Knowledge (XXG)

Unimodality

Source 📝

1288: 775: 1283:{\displaystyle {\frac {\left|{\frac {q_{\alpha }+q_{(1-\alpha )}}{2}}-\mu \right|}{\sigma }}\leq \left\{{\begin{array}{cl}{\frac {{\sqrt{{\frac {4}{9(1-\alpha )}}-1}}{\text{ }}+{\text{ }}{\sqrt{\frac {1-\alpha }{1/3+\alpha }}}}{2}}&{\text{for }}\alpha \in \left{\frac {3\alpha }{4-3\alpha }}}{\text{ }}+{\text{ }}{\sqrt{\frac {1-\alpha }{1/3+\alpha }}}}{2}}&{\text{for }}\alpha \in \left({\frac {1}{6}},{\frac {5}{6}}\right)\!,\\{\frac {{\sqrt{\frac {3\alpha }{4-3\alpha }}}{\text{ }}+{\text{ }}{\sqrt{{\frac {4}{9\alpha }}-1}}}{2}}&{\text{for }}\alpha \in \left(0,{\frac {1}{6}}\right]\!.\end{array}}\right.} 62: 87: 488:. The Chebyshev inequality guarantees that in any probability distribution, "nearly all" the values are "close to" the mean value. The Vysochanskiï–Petunin inequality refines this to even nearer values, provided that the distribution function is continuous and unimodal. Further results were shown by Sellke and Sellke. 76: 2287:
Gauss C.F. Theoria Combinationis Observationum Erroribus Minimis Obnoxiae. Pars Prior. Pars Posterior. Supplementum. Theory of the Combination of Observations Least Subject to Errors. Part One. Part Two. Supplement. 1995. Translated by G.W. Stewart. Classics in Applied Mathematics Series, Society for
202:
is unimodal, as well as any other distribution in which the maximum distribution is achieved for a range of values, e.g. trapezoidal distribution. Usually this definition allows for a discontinuity at the mode; usually in a continuous distribution the probability of any single value is zero, while
444:
are given below which are only valid for unimodal distributions. Thus, it is important to assess whether or not a given data set comes from a unimodal distribution. Several tests for unimodality are given in the article on
430: 696: 1540: 1476: 1680: 595: 1611: 767: 532: 291: 120:
If there is a single mode, the distribution function is called "unimodal". If it has more modes it is "bimodal" (2), "trimodal" (3), etc., or in general, "multimodal". Figure 1 illustrates
1848:, a method for doing numerical optimization, is often demonstrated with such a function. It can be said that a unimodal function under this extension is a function with a single local 1763:
Proving unimodality is often hard. One way consists in using the definition of that property, but it turns out to be suitable for simple functions only. A general method based on
217:
Another way to define a unimodal discrete distribution is by the occurrence of sign changes in the sequence of differences of the probabilities. A discrete distribution with a
1624:
is the skewness. Klaassen, Mokveld, and van Es showed that this only applies in certain settings, such as the set of unimodal distributions where the mode and mean coincide.
1408: 1350: 1376: 1317: 1915: 472:. Gauss's inequality gives an upper bound on the probability that a value lies more than any given distance from its mode. This inequality depends on unimodality. 1935: 2589: 207: 296: 708:
In 2020, Bernard, Kazzi, and Vanduffel generalized the previous inequality by deriving the maximum distance between the symmetric quantile average
2392:
Klaassen, Chris A.J.; Mokveld, Philip J.; Van Es, Bert (2000). "Squared skewness minus kurtosis bounded by 186/125 for unimodal distributions".
481: 641: 2487: 1685:
This bound is sharp, as it is reached by the equal-weights mixture of the uniform distribution on and the discrete distribution at {0}.
1844:
Depending on context, unimodal function may also refer to a function that has only one local minimum, rather than maximum. For example,
1487: 1423: 1868: 1633: 113:
which has a single peak. The term "mode" in this context refers to any peak of the distribution, not just to the strict definition of
2154: 543: 199: 167: 1564: 211: 93:
A bimodal distribution. Note that only the largest peak would correspond to a mode in the strict sense of the definition of mode
2584: 2579: 711: 2132: 68: 2012:
and quasiconcave functions extend the concept of unimodality to functions whose arguments belong to higher-dimensional
2127: 2003: 502: 224: 129: 617: 440:
One reason for the importance of distribution unimodality is that it allows for several important results. Several
1944:
if a function is unimodal it permits the design of efficient algorithms for finding the extrema of the function.
458: 218: 152:
can be seen as unimodal, though for some parameters they can have two adjacent values with the same probability.
