Predicting Small-Medium-Enterprise Digital Success Using Polytomous Analysis: A Pilot Study

DOI

10.2991/piceeba2-18.2019.27How to use a DOI?

Keywords

SME, Polytomous, Logistic-regression, Category data, Digital Success

Abstract

The objective of the pilot study is to examine the predictability of digital transformation among Small and Medium Enterprises (SMEs) - using the same previous data collected – employing two step polytomous latent variable analysis technique. The dataset contains 415 observations and 13 variables. The independent latent variables are Company Presence (CompPres), User Connecttion (UserConn), Type of Media for Content Transmission (MediaType), User Content Personalization (UserContPerz), Store Presence (StorePres), Organizational Support (Support), Knowledge Development and Decision Making (KDDM), Marketing and Sales (MarkSale), Customers Relationship (CustRel), Internal Communications (IntComm), Ecosystem engagement (EcoEngg), and dependent latent variable is Digital Transformation Success (Success). Step one is clustering category manifest variables into classes grouped by independent and dependent latent variables. Step two, once latent variables class dataset is created, eight independent latent variables classes are selected. We then test eight one-tailed hypotheses concerning the relationship of eight independent latent variables to the successfulness of digital transformation, Success. Four out of eight variables proved to have significant impact to Success. The result of the study shows 59.3% overall prediction accuracy and 55.775% average class accuracy. Certain class has shown prediction accuracy as good as 71.6%. The applicability of this analysis technique to category dataset is confirmed and may find extension to other cases with similar category data

Copyright

© 2019, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Gadang Ramantoko
PY  - 2019/04
DA  - 2019/04
TI  - Predicting Small-Medium-Enterprise Digital Success Using Polytomous Analysis: A Pilot Study
BT  - Proceedings of the 2nd Padang International Conference on Education, Economics, Business and Accounting (PICEEBA-2 2018)
PB  - Atlantis Press
SP  - 201
EP  - 209
SN  - 2352-5428
UR  - https://doi.org/10.2991/piceeba2-18.2019.27
DO  - 10.2991/piceeba2-18.2019.27
ID  - Ramantoko2019/04
ER  -