| | SLO | ENG | Cookies and privacy

Bigger font | Smaller font

Show document Help

Title:Analiza podatkov pridobljenih z aplikacijo kambi
Authors:ID Stojković, Vuk (Author)
ID Leskovar, Robert (Mentor) More about this mentor... New window
Files:.pdf UN_Stojkovic_Vuk_2021.pdf (4,45 MB)
MD5: 36270B5122C9C1242E0498B864C7035C
PID: 20.500.12556/dkum/6f9a41a5-2dd4-485e-bd4c-a33ef3e14027
 
Language:Slovenian
Work type:Bachelor thesis/paper
Typology:2.11 - Undergraduate Thesis
Organization:FOV - Faculty of Organizational Sciences in Kranj
Abstract:Diplomska naloga obravnava podatke, ki so bili pridobljeni s spletno aplikacijo KAMbi.Ta je namenjena dijakom zaključnih letnikov srednjih šol kot pomoč pri izbiri inženirskega študija. Aplikacija uporabnika vodi preko 78 vprašanj o želeni naravi dela in samooceni lastnih kompetenc. Obdelano je bilo 1750 anket. Predstavljena so programska orodja za izvedbo ankete in obdelavo: a) aplikacija KAMbi, ki je napisana z orodjem za malo-kodno programiranje Oracle Application Express in b) jezik R z nekaj najpomembnejših knjižnic, ki so bile uporabljene pri analizi podatkov. Razvit je skript v jeziku R, katerega glavne komponente so: a) branje vhodnih podatkov iz izvoženih tabel baze ali pa direktno branje iz baze podatkov, b) priprava delovnih spremenljivk kot so matrika odgovorov in matrika časov, c) funkcije za izračun dosežka anketiranca po področjih in primerjavo podobnosti odgovorov, d) opisna statistika s histogrami odgovorov ter področij, e) korelacijska analiza ter f) analiza gruč in čiščenje podatkov. Iz opisne statistike je razvidno, da odgovori pogosteje izražajo pozitivne lastnosti anketiranca. Časi reševanja posameznih odgovorov so od 1 do 30 sekund. Pri čiščenju podatkov smo predpostavili, da anketiranec s poprečnimi kognitivnimi sposobnostmi ne more pošteno odgovoriti na vsa vprašanja v manj kot 380 sekundah. Korelacije med odgovori in področji so statistično šibke in nesignifikantne. Analiza gruč je odgovore klasificirala v dve skupini tako v primeru vseh anket kot v primeru očiščenih podatkov.
Keywords:analiza podatkov, KAMbi, R, programiranje, znanost o podatkih
Place of publishing:Maribor
Year of publishing:2021
PID:20.500.12556/DKUM-79565 New window
COBISS.SI-ID:83439619 New window
Publication date in DKUM:04.11.2021
Views:1280
Downloads:50
Metadata:XML DC-XML DC-RDF
Categories:FOV
:
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:21.07.2021

Secondary language

Language:English
Title:Analysis of data collected by kambi application
Abstract:The research addresses the analysis of the data obtained with the KAMbi web application. The application is intended as support to choose higher education study programme in engineering. The application guides the user over 78 questions about the desired nature of work and self-assessment of their own competencies. In total 1750 surveys were processed. The software tools for conducting the survey and processing are presented: a) the KAMbi application, which is written in Oracle Application Express, and the R language with most important libraries that were used in the data analysis. A script in R language has been developed. The main components of this script: a) reading input data from exported database tables or reading directly from the database, b) preparation of working variables such as answer matrix and time matrix, c) functions for calculating the respondent’s achievement in areas and comparison of similarity of responses, d) descriptive statistics with histograms of responses and areas, e) correlation analysis, and f) cluster analysis and data cleaning. Descriptive statistics shows that the answers more often express the positive characteristics of the respondent. The times for answering individual answers vary from 1 to 30 seconds. In data cleaning step we assumed that a respondent with average cognitive abilities could not honestly answer all the questions in less than 380 seconds. Correlations between responses and areas are statistically weak and insignificant. The cluster analysis classified the responses into two groups both in the case of all surveys and in the case of cleaned data.
Keywords:data analysis, KAMbi, R, programming, data science


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