441: 141: 137: 110: 1352:), which indeed motivates the common choice of the median as a robust estimator for the mean. Moreover, when 1845: 446: 2122: 1941: 1694: 2253: 1888: 1860: 145: 469: 2474:. Lecture Notes in Computer Science. Vol. 3669. Berlin, Heidelberg: Springer. pp. 887–898. 2232:
D. F. Vysochanskij, Y. I. Petunin (1980). "Justification of the 3σ rule for unimodal distributions".
2210: 2030: 2025: 2009: 1838: 1771: 485: 149: 1964: 1381: 125: 121: 50: 49:. More generally, unimodality means there is only a single highest value, somehow defined, of some 1322: 2556: 2521: 2362:
Rohatgi, Vijay K.; Székely, Gábor J. (1989). "Sharp inequalities between skewness and kurtosis".
2270: 2192: 1355: 1296: 632: 1837:. An example of a weakly unimodal function which is not strongly unimodal is every other row in 1697:, the definitions above do not apply. The definition of "unimodal" was extended to functions of 2483: 2150: 2075: 2050: 114: 46: 2419: 1894: 1693:
As the term "modal" applies to data sets and probability distribution, and not in general to
203:
this definition allows for a non-zero probability, or an "atom of probability", at the mode.
2548: 2513: 2475: 2401: 2371: 2342: 2311: 2262: 2184: 1856: 1410:, which is the maximum distance between the median and the mean of a unimodal distribution. 183: 2299: 2013: 171: 2446: 2467: 2251:
Sellke, T.M.; Sellke, S.H. (1997). "Chebyshev inequalities for unimodal distributions".
61: 1967: 1920: 1864: 702: 2405: 2213:(1823). "Theoria Combinationis Observationum Erroribus Minimis Obnoxiae, Pars Prior". 2573: 2375: 2347: 2330: 2196: 2172: 1855:
One important property of unimodal functions is that the extremum can be found using
30:"Unimodal" redirects here. For the company that promotes personal rapid transit, see 2560: 2420:"On the unimodality of METRIC Approximation subject to normally distributed demands" 166:
In continuous distributions, unimodality can be defined through the behavior of the
86: 2504:
John Guckenheimer; Stewart Johnson (July 1990). "Distortion of S-Unimodal Maps".
2331:"Range Value-at-Risk bounds for unimodal distributions under partial information" 1698: 854: 425:{\displaystyle \dots ,p_{-2}-p_{-1},p_{-1}-p_{0},p_{0}-p_{1},p_{1}-p_{2},\dots } 38: 2315: 2053: 1764: 1627:
They derived a weaker inequality which applies to all unimodal distributions:
98: 2539:
Godfried T. Toussaint (June 1984). "Complexity, convexity, and unimodality".
2083: 2058: 1721: 1481:
It can also be shown that the mean and the mode lie within 3 of each other:
1767:
exists, but it does not succeed for every function despite its simplicity.
2300:"The Mean, Median, and Mode of Unimodal Distributions: A Characterization" 2078: 1849: 1775: 1555: 1551: 691:{\displaystyle {\frac {|\nu -\mu |}{\sigma }}\leq {\sqrt {\frac {3}{5}}}} 2479: 17: 2552: 2525: 2274: 2188: 1741: 163:
Other definitions of unimodality in distribution functions also exist.
124:, which are unimodal. Other examples of unimodal distributions include 31: 2215:
Commentationes Societatis Regiae Scientiarum Gottingensis Recentiores
601: 2517: 2266: 75: 1535:{\displaystyle {\frac {|\mu -\theta |}{\sigma }}\leq {\sqrt {3}}.} 1471:{\displaystyle {\frac {|\nu -\theta |}{\sigma }}\leq {\sqrt {3}}.} 85: 74: 60: 1887:) is "S-unimodal" (often referred to as "S-unimodal map") if its 1675:{\displaystyle \gamma ^{2}-\kappa \leq {\frac {186}{125}}=1.488} 1417:: they lie within 3 ≈ 1.732 standard deviations of each other: 590:{\displaystyle |\nu -\mu |\leq {\sqrt {\frac {3}{4}}}\omega ,} 1293:
It is worth noting that the maximum distance is minimized at
71:
of normal distributions, an example of unimodal distribution.
2468:"Optimizing a 2D Function Satisfying Unimodality Properties" 2329:
Bernard, Carole; Kazzi, Rodrigue; Vanduffel, Steven (2020).
623:
It can be shown for a unimodal distribution that the median
1277: 496:
Gauss also showed in 1823 that for a unimodal distribution
2541:
International Journal of Computer and Information Sciences
1606:{\displaystyle \gamma ^{2}-\kappa \leq {\frac {6}{5}}=1.2} 1558:
of a unimodal distribution are related by the inequality:
1413:
A similar relation holds between the median and the mode
206:
Criteria for unimodality can also be defined through the
1319:(i.e., when the symmetric quantile average is equal to 762:{\displaystyle {\frac {q_{\alpha }+q_{(1-\alpha )}}{2}}} 155:
Figure 2 and Figure 3 illustrate bimodal distributions.
