson distribution, ( ) make a judgment on normality, ( ) transform data to a more nearly normal distribution, or ( ) use Practice D4467. Use the procedures in Practice D4467 for test methods that produce data that are ( ) continuous data that are not normally distributed or ( ) discrete data, such as ratings on an arbitrary scale, counts that may be modelled by use of the Poisson distribution, or proportions or counts of successes in a specified number of trials that may be modelled by the binomial distribution. Note 1-Additional information on interlaboratory testing and on statistical treatment of data can be found in Practice D1749, D3040, E173, E177, E691, and Terminology E456.
General Information
Relations
Standards Content (Sample)
NOTICE: This standard has either been superseded and replaced by a new version or discontinued.
Contact ASTM International (www.astm.org) for the latest information.
Designation: D 2904 – 97
Standard Practice for
Interlaboratory Testing of a Textile Test Method that
Produces Normally Distributed Data
This standard is issued under the fixed designation D 2904; the number immediately following the designation indicates the year of
original adoption or, in the case of revision, the year of last revision. A number in parentheses indicates the year of last reapproval. A
superscript epsilon (e) indicates an editorial change since the last revision or reapproval.
E 173, E 177, E 691, and Terminology E 456.
1. Scope
1.1 This practice serves as a guide for planning interlabo-
2. Referenced Documents
ratory tests in preparation for the calculation of the number of
2.1 ASTM Standards:
tests to determine the average quality of a textile material as
D 123 Terminology Relating to Textiles
discussed in Practice D 2905 and for the development of
D 1749 Practice for Interlaboratory Evaluation of Test
statements on precision as required in Practice D 2906.
Methods Used with Paper and Paper Products
1.2 The planning of interlaboratory tests requires a general
D 2905 Practice for Statements on Number of Specimens
knowledge of statistical principles including the use of vari-
for Textiles
ance components estimated from an analysis of variance.
D 2906 Practice for Statements on Precision and Bias for
Interlaboratory tests should be planned, conducted, and ana-
Textiles
lyzed after consultation with statisticians who are experienced
D 3025 Practice for Standardizing Cotton Fiber Test Results
in the design and analysis of experiments and who have some
by Use of Calibration Cotton Standards
knowledge of the nature of the variability likely to be encoun-
D 3040 Practice for Preparing Statements for Standards
tered in the test method.
Related to Rubber and Rubber Testing
1.3 The instructions in this practice are specifically appli-
D 4270 Guide for Using Existing Practices in Developing
cable to design and analysis of:
and Writing Test Methods
1.3.1 Single laboratory preliminary trial,
D 4467 Practice for Interlaboratory Testing of a Textile Test
1.3.2 Pilot-scale interlaboratory tests, and
Method that Produces Non-Normally Distributed Data
1.3.3 Full-scale interlaboratory tests.
5,6
D 4853 Guide for Reducing Test Variability
1.4 Guides for decisions pertaining to data transformations
E 173 Practices for Conducting Interlaboratory Studies of
prior to analysis, the handling of missing data, and handling of
Methods for Chemical Analysis of Metals
outlying observations are provided.
E 177 Practice for Use of the Terms Precision and Bias in
1.5 Procedures given in this practice are applicable to test
ASTM Test Methods
methods based on the measurement of continuous variates
E 178 Practice for Dealing with Outlying Observations
from normal distributions or from distributions which can be
E 456 Terminology Relating to Quality and Statistics
made normal by a transformation. Get qualified statistical help
E 691 Practice for Conducting an Interlaboratory Study to
to (1) decide if the data are from another known distribution,
Determine the Precision of a Test Method
such as the Poisson distribution, (2) make a judgment on
2.2 ASTM Adjuncts:
normality, ( 3) transform data to a more nearly normal
TEX-PAC
distribution, or ( 4) use Practice D 4467. Use the procedures in
Practice D 4467 for test methods that produce data that are (1) NOTE 2—Tex-Pac is a group of PC programs on floppy disks, available
through ASTM Headquarters, 100 Barr Harbor Drive, West Consho-
continuous data that are not normally distributed or (2) discrete
hocken, PA 19428, USA. The calculations required by the Annexes of this
data, such as ratings on an arbitrary scale, counts that may be
practice can be performed using this adjunct and the ouput is printed in a
modelled by use of the Poisson distribution, or proportions or
format suitable for direct insertion in the Research Report required when
counts of successes in a specified number of trials that may be
an interlaboratory evaluation is conducted for the purpose of establishing
modelled by the binomial distribution.
