Lorentz Jäntschi , Donatella Bálint , Lavinia L. Pruteanu , Sorana D. Bolboacă
{"title":"单笼五边形面纳米结构同源物的元素因子研究","authors":"Lorentz Jäntschi , Donatella Bálint , Lavinia L. Pruteanu , Sorana D. Bolboacă","doi":"10.1016/j.md.2016.12.001","DOIUrl":null,"url":null,"abstract":"<div><p>A full factorial design with two factors applied on the family of 81 dodecahedrane congeners is presented. One of the factors used four levels (the layers of the structure), while the other factor used three levels (the atom as Boron, Carbon, or Nitrogen, with the same atom for the layer). Ten calculated properties were input for investigation of the link between properties and structural features. Boron, Carbon or Nitrogen were considered as a reference atom. The models with determination coefficient near 1 comprised 22 to 44 distinct factors. The complexity of the models increases from boron taken as a reference to carbon taken as reference. Therefore, along with the less complexity with the factorial analysis (here elements were accounted in a trinomial scale), alternatives for the reference should also be sought (the available software packages for this type of regression do not check when the table of transformation from multinomial data type to binomial variables is built).</p></div>","PeriodicalId":100888,"journal":{"name":"Materials Discovery","volume":"5 ","pages":"Pages 14-21"},"PeriodicalIF":0.0000,"publicationDate":"2016-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1016/j.md.2016.12.001","citationCount":"4","resultStr":"{\"title\":\"Elemental factorial study on one-cage pentagonal face nanostructure congeners\",\"authors\":\"Lorentz Jäntschi , Donatella Bálint , Lavinia L. Pruteanu , Sorana D. Bolboacă\",\"doi\":\"10.1016/j.md.2016.12.001\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div><p>A full factorial design with two factors applied on the family of 81 dodecahedrane congeners is presented. One of the factors used four levels (the layers of the structure), while the other factor used three levels (the atom as Boron, Carbon, or Nitrogen, with the same atom for the layer). Ten calculated properties were input for investigation of the link between properties and structural features. Boron, Carbon or Nitrogen were considered as a reference atom. The models with determination coefficient near 1 comprised 22 to 44 distinct factors. The complexity of the models increases from boron taken as a reference to carbon taken as reference. Therefore, along with the less complexity with the factorial analysis (here elements were accounted in a trinomial scale), alternatives for the reference should also be sought (the available software packages for this type of regression do not check when the table of transformation from multinomial data type to binomial variables is built).</p></div>\",\"PeriodicalId\":100888,\"journal\":{\"name\":\"Materials Discovery\",\"volume\":\"5 \",\"pages\":\"Pages 14-21\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2016-08-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"https://sci-hub-pdf.com/10.1016/j.md.2016.12.001\",\"citationCount\":\"4\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Materials Discovery\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://www.sciencedirect.com/science/article/pii/S2352924516300308\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Materials Discovery","FirstCategoryId":"1085","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S2352924516300308","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Elemental factorial study on one-cage pentagonal face nanostructure congeners
A full factorial design with two factors applied on the family of 81 dodecahedrane congeners is presented. One of the factors used four levels (the layers of the structure), while the other factor used three levels (the atom as Boron, Carbon, or Nitrogen, with the same atom for the layer). Ten calculated properties were input for investigation of the link between properties and structural features. Boron, Carbon or Nitrogen were considered as a reference atom. The models with determination coefficient near 1 comprised 22 to 44 distinct factors. The complexity of the models increases from boron taken as a reference to carbon taken as reference. Therefore, along with the less complexity with the factorial analysis (here elements were accounted in a trinomial scale), alternatives for the reference should also be sought (the available software packages for this type of regression do not check when the table of transformation from multinomial data type to binomial variables is built).