2470:. In Brodal, Gerth Stølting; Leonardi, Stefano (eds.). 432:
has exactly one sign change (when zeroes don't count).
2145:
Vladimirovich Gnedenko and Victor Yu Korolev (1996).
1923: 1897: 1833:) can be reached for a continuous range of values of 1636: 1567: 1490: 1426: 1384: 1358: 1325: 1299: 778: 714: 644: 546: 505: 299: 227: 2102:
A.Ya. Khinchin (1938). "On unimodal distributions".
1947:
A more general definition, applicable to a function
1809:
for which it is weakly monotonically increasing for
459:
Chebyshev's inequality § Unimodal distributions
198:
being the mode. Note that under this definition the
1929: 1909: 1674: 1605: 1534: 1470: 1402: 1370: 1344: 1311: 1282: 761: 690: 589: 526: 424: 285: 2427:Method in appendix D, Example in theorem 2 page 5 2234:Theory of Probability and Mathematical Statistics 2147:Random summation: limit theorems and applications 1789:, from the fact that the monotonicity implied is 1774:functions with a negative quadratic coefficient, 1269: 1141: 997: 27:Property of having a unique mode or maximum value 2288:Industrial and Applied Mathematics, Philadelphia 527:{\displaystyle \sigma \leq \omega \leq 2\sigma } 286:{\displaystyle \{p_{n}:n=\dots ,-1,0,1,\dots \}} 2387: 2385: 2261:(1). American Statistical Association: 34–40. 2173:"On the unimodality of discrete distributions" 1704:A common definition is as follows: a function 8: 2466:Demaine, Erik D.; Langerman, Stefan (2005). 2304:Theory of Probability & Its Applications 280: 228: 2097: 2095: 2346: 1922: 1896: 1656: 1641: 1635: 1587: 1572: 1566: 1522: 1508: 1494: 1491: 1489: 1458: 1444: 1430: 1427: 1425: 1390: 1385: 1383: 1357: 1330: 1324: 1298: 1254: 1232: 1220: 1198: 1195: 1190: 1182: 1178: 1152: 1149: 1126: 1113: 1097: 1085: 1069: 1051: 1046: 1038: 1034: 1008: 1005: 976: 960: 948: 932: 914: 909: 901: 897: 863: 860: 857: 853: 806: 793: 786: 779: 777: 735: 722: 715: 713: 676: 662: 648: 645: 643: 569: 561: 547: 545: 504: 410: 397: 384: 371: 358: 342: 326: 310: 298: 235: 226: 1817:and weakly monotonically decreasing for 2041: 1770:Examples of unimodal functions include 1760:) and there are no other local maxima. 1994:)) is convex. Usually one would want 1781:The above is sometimes related to as 1550:Rohatgi and Szekely claimed that the 293:, is called unimodal if the sequence 194:, then the distribution is unimodal, 7: 2394:Statistics & Probability Letters 2364:Statistics & Probability Letters 2335:Insurance: Mathematics and Economics 144:. Among discrete distributions, the 2590:Theory of probability distributions 2447:"Mathematical Programming Glossary" 1825:. In that case, the maximum value 210:of the distribution or through its 2006:with nonsingular Jacobian matrix. 1869:successive parabolic interpolation 25: 1732:and monotonically decreasing for 103:unimodal probability distribution 57:Unimodal probability distribution 2348:10.1016/j.insmatheco.2020.05.013 168:cumulative distribution function 117:which is usual in statistics. 2298:Basu, S.; Dasgupta, A. (1997). 2177:Periodica Mathematica Hungarica 482:Vysochanskiï–Petunin inequality 476:Vysochanskiï–Petunin inequality 2110:(2). University of Tomsk: 1–7. 1509: 1495: 1445: 1431: 884: 872: 819: 807: 748: 736: 663: 649: 562: 548: 82:A simple bimodal distribution. 