NOTE 1—Additional information on interlaboratory testing and on
Annual Book of ASTM Standards, Vol 07.01.
statistical treatment of data can be found in Practice D 1749, D 3040,
Annual Book of ASTM Standards, Vol 15.09.
Discontinued. See 1988 Annual Book of ASTM Standards, Vol 09.01.
Annual Book of ASTM Standards, Vol 07.02.
1 6
This practice is under the jurisdiction of ASTM Committee D-13 on Textiles Discontinued. See 1993 Annual Book of ASTM Standards, Vol 07.02.
and is the direct responsibility of Subcommittee D13.93 on Statistics. Annual Book of ASTM Standards, Vol 03.05.
Current edition approved Nov. 10, 1997. Published August 1998. Originally Annual Book of ASTM Standards, Vol 14.02.
published as D 2904 – 73 T. Last previous edition D 2904 – 91. PC programs on floppy disks are available through ASTM. Request ADJD2904.
Copyright © ASTM, 100 Barr Harbor Drive, West Conshohocken, PA 19428-2959, United States.
NOTICE: This standard has either been superseded and replaced by a new version or discontinued.
Contact ASTM International (www.astm.org) for the latest information.
D 2904
the precision of a Test Method.
operators, equipment, and environments when following pro-
cedures prescribed in a specific test method and of determining
3. Terminology
that the method produces results of essentially uniform vari-
3.1 For definitions of textile and statistical terms used in this
ability and at a consistent level when the same materials are
practice, and discussions of their use, refer to Terminologies
tested in a number of laboratories.
D 123, and E 456 and appropriate textbooks on statistics
5.2 The estimates of the components of variance from the
(1-9).
interlaboratory test provide the information needed for the
preparation of statements on the number of specimens and on
4. Summary of Practice
precision as directed in Practices D 2905 and D 2906.
4.1 Planning and running an interlaboratory test program
6. Basic Statistical Design
presumes that the test method has been adequately developed
as directed in Sections 1–7 of Guide D 4270.
6.1 It is desirable to keep the design as simple as possible,
4.2 In this practice, directions are given on how to run a
yet to obtain estimates of within and between-laboratory
pilot-scale interlaboratory test to validate the state of control
variability unconfounded with secondary effects. Provisions
for a test procedure. A pilot-scale test is run to decide whether
also should be made for estimates of the variability due to:
( 1) the procedures for the test method and for the interlabo-
materials times laboratories, operators times materials interac-
ratory test program are adequate or (2) more development work
tions, and instruments within laboratories where two or more
needs to be done on one or both of the procedures.
instruments may be used in one laboratory.
4.3 Directions are given on how to run a full-scale inter-
NOTE 3—Generally, for a test method, there are only a limited or fixed
laboratory test.
number of laboratories or operators in each laboratory who participate in
4.4 Directions are given on making data transformations,
the interlaboratory tests. Since all do not participate, one assumes that the
handling missing data, testing outlying observations, and
sampling of laboratories, and operators within laboratories are drawn from
running auxiliary tests. a larger population of such laboratories or operators. For this reason, an
analysis of variance (ANOVA) model based on random effects is used (1,
4.5 In Annex A1, the following steps are described on how
3, 4, and 8). Since specimens are always a random effect, a fixed ANOVA
to examine the data from either the pilot-scale or full-scale
model does not normally apply.
interlaboratory tests.
6.2 The basic statistical design should include: a minimum
4.5.1 Analyze the data by materials by preparing an analysis
of two or more materials spanning the range of interest for the
of variance table for each material.
property being measured, a minimum of five laboratories, and
4.5.2 Validate a state of statistical control by testing the
a minimum of two operators per laboratory with each operator
mean squares in the analysis of variance tables for significant
testing at least two specimens of each material in a designated
effects. If significant effects are found, a decision must be made
order. There is, generally, no major advantage in having the
on whether to (1) return to further development of the test
degrees of freedom for error exceeding 40, but it is desirable
procedure or the instructions for the interlaboratory test, or
for the degrees of freedom for all other mean squares to be as
both, or ( 2) continue with the analysis of the data from the
large as practical. This basic design may be expanded accord-
interlaboratory test.
ing to the experience of the task group, the number of
4.5.3 Make a decision on whether to ( 1) combine the data
from all materials into a single analysis of variance, (2) laboratories available to perform the specified tests and the
degree of heterogeneity (or homogeneity) of the test materials.
combine the data into a single analysis of variance with
variability expressed as a transformation such as coefficients of 6.3 The Laboratory Report Format is represented in Fig. 1
by a two-way classification table in which the rows represent
variation or (3) stop the analysis and write separate statements
on precision for each material. the materials and the columns represent the operators in the
laboratory. Each cell contains the replicate observations per
4.5.4 If a decision is made to combine the data from all
materials, analyze the data from all materials as a single operator.
6.4 A basic analysis of variance (ANOVA) design should be
analysis of variance and validate a state of control by testing
for significant effects. If significant effects are found, a decision a randomized complete-block design or other more suitable
factorial, having the following successive subsets:
must be made on whether to (1) return to further development
of the test procedure or the instructions for the interlaboratory 6.4.1 Materials, M,
6.4.2 Laboratories, L,
test, or both, or ( 2) continue with the analysis of the data from
6.4.3 Operators in laboratories, O(L), and
the interlaboratory test.
6.4.4 Specimens per operator within laboratories and mate-
4.5.5 Calculate the necessary components of variance for
rials, S (MLO).
use as directed in Practice D 2905 and Practice D 2906.
6.5 The basic statistical design outlined in 6.2-6.4 will
5. Significance and Use
provide the following estimated components of variance:
6.5.1 Specimens within operators, laboratories, and materi-
5.1 Interlaboratory testing is a means of securing estimates
als, S·MLO,
of the variability in results obtained by different laboratories,
6.5.2 Operator times materials interactions within laborato-
ries, MO·L,
6.5.3 Operators within laboratories, O·L,
The boldface numbers in parentheses refer to the references listed at the end
of this practice. 6.5.4 Materials times laboratories interactions, ML,
NOTICE: This standard has either been superseded and replaced by a new version or discontinued.
Contact ASTM International (www.astm.org) for the latest information.
D 2904
Laboratory Number____
Material Number Operator Number
123 . j . q
1 . . . . . .
... ... ... ... ...
...
... ... ... ...
2 . . . . . .
... ... ... ... ...
... ... ... ... ...
3 . . . . . .
... ... ... ... ...
... ... ... ... ...
... ij cell
i . . . . .
...
... ... ... ...
n
...
... ... ... ...
...
P . . . . . .
... ... ... ... ...
... ... ... ... ...
FIG. 1 Laboratory Report Format for Interlaboratory Test Data Involving p Materials, q Operators, and nTests or Replications
6.5.5 Laboratories, L, and mens tested by each operator in each laboratory for each
6.5.6 Materials, M. material may be calculated from previous information or from
6.6 A range of materials should be intentionally chosen so a pilot run. This number of specimens or replications (mini-
that the component of variance for materials will be significant. mum of two) depends on the relative size of the random error
Since this component is not used in estimating the precision of and the smallest systematic effect it is desired to be able to
the test method, it is normally not calculated from the associ- detect. A replication consists of one specimen of each condition
ated mean square in the analysis of variance (ANOVA) table. and material to be tested in the statistical design.
6.7 The estimates of the components of variance provided
NOTE 5—It is desirable to test a larger number of materials in more
for in 6.5 provide the basic data for estimating the number of
laboratories with the number of operators per laboratory and the number
tests required for a specified allowable variation as directed in
of tests per operator at a minimum. When the established sampling error
Practice D 2905 and for the preparation of statements on
for material exceeds 5 % of the material mean, (when tested by one skilled
precision as directed in Practice D 2906. operator in one laboratory), increased test replication may be necessary.
6.8 An illustrative example of a full-scale interlaboratory
7.5 Order of Tests—In many situations, variability among
design and its analysis is shown in Annex A1.
replicate tests is greater when measurements are made at
different times than when they are made together, as part of a
7. General Considerations
group. Sometimes trends are apparent among results obtained
7.1 Sampling of Materials—It is desirable that any one
consecutively. Furthermore, some materials undergo measur-
subsample of the material, within which laboratories, opera-
able changes within relatively short storage periods. For these
tors, days, or other factors are to be compared, be as homoge-
reasons, the dates of testing, as well as the order of tests carried
neous as possible with respect to the property being measured.
out in a group shall, wherever possible, be treated as controlled
Otherwise, increased replication will be required to reduce the
systematic variables.
size of the random error.
7.6 Alternative Methods—When possible, values for each
7.2 Complete Randomization—Divide all the randomized
material should be established by a
...
Questions, Comments and Discussion
Ask us and Technical Secretary will try to provide an answer. You can facilitate discussion about the standard in here.