Chapter 11 - Section D

Analysis of the Results

CHAPTER II - Section D
Analysis of the Results
The results should be evaluated to determine if the measurement device
is acceptable for its ~tended application. A measurement system should
be stable before any additional analysis is valid.
Acceptability Criteria - Location Error
Location Error
Location error is normally defmed by analyzing bias and linearity.
In general, the bias or linearity error of a measurement system is
unacceptable if it is significantly different from zero or exceeds the
maximum permissible error established by the gage calibration
procedure. In such cases, the measurement system should be recalibrated
or an offset correction applied to minimize this error.
Acceptability Criteria - Width Error
Width Error The criteria as to whether a measurement system's variability is
satisfactory are dependent upon the percentage of the manufacturing
production process variability or the part tolerance that is consumed by
measurement system variation. The fmal acceptance criteria for specific
measurement systems depends on the measurement system's
environment and purpose and should be agreed to by the customer.
F or measurement systems whose purpose is to analyze a process, a
general rule of thumb for measurement system acceptability is as
follows:
Under 10 percent error - generally considered to be an acceptable
measurement system.
10 percent to 30 percent error - may be acceptable based upon
importance of application, cost of measurement device, cost of
repair, etc.
Over 30 percent - considered to be not acceptable - every effort
should be made to improve the measurement system.
Further, the number of distinct categories (ndci2 the process can be
divided into by the measurement system ought to be greater than or
equal to 5.

The final acceptance of a measurement system should not come

down to a single set of indices. The long-term performance of the
measurement system should also be reviewed using graphical
I analyses over time.

32
See Chapter III, Section B, "Analysis of Results - Numerical".

77
 Chapter ill - Section B
Variable Measurement System Study - Guidelines

Average and Range Method

The Average' and Range method (X & R) is an approach which will

provide an estimate of both repeatability and reproducibility for a
measurement system. Unlike the Range method, this approach will allow
the measurement system's variation to be decomposed into two separate
45
components, repeatability and reproducibility, but not their interaction .

Conducting the Study

Although the number of appraisers, trials and parts may be varied, the
subsequent discussion represents the optimum conditions for conducting
the study. Refer to the GRR data sheet in Figure 12. The detailed
procedure is as follows:
1) Obtain a sample of n > 5 parts 46 that represent the actual or expected
range of process variation.
2) Refer to the appraisers as A, B, C, etc. and number the parts
through n so that the numbers are not visible to the appraisers.
I See Chapter 2, Section C.
3) Calibrate the gage if this is part of the nonnal measurement system
procedures. Let appraiser A measure n parts in a random order47 and
enter the results in row 1.
4) Let appraisers Band C measure the same n parts without seeing each
other's readings; then enter the results in rows 6 and 11, respectively.
5) Repeat the cycle using a different random order of measurement. :J.!
Enter data in rows 2, 7 and 12. Record the data in the appropriate
column. For example if the first piece measured is part 7 then record
the result in the column labeled part 7. If three trials are needed,
repeat the cycle and enter data in rows 3, 8 and 13.
6) Steps 4 and 5 may be changed to the following when large part size
or simultaneous unavailability of parts makes it necessary:

./ Let appraiser A measure the first part and record the reading in
row 1. Let appraiser B measure the first part and record the I;.
reading in row 6. Let appraiser C measure the first part and
record the reading in row 11.

45
The ANOVA method can be used to determine the interaction between the gage and appraisers, if such exists.
46
The total number of "ranges" generated ought to be > 15 for a minimal level of confidence in the results.
Although the form was designed with a maximum of 10 parts, this approach is not limited by that number. As
with any statistical technique, the larger the sample size, the less sampling variation and less resultant risk will
be present.
47
See Chapter III, Section B, "Randomization and Statistical Independence"

99

,f,-.
!
;
 Chapter III - Section B
Variable Measurement System Study - Guidelines

./ Let appraiser A repeat reading on the first part and record the
reading in row 2, appraiser B record the repeat reading in row 7,
and appraiser C record the repeat reading in row 12. Repeat this
cycle and enter the results in rows 3, 8, and 13, if three trials are
to be used.
7) An alternative method may be used if the appraisers are on different
shifts. Let appraiser A measure all 10 parts and enter the reading in
row 1. Then have appraiser A repeat the reading in a different order
and enter the results in rows 2 and 3. Do the same with appraisers B
andC.

100

Ii,
1: I
 Chapter III - Section B
Variable Measurement System Study - Guidelines

ApprA

...4-

1.25

.......
Appr B

-1.25

., .. ... ..