1: 2406:10.1016/S0167-7152(00)00090-0 2104:Trams. Res. Inst. Math. Mech. 1403:{\displaystyle {\sqrt {3/5}}} 2376:10.1016/0167-7152(89)90035-7 2171:Medgyessy, P. (March 1972). 1345:{\displaystyle q_{0.5}=\nu } 468:A first important result is 69:Probability density function 2128:Encyclopedia of Mathematics 2004:continuously differentiable 1371:{\displaystyle \alpha =0.5} 1312:{\displaystyle \alpha =0.5} 635:of each other. In symbols, 212:Laplace–Stieltjes transform 2606: 1963:is unimodal if there is a 631:lie within (3/5) ≈ 0.7746 618:root mean square deviation 463: 456: 45:means possessing a unique 29: 2316:10.1137/S0040585X97975447 219:probability mass function 1805:if there exists a value 1803:weakly unimodal function 1378:, the bound is equal to 142:exponential distribution 138:chi-squared distribution 111:probability distribution 2123:"Unimodal distribution" 2121:Ushakov, N.G. (2001) , 1955:) of a vector variable 1937:is the critical point. 1910:{\displaystyle x\neq c} 1846:local unimodal sampling 447:multimodal distribution 208:characteristic function 2585:Mathematical relations 2580:Functions and mappings 1942:computational geometry 1931: 1911: 1676: 1607: 1536: 1472: 1404: 1372: 1346: 1313: 1284: 763: 692: 591: 528: 484:, a refinement of the 426: 287: 94: 83: 72: 2506:Annals of Mathematics 2472:Algorithms – ESA 2005 2254:American Statistician 2010:Quasiconvex functions 1932: 1912: 1889:Schwarzian derivative 1861:golden section search 1778:functions, and more. 1677: 1608: 1546:Skewness and kurtosis 1537: 1473: 1405: 1373: 1347: 1314: 1285: 764: 693: 592: 529: 492:Mode, median and mean 427: 288: 170:(cdf). If the cdf is 146:binomial distribution 107:unimodal distribution 89: 78: 64: 2026:Bimodal distribution 1921: 1895: 1891:is negative for all 1772:quadratic polynomial 1740:. In that case, the 1634: 1620:is the kurtosis and 1565: 1488: 1424: 1382: 1356: 1323: 1297: 776: 712: 642: 544: 503: 486:Chebyshev inequality 297: 225: 200:uniform distribution 150:Poisson distribution 122:normal distributions 2480:10.1007/11561071_78 1791:strong monotonicity 701:where | . | is the 633:standard deviations 126:Cauchy distribution 51:mathematical object 2553:10.1007/bf00979872 2189:10.1007/bf02018665 2076:Weisstein, Eric W. 2051:Weisstein, Eric W. 1927: 1907: 1785:strong unimodality 1716:if for some value 1672: 1603: 1532: 1468: 1400: 1368: 1342: 1309: 1280: 1275: 759: 688: 587: 524: 470:Gauss's inequality 464:Gauss's inequality 422: 283: 95: 84: 73: 2508:. Second Series. 2489:978-3-540-31951-1 2031:Read's conjecture 1930:{\displaystyle c} 1857:search algorithms 1839:Pascal's triangle 1714:unimodal function 1689:Unimodal function 1664: 1595: 1527: 1517: 1463: 1453: 1398: 1262: 1235: 1228: 1222: 1211: 1193: 1185: 1180: 1177: 1134: 1121: 1100: 1093: 1087: 1084: 1049: 1041: 1036: 1033: 984: 963: 956: 950: 947: 912: 904: 899: 888: 844: 828: 757: 686: 685: 671: 579: 578: 159:Other definitions 16:(Redirected from 2597: 2565: 2564: 2536: 2530: 2529: 2500: 2494: 2493: 2463: 2457: 2456: 2454: 2453: 2443: 2437: 2436: 2434: 2433: 2424: 2416: 2410: 2409: 2389: 2380: 2379: 2359: 2353: 2352: 2350: 2326: 2320: 2319: 2295: 2289: 2285: 2279: 2278: 2248: 2242: 2241: 2229: 2223: 2222: 2207: 2201: 2200: 2183:(1–4): 245–257. 2168: 2162: 2160: 2142: 2136: 2135: 2118: 2112: 2111: 2099: 2090: 2089: 2088: 2071: 2065: 2064: 2063: 2046: 2014:Euclidean spaces 1936: 1934: 1933: 1928: 1916: 1914: 1913: 1908: 1875:Other extensions 1787: 1786: 1681: 1679: 1678: 1673: 1665: 1657: 1646: 1645: 1612: 1610: 1609: 1604: 1596: 1588: 1577: 1576: 1541: 1539: 1538: 1533: 1528: 1523: 1518: 1513: 1512: 1498: 1492: 1477: 1475: 1474: 1469: 1464: 1459: 1454: 1449: 1448: 1434: 1428: 1409: 1407: 1406: 1401: 1399: 1394: 1386: 1377: 1375: 1374: 1369: 1351: 1349: 1348: 1343: 1335: 1334: 1318: 1316: 1315: 1310: 1289: 1287: 1286: 1281: 1279: 1276: 1268: 1264: 1263: 1255: 1236: 1233: 1229: 1224: 1223: 1221: 1219: 1212: 1210: 1199: 1196: 1194: 1191: 1186: 1183: 1181: 1179: 1176: 1162: 1154: 1153: 1150: 1140: 1136: 1135: 1127: 1122: 1114: 1101: 1098: 1094: 1089: 1088: 1086: 1083: 1073: 1064: 1053: 1052: 1050: 1047: 1042: 1039: 1037: 1035: 1032: 1018: 1010: 1009: 1006: 996: 992: 985: 977: 964: 961: 957: 952: 951: 949: 946: 936: 927: 916: 915: 913: 910: 905: 902: 900: 898: 896: 889: 887: 864: 861: 858: 845: 840: 836: 829: 824: 823: 822: 798: 797: 787: 780: 768: 766: 765: 760: 758: 753: 752: 751: 727: 726: 716: 697: 695: 694: 689: 687: 678: 677: 672: 667: 666: 652: 646: 596: 594: 593: 588: 580: 571: 570: 565: 551: 533: 531: 530: 525: 480:A second is the 436:Uses and results 431: 429: 428: 423: 415: 414: 402: 401: 389: 388: 376: 375: 363: 362: 350: 349: 334: 333: 318: 317: 292: 290: 289: 284: 240: 239: 190: >  178: <  21: 2605: 2604: 2600: 2599: 2598: 2596: 2595: 2594: 2570: 2569: 2568: 2538: 2537: 2533: 2518:10.2307/1971501 2503: 2501: 2497: 2490: 2465: 2464: 2460: 2451: 2449: 2445: 2444: 2440: 2431: 2429: 2422: 2418: 2417: 2413: 2391: 2390: 2383: 2361: 2360: 2356: 2328: 2327: 2323: 2297: 2296: 2292: 2286: 2282: 2267:10.2307/2684690 2250: 2249: 2245: 2231: 2230: 2226: 2209: 2208: 2204: 2170: 2169: 2165: 2157: 2144: 2143: 2139: 2120: 2119: 2115: 2101: 2100: 2093: 2074: 2073: 2072: 2068: 2049: 2048: 2047: 2043: 2039: 2022: 1919: 1918: 1893: 1892: 1877: 1784: 1783: 1724:increasing for 1691: 1637: 1632: 1631: 1568: 1563: 1562: 1548: 1493: 1486: 1485: 1429: 1422: 1421: 1380: 1379: 1354: 1353: 1326: 1321: 1320: 1295: 1294: 1274: 1273: 1247: 1243: 1230: 1203: 1197: 1163: 1155: 1151: 1146: 1145: 1112: 1108: 1095: 1065: 1054: 1019: 1011: 1007: 1002: 1001: 975: 971: 958: 928: 917: 868: 862: 859: 849: 802: 789: 788: 785: 781: 774: 773: 731: 718: 717: 710: 709: 647: 640: 639: 620:from the mode. 542: 541: 501: 500: 494: 478: 466: 461: 455: 438: 406: 393: 380: 367: 354: 338: 322: 306: 295: 294: 231: 223: 222: 161: 59: 35: 28: 23: 22: 15: 12: 11: 5: 2603: 2601: 2593: 2592: 2587: 2582: 2572: 2571: 2567: 2566: 2547:(3): 197–217. 2531: 2495: 2488: 2458: 2438: 2411: 2400:(2): 131–135. 2381: 2370:(4): 297–299. 2354: 2321: 2310:(2): 210–223. 2290: 2280: 2243: 2224: 2202: 2163: 2155: 2137: 2113: 2106:(in Russian). 