781:
obtained from the experiment directly) in Yates' order, the first two terms are added and that sum is now the first term in the new column. The next two terms are then added and that is the second term in the new column. Since the terms are added pairwise, half of the new column is now filled and should be composed entirely of the pairwise sums of the data. The second half of the column is found in an analogous manner, only the pairwise differences are taken, where the first term is subtracted from the second, the third from the fourth, and so on. Thus completes the column. Should more columns be needed, the same process is repeated, only using the new column. In other words, the nth column is generated from the (n-1)th column (Berger et al. calls this process "Yatesing the data"). In a
1435:(Adapted from Berger et al., chapter 9) Say there is a study done where one is selling some product by mail and is trying to determine the effect of three factors (postage, product price, envelope size) on people's response rate (that is, will they buy the product). Each factor has two levels: for postage (labeled A), they are third-class (low) and first-class (high), for product price (labeled B) the low level is $ 9.95 and the high level is $ 12.95, and for envelope size (labeled C) the low level is #10 and the high level is 9x12. From the experiment, the following data are acquired. Note that the response rate is given as a proportion of the people who answered the survey (favorably and unfavorably) for each treatment combination.
1757:
1765:
to produce the effect estimates for every treatment combination. Observe that the columns for A, B, and C are the same as those in the design matrix in the above Yates' order section. Observe also that the columns of the interaction effects can be produced by taking the dot product of the columns of the individual factors (i.e., multiplying the columns element-wise to produce another column of the same length). Note that all sums must divided by 4 to yield the actual effect estimate, as shown earlier. Using this table, the effect estimates are calculated as:
1891:
factors. Instead, seven criteria are utilized to define important factors. These seven criteria are not all equally important, nor will they yield identical subsets, in which case a consensus subset or a weighted consensus subset must be extracted. In practice, some of these criteria may not apply in all situations, and some analysts may have additional criteria. These criteria are given as useful guidelines. Mosts analysts will focus on those criteria that they find most useful.
2001:
2199:
1839:
A positive value means that an increase in the factor creates an increase in the response rate, while a negative value means that that same factor increase actually produces a decrease in the response rate. Note however that these effects have not yet been determined to be statistically significant,
1764:
The full table of signs for a three-factor, two-level design is given to the right. Both the factors (columns) and the treatment combinations (rows) are written in Yates' order. The value of arranging the sum in Yates' order is now apparent, as only the signs need to be altered according to the table
780:
To determine the magnitudes, the response variables are first arranged in Yates' order, as described in the aforementioned section above. Then, terms are added and subtracted pairwise to determine the next column. More specifically, given the values of the response variables (as they should have been
680:
in which it is evident that the exponents in the modern notation names are simply the subscripts of the former (note that anything raised to the zeroth power is 1 and anything raised to the first power is itself). Each response variable then gets assigned row-wise to the table above. Thus, the first
1942:
with three numeric criteria and one graphical criterion. The fifth criterion focuses on averages. The last two criteria focus on the residual standard deviation of the model. Once a tentative model has been selected, the error term should follow the assumptions for a univariate measurement process.
1878:
From the above Yates output, one can define the potential models from the Yates analysis. An important component of a Yates analysis is selecting the best model from the available potential models. The above step lists all the potential models. From this list, we want to select the most appropriate
316:
To better understand and utilize the sign table above, one method of detailing the factors and treatment combinations is called modern notation. The notation is a shorthand that arises from taking the subscripts of each treatment combination, making them exponents, and then evaluating the resulting
1869:
term was included in the model. This is not the case when the design is orthogonal, as is a 2 full factorial design. For orthogonal designs, the estimates for the previously included terms do not change as additional terms are added. This means the ranked list of effect estimates simultaneously
1890:
In short, we want our model to include all the important factors and interactions and to omit the unimportant factors and interactions. Note that the residual standard deviation alone is insufficient for determining the most appropriate model as it will always be decreased by adding additional
32:
has been used. Full- and fractional-factorial designs are common in designed experiments for engineering and scientific applications. In these designs, each factor is assigned two levels, typically called the low and high levels, and referred to as "-" and "+". For computational purposes, the
1209:
595:
317:
expression and using that as the new name of the treatment combination. Note that while the names look very much like algebraic expressions, they are simply names and no new values are assigned. Taking the 3-factor, 2-level model from above, in Yates' order the response variables are:
1420:
36:
A full factorial design contains all possible combinations of low/high levels for all the factors. A fractional factorial design contains a carefully chosen subset of these combinations. The criterion for choosing the subsets is discussed in detail in the
2203:
1216:
This consists of a monotonically decreasing set of residual standard deviations (indicating a better fit as the number of terms in the model increases). The first cumulative residual standard deviation is for the model
971:
94:
column consists of 2 minus signs (i.e., the low level of the factor) followed by 2 plus signs (i.e., the high level of the factor). For example, for a full factorial design with three factors, the design matrix is
322:
940:
1254:
1517:
Singling out factor A (postage) for calculation for now, the overall estimate for A must take into account the interaction effects of B and C on it as well. The four terms for calculation are:
1749:
1753:
The estimates for B and C can be determined in a similar fashion. Calculating the interaction effects is also similar, but the responses are averaged over all other effects not considered.
1638:
1269:
776:
A ranked list of important factors. That is, least squares estimated factor effects ordered from largest in magnitude (most significant) to smallest in magnitude (least significant).
860:
676:
1642:
where the sum has been rearranged to have all the positive terms grouped together and the negatives together for ease of viewing. In Yates' order, the sum is written as
806:
311:
284:
257:
230:
203:
176:
149:
122:
719:
699:
721:, and so on. The signs in each column then represent the signs each response variable should take in the calculation of the effect estimates for that factor.
1855:
In most cases of least squares fitting, the model coefficients for previously added terms change depending on what was successively added. For example, the
1204:{\displaystyle {\textrm {response}}={\textrm {constant}}+0.5\mathrm {(all\ effect\ estimates\ down\ to\ and\ including\ the\ effect\ of\ interest)} }
590:{\displaystyle a_{0}b_{0}c_{0},a_{1}b_{0}c_{0},a_{0}b_{1}c_{0},a_{1}b_{1}c_{0},a_{0}b_{0}c_{1},a_{1}b_{0}c_{1},a_{0}b_{1}c_{1},a_{1}b_{1}c_{1}}
1840:
only that there are such effects on the response rate for each factor. Statistical significance must be ascertained via other methods such as
886:
The residual standard deviation that results from the model with the single term only. That is, the residual standard deviation from the model
52:
estimates for factor effects for all factors and all relevant interactions. The Yates analysis can be used to answer the following questions:
2187:
962:
The cumulative residual standard deviation that results from the model using the current term plus all terms preceding that term. That is,
740:
A factor identifier (from Yates' order). The specific identifier will vary depending on the program used to generate the Yates analysis.
895:
2148:
2117:
2084:
1974:
1913:
2159:
1261:
where the constant is the overall mean of the response variable. The last cumulative residual standard deviation is for the model
1756:
2018:
1951:
Some analysts may prefer a more graphical presentation of the Yates results. In particular, the following plots may be useful:
1225:
2233:
2065:
2022:
1760:
Table of signs to calculate the effect estimates for a 3-level, 2-factor factorial design. Adapted from Berger et al., ch. 9
2037:
38:
2044:
1932:
1926:
1647:
1539:
2011:
1415:{\displaystyle {\textrm {response}}={\textrm {constant}}+0.5\mathrm {(all\ factor\ and\ interaction\ estimates)} }
33:
factors are scaled so that the low level is assigned a value of -1 and the high level is assigned a value of +1.
2051:
1907:
808:
design, k columns will be required, and the last column is the column used to calculate the effect estimates.
1895:
2033:
725:
825:
604:
63:
The mathematical details of the Yates analysis are given in chapter 10 of Box, Hunter, and Hunter (1978).
1534:
The total estimate is the sum of these four terms divided by four. In other words, the estimate of A is
25:
1989:
75:
1841:
59:
What is the goodness-of-fit (as measured by the residual standard deviation) for the various models?
67:
2218:
86:
Before performing a Yates analysis, the data should be arranged in "Yates' order". That is, given
1919:
1901:
879:
1984:
2183:
2144:
2113:
1870:
serves as the least squares coefficient estimates for progressively more complicated models.
2175:
2058:
29:
784:
2108:
Statistics for
Experimenters: An Introduction to Design, Data Analysis, and Model Building
2164:(Technical Communication), vol. 35, Harpenden, England: Commonwealth Bureau of Soils
1886:
We want the model to be parsimonious. That is, the model should be as simple as possible.
290:
263:
236:
209:
182:
155:
128:
101:
724:
Determining the Yates' order for fractional factorial designs requires knowledge of the
704:
684:
2227:
2106:
1979:
71:
49:
2143:(Ph.D. thesis), Dept. CS Ser. Pub. A, vol. A-2004-1, University of Helsinki,
2179:
2000:
1939:
45:
2170:
Berger, Paul D.; Maurer, Robert E.; Celli, Giovana B. (30 November 2017). "9".
2138:
48:, a Yates analysis exploits the special structure of these designs to generate
17:
2131:, The Art of Computer Programming, vol. 2 (3rd ed.), Addison-Wesley
1956:
741:
813:
816:
for the individual factor effect estimates. The t-value is computed as
1943:
That is, the model should be validated by analyzing the residuals.
1755:
935:{\displaystyle {\textrm {response}}={\textrm {constant}}+0.5X_{i}}
1427:
This last model will have a residual standard deviation of zero.
1994:
66:
The Yates analysis is typically complemented by a number of
1847:
Further reading can be found in Berger et al., chapter 9.
1249:{\displaystyle {\textrm {response}}={\textrm {constant}}}
2140:
Sum-Product
Algorithms for the Analysis of Genetic Risks
1879:
model. This requires balancing the following two goals.
1862:
coefficient might change depending on whether or not an
2207:
744:, for example, uses the following for a 3-factor model.
1650:
1542:
1272:
1228:
974:
898:
828:
787:
707:
687:
607:
325:
293:
266:
239:
212:
185:
158:
131:
104:
2104:
Box, G. E. P.; Hunter, W. G.; Hunter, J. S. (1978).
2025:. Unsourced material may be challenged and removed.
1883:
We want the model to include all important factors.
2105:
1743:
1632:
1414:
1248:
1203:
934:
854:
800:
713:
693:
670:
589:
305:
278:
251:
224:
197:
170:
143:
116:
736:A Yates analysis generates the following output.
24:is an approach to analyzing data obtained from a
2161:The design and analysis of factorial experiments
1744:{\displaystyle E_{a}=(-1+a-b+ab-c+ac-bc+abc)/4}
2208:National Institute of Standards and Technology
1633:{\displaystyle E_{a}=(a+ab+ac+abc-1-b-c-bc)/4}
8:
78:("DOE" stands for "design of experiments").
1964:Cumulative residual standard deviation plot
1527:ac – c, estimate of A with B low and C high
1524:ab – b, estimate of A with B high and C low
1769:Effect estimate for treatment combination
766:23 = interaction of factor 2 and factor 3
763:13 = interaction of factor 1 and factor 3
760:12 = interaction of factor 1 and factor 2
2085:Learn how and when to remove this message
1733:
1655:
1649:
1622:
1547:
1541:
1530:abc – bc, estimate of A with B and C high
1296:
1284:
1283:
1274:
1273:
1271:
1240:
1239:
1230:
1229:
1227:
998:
986:
985:
976:
975:
973:
926:
910:
909:
900:
899:
897:
844:
835:
827:
792:
786:
769:123 = interaction of factors 1, 2, and 3
706:
686:
606:
581:
571:
561:
548:
538:
528:
515:
505:
495:
482:
472:
462:
449:
439:
429:
416:
406:
396:
383:
373:
363:
350:
340:
330:
324:
292:
265:
238:
211:
184:
157:
130:
103:
1767:
1439:Response rate for treatment combination
1437:
1851:Parameter estimates as terms are added
7:
2023:adding citations to reliable sources
1521:a –1, estimate of A with B and C low
855:{\displaystyle t={\frac {e}{s_{e}}}}
728:of the fractional factorial design.
671:{\displaystyle 1,a,b,ab,c,ac,bc,abc}
2172:Introduction to Experimental Design
871:is the estimated factor effect and
56:What is the ranked list of factors?
2174:. SpringerLink. pp. 295–342.
1405:
1402:
1399:
1396:
1393:
1390:
1387:
1384:
1381:
1375:
1372:
1369:
1366:
1363:
1360:
1357:
1354:
1351:
1348:
1345:
1339:
1336:
1333:
1327:
1324:
1321:
1318:
1315:
1312:
1306:
1303:
1300:
1194:
1191:
1188:
1185:
1182:
1179:
1176:
1173:
1167:
1164:
1158:
1155:
1152:
1149:
1146:
1143:
1137:
1134:
1131:
1125:
1122:
1119:
1116:
1113:
1110:
1107:
1104:
1101:
1095:
1092:
1089:
1083:
1080:
1074:
1071:
1068:
1065:
1059:
1056:
1053:
1050:
1047:
1044:
1041:
1038:
1035:
1029:
1026:
1023:
1020:
1017:
1014:
1008:
1005:
1002:
599:which in modern notation becomes:
14:
1975:Multi-factor analysis of variance
1938:The first four criteria focus on
2202: This article incorporates
2197:
1999:
882:of the estimated factor effect.
2010:needs additional citations for
1874:Model selection and validation
1730:
1664:
1619:
1556:
1408:
1297:
1197:
999:
958:factor or interaction effect.
1:
1961:Ordered absolute effects plot
2137:Koivisto, Mikko (Jan 2004),
2127:Knuth, Donald Ervin (1997),
1931:Statistical significance of
1842:analysis of variance (ANOVA)
39:fractional factorial designs
2180:10.1007/978-3-319-64583-4_1
2154:. Here: p. 45, 96–103.
1933:residual standard deviation
1927:residual standard deviation
2250:
1925:Practical significance of
2129:Seminumerical Algorithms
1908:Statistical significance
701:, the second row is for
2112:. John Wiley and Sons.
954:is the estimate of the
2204:public domain material
2166:. Here: p. 66-67.
1947:Graphical presentation
1896:Practical significance
1774:Treatmemt combination
1761:
1745:
1634:
1444:Treatmemt combination
1416:
1250:
1205:
936:
856:
802:
715:
695:
672:
591:
307:
280:
253:
226:
199:
172:
145:
118:
2234:Design of experiments
1759:
1746:
1635:
1417:
1251:
1206:
937:
857:
803:
801:{\displaystyle 2^{k}}
726:confounding structure
716:
696:
673:
592:
308:
281:
254:
227:
200:
173:
146:
119:
2133:. Here: sect. 4.3.4.
2019:improve this article
1648:
1540:
1270:
1226:
972:
896:
826:
785:
705:
685:
605:
323:
291:
264:
237:
210:
183:
156:
129:
102:
81:
68:graphical techniques
1770:
1440:
306:{\displaystyle +++}
279:{\displaystyle -++}
252:{\displaystyle +-+}
225:{\displaystyle --+}
198:{\displaystyle ++-}
171:{\displaystyle -+-}
144:{\displaystyle +--}
117:{\displaystyle ---}
26:designed experiment
2158:Yates, F. (1937),
1969:Related Techniques
1902:Order of magnitude
1768:
1762:
1741:
1630:
1438:
1412:
1246:
1201:
932:
880:standard deviation
852:
798:
711:
691:
668:
587:
303:
276:
249:
222:
195:
168:
141:
114:
2189:978-3-319-64583-4
2095:
2094:
2087:
2069:
1914:Probability plots
1837:
1836:
1515:
1514:
1380:
1344:
1332:
1311:
1287:
1277:
1243:
1233:
1172:
1163:
1142:
1130:
1100:
1088:
1079:
1064:
1034:
1013:
989:
979:
913:
903:
850:
714:{\displaystyle a}
694:{\displaystyle 1}
2241:
2201:
2200:
2193:
2165:
2153:
2132:
2123:
2111:
2090:
2083:
2079:
2076:
2070:
2068:
2034:"Yates analysis"
2027:
2003:
1995:
1990:DOE contour plot
1777:Effect estimate
1771:
1750:
1748:
1747:
1742:
1737:
1660:
1659:
1639:
1637:
1636:
1631:
1626:
1552:
1551:
1441:
1421:
1419:
1418:
1413:
1411:
1378:
1342:
1330:
1309:
1289:
1288:
1285:
1279:
1278:
1275:
1255:
1253:
1252:
1247:
1245:
1244:
1241:
1235:
1234:
1231:
1210:
1208:
1207:
1202:
1200:
1170:
1161:
1140:
1128:
1098:
1086:
1077:
1062:
1032:
1011:
991:
990:
987:
981:
980:
977:
941:
939:
938:
933:
931:
930:
915:
914:
911:
905:
904:
901:
861:
859:
858:
853:
851:
849:
848:
836:
807:
805:
804:
799:
797:
796:
720:
718:
717:
712:
700:
698:
697:
692:
677:
675:
674:
669:
596:
594:
593:
588:
586:
585:
576:
575:
566:
565:
553:
552:
543:
542:
533:
532:
520:
519:
510:
509:
500:
499:
487:
486:
477:
476:
467:
466:
454:
453:
444:
443:
434:
433:
421:
420:
411:
410:
401:
400:
388:
387:
378:
377:
368:
367:
355:
354:
345:
344:
335:
334:
312:
310:
309:
304:
285:
283:
282:
277:
258:
256:
255:
250:
231:
229:
228:
223:
204:
202:
201:
196:
177:
175:
174:
169:
150:
148:
147:
142:
123:
121:
120:
115:
76:DOE contour plot
30:factorial design
2249:
2248:
2244:
2243:
2242:
2240:
2239:
2238:
2224:
2223:
2215:
2198:
2190:
2169:
2157:
2151:
2136:
2126:
2120:
2103:
2100:
2091:
2080:
2074:
2071:
2028:
2026:
2016:
2004:
1971:
1949:
1876:
1868:
1861:
1853:
1651:
1646:
1645:
1543:
1538:
1537:
1433:
1268:
1267:
1224:
1223:
970:
969:
952:
922:
894:
893:
876:
840:
824:
823:
788:
783:
782:
734:
703:
702:
683:
682:
603:
602:
577:
567:
557:
544:
534:
524:
511:
501:
491:
478:
468:
458:
445:
435:
425:
412:
402:
392:
379:
369:
359:
346:
336:
326:
321:
320:
289:
288:
262:
261:
235:
234:
208:
207:
181:
180:
154:
153:
127:
126:
100:
99:
84:
12:
11:
5:
2247:
2245:
2237:
2236:
2226:
2225:
2222:
2221:
2219:Yates Analysis
2214:
2213:External links
2211:
2195:
2194:
2188:
2167:
2155:
2149:
2134:
2124:
2118:
2099:
2096:
2093:
2092:
2007:
2005:
1998:
1993:
1992:
1987:
1982:
1977:
1970:
1967:
1966:
1965:
1962:
1959:
1948:
1945:
1936:
1935:
1929:
1923:
1917:
1911:
1905:
1899:
1888:
1887:
1884:
1875:
1872:
1866:
1859:
1852:
1849:
1835:
1834:
1831:
1827:
1826:
1823:
1819:
1818:
1815:
1811:
1810:
1807:
1803:
1802:
1799:
1795:
1794:
1791:
1787:
1786:
1783:
1779:
1778:
1775:
1740:
1736:
1732:
1729:
1726:
1723:
1720:
1717:
1714:
1711:
1708:
1705:
1702:
1699:
1696:
1693:
1690:
1687:
1684:
1681:
1678:
1675:
1672:
1669:
1666:
1663:
1658:
1654:
1629:
1625:
1621:
1618:
1615:
1612:
1609:
1606:
1603:
1600:
1597:
1594:
1591:
1588:
1585:
1582:
1579:
1576:
1573:
1570:
1567:
1564:
1561:
1558:
1555:
1550:
1546:
1532:
1531:
1528:
1525:
1522:
1513:
1512:
1509:
1505:
1504:
1501:
1497:
1496:
1493:
1489:
1488:
1485:
1481:
1480:
1477:
1473:
1472:
1469:
1465:
1464:
1461:
1457:
1456:
1453:
1449:
1448:
1447:Response rate
1445:
1432:
1429:
1425:
1424:
1423:
1422:
1410:
1407:
1404:
1401:
1398:
1395:
1392:
1389:
1386:
1383:
1377:
1374:
1371:
1368:
1365:
1362:
1359:
1356:
1353:
1350:
1347:
1341:
1338:
1335:
1329:
1326:
1323:
1320:
1317:
1314:
1308:
1305:
1302:
1299:
1295:
1292:
1282:
1259:
1258:
1257:
1256:
1238:
1214:
1213:
1212:
1211:
1199:
1196:
1193:
1190:
1187:
1184:
1181:
1178:
1175:
1169:
1166:
1160:
1157:
1154:
1151:
1148:
1145:
1139:
1136:
1133:
1127:
1124:
1121:
1118:
1115:
1112:
1109:
1106:
1103:
1097:
1094:
1091:
1085:
1082:
1076:
1073:
1070:
1067:
1061:
1058:
1055:
1052:
1049:
1046:
1043:
1040:
1037:
1031:
1028:
1025:
1022:
1019:
1016:
1010:
1007:
1004:
1001:
997:
994:
984:
964:
963:
950:
945:
944:
943:
942:
929:
925:
921:
918:
908:
888:
887:
874:
865:
864:
863:
862:
847:
843:
839:
834:
831:
818:
817:
795:
791:
778:
777:
773:
772:
771:
770:
767:
764:
761:
758:
755:
752:
746:
745:
733:
730:
710:
690:
667:
664:
661:
658:
655:
652:
649:
646:
643:
640:
637:
634:
631:
628:
625:
622:
619:
616:
613:
610:
584:
580:
574:
570:
564:
560:
556:
551:
547:
541:
537:
531:
527:
523:
518:
514:
508:
504:
498:
494:
490:
485:
481:
475:
471:
465:
461:
457:
452:
448:
442:
438:
432:
428:
424:
419:
415:
409:
405:
399:
395:
391:
386:
382:
376:
372:
366:
362:
358:
353:
349:
343:
339:
333:
329:
314:
313:
302:
299:
296:
286:
275:
272:
269:
259:
248:
245:
242:
232:
221:
218:
215:
205:
194:
191:
188:
178:
167:
164:
161:
151:
140:
137:
134:
124:
113:
110:
107:
83:
80:
61:
60:
57:
44:Formalized by
22:Yates analysis
13:
10:
9:
6:
4:
3:
2:
2246:
2235:
2232:
2231:
2229:
2220:
2217:
2216:
2212:
2210:
2209:
2206:from the
2205:
2191:
2185:
2181:
2177:
2173:
2168:
2163:
2162:
2156:
2152:
2150:952-10-1578-0
2146:
2142:
2141:
2135:
2130:
2125:
2121:
2119:0-471-09315-7
2115:
2110:
2109:
2102:
2101:
2097:
2089:
2086:
2078:
2067:
2064:
2060:
2057:
2053:
2050:
2046:
2043:
2039:
2036: –
2035:
2031:
2030:Find sources:
2024:
2020:
2014:
2013:
2008:This article
2006:
2002:
1997:
1996:
1991:
1988:
1986:
1983:
1981:
1980:DOE mean plot
1978:
1976:
1973:
1972:
1968:
1963:
1960:
1958:
1954:
1953:
1952:
1946:
1944:
1941:
1934:
1930:
1928:
1924:
1921:
1918:
1915:
1912:
1909:
1906:
1903:
1900:
1897:
1894:
1893:
1892:
1885:
1882:
1881:
1880:
1873:
1871:
1865:
1858:
1850:
1848:
1845:
1843:
1832:
1829:
1828:
1824:
1821:
1820:
1816:
1813:
1812:
1808:
1805:
1804:
1800:
1797:
1796:
1792:
1789:
1788:
1784:
1781:
1780:
1776:
1773:
1772:
1766:
1758:
1754:
1751:
1738:
1734:
1727:
1724:
1721:
1718:
1715:
1712:
1709:
1706:
1703:
1700:
1697:
1694:
1691:
1688:
1685:
1682:
1679:
1676:
1673:
1670:
1667:
1661:
1656:
1652:
1643:
1640:
1627:
1623:
1616:
1613:
1610:
1607:
1604:
1601:
1598:
1595:
1592:
1589:
1586:
1583:
1580:
1577:
1574:
1571:
1568:
1565:
1562:
1559:
1553:
1548:
1544:
1535:
1529:
1526:
1523:
1520:
1519:
1518:
1510:
1507:
1506:
1502:
1499:
1498:
1494:
1491:
1490:
1486:
1483:
1482:
1478:
1475:
1474:
1470:
1467:
1466:
1462:
1459:
1458:
1454:
1451:
1450:
1446:
1443:
1442:
1436:
1430:
1428:
1293:
1290:
1280:
1266:
1265:
1264:
1263:
1262:
1236:
1222:
1221:
1220:
1219:
1218:
995:
992:
982:
968:
967:
966:
965:
961:
960:
959:
957:
953:
927:
923:
919:
916:
906:
892:
891:
890:
889:
885:
884:
883:
881:
877:
870:
845:
841:
837:
832:
829:
822:
821:
820:
819:
815:
811:
810:
809:
793:
789:
775:
774:
768:
765:
762:
759:
757:3 = factor 3
756:
754:2 = factor 2
753:
751:1 = factor 1
750:
749:
748:
747:
743:
739:
738:
737:
731:
729:
727:
722:
708:
688:
678:
665:
662:
659:
656:
653:
650:
647:
644:
641:
638:
635:
632:
629:
626:
623:
620:
617:
614:
611:
608:
600:
597:
582:
578:
572:
568:
562:
558:
554:
549:
545:
539:
535:
529:
525:
521:
516:
512:
506:
502:
496:
492:
488:
483:
479:
473:
469:
463:
459:
455:
450:
446:
440:
436:
430:
426:
422:
417:
413:
407:
403:
397:
393:
389:
384:
380:
374:
370:
364:
360:
356:
351:
347:
341:
337:
331:
327:
318:
300:
297:
294:
287:
273:
270:
267:
260:
246:
243:
240:
233:
219:
216:
213:
206:
192:
189:
186:
179:
165:
162:
159:
152:
138:
135:
132:
125:
111:
108:
105:
98:
97:
96:
93:
90:factors, the
89:
79:
77:
73:
72:DOE mean plot
69:
64:
58:
55:
54:
53:
51:
50:least squares
47:
42:
40:
34:
31:
27:
23:
19:
2196:
2171:
2160:
2139:
2128:
2107:
2081:
2072:
2062:
2055:
2048:
2041:
2029:
2017:Please help
2012:verification
2009:
1950:
1940:effect sizes
1937:
1889:
1877:
1863:
1856:
1854:
1846:
1838:
1763:
1752:
1644:
1641:
1536:
1533:
1516:
1434:
1426:
1260:
1215:
955:
948:
946:
872:
868:
866:
779:
735:
723:
679:
601:
598:
319:
315:
91:
87:
85:
82:Yates' Order
70:such as the
65:
62:
43:
35:
21:
15:
1922:of averages
1920:Youden plot
681:row is for
46:Frank Yates
2098:References
2045:newspapers
1985:Block plot
1916:of effects
1910:of effects
1904:of effects
1898:of effects
28:, where a
18:statistics
2075:June 2012
1957:data plot
1710:−
1695:−
1680:−
1668:−
1611:−
1605:−
1599:−
1593:−
268:−
244:−
217:−
214:−
193:−
166:−
160:−
139:−
136:−
112:−
109:−
106:−
41:article.
