prikaz prve stranice dokumenta Analiza bioekvivalencije
  Download
PDF 449.33 KB
master's thesis
Analiza bioekvivalencije
Zagreb: University of Zagreb, Faculty of Science, 2017. urn:nbn:hr:217:260543
Jelić, Mateja
University of Zagreb
Faculty of Science
Department of Mathematics

Institutional repository: Repository of the Faculty of Science

Cite this document

Jelić, M. (2017). Analiza bioekvivalencije (Master's thesis). Zagreb: University of Zagreb, Faculty of Science. Retrieved from https://urn.nsk.hr/urn:nbn:hr:217:260543

Jelić, Mateja. "Analiza bioekvivalencije." Master's thesis, University of Zagreb, Faculty of Science, 2017. https://urn.nsk.hr/urn:nbn:hr:217:260543

Jelić, Mateja. "Analiza bioekvivalencije." Master's thesis, University of Zagreb, Faculty of Science, 2017. https://urn.nsk.hr/urn:nbn:hr:217:260543

Jelić, M. (2017). 'Analiza bioekvivalencije', Master's thesis, University of Zagreb, Faculty of Science, accessed 11 October 2024, https://urn.nsk.hr/urn:nbn:hr:217:260543

Jelić M. Analiza bioekvivalencije [Master's thesis]. Zagreb: University of Zagreb, Faculty of Science; 2017 [cited 2024 October 11] Available at: https://urn.nsk.hr/urn:nbn:hr:217:260543

M. Jelić, "Analiza bioekvivalencije", Master's thesis, University of Zagreb, Faculty of Science, Zagreb, 2017. Available at: https://urn.nsk.hr/urn:nbn:hr:217:260543

Metadata
TitleAnaliza bioekvivalencije
AuthorMateja Jelić
MentorVesna Lužar-Stiffler (mentor)
Committee memberVesna Lužar-Stiffler (predsjednik povjerenstva)
Committee memberLjiljana Arambašić (član povjerenstva)
Committee memberPavle Goldstein (član povjerenstva)
GranterUniversity of Zagreb
Faculty of Science
(Department of Mathematics)
Zagreb
Defense date and country2017-09-27, Croatia
Scientific / art field,
discipline and subdiscipline		NATURAL SCIENCES
Mathematics
Abstract
Analizom bioekvivalencije utvrđuje se jesu li dva lijeka ekvivalentna, odnosno imaju li isti terapeutski učinak. Za ispitivanje se koriste dva dizajna, paralelni i cross-over, bazirani na dva jednostrana testa (TOST-u). Za dane granice ekvivalencije, koje kod paralelnog dizajna (kojeg sam i koristila u istraživanju) iznose 0.85 i 1.175, testira se na statističkoj razini značajnosti α =0.05 da li je cijeli 90% pouzdani interval omjera sredina grupa sadržan unutar granica ekvivalencije. Ukoliko je, tada imamo ekvivalenciju. Ispitivanjem utjecaja veličine i varijanci grupa na snagu TOST-a za dvije distribucije, normalne (skewness=0, kurtosis=0) i nenormalne (skewness=2 i kurtosis=11) zaključili smo da nije dobro imati premale (prevelike) varijance (npr. 25(400)) niti pak premale veličine grupa, kao npr. 10 ili 20 podataka po grupi. Sama distribucija za razumne veličine grupa i varijanci nema velikog utjecaja na snagu testa.
Abstract (english)
Bioequivalence analysis is used to determine if two drugs are equivalent, i.e. if they have the same therapeutic effect. There are two designs in use, parallel and cross-over design. Both of them are based on two one-sided tests (abbr. TOST) where we test if 90% confident interval of mean ratio is within bioequivalence limits 0.85 and 1.175, which are for parallel design, as I used it in my research. By examining the influence of sizes and variances of two groups on power of TOST test for normal (skewness=0, kurtosis=0) and non-normal (skewness=2 and kurtosis=11) distribution, we conclude it is not good to have too small/high variances (e.g. 25(400)) or small number of subjects per group, like 10 od 20. Distribution doesn’t have too much influences on power if sizes and variances of groups are reasonable.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:217:260543
Study programmeTitle: Mathematical Statistics
Study programme type: university
Study level: graduate
Academic / professional title: magistar/magistra matematike (magistar/magistra matematike)
Type of resourceText
File originBorn digital
Access conditionsOpen access
Terms of useLicence In copyright icon
Created on2018-01-31 11:05:29