2017
DOI: 10.4135/9781071802724
|View full text |Cite
|
Sign up to set email alerts
|

Regression & Linear Modeling: Best Practices and Modern Methods

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
2
1

Citation Types

1
84
0
2

Year Published

2018
2018
2022
2022

Publication Types

Select...
6
1

Relationship

0
7

Authors

Journals

citations
Cited by 69 publications
(87 citation statements)
references
References 0 publications
1
84
0
2
Order By: Relevance
“…Since the dependent variable (ASE) is measured at the ordinal level, we used ordinal logistic regression (OLR) to identify which independent variable had a statistically significant effect on our dependent variable (see Figure 1). Deemed as a suitable procedure to analyze the influence of categorical predictors on an ordinal dependent variable, OLR requires two main assumptions: (1) absence of multicollinearity and (2) proportional odds (Osborne, 2016). For the absence-of-multicollinearity assumption, we verified that our predictors were not correlated with each other, by dummy coding our categorical variables (experience, satisfaction, age, and academic year) and by running a linear regression including all the independent variables.…”
Section: Multivariate Analysis: Ordinal Logistic Regressionmentioning
confidence: 92%
See 1 more Smart Citation
“…Since the dependent variable (ASE) is measured at the ordinal level, we used ordinal logistic regression (OLR) to identify which independent variable had a statistically significant effect on our dependent variable (see Figure 1). Deemed as a suