22:
126:
BEST is based on a population, P, relative to some hyperspace, R, that represents the universe of possible samples. P is the realized values of P based on a calibration set, T. T is used to find all possible variation in P. P is bound by parameters C and B. C is the expectation value of P, written
144:
BEST is used in detection of sample tampering in pharmaceutical products. Valid (unaltered) samples are defined as those that fall inside the cluster of training-set points when the BEST is trained with unaltered product samples. False (tampered) samples are those that fall outside of the same
325:
Y. Zou, Robert A. Lodder (1993) "The Effect of
Different Data Distributions on the Performance of the Extended Quantile BEAST in Pattern Recognition", paper #593 at the Pittsburgh Conference on Analytical Chemistry and Applied Spectroscopy, Atlanta,
321:
Y. Zou, Robert A. Lodder (1993) "An
Investigation of the Performance of the Extended Quantile BEAST in High Dimensional Hyperspace", paper #885 at the Pittsburgh Conference on Analytical Chemistry and Applied Spectroscopy, Atlanta,
135:
can be found using this technique. The values of B projected into hyperspace give rise to X. The hyperline from C to X gives rise to the skew adjusted standard deviation which is calculated in both directions of the hyperline.
123:
algorithm. Multidimensional standard deviations (MDSs) between clusters and spectral data points are calculated, where BEST considers each frequency to be taken from a separate dimension.
254:
Joseph
Mendendorp and Robert A. Lodder (2006) "Acoustic-Resonance Spectrometry as a Process Analytical Technology for Rapid and Accurate Tablet Identification"
267:
Sara J. Hamilton and Robert Lodder, "Hyperspectral
Imaging Technology for Pharmaceutical Analysis", Society of Photo-Optical Instrumentation Engineers
40:
189:
Lodder, Robert A.; Selby, Mark.; Hieftje, Gary M. (1987). "Detection of capsule tampering by near-infrared reflectance analysis".
91:
method that is intended to allow an assessment to be made of the validity of a single sample. It is based on estimating a
36:
344:
58:
339:
191:
160:
Detect any tampered product by determining that it is not similar to the previously analyzed unaltered product.
96:
218:
Efron, B.; Gong, G. (1983). "A Leisurely Look at the
Bootstrap, the Jackknife, and Cross-Validation".
220:
88:
95:
representing what can be expected from valid samples. This is done use a statistical method called
156:
method is valuable. A method such as NIRA can be coupled to the BEST method in the following ways.
92:
153:
282:
163:
Quantitatively identify the contaminant from a library of known adulterants in that product.
294:
108:
8:
116:
298:
310:
283:"Quantile BEAST Attacks the False-Sample Problem in Near-Infrared Reflectance Analysis"
237:
132:
128:
314:
302:
229:
200:
120:
333:
306:
204:
241:
112:
72:
166:
Provide quantitative indication of the amount of contaminant present.
111:, because it does not assume that for all spectral groups have equal
233:
119:. A quantitative approach involves BEST along with a nonparametric
149:
99:, applied to previous samples that are known to be valid.
107:
BEST provides advantages over other methods such as the
127:
E(P), and B is a bootstrapping distribution called the
31:
may be too technical for most readers to understand
188:
331:
77:bootstrap error-adjusted single-sample technique
152:require capsules to be emptied for analysis. A
280:
184:
182:
180:
217:
177:
59:Learn how and when to remove this message
43:, without removing the technical details.
332:
41:make it understandable to non-experts
15:
248:
13:
274:
115:or that each group is drawn for a
14:
356:
281:Lodder, R.; Hieftje, G. (1988).
20:
117:normally distributed population
261:
211:
139:
102:
1:
170:
7:
10:
361:
221:The American Statistician
345:Computational statistics
307:10.1366/0003702884429652
93:probability distribution
340:Resampling (statistics)
287:Applied Spectroscopy
192:Analytical Chemistry
299:1988ApSpe..42.1351L
258:, 7 (1) Article 25.
205:10.1021/ac00142a008
131:approximation. The
133:standard deviation
109:Mahalanobis metric
256:AAPS PharmSciTech
199:(15): 1921–1930.
69:
68:
61:
352:
318:
293:(8): 1351–1365.
268:
265:
259:
252:
246:
245:
215:
209:
208:
186:
148:Methods such as
121:cluster analysis
64:
57:
53:
50:
44:
24:
23:
16:
360:
359:
355:
354:
353:
351:
350:
349:
330:
329:
277:
275:Further reading
272:
271:
266:
262:
253:
249:
234:10.2307/2685844
216:
212:
187:
178:
173:
142:
105:
65:
54:
48:
45:
37:help improve it
34:
25:
21:
12:
11:
5:
358:
348:
347:
342:
328:
327:
323:
319:
276:
273:
270:
269:
260:
247:
210:
175:
174:
172:
169:
168:
167:
164:
161:
154:nondestructive
141:
138:
104:
101:
89:non-parametric
67:
66:
28:
26:
19:
9:
6:
4:
3:
2:
357:
346:
343:
341:
338:
337:
335:
324:
320:
316:
312:
308:
304:
300:
296:
292:
288:
284:
279:
278:
264:
257:
251:
243:
239:
235:
231:
227:
223:
222:
214:
206:
202:
198:
194:
193:
185:
183:
181:
176:
165:
162:
159:
158:
157:
155:
151:
146:
137:
134:
130:
124:
122:
118:
114:
110:
100:
98:
97:bootstrapping
94:
90:
86:
82:
78:
74:
63:
60:
52:
42:
38:
32:
29:This article
27:
18:
17:
290:
286:
263:
255:
250:
228:(1): 36–48.
225:
219:
213:
196:
190:
147:
143:
125:
106:
84:
80:
76:
70:
55:
46:
30:
140:Application
129:Monte Carlo
113:covariances
103:Methodology
334:Categories
171:References
73:statistics
49:March 2011
145:cluster.
85:the BEAST
315:67835182
295:Bibcode
242:2685844
150:ICP-AES
87:) is a
35:Please
313:
240:
75:, the
311:S2CID
238:JSTOR
81:BEST
303:doi
230:doi
201:doi
83:or
71:In
39:to
336::
326:GA
322:GA
309:.
301:.
291:42
289:.
285:.
236:.
226:37
224:.
197:59
195:.
179:^
317:.
305::
297::
244:.
232::
207:.
203::
79:(
62:)
56:(
51:)
47:(
33:.
Text is available under the Creative Commons Attribution-ShareAlike License. Additional terms may apply.