369:
respondents had an internal ranking of all items and just chose the highest/lowest ranked item in a given question. More recent work has suggested that in some contexts this is not the case: a person might (for instance) choose according to traditional economic theory for best (trading across attributes) but choose worst using an elimination by attributes strategy (choosing as worst the item that is simply unacceptable on one attribute). In the presence of such different decision rules it becomes impossible to know how to combine the data: at what point does the person, when moving down the rankings, move from "economic trading" to "elimination by aspects".
243:, Uruguay, Steve and his co-author, Dr. Leopldo Neira, compared BWS results to those obtained by rating scale methods. This paper won Best Methodological Paper at that conference. Later the same year, it was selected as winner of the John and Mary Goodyear Award for Best Paper at all ESOMAR Conferences in 2003 and then it was published as the lead article in "Excellence in International Research 2004," published by ESOMAR. At the 2003 Sawtooth Software Conference, Steve Cohen's paper, "Maximum Difference Scaling: Improved Measures of Importance and Preference for Segmentation," was selected as Best Presentation. Cohen and
195:
mobile (cell) phone, the choices would be the most acceptable and least acceptable features of a given phone. Case 2 has proved to be powerful in eliciting preferences among vulnerable groups, such as the elderly, older carers, and children, who find conventional multi-profile discrete choice experiments difficult. Indeed, the first comparison of Case 2 with a DCE in a single model found that whilst the vast majority of (older) respondents provided usable data from the BWS task, only around one half do so for the DCE.
1010:
164:
same way (by, for instance, asking best first, greying out the chosen option, then asking worst); (2) Enables collection of a full ranking, if repeated BWS questioning is implemented to collect the "inner rankings". In many contexts, BWS for data collection has been regarded merely as a way to obtain such data in order to facilitate data expansion (to estimate conditional logit models with far more choice sets) or to estimate conventional rank ordered logit models.
252:
the properties of BWS estimators. The popularity of the three cases has largely varied by academic discipline, with case 1 proving popular in marketing and food research, case 2 largely being adopted in health, and case 3 being used across a variety of disciplines that already use DCEs. It was partly this lack of understanding in many disciplines that there are actually three cases of BWS that prompted the three main developers to write the textbook.
322:. The Hierarchical Bayes model is beneficial because it allows for borrowing across the data, although since BWS often allows the estimation of individual level models, the benefits of Bayesian models are heavily attenuated. Response time models have recently been shown to replicate the utility estimates of BWS, which represents a major step forward in the validation of stated preferences generally, and BWS preferences specifically.
142:. The maxdiff model has proved to be useful in proving the properties of a number of estimators in BWS. However, its realism as a description of how humans might actually provide best and worst data can be questioned for the following reason. As the number of items increases, the number of possible pairs increases in a multiplicative fashion: n items produces n(n-1) pairs (where best-worst order matters). To assume that respondents
216:(BIBDs). These cause every item to appear the same number of times and also force every item to compete with every other the same number of times. These features are attractive since the respondent is prevented from inferring erroneous information about the items (what items the designer is "really" interested in). They also ensure that there can be no "ties" in importance/salience at the very top or bottom of the scale.
381:
BWS choices. In others, quite often health, there are no revealed preference data and validation appears impossible. More recently attempts have been made to validate SP data using physiological data, such as eye-tracking and response times. Early work suggests that response time models are consistent with results from BWS models in health care but more research is required in other contexts.
256:
case, follow, detailing the intuition and application of each. A chapter bringing together Marley's work proving the properties of the key estimators and laying out some open issues then follows. After laying out open issues for further analysis, nine chapters (three per case – describing applications from a variety of disciplines) then follow.
38:. In general with BWS, survey respondents are shown a subset of items from a master list and are asked to indicate the best and worst items (or most and least important, or most and least appealing, etc.). The task is repeated a number of times, varying the particular subset of items in a systematic way, typically according to a
81:
peer-reviewed articles describing BWS theory, practice, and a number of applications in health, social care, marketing, transport, voting, and environmental economics. However, the method has now become popular in the wider research and practitioner communities, with other researchers exploring its use in areas as diverse as
186:) scale data. It is particularly useful when eliciting the degree of importance or agreement that respondents ascribe from a set of statements and when the researcher wishes to ensure that the items compete with each other (so that respondents cannot easily rate multiple items as being of the same importance).
380:
BWS also suffers from the same disadvantages of all stated preference techniques. It is unknown if the preferences are consistent with choices made in the real world (revealed preferences). In some instances revealed preferences (typically real market decisions) are available, providing a test of the
106:
to describe the method. As Marley and
Louviere note, maxdiff is a long-established academic mathematical theory with very specific assumptions about how people make choices: it assumes that respondents evaluate all possible pairs of items within the displayed set and choose the pair that reflects the
46:
item A over item B is provided by how often item A is chosen over item B in repeated choices. Thus, choice frequencies estimate the utilities on the relevant latent scale. BWS essentially aims to provide more choice information at the lower end of this scale without having to ask additional questions
368:
Best–worst scaling involves the collection of at least two sets of data: at a minimum, first-best and first-worst, and in some cases additional ranks (second best, second worst, etc...) The issue of how to combine these data is pertinent. Early work assumed best was simply the inverse of worst: that
344:
Distributions of "the scores" (calculated as the best frequency minus the worst frequency) for all items which allow the researcher to observe the empirical distribution of estimated utilities. This produces information on how realistic the results from traditional analysis methods assuming standard
281:
Input the data into a statistical software program and analyse. The software will produce utility functions for each of the features. In addition to utility scores, you can also request raw counts which will simply sum the total number of times a product was selected as best and worst. These utility
255:
The book contains an introductory chapter summarising the history of BWS and the three cases, together with why the respondent must think whether (s)he wishes to use it to understand theory (processes) of decision-making and/or merely to collect data in a systematic way. Three chapters, one for each
247:
president Bryan Orme agreed that MaxDiff should be part of the
Sawtooth package and it was introduced later that year. Later in 2004, Cohen and Orme won the David K. Hardin Award from the AMA for their paper which was published in Marketing Research Magazine entitled, "What's your preference? Asking
376:
motivation for BWS but not necessarily for BWS when used as a way to understand process (decision-making). Psychologists in particular would be particularly interested in the different types of decision-making. Marketers, also, might wish to know if a given product had an unacceptable feature. Work
251:
In parallel to this, Emma McIntosh and Jordan
Louviere introduced BWS (case 2) to the health community at the 2002 Health Economists' Study Group conference. This prompted the collaboration with Flynn and ultimately the link-up with Marley, who had begun working with Louviere independently to prove
80:
and
University of South Australia). The book brings together the disparate research from various academic and practical disciplines, in the hope that replication and mistakes in implementation are avoided. The three authors have (individually and together) already published many of the key academic
67:
to axiomatise utility theory. Marley had encountered problems axiomatising certain types of ranking data and speculated in the discussion of his thesis that examination of the "inferior" and "superior" items in a list might be a fruitful topic for future research. The idea then languished for three
339:
Respondents find these ratings scales very easy but they do tend to deliver results which indicate that everything is "quite important", making the data not especially actionable. BWS on the other hand forces respondents to make choices between options, while still delivering rankings showing the
163:
The second use of BWS is as a method of data collection (rather than as a theory of how humans produce a best and a worst item). BWS can, particularly in the age of web-based surveys, be used to collect data in a systematic way that (1) forces all respondents to provide best and worst data in the
146:
evaluate all possible pairs is a strong assumption and in 14 years of presentations, the three co-authors have virtually never found a course or conference participant who admitted to using this method to decide their best and worst choices. Virtually all admitted to using sequential models (best
331:
BWS questionnaires are relatively easy for most respondents to understand. Furthermore, humans are much better at judging items at extremes than in discriminating among items of middling importance or preference. And since the responses involve choices of items rather than expressing strength of
194:
Case 2 has predominated in health and the items are the attribute levels describing a single profile of the type familiar to choice modellers. Instead of making choices between profiles, the respondent must make best and worst (most and least) choices within a profile. Thus, for the example of a
348:
Data that allow investigation of the decision rule (functional form of the utility function) at various ranking depths (most simply, the "best decision rule vs the worst decision rule"). Emerging research is suggesting that in some contexts respondents do not use the same rule, which calls into
150:
Early work (including that of
Louviere himself) did use the term maxdiff to refer to BWS, but with the recruitment of Marley to the team developing the method, correct academic terminology has been disseminated throughout Europe and Asia-Pacific (if not North America, which continues to use the
172:
The renaming of the method, to make clear that maxdiff scaling is BWS but BWS is not necessarily maxdiff, was decided by
Louviere in consultation with his two key contributors (Flynn and Marley) in preparation for the book, and was presented in an article by Flynn. That paper also took the
203:
Case 3 is perhaps the most familiar to choice modellers, being merely an extension of a discrete choice model: the number of profiles must be three or more, and instead of simply choosing the one the respondent would purchase, (s)he chooses the best and worst profile.
173:
opportunity to make clear that there are, in fact, three types ("cases") of BWS: Case 1 (the "object case"), Case 2 (the "profile case") and Case 3 (the "multi-profile case"). These three cases differ largely in the complexity of the choice items on offer.
1385:
Coast, Joanna; Al-Janabi, Hareth; Sutton, Eileen J.; Horrocks, Susan A.; Vosper, A. Jane; Swancutt, Dawn R.; Flynn, Terry N. (2012-06-01). "Using qualitative methods for attribute development for discrete choice experiments: issues and recommendations".
306:
In many cases, particularly cases 1 and 2, simple observation and plotting of choice frequencies should actually be the first step, as it is very useful in identifying preference heterogeneity and respondents using decision-rules based on a single
355:
More data, that allow greater insights into choices, for a given number of choice sets. The same information could be obtained by simply presenting more choice sets but this runs the risk that respondents become bored and disengage with the
271:
Construct a statistical design that indicates what items are to be presented in each set of items ("choice set") – designs may come from publicly available catalogues, be constructed by hand, or produced from commercially available
101:
There are two different purposes of BWS – as a method of data collection, and/or as a theory of how people make choices when confronted with three or more items. This distinction is crucial, given the continuing misuse of the term
303:, although the two terms are now used interchangeably). The multinomial logit (MNL) model is often the first stage in analysis and provides a measure of average utility for the attribute levels or objects (depending on the Case).
124:
The only paired comparison that cannot be inferred is B vs. C. In a choice among five items, MaxDiff questioning informs on seven of ten implied paired comparisons. Thus BWS may be thought of as a variation of the method of
181:
Case 1 presents items that may be attitudinal statements, policy goals, marketing slogans or any type of item that has no attribute and level structure. It is primarily used to avoid scale biases known to affect rating
115:
Consider a set in which a respondent evaluates four items: A, B, C and D. If the respondent says that A is best and D is worst, these two responses inform us about five of six possible implied paired comparisons:
222:
Case 3 BWS studies may use any of the types of design typically used for a DCE, with the proviso that the number of profiles (alternatives) in a choice set must be three or more for the BWS task to make sense.
702:
Scarpa, Riccardo; Notaro, Sandra; Louviere, Jordan; Raffaelli, Roberta (2011-06-19). "Exploring Scale
Effects of Best/Worst Rank Ordered Choice Data to Estimate Benefits of Tourism in Alpine Grazing Commons".
1333:
Ratcliffe, Professor Julie; Flynn, Terry; Terlich, Frances; Stevens, Katherine; Brazier, John; Sawyer, Michael (2012-12-23). "Developing
Adolescent-Specific Health State Values for Economic Evaluation".
42:. Analysis is typically conducted, as with DCEs more generally, assuming that respondents makes choices according to a random utility model (RUM). RUMs assume that an estimate of how much a respondent
278:
Obtain response data where respondents choose the best and worst from each task; repeat best-worst (to obtain second best, second worst, etc.) may be conducted if the analyst wishes for more data.
1210:
N. Flynn, Terry; J. Peters, Tim; Coast, Joanna (2013-03-01). "Quantifying response shift or adaptation effects in quality of life by synthesising best-worst scaling and discrete choice data".
404:
68:
decades until the first working papers and publications appeared in the early 1990s. The definitive textbook describing the theory, methods and applications was published in
September 2015 (
1072:
1237:
Coast, Joanna; Flynn, Terry N.; Natarajan, Lucy; Sproston, Kerry; Lewis, Jane; Louviere, Jordan J.; Peters, Tim J. (2008-09-01). "Valuing the ICECAP capability index for older people".
136:
model), they might choose the best from n items, the worst from the remaining n-1, or vice versa. Or indeed they may use another method entirely. Thus it should be clear that
232:
873:
Mueller Loose, Simone; Lockshin, Larry (2013-03-01). "Testing the robustness of best worst scaling for cross-national segmentation with different numbers of choice sets".
282:
functions indicate the perceived value of the product on an individual level and how sensitive consumer perceptions and preferences are to changes in product features.
537:
Flynn, Terry N.; Louviere, Jordan J.; Peters, Tim J.; Coast, Joanna (2007-01-01). "Best–worst scaling: What it can do for health care research and how to do it".
345:
continuous distributions are likely to be. Consumers tend to form distinct groups with often very different preferences, giving rise to multi-modal distributions.
352:
Estimation of attribute impact, a measure of the overall impact of an attribute upon choices that is not available from conventional discrete choice models.
239:: Some new tools to correct old problems." This paper was nominated for Best paper at that conference. In 2003 at the ESOMAR Latin America Conference in
659:
García-Lapresta, José Luis; Marley, A. a. J.; Martínez-Panero, Miguel (2009-09-12). "Characterizing best–worst voting systems in the scoring context".
86:
610:
151:
maxdiff term). Indeed, it is an open question whether major software manufacturers of discrete choice maxdiff routines actually implement maxdiff
463:
Marley, A. A. J.; Flynn, Terry N.; Louviere, J. J. (2008-10-01). "Probabilistic models of set-dependent and attribute-level best–worst choice".
1070:
Flynn, Terry N. (2010-06-01). "Valuing citizen and patient preferences in health: recent developments in three types of best–worst scaling".
902:"Eliciting preferences for priority setting in genetic testing: a pilot study comparing best-worst scaling and discrete-choice experiments"
1123:
Baumgartner, Hans; Steenkamp, Jan-Benedict E.M. (2001-05-01). "Response Styles in
Marketing Research: A Cross-National Investigation".
1029:"Modeling the choices of individual decision-makers by combining efficient choice experiment designs with extra preference information"
219:
Case 2 BWS studies can use Orthogonal Main Effects Plans (OMEPs) or efficient designs, although the former has predominated to date.
377:
is ongoing to investigate when different decision rules arise, and whether/how data from such different sources may be combined.
213:
126:
816:
Ross, Melissa; Bridges, John F. P.; Ng, Xinyi; Wagner, Lauren D.; Frosch, Emily; Reeves, Gloria; dosReis, Susan (2014-11-17).
609:
Potoglou, Dimitris; Burge, Peter; Flynn, Terry; Netten, Ann; Malley, Juliette; Forder, Julien; Brazier, John E. (2011-05-01).
1282:
Al-Janabi, Hareth; Flynn, Terry N.; Coast, Joanna (2011-05-01). "Estimation of a Preference-Based Carer Experience Scale".
959:"Estimating preferences for a dermatology consultation using Best-Worst Scaling: Comparison of various methods of analysis"
73:
1432:
Hawkins, Guy E.; Marley, A.a.j.; Heathcote, Andrew; Flynn, Terry N.; Louviere, Jordan J.; Brown, Scott D. (2014-05-01).
504:
132:
Yet respondents can produce best-worst data in any of a number of ways. Instead of evaluating all possible pairs (the
433:
Marley, A. A. J.; Louviere, J. J. (2005-12-01). "Some probabilistic models of best, worst, and best–worst choices".
69:
1528:
34:(or discrete choice experiment – "DCE") and were invented by Jordan Louviere in 1987 while on the faculty at the
319:
275:
Use the design to construct the choice sets, which contain the actual relevant items (textually or visually).
296:
60:
55:
Louviere attributes the idea to the early work of Anthony A. J. Marley in his PhD thesis, who together with
1009:
437:. Special Issue Honoring Jean-Claude Falmagne: Part 1Special Issue Honoring Jean-Claude Falmagne: Part 1.
77:
43:
39:
35:
818:"A Best-Worst Scaling Experiment to Prioritize Caregiver Concerns About ADHD Medication for Children"
268:
Conduct proper qualitative or other research to properly identify and describe all items of interest.
611:"Best–worst scaling vs. discrete choice experiments: An empirical comparison using social care data"
236:
82:
1481:
1367:
1315:
1187:
1148:
1105:
763:
684:
641:
311:
575:
Louviere, Jordan; Lings, Ian; Islam, Towhidul; Gudergan, Siegfried; Flynn, Terry (2013-09-01).
1473:
1465:
1411:
1403:
1359:
1351:
1307:
1299:
1264:
1140:
1097:
1089:
998:
980:
939:
921:
855:
837:
798:
755:
720:
676:
633:
554:
373:
300:
244:
738:
Huybers, Twan (2014-05-19). "Student evaluation of teaching: the use of best–worst scaling".
1455:
1445:
1395:
1343:
1291:
1254:
1246:
1219:
1179:
1132:
1081:
1050:
1040:
988:
970:
929:
913:
882:
845:
829:
790:
747:
712:
668:
625:
591:
546:
516:
480:
472:
442:
31:
315:
90:
577:"An introduction to the application of (case 1) best–worst scaling in marketing research"
1024:
993:
958:
934:
901:
900:
Severin, Franziska; Schmidtke, Jörg; Mühlbacher, Axel; Rogowski, Wolf H. (2013-11-01).
850:
817:
240:
155:
in estimating parameters, despite this continuing advertising of maxdiff capabilities.
56:
1045:
1028:
231:
Steve Cohen introduced BWS to the marketing research world in a paper presented at an
1522:
1347:
767:
333:
64:
1485:
1371:
1319:
1250:
1152:
1109:
1027:; Burgess, Leonie; Wasi, Nada; Islam, Towhidul; Marley, Anthony A. J. (2008-01-01).
688:
645:
629:
89:
medication, the importance of environmental sustainability, and priority-setting in
1434:"Integrating Cognitive Process and Descriptive Models of Attitudes and Preferences"
886:
595:
550:
291:
Estimation of the utility function is performed using any of a variety of methods.
183:
957:
Flynn, Terry N.; Louviere, Jordan J.; Peters, Tim J.; Coast, Joanna (2008-11-18).
751:
505:"Models of best–worst choice and ranking among multiattribute options (profiles)"
359:
Quantifying the phenomena of response shift and adaptation to poor health states.
1241:. Part Special Issue: Ethics and the ethnography of medical research in Africa.
1136:
1499:
1223:
1167:
576:
1191:
833:
794:
781:
Cohen, Eli (2009-03-20). "Applying best‐worst scaling to wine marketingnull".
672:
520:
476:
446:
1469:
1407:
1355:
1303:
1295:
1144:
1093:
984:
925:
841:
802:
759:
724:
680:
349:
question the use of estimation methods such as the rank ordered logit model.
1477:
1460:
1415:
1363:
1311:
1268:
1101:
1002:
975:
943:
859:
637:
558:
248:
survey respondents about their preferences creates new scaling decisions."
716:
917:
1450:
1433:
310:
Several algorithms could be used in this estimation process, including
133:
103:
17:
1259:
1168:"Assessing Measurement Invariance in Cross‐National Consumer Research"
1085:
1055:
485:
1399:
1183:
340:
relative importance of the items being rated. It also produces:
85:
of teaching, marketing of wine, quantification of concerns over
1166:
Steenkamp, Jan‐Benedict E. M.; Baumgartner, Hans (1998-06-01).
1500:"The best of times and the worst of times are interchangeable"
59:
in the 1960s produced much of the ground-breaking research in
76:), Terry N Flynn (TF Choices Ltd.) and Anthony A. J Marley (
1073:
Expert Review of Pharmacoeconomics & Outcomes Research
264:
The basic steps in conducting all types of BWS study are:
295:
multinomial discrete choice analysis, in particular
235:
Conference in Barcelona in 2002 entitled, "Renewing
111:As a theory of process (theory of decision-making)
120:A > B, A > C, A > D, B > D, C > D
107:maximum difference in preference or importance.
783:International Journal of Wine Business Research
740:Assessment & Evaluation in Higher Education
584:International Journal of Research in Marketing
8:
877:. Ninth Pangborn Sensory Science Symposium.
503:Marley, A. A. J.; Pihlens, D. (2012-02-01).
705:American Journal of Agricultural Economics
1459:
1449:
1258:
1054:
1044:
992:
974:
933:
849:
484:
47:that are specific to lower ranked items.
332:preference, there is no opportunity for
570:
568:
389:
532:
530:
372:This presents a clear problem for the
1427:
1425:
1205:
1203:
1201:
7:
498:
496:
458:
456:
428:
426:
424:
399:
397:
395:
393:
906:European Journal of Human Genetics
509:Journal of Mathematical Psychology
465:Journal of Mathematical Psychology
435:Journal of Mathematical Psychology
14:
214:balanced incomplete block designs
212:Case 1 BWS studies typically use
199:Case 3 (the "multi-profile case")
1348:10.2165/11597900-000000000-00000
1008:
963:BMC Medical Research Methodology
147:then worst or worst then best).
1251:10.1016/j.socscimed.2008.05.015
630:10.1016/j.socscimed.2011.03.027
887:10.1016/j.foodqual.2012.02.002
596:10.1016/j.ijresmar.2012.10.002
551:10.1016/j.jhealeco.2006.04.002
159:As a method of data collection
1:
1239:Social Science & Medicine
1125:Journal of Marketing Research
1046:10.1016/S1755-5345(13)70025-3
618:Social Science & Medicine
74:University of South Australia
1172:Journal of Consumer Research
752:10.1080/02602938.2013.851782
1212:Journal of Choice Modelling
1137:10.1509/jmkr.38.2.143.18840
1033:Journal of Choice Modelling
875:Food Quality and Preference
539:Journal of Health Economics
190:Case 2 (the "profile case")
1545:
1224:10.1016/j.jocm.2013.04.004
409:Cambridge University Press
177:Case 1 (the "object case")
139:maxdiff is a subset of BWS
70:Cambridge University Press
15:
834:10.1176/appi.ps.201300525
795:10.1108/17511060910948008
673:10.1007/s00355-009-0417-1
661:Social Choice and Welfare
521:10.1016/j.jmp.2011.09.001
477:10.1016/j.jmp.2008.02.002
447:10.1016/j.jmp.2005.05.003
1296:10.1177/0272989X10381280
320:hierarchical Bayes model
16:Not to be confused with
1284:Medical Decision Making
299:(strictly speaking the
61:mathematical psychology
976:10.1186/1471-2288-8-76
78:University of Victoria
72:) by Jordan Louviere (
1023:Louviere, Jordan J.;
36:University of Alberta
30:) techniques involve
918:10.1038/ejhg.2013.36
822:Psychiatric Services
405:"Best-Worst Scaling"
717:10.1093/ajae/aaq174
237:market segmentation
208:Designs for studies
1451:10.1111/cogs.12094
312:maximum likelihood
260:Conducting a study
127:Paired Comparisons
83:student evaluation
40:statistical design
24:Best–worst scaling
1438:Cognitive Science
1336:PharmacoEconomics
1086:10.1586/erp.10.29
912:(11): 1202–1208.
624:(10): 1717–1727.
374:data augmentation
301:conditional logit
297:multinomial logit
245:Sawtooth Software
1536:
1529:Choice modelling
1514:
1513:
1511:
1510:
1496:
1490:
1489:
1463:
1453:
1429:
1420:
1419:
1400:10.1002/hec.1739
1388:Health Economics
1382:
1376:
1375:
1330:
1324:
1323:
1279:
1273:
1272:
1262:
1234:
1228:
1227:
1207:
1196:
1195:
1163:
1157:
1156:
1120:
1114:
1113:
1067:
1061:
1060:
1058:
1048:
1020:
1014:
1013:
1012:
1006:
996:
978:
954:
948:
947:
937:
897:
891:
890:
870:
864:
863:
853:
813:
807:
806:
778:
772:
771:
735:
729:
728:
699:
693:
692:
656:
650:
649:
615:
606:
600:
599:
581:
572:
563:
562:
534:
525:
524:
500:
491:
490:
488:
460:
451:
450:
430:
419:
418:
416:
415:
401:
32:choice modelling
1544:
1543:
1539:
1538:
1537:
1535:
1534:
1533:
1519:
1518:
1517:
1508:
1506:
1498:
1497:
1493:
1461:1959.13/1053320
1431:
1430:
1423:
1384:
1383:
1379:
1332:
1331:
1327:
1281:
1280:
1276:
1236:
1235:
1231:
1209:
1208:
1199:
1165:
1164:
1160:
1122:
1121:
1117:
1069:
1068:
1064:
1025:Street, Deborah
1022:
1021:
1017:
1007:
956:
955:
951:
899:
898:
894:
872:
871:
867:
815:
814:
810:
780:
779:
775:
737:
736:
732:
701:
700:
696:
658:
657:
653:
613:
608:
607:
603:
579:
574:
573:
566:
536:
535:
528:
502:
501:
494:
462:
461:
454:
432:
431:
422:
413:
411:
403:
402:
391:
387:
366:
329:
316:neural networks
289:
262:
229:
210:
201:
192:
179:
170:
168:Types ("cases")
161:
113:
99:
91:genetic testing
53:
21:
12:
11:
5:
1542:
1540:
1532:
1531:
1521:
1520:
1516:
1515:
1491:
1444:(4): 701–735.
1421:
1394:(6): 730–741.
1377:
1342:(8): 713–727.
1325:
1290:(3): 458–468.
1274:
1245:(5): 874–882.
1229:
1197:
1192:10.1086/209528
1184:10.1086/209528
1158:
1131:(2): 143–156.
1115:
1080:(3): 259–267.
1062:
1039:(1): 128–164.
1015:
949:
892:
881:(2): 230–242.
865:
828:(2): 208–211.
808:
773:
746:(4): 496–513.
730:
711:(3): 813–828.
694:
667:(3): 487–496.
651:
601:
590:(3): 292–303.
564:
545:(1): 171–189.
526:
492:
471:(5): 281–296.
452:
441:(6): 464–480.
420:
388:
386:
383:
365:
362:
361:
360:
357:
353:
350:
346:
334:scale use bias
328:
325:
324:
323:
308:
304:
288:
285:
284:
283:
279:
276:
273:
269:
261:
258:
241:Punta del Este
228:
227:Recent history
225:
209:
206:
200:
197:
191:
188:
178:
175:
169:
166:
160:
157:
122:
121:
112:
109:
98:
95:
52:
49:
13:
10:
9:
6:
4:
3:
2:
1541:
1530:
1527:
1526:
1524:
1505:
1501:
1495:
1492:
1487:
1483:
1479:
1475:
1471:
1467:
1462:
1457:
1452:
1447:
1443:
1439:
1435:
1428:
1426:
1422:
1417:
1413:
1409:
1405:
1401:
1397:
1393:
1389:
1381:
1378:
1373:
1369:
1365:
1361:
1357:
1353:
1349:
1345:
1341:
1337:
1329:
1326:
1321:
1317:
1313:
1309:
1305:
1301:
1297:
1293:
1289:
1285:
1278:
1275:
1270:
1266:
1261:
1256:
1252:
1248:
1244:
1240:
1233:
1230:
1225:
1221:
1217:
1213:
1206:
1204:
1202:
1198:
1193:
1189:
1185:
1181:
1178:(1): 78–107.
1177:
1173:
1169:
1162:
1159:
1154:
1150:
1146:
1142:
1138:
1134:
1130:
1126:
1119:
1116:
1111:
1107:
1103:
1099:
1095:
1091:
1087:
1083:
1079:
1075:
1074:
1066:
1063:
1057:
1052:
1047:
1042:
1038:
1034:
1030:
1026:
1019:
1016:
1011:
1004:
1000:
995:
990:
986:
982:
977:
972:
968:
964:
960:
953:
950:
945:
941:
936:
931:
927:
923:
919:
915:
911:
907:
903:
896:
893:
888:
884:
880:
876:
869:
866:
861:
857:
852:
847:
843:
839:
835:
831:
827:
823:
819:
812:
809:
804:
800:
796:
792:
788:
784:
777:
774:
769:
765:
761:
757:
753:
749:
745:
741:
734:
731:
726:
722:
718:
714:
710:
706:
698:
695:
690:
686:
682:
678:
674:
670:
666:
662:
655:
652:
647:
643:
639:
635:
631:
627:
623:
619:
612:
605:
602:
597:
593:
589:
585:
578:
571:
569:
565:
560:
556:
552:
548:
544:
540:
533:
531:
527:
522:
518:
514:
510:
506:
499:
497:
493:
487:
482:
478:
474:
470:
466:
459:
457:
453:
448:
444:
440:
436:
429:
427:
425:
421:
410:
406:
400:
398:
396:
394:
390:
384:
382:
378:
375:
370:
364:Disadvantages
363:
358:
354:
351:
347:
343:
342:
341:
337:
335:
326:
321:
317:
313:
309:
305:
302:
298:
294:
293:
292:
286:
280:
277:
274:
270:
267:
266:
265:
259:
257:
253:
249:
246:
242:
238:
234:
226:
224:
220:
217:
215:
207:
205:
198:
196:
189:
187:
185:
176:
174:
167:
165:
158:
156:
154:
148:
145:
141:
140:
135:
130:
128:
119:
118:
117:
110:
108:
105:
96:
94:
92:
88:
84:
79:
75:
71:
66:
65:psychophysics
62:
58:
50:
48:
45:
41:
37:
33:
29:
25:
19:
1507:. Retrieved
1503:
1494:
1441:
1437:
1391:
1387:
1380:
1339:
1335:
1328:
1287:
1283:
1277:
1242:
1238:
1232:
1215:
1211:
1175:
1171:
1161:
1128:
1124:
1118:
1077:
1071:
1065:
1036:
1032:
1018:
966:
962:
952:
909:
905:
895:
878:
874:
868:
825:
821:
811:
786:
782:
776:
743:
739:
733:
708:
704:
697:
664:
660:
654:
621:
617:
604:
587:
583:
542:
538:
515:(1): 24–34.
512:
508:
468:
464:
438:
434:
412:. Retrieved
408:
379:
371:
367:
338:
330:
290:
263:
254:
250:
230:
221:
218:
211:
202:
193:
180:
171:
162:
152:
149:
143:
138:
137:
131:
123:
114:
100:
54:
27:
23:
22:
1504:APA PsycNET
789:(1): 8–23.
57:Duncan Luce
1509:2015-10-01
1260:10453/9747
1056:10453/9977
486:10453/8292
414:2015-10-01
385:References
327:Advantages
318:, and the
307:attribute.
1470:1551-6709
1408:1099-1050
1356:1170-7690
1304:0272-989X
1218:: 34–43.
1145:0022-2437
1094:1473-7167
985:1471-2288
969:(1): 76.
926:1018-4813
842:1075-2730
803:1751-1062
768:144637200
760:0260-2938
725:0002-9092
681:0176-1714
272:software.
1523:Category
1486:15328149
1478:24124986
1416:21557381
1372:21778695
1364:22788261
1320:30922199
1312:20924044
1269:18572295
1153:11304067
1110:39949090
1102:20545591
1003:19017376
944:23486538
860:25642618
689:18334695
646:10594387
638:21530040
559:16707175
287:Analysis
97:Purposes
994:2600822
935:3798841
851:5294953
134:maxdiff
104:maxdiff
51:History
44:prefers
18:MaxDiff
1484:
1476:
1468:
1414:
1406:
1370:
1362:
1354:
1318:
1310:
1302:
1267:
1190:
1151:
1143:
1108:
1100:
1092:
1001:
991:
983:
942:
932:
924:
858:
848:
840:
801:
766:
758:
723:
687:
679:
644:
636:
557:
233:ESOMAR
184:Likert
153:models
1482:S2CID
1368:S2CID
1316:S2CID
1188:JSTOR
1149:S2CID
1106:S2CID
764:S2CID
685:S2CID
642:S2CID
614:(PDF)
580:(PDF)
356:task.
1474:PMID
1466:ISSN
1412:PMID
1404:ISSN
1360:PMID
1352:ISSN
1308:PMID
1300:ISSN
1265:PMID
1141:ISSN
1098:PMID
1090:ISSN
999:PMID
981:ISSN
940:PMID
922:ISSN
856:PMID
838:ISSN
799:ISSN
756:ISSN
721:ISSN
677:ISSN
634:PMID
555:PMID
87:ADHD
63:and
1456:hdl
1446:doi
1396:doi
1344:doi
1292:doi
1255:hdl
1247:doi
1220:doi
1180:doi
1133:doi
1082:doi
1051:hdl
1041:doi
989:PMC
971:doi
930:PMC
914:doi
883:doi
846:PMC
830:doi
791:doi
748:doi
713:doi
669:doi
626:doi
592:doi
547:doi
517:doi
481:hdl
473:doi
443:doi
28:BWS
1525::
1502:.
1480:.
1472:.
1464:.
1454:.
1442:38
1440:.
1436:.
1424:^
1410:.
1402:.
1392:21
1390:.
1366:.
1358:.
1350:.
1340:30
1338:.
1314:.
1306:.
1298:.
1288:31
1286:.
1263:.
1253:.
1243:67
1214:.
1200:^
1186:.
1176:25
1174:.
1170:.
1147:.
1139:.
1129:38
1127:.
1104:.
1096:.
1088:.
1078:10
1076:.
1049:.
1035:.
1031:.
997:.
987:.
979:.
965:.
961:.
938:.
928:.
920:.
910:21
908:.
904:.
879:27
854:.
844:.
836:.
826:66
824:.
820:.
797:.
787:21
785:.
762:.
754:.
744:39
742:.
719:.
709:93
707:.
683:.
675:.
665:34
663:.
640:.
632:.
622:72
620:.
616:.
588:30
586:.
582:.
567:^
553:.
543:26
541:.
529:^
513:56
511:.
507:.
495:^
479:.
469:52
467:.
455:^
439:49
423:^
407:.
392:^
336:.
314:,
144:do
129:.
93:.
1512:.
1488:.
1458::
1448::
1418:.
1398::
1374:.
1346::
1322:.
1294::
1271:.
1257::
1249::
1226:.
1222::
1216:6
1194:.
1182::
1155:.
1135::
1112:.
1084::
1059:.
1053::
1043::
1037:1
1005:.
973::
967:8
946:.
916::
889:.
885::
862:.
832::
805:.
793::
770:.
750::
727:.
715::
691:.
671::
648:.
628::
598:.
594::
561:.
549::
523:.
519::
489:.
483::
475::
449:.
445::
417:.
182:(
26:(
20:.
Text is available under the Creative Commons Attribution-ShareAlike License. Additional terms may apply.