1.25

-1.25
-

.. ':.4:
", ...
.....
..
,
Appr C

Figure 23: Comparison X-Y Plots

NUMERICAL CALCULATIONS
The Gage Repeatability and Reproducibility calculations are shown in
Figures 24 and 25. Figure 24 shows the data collection sheet on which all
study results are recorded. Figure 25 displays a report sheet on which all
identifying infonnation is to be recorded and all calculations made
according to the prescribed fonnula.
Reproducible blank forms are available in the Sample Forms
section. The procedure for doing the calculations after data have
I been collected is as follows:

(The following refers to Figure 24)

I) Subtract the smallest reading from the largest reading in rows I, 2
and 3; enter the result in row 5. Do the same for rows 6, 7, and 8; and
11, 12, and 13 and enter results in rows 10 and 15, respectively.
2) Entries in rows 5, 10 and 15 are ranges and therefore always positive
values.
3) Total row 5 and divide the total by the number of parts sampled to
obtain the average range for the first appraisers trials Ra' Do the
same for rows 10 and 15 to obtain Rb and Rc'

4) Transfer the averages of rows 5, 10, and 15 (Ra' Rb , Rc) to row 17.
Add them together and divide by the number of appraisers and enter
results R (average of all ranges).

III

 Chapter III - Section B

Variable Measurement System Study - Guidelines

5) Enter R (average value) in rows 19 and multiply by D4 51 to get the

upper control limit. Note D4 is 3.27 if two trials are used. The value
of the Upper Control Limit (UCLR ) of .the individual ranges is
entered in row 19. NOTE: The value of Lower Control Limit (LCL R )
for less than seven trials is equal to zero.
6) Repeat any readings that produced a range greater than the calculated
UCL R using the same appraiser and part as originally used, or discard
those values and re-average and recompute R and the limiting value
UCL R based upon the revised sample size. Correct the special cause
that produced the out of control condition. If the data were plotted
and analyzed using a control chart as discussed previously, this
condition would have already been corrected and would not occur
here.
7) Sum the rows (rows 1,2,3,6,7,8,11,12, and 13). Divide the sum
in each row by the number of parts sampled and enter these values in
the right most column labeled "Average".
8) Add the averages in rows 1, 2 and 3 and divide the total by the
number of trials and enter the value in row 4 in theXa block. Repeat
this for rows 6, 7 and 8; and 11, 12 and 13, and enter the results in
the blocks for Xb and Xc in rows 9 and 14, respectively.

9) Enter the maximum and minimum averages of rows 4, 9 and 14 in

the appropriate space in row 18 and determine the differences. Enter
this difference in the space labeled X DIFF in row 18.

10) Sum the measurements for each trial, for each part, and divide the
total by the number of measurements (number of trials times the
number of appraisers). Enter the results in row 16 in the spaces
provided for part average.
11) Subtract the smallest part average from the largest part average and
enter the result in the space labeled Rp in row 16. Rp is the range of
part averages.

(The following refers to Figure 25)

12) Transfer the calculated values of R, X DIFF and Rp to the blanks
provided on the report side of the form.
13) Perform the calculations under the column entitled "Measurement
Unit Analysis" on the left side of the form.
14) Perform the calculations under the column entitled "% Total
Variation" on the right side of the form.
"i
15) Check the results to make sure no errors have been made.

51
See Statistical Process Control (SPC) Reference Manual, 1995, or other statistical reference source for(cl table
of factors.

112
 Chapter III - Section B
Variable Measurement System Study - Guidelines

Gage Repeatability and Reproducibility Data Collection Sheet

PART
Appraiser
AVERAGE
ITrial # 2 . 3 4 5 6 7 8 9 10

2
3
4 Average
0.447 -0.607 1.260 0.537 -0.853 -0.100 0.667 -0.227 2.087 -1.307
xa = 0.19

5 Range Ra = 0.1
0.35 0.12 0.17 0.17 0.12 0.23 0.16 0.14 0.27 0.11
6 B 0.0
7 0.1
8 0.0
9 Average X=
0.133 -0.790 1.157 0.413 -1.013 0.027 0.617 -0.297 2.037 -1.600 b 0.06

10 Range R = 05
0.18 0.75 0.40 1.02 0.72 0.42 0.36 0.71 0.39 0.18 b

Average
0.073 -1.157 0.880 0.150 -1.327 -0.483 0.080 -0.503 1.697 -1.807
xc =
-0.25
15 Range Rc =
0.19 0.42 0.42 0.09 0.39 0.38 0.20 0.10 0.42 0.67 0.3
r_--------r----+----~----+_----+_----r_--_+----_r----+_----_r----~----------- ------

16
Part X=
Average
.00
0.169 -0.851 1.099 0.367 -1.064 -0.186 0.454 -0.342 1.940 -1.571
Rp =
3.5
17 ([ J{ = 0.184] + [R b = 0.513] + [Rc = 0.328]) I [ # OF APPRAISERS = 3] = R= 0.34

18 [Max X = 0.1903] [Min X = -0.2543] = XDIFF = 0.4446

19 * [R = 0.3417J X [D4 = 2.58] = UCL R = 0.8816

*D4 = 3.27 for 2 trials and 2.58 for 3 trials. UCL R represents the limit of individual R 's. Circle those that are

beyond this limit. Identify the cause and correct. Repeat these readings using the same appraiser and unit as originally used or

discard values and re-average and recompute R and the limiting value from the remaining observations.

Notes:
----------------------------------------------------------------- - -

Figure 24: Completed GR&R Data Collection Sheet

I 113
J
Chapter III - Section B
Variable Measurement System Study - Guidelines

Gage Repeatability and Reproducibility Report

Part No. & Name: Gage Name: Date:
Characteristics: Gage No: Perfonned by:
Specifications: Gage Type:

From data sheet: R = 0.3417 X DIFF = 0.4446

Measurement Unit Analysis % Total Variation (TV)
Repeatability - Equipment Variation (EV)
EV = R X K1 %EV = 100 [EV/TV]

= 0.3417 x 0.5908 Trials K1 = 100 [0.20188/1.14610]

= 0.20188 2 0.8862 = 17.62%

3 0.5908

Reproducibility - Appraiser Variation (A V)

AV = ~(XDIFFXK2Y 2
(EV /(nr)) %AV = 100'[AV/TV]

= ~(0.4446xO.5231)2 2
(O.20188 /(10x3))
= 100 [0.22963/1.1461 0]

= 0.22963 Appraisers 2 3 =20.04%

n = parts r = trials K2 r~ 0.7071 0.5231

Repeatability & Reproducibility (GRR)

GRR = JEV 2 + AV2 %GRR = 100 [GRRlTV]

= ~( 0.20188 2 + 0.22963 2 ) Parts K3 = 100 [= 0.30575/1.14610]

= 0.30575 2 0.7071 = 26.68%

3 0.5231
Part Variation (PV) 4 0.4467 % PV = 100 [PV/TV]

PV = Rp X K3 5 0.4030 = 100 [1.10456/1.14610]

= 1.10456 6 0.3742 =96.38%

Total Variation (TV) 7 0.3534

2 2 8 0.3375
TV = JGRR + PV

= ~( 0.30575 2 + 1.1 0456 2) 9 0.3249 ndc = 1.41(P%RR)

= 1.14610 = 1.41(1.10456/0.30575)
10 0.3146
= 5.094 5
For information on the theory and constants used in the form see MSA Reference Manual, Third edition.
~.--------------------------------------------------------------------------~

Figure 25: Gage Repeatability and Reproducibility Report

114
 Gage Repeatability and Reproducibility Data Collection Sheet
PART
Appraiser
AVERAGE
ITrial # 1 2 3 4 5 6 7 8 9 10
A 1
2

3
Average -
Xa =

-
Range (~
Ra =

B 1

Average X=
b

Range Rb =

C 1
2
3
Average x c
=

Range Rc =

Part Average X=
Rp =

([Jia = ] + [Rb = ] + [Rc = ]) I [# OF APPRAISERS = ]= R=

- - -
X DIFF = [Max X = } - [MinX= J=
-
*UCLR=/R= } x rD, = J=

*D4 = 3.27 for 2 trials and 2.58 for 3 trials. UCL R represents the limit of individual R's. Circle those that are

beyond this limit. Identify the cause and correct. Repeat these readings using the same appraiser and unit as originally used or
discard values and re-average and recompute R and the limiting value from the remaining observations.

Notes:
------------------------------------------------------------------

216

 Part No. & Name:

Characteristics:
Specifications:
Gage Repeatability and Reproducibility Report
Gage Name:
Gage No:
Gage Type:
Date:
Performed by:

From data sheet: R

= DIFF X p = R =
~----------------------------------------------~------------------------------
Measurement Unit Analysis % Total Variation (TV)
Repeatability - Equipment Variation (EV)

EV Trials %EV = 100 [EV/TV]

=- - - X
--- 2 0.8862 = 100 L-[_ _ ---'1_ _-.1]
3 0.5908 %
Reproducibility - Appraiser Variation (A V)

AV = ~(X DIFF X
2
K2)2 - (EV /(nr)) %AV= 100 [AV/TV]

= ~(_x_)2 _ (_2/Lx_)) =100r~____~/___~1

Appraisers 2 3 =--_%
n = parts r = trials 0.7071 0.5231

,
~. '
Repeatability & Reproducibility (GRR)

GRR = JEV

=~(_2+_2)
2 + AV2

Parts K3
%GRR= 100 [GRR/TV]

= 100 [ '(
/ J
= 2 0.7071 = %
Part Variation (PV) 3 0.5231

PV = Rp X K3 4 0.4467 %PV = 100 [PVITV]

= X 5 0.4030 = 100 [ 1 1
= 6 0.3742 = %
Total Variation (TV) 7 0.3534

TV = ~GRR2 + PV
2 8 0.3375 ndc = 1.41 (P%RR)
=~(_2+_2) 9 0.3249 = 1Al( I )

= 10 0.3146 =

For information on the theory and constants used in the form see MSA Reference Manual, Third edition.

','
(I
.
\",
" '~

217