| | SLO | ENG | Cookies and privacy

Bigger font | Smaller font

Show document Help

Title:Vpliv velikosti vzorca na rezultate ANOVE - simulacijska študija z uporabo realnih podatkov : diplomsko delo
Authors:ID Chapo, Lan Taona (Author)
ID Sem, Vilma (Mentor) More about this mentor... New window
ID Kraner Šumenjak, Tadeja (Comentor)
Files:.pdf VS_Chapo_Lan_Taona_2026.pdf (3,16 MB)
MD5: D420005693448F7FFA007D0D8F39E5F1
 
Language:Slovenian
Work type:Bachelor thesis/paper
Typology:2.11 - Undergraduate Thesis
Organization:FKBV - Faculty of Agriculture and Life Sciences
Abstract:V diplomskem delu je obravnavan vpliv velikosti vzorca na rezultate enosmerne analize variance (ANOVA) in povezane statistične mere, pri čemer je bil namen ugotoviti, kako se pri različnih velikostih vzorca spreminjajo p-vrednost, F-statistika, mere velikosti učinka, Tukey HSD test ter moč testa. Izvedena je bila simulacijska študija v programskem jeziku R, ki je vključevala štiri scenarije umetno generiranih podatkov z različnimi razlikami med skupinami ter realne podatke iz nabora iris; za vsak scenarij in vsako velikost vzorca od n = 2 do n = 15 je bilo izvedenih 10.000 ponovitev. Rezultati so pokazali, da velikost vzorca vpliva na stabilnost in zanesljivost rezultatov ANOVE: pri scenariju brez razlik med skupinami je bila stopnja napačne zavrnitve ničelne hipoteze skladna z izbrano stopnjo značilnosti, pri scenarijih z manjšimi razlikami ANOVA ni dosegla statistične značilnosti, kar kaže na nezadostno moč testa, pri realnih podatkih pa se je moč testa z večanjem vzorca hitro povečevala in dosegla ustrezno raven že pri manjših vzorcih. Tukey HSD test je dodatno pokazal, da so bile primerjave med posameznimi pari skupin pri majhnih vzorcih manj stabilne, z večanjem vzorca pa zanesljivejše. Pokazalo se je tudi, da sta eta-kvadrat in Cohenov f pri majhnih vzorcih lahko pristranska navzgor, medtem ko je omega-kvadrat stabilnejša in bolj konservativna mera velikosti učinka, zato se je velikost vzorca izkazala kot pomemben dejavnik pri načrtovanju in interpretaciji eksperimentalnih raziskav.
Keywords:ANOVA, simulacijska študija, velikost vzorca, realni podatki
Place of publishing:Maribor
Place of performance:Maribor
Publisher:L. T. Chapo
Year of publishing:2026
Number of pages:1 spletni vir (1 datoteka PDF (X, 42 str., pril.))
PID:20.500.12556/DKUM-98397 New window
UDC:519.233:004-942(043.2)=163.6
COBISS.SI-ID:286327811 New window
Publication date in DKUM:29.07.2026
Views:177
Downloads:21
Metadata:XML DC-XML DC-RDF
Categories:FKBV
:
Copy citation
  
Average score:(0 votes)
Your score:Voting is allowed only for logged in users.
Share:Bookmark and Share



Hover the mouse pointer over a document title to show the abstract or click on the title to get all document metadata.

Licences

License:CC BY-NC-ND 4.0, Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International
Link:http://creativecommons.org/licenses/by-nc-nd/4.0/
Description:The most restrictive Creative Commons license. This only allows people to download and share the work for no commercial gain and for no other purposes.
Licensing start date:09.06.2026

Secondary language

Language:English
Title:The Impact of Sample Size on ANOVA Results – A Simulation Study Based on Empirical Agricultural Data
Abstract:This thesis examines the effect of sample size on the results of one-way analysis of variance (ANOVA) and related statistical measures. The aim of the study was to determine how the p-value, F-statistic, effect size measures, and test power change with different sample sizes. To this end, a simulation study was conducted using the R programming language. Four scenarios of artificially generated data with varying differences between groups and real data from the Iris dataset were used. 10,000 repetitions were performed for each scenario and each sample size from n = 2 to n = 15. The results showed that sample size affects the stability and reliability of ANOVA results. In the scenario with no differences between groups, the rate of false rejection of the null hypothesis was consistent with the selected significance level. In scenarios with smaller differences between groups, ANOVA did not reach statistical significance at the sample sizes considered, indicating insufficient test power. With real data, however, test power increased rapidly as the sample size grew and reached an adequate level even with smaller samples.
Keywords:ANOVA, simulation study, sample size, real data


Comments

Leave comment

You must log in to leave a comment.

Comments (0)
0 - 0 / 0
 
There are no comments!

Back
Logos of partners University of Maribor University of Ljubljana University of Primorska University of Nova Gorica