2091: 2066: 2040: 2038: 2035: 2034: 2033: 2028: 2021: 2018: 1968:differentiable 1926: 1906: 1903: 1900: 1876: 1873: 1865:ternary search 1690: 1687: 1683: 1682: 1671: 1668: 1663: 1660: 1655: 1652: 1649: 1644: 1640: 1614: 1613: 1602: 1599: 1594: 1591: 1586: 1583: 1580: 1575: 1571: 1547: 1544: 1543: 1542: 1531: 1526: 1521: 1516: 1511: 1507: 1504: 1501: 1497: 1479: 1478: 1467: 1462: 1457: 1452: 1447: 1443: 1440: 1437: 1433: 1397: 1393: 1389: 1367: 1364: 1361: 1341: 1338: 1333: 1329: 1308: 1305: 1302: 1291: 1290: 1278: 1272: 1267: 1261: 1258: 1253: 1250: 1246: 1242: 1239: 1231: 1227: 1218: 1215: 1209: 1206: 1202: 1189: 1175: 1172: 1169: 1166: 1161: 1158: 1148: 1147: 1144: 1139: 1133: 1130: 1125: 1120: 1117: 1111: 1107: 1104: 1096: 1092: 1082: 1079: 1076: 1072: 1068: 1063: 1060: 1057: 1045: 1031: 1028: 1025: 1022: 1017: 1014: 1004: 1003: 1000: 995: 991: 988: 983: 980: 974: 970: 967: 959: 955: 945: 942: 939: 935: 931: 926: 923: 920: 908: 895: 892: 886: 883: 880: 877: 874: 871: 867: 856: 855: 852: 848: 843: 839: 835: 832: 827: 821: 818: 815: 812: 809: 805: 801: 796: 792: 784: 769:and the mean, 756: 750: 747: 744: 741: 738: 734: 730: 725: 721: 703:absolute value 699: 698: 684: 681: 675: 670: 665: 661: 658: 655: 651: 627:and the mean 608:, the mean is 598: 597: 586: 583: 577: 574: 568: 564: 560: 557: 554: 550: 535: 534: 523: 520: 517: 514: 511: 508: 493: 490: 477: 474: 465: 462: 454: 451: 437: 434: 421: 418: 413: 409: 405: 400: 396: 392: 387: 383: 379: 374: 370: 366: 361: 357: 353: 348: 345: 341: 337: 332: 329: 325: 321: 316: 313: 309: 305: 302: 282: 279: 276: 273: 270: 267: 264: 261: 258: 255: 252: 249: 246: 243: 238: 234: 230: 160: 157: 58: 55: 26: 24: 14: 13: 10: 9: 6: 4: 3: 2: 2602: 2591: 2588: 2586: 2583: 2581: 2578: 2577: 2575: 2562: 2558: 2554: 2550: 2546: 2542: 2535: 2532: 2527: 2523: 2519: 2515: 2512:(1): 71–130. 2511: 2507: 2499: 2496: 2491: 2485: 2481: 2477: 2473: 2469: 2462: 2459: 2448: 2442: 2439: 2428: 2421: 2415: 2412: 2407: 2403: 2399: 2395: 2388: 2386: 2382: 2377: 2373: 2369: 2365: 2358: 2355: 2349: 2344: 2340: 2336: 2332: 2325: 2322: 2317: 2313: 2309: 2305: 2301: 2294: 2291: 2284: 2281: 2276: 2272: 2268: 2264: 2260: 2256: 2255: 2247: 2244: 2239: 2235: 2228: 2225: 2220: 2216: 2212: 2206: 2203: 2198: 2194: 2190: 2186: 2182: 2178: 2174: 2167: 2164: 2158: 2156:0-8493-2875-6 2152: 2149:. CRC-Press. 2148: 2141: 2138: 2134: 2130: 2129: 2124: 2117: 2114: 2109: 2105: 2098: 2096: 2092: 2086: 2085: 2080: 2077: 2070: 2067: 2061: 2060: 2055: 2052: 2045: 2042: 2036: 2032: 2029: 2027: 2024: 2023: 2019: 2017: 2015: 2011: 2007: 2005: 2001: 1997: 1993: 1989: 1985: 1981: 1977: 1973: 1969: 1966: 1962: 1958: 1954: 1950: 1945: 1943: 1938: 1924: 1904: 1901: 1898: 1890: 1886: 1882: 1874: 1872: 1870: 1866: 1862: 1858: 1853: 1851: 1847: 1842: 1840: 1836: 1832: 1828: 1824: 1821: ≥  1820: 1816: 1813: ≤  1812: 1808: 1804: 1800: 1796: 1793:. A function 1792: 1788: 1779: 1777: 1773: 1768: 1766: 1761: 1759: 1755: 1751: 1747: 1743: 1739: 1736: ≥  1735: 1731: 1728: ≤  1727: 1723: 1722:monotonically 1719: 1715: 1711: 1707: 1702: 1700: 1696: 1688: 1686: 1669: 1666: 1661: 1658: 1653: 1650: 1647: 1642: 1638: 1630: 1629: 1628: 1625: 1623: 1619: 1600: 1597: 1592: 1589: 1584: 1581: 1578: 1573: 1569: 1561: 1560: 1559: 1557: 1553: 1545: 1529: 1524: 1519: 1514: 1505: 1502: 1499: 1484: 1483: 1482: 1465: 1460: 1455: 1450: 1441: 1438: 1435: 1420: 1419: 1418: 1416: 1411: 1395: 1391: 1387: 1365: 1362: 1359: 1339: 1336: 1331: 1327: 1306: 