2023
DOI: 10.4018/978-1-6684-6859-3.ch009
|View full text |Cite
|
Sign up to set email alerts
|

The Acceptable R-Square in Empirical Modelling for Social Science Research

Abstract: This chapter examines the acceptable R-square in social science empirical modelling with particular focus on why a low R-square model is acceptable in empirical social science research. The paper shows that a low R-square model is not necessarily bad. This is because the goal of most social science research modelling is not to predict human behaviour. Rather, the goal is often to assess whether specific predictors or explanatory variables have a significant effect on the dependent variable. Therefore, a low R-… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

1
46
0

Year Published

2023
2023
2024
2024

Publication Types

Select...
7
2

Relationship

0
9

Authors

Journals

citations
Cited by 98 publications
(47 citation statements)
references
References 14 publications
1
46
0
Order By: Relevance
“…The low R -squared of 0.341 reported in the LPM in Table 4 was because the study focused on the human decision of whether to use formal financial services or not. This is consistent with Ozili (2023b) who posited that any field that attempts to predict human behaviour typically has R -squared values lower than 50%.…”
Section: Analysis Results and Discussionsupporting
confidence: 88%
“…The low R -squared of 0.341 reported in the LPM in Table 4 was because the study focused on the human decision of whether to use formal financial services or not. This is consistent with Ozili (2023b) who posited that any field that attempts to predict human behaviour typically has R -squared values lower than 50%.…”
Section: Analysis Results and Discussionsupporting
confidence: 88%
“…The two models reported in Table 3 explained between 43 and 50% of the variance in performance quality scores. Nevertheless, we prefer not to further comment on R 2 values, as their interpretation is quite controversial (i.e., Ozili, 2022 ), nor is a comparison between the two models reported in Table 3 meaningful, as they consider participants’ state anxiety measured at two distinct timepoints.…”
Section: Resultsmentioning
confidence: 99%
“…The model's in‐sample predictive power was ascertained using the coefficient of determination ( R 2 ) (Hair et al, 2011). Ozili (2023) concluded that R 2 values of 0.02, 0.13, and 0.26 have weak, moderate, and strong predictive power, respectively.…”
Section: Resultsmentioning
confidence: 99%