2228:Category
1955:Ordered
1833:–0.0050
1801:–0.0060
1793:–0.0485
1286:constant
1276:response
1242:constant
1232:response
988:constant
978:response
912:constant
902:response
742:Dataplot
74:and the
2059:scholar
1825:0.0045
1817:0.0015
1809:0.0060
1785:0.0125
1431:Example
878:is the
814:t-value
2186:
2147:
2116:
2061:
2054:
2047:
2040:
2032:
1511:0.027
1503:0.024
1495:0.082
1487:0.057
1479:0.020
1471:0.010
1463:0.074
1455:0.062
1379:
1343:
1331:
1310:
1171:
1162:
1141:
1129:
1099:
1087:
1078:
1063:
1033:
1012:
947:where
867:where
732:Output
2066:JSTOR
2052:books
2184:ISBN
2145:ISBN
2114:ISBN
2038:news
1830:ABC
1508:abc
20:, a
2176:doi
2021:by
1822:BC
1814:AC
1798:AB
1500:bc
1492:ac
1476:ab
1294:0.5
996:0.5
920:0.5
16:In
2230::
2182:.
1844:.
1806:C
1790:B
1782:A
1484:c
1468:b
1460:a
1452:1
812:A
2192:.
2178::
2122:.
2088:)
2082:(
2077:)
2073:(
2063:·
2056:·
2049:·
2042:·
2015:.
1867:2
1864:X
1860:1
1857:X
1739:4
1735:/
1731:)
1728:c
1725:b
1722:a
1719:+
1716:c
1713:b
1707:c
1704:a
1701:+
1698:c
1692:b
1689:a
1686:+
1683:b
1677:a
1674:+
1671:1
1665:(
1662:=
1657:a
1653:E
1628:4
1624:/
1620:)
1617:c
1614:b
1608:c
1602:b
1596:1
1590:c
1587:b
1584:a
1581:+
1578:c
1575:a
1572:+
1569:b
1566:a
1563:+
1560:a
1557:(
1554:=
1549:a
1545:E
1409:)
1406:s
1403:e
1400:t
1397:a
1394:m
1391:i
1388:t
1385:s
1382:e
1376:n
1373:o
1370:i
1367:t
1364:c
1361:a
1358:r
1355:e
1352:t
1349:n
1346:i
1340:d
1337:n
1334:a
1328:r
1325:o
1322:t
1319:c
1316:a
1313:f
1307:l
1304:l
1301:a
1298:(
1291:+
1281:=
1237:=
1198:)
1195:t
1192:s
1189:e
1186:r
1183:e
1180:t
1177:n
1174:i
1168:f
1165:o
1159:t
1156:c
1153:e
1150:f
1147:f
1144:e
1138:e
1135:h
1132:t
1126:g
1123:n
1120:i
1117:d
1114:u
1111:l
1108:c
1105:n
1102:i
1096:d
1093:n
1090:a
1084:o
1081:t
1075:n
1072:w
1069:o
1066:d
1060:s
1057:e
1054:t
1051:a
1048:m
1045:i
1042:t
1039:s
1036:e
1030:t
1027:c
1024:e
1021:f
1018:f
1015:e
1009:l
1006:l
1003:a
1000:(
993:+
983:=
956:i
951:i
949:X
928:i
924:X
917:+
907:=
875:e
873:s
869:e
846:e
842:s
838:e
833:=
830:t
794:k
790:2
709:a
689:1
666:c
663:b
660:a
657:,
654:c
651:b
648:,
645:c
642:a
639:,
636:c
633:,
630:b
627:a
624:,
621:b
618:,
615:a
612:,
609:1
583:1
579:c
573:1
569:b
563:1
559:a
555:,
550:1
546:c
540:1
536:b
530:0
526:a
522:,
517:1
513:c
507:0
503:b
497:1
493:a
489:,
484:1
480:c
474:0
470:b
464:0
460:a
456:,
451:0
447:c
441:1
437:b
431:1
427:a
423:,
418:0
414:c
408:1
404:b
398:0
394:a
390:,
385:0
381:c
375:0
371:b
365:1
361:a
357:,
352:0
348:c
342:0
338:b
332:0
328:a
301:+
298:+
295:+
274:+
271:+
247:+
241:+
220:+
190:+
187:+
163:+
133:+
92:k
88:k
Text is available under the Creative Commons Attribution-ShareAlike License. Additional terms may apply.