1303: 1300: 1270: 1265: 1259: 1256: 1251: 1248: 1244: 1240: 1237: 1225: 1216: 1213: 1207: 1204: 1200: 1187: 1173: 1170: 1167: 1164: 1159: 1156: 1142: 1137: 1131: 1128: 1123: 1118: 1115: 1109: 1105: 1102: 1090: 1080: 1077: 1074: 1070: 1066: 1061: 1058: 1055: 1043: 1029: 1026: 1023: 1020: 1015: 1012: 998: 993: 989: 986: 981: 978: 972: 968: 965: 953: 943: 940: 937: 933: 929: 924: 921: 918: 906: 893: 890: 881: 878: 875: 869: 865: 850: 846: 841: 837: 833: 830: 825: 816: 813: 810: 803: 799: 794: 790: 782: 772: 771: 770: 754: 745: 742: 739: 732: 728: 723: 719: 706: 704: 682: 679: 673: 668: 659: 656: 653: 638: 637: 636: 634: 630: 626: 621: 619: 615: 611: 607: 603: 584: 581: 575: 572: 566: 558: 555: 552: 540: 539: 538: 521: 518: 515: 512: 509: 506: 499: 498: 497: 491: 489: 487: 483: 475: 473: 471: 460: 452: 450: 448: 443: 435: 433: 419: 416: 411: 407: 403: 398: 394: 390: 385: 381: 377: 372: 368: 364: 359: 355: 351: 346: 343: 339: 335: 330: 327: 323: 319: 314: 311: 307: 303: 300: 277: 274: 271: 268: 265: 262: 259: 256: 253: 250: 247: 244: 241: 236: 232: 220: 215: 213: 209: 204: 201: 197: 193: 189: 185: 181: 177: 173: 169: 164: 158: 156: 153: 151: 147: 143: 139: 135: 134:-distribution 133: 127: 123: 118: 116: 112: 108: 104: 100: 92: 88: 81: 77: 70: 67: 63: 56: 54: 52: 48: 44: 40: 33: 19: 2544: 2540: 2534: 2509: 2505: 2498: 2471: 2461: 2450:. Retrieved 2441: 2430:. Retrieved 2426: 2414: 2397: 2393: 2367: 2363: 2357: 2338: 2334: 2324: 2307: 2303: 2293: 2283: 2258: 2252: 2246: 2237: 2233: 2227: 2218: 2214: 2211:Gauss, C. F. 2205: 2180: 2176: 2166: 2146: 2140: 2126: 2116: 2107: 2103: 2082: 2069: 2057: 2044: 2008: 1999: 1995: 1991: 1987: 1983: 1982:) such that 1979: 1975: 1971: 1960: 1956: 1952: 1948: 1946: 1939: 1884: 1880: 1878: 1854: 1843: 1834: 1830: 1826: 1822: 1818: 1814: 1810: 1806: 1802: 1798: 1794: 1790: 1782: 1780: 1769: 1762: 1757: 1753: 1749: 1745: 1737: 1733: 1729: 1725: 1717: 1713: 1709: 1705: 1703: 1699:real numbers 1692: 1684: 1626: 1621: 1617: 1615: 1549: 1480: 1414: 1412: 1292: 707: 700: 628: 624: 622: 613: 609: 605: 599: 536: 495: 479: 467: 453:Inequalities 442:inequalities 439: 216: 205: 195: 191: 187: 179: 175: 165: 162: 154: 131: 119: 106: 102: 96: 90: 79: 65: 42: 36: 1879:A function 1765:derivatives 1701:as well. 43:unimodality 39:mathematics 2574:Categories 2452:2020-03-29 2432:2013-08-28 2161:p. 31 2054:"Unimodal" 2037:References 1965:one-to-one 600:where the 457:See also: 130:Student's 99:statistics 2502:See e.g. 2197:119817256 2133:EMS Press 2084:MathWorld 2059:MathWorld 1902:≠ 1744:value of 1695:functions 1654:≤ 1651:κ 1648:− 1639:γ 1585:≤ 1582:κ 1579:− 1570:γ 1520:≤ 1515:σ 1506:θ 1503:− 1500:μ 1456:≤ 1451:σ 1442:θ 1439:− 1436:ν 1360:α 1340:ν 1301:α 1241:∈ 1238:α 1234:for  1214:− 1208:α 1174:α 1168:− 1160:α 1106:∈ 1103:α 1099:for  1081:α 1062:α 1059:− 1030:α 1024:− 1016:α 969:∈ 966:α 962:for  944:α 925:α 922:− 891:− 882:α 879:− 847:≤ 842:σ 834:μ 831:− 817:α 814:− 795:α 746:α 743:− 724:α 674:≤ 669:σ 660:μ 657:− 654:ν 582:ω 567:≤ 559:μ 556:− 553:ν 522:σ 516:≤ 513:ω 510:≤ 507:σ 420:… 404:− 378:− 352:− 344:− 328:− 320:− 312:− 301:… 278:… 257:− 251:… 91:Figure 3. 80:Figure 2. 66:Figure 1. 2561:11577312 2341:: 9–24. 2240:: 25–36. 2020:See also 2002:) to be 1970:mapping 1959:is that 1917:, where 1859:such as 1850:extremum 1776:tent map 1720:, it is 1556:kurtosis 1552:skewness 18:Unimodal 2526:1971501 2275:2684690 1801:) is a 1742:maximum 1712:) is a 616:is the 184:concave 32:SkyTran 2559:  2524:  2486:  2273:  2195:  2153:  2079:"Mode" 1616:where 1192:  1184:  1048:  1040:  911:  903:  602:median 172:convex 2557:S2CID 2522:JSTOR 2423:(PDF) 2271:JSTOR 2193:S2CID 1752:) is 1670:1.488 612:and 109:is a 2484:ISBN 2151:ISBN 1554:and 537:and 186:for 182:and 174:for 148:and 140:and 115:mode 101:, a 47:mode 2549:doi 2514:doi 2510:132 2476:doi 2402:doi 2372:doi 2343:doi 2312:doi 2263:doi 2185:doi 1940:In 1867:or 1662:125 1659:186 1601:1.2 1366:0.5 1332:0.5 1307:0.5 604:is 105:or 97:In 37:In 2576:: 2555:. 2545:13 2543:. 2520:. 2482:. 2425:. 2398:50 2396:. 2384:^ 2366:. 2339:94 2337:. 2333:. 2308:41 2306:. 2302:. 2269:. 2259:51 2257:. 2238:21 2236:. 2217:. 2191:. 2179:. 2175:. 2131:, 2125:, 2094:^ 2081:. 2056:. 2016:. 1974:= 1871:. 1863:, 1852:. 1841:. 705:. 449:. 221:, 214:. 136:, 128:, 53:. 41:, 2563:. 2551:: 2528:. 2516:: 2492:. 2478:: 2455:. 2435:. 2408:. 2404:: 2378:. 2374:: 2368:8 2351:. 2345:: 2318:. 2314:: 2277:. 2265:: 2221:. 2219:5 2199:. 2187:: 2181:2 2159:. 2108:2 2087:. 2062:. 2000:Z 1998:( 1996:G 1992:Z 1990:( 1988:G 1986:( 1984:f 1980:Z 1978:( 1976:G 1972:X 1961:f 1957:X 1953:X 1951:( 1949:f 1925:c 1905:c 1899:x 1885:x 1883:( 1881:f 1835:x 1831:m 1829:( 1827:f 1823:m 1819:x 1815:m 1811:x 1807:m 1799:x 1797:( 1795:f 1758:m 1756:( 1754:f 1750:x 1748:( 1746:f 1738:m 1734:x 1730:m 1726:x 1718:m 1710:x 1708:( 1706:f 1667:= 1643:2 1622:γ 1618:κ 1598:= 1593:5 1590:6 1574:2 1530:. 1525:3 1510:| 1496:| 1466:. 1461:3 1446:| 1432:| 1415:θ 1396:5 1392:/ 1388:3 1363:= 1337:= 1328:q 1304:= 1271:. 1266:] 1260:6 1257:1 1252:, 1249:0 1245:( 1226:2 1217:1 1205:9 1201:4 1188:+ 1171:3 1165:4 1157:3 1143:, 1138:) 1132:6 1129:5 1124:, 1119:6 1116:1 1110:( 1091:2 1078:+ 1075:3 1071:/ 1067:1 1056:1 1044:+ 1027:3 1021:4 1013:3 999:, 994:) 990:1 987:, 982:6 979:5 973:[ 954:2 941:+ 938:3 934:/ 930:1 919:1 907:+ 894:1 885:) 876:1 873:( 870:9 866:4 851:{ 838:| 826:2 820:) 811:1 808:( 804:q 800:+ 791:q 783:| 755:2 749:) 740:1 737:( 733:q 729:+ 720:q 683:5 680:3 664:| 650:| 629:μ 625:ν 614:ω 610:μ 606:ν 585:, 576:4 573:3 563:| 549:| 519:2 417:, 412:2 408:p 399:1 395:p 391:, 386:1 382:p 373:0 369:p 365:, 360:0 356:p 347:1 340:p 336:, 331:1 324:p 315:2 308:p 304:, 281:} 275:, 272:1 269:, 266:0 263:, 260:1 254:, 248:= 245:n 242:: 237:n 233:p 229:{ 196:m 192:m 188:x 180:m 176:x 132:t 34:. 20:)

Index

Unimodal
SkyTran
mathematics
mode
mathematical object

Probability density function


statistics
probability distribution
mode
normal distributions
Cauchy distribution
Student's t-distribution
chi-squared distribution
exponential distribution
binomial distribution
Poisson distribution
cumulative distribution function
convex
concave
uniform distribution
characteristic function
Laplace–Stieltjes transform
probability mass function
inequalities
multimodal distribution
Chebyshev's inequality § Unimodal distributions
Gauss's inequality

Text is available under the Creative Commons Attribution-ShareAlike License. Additional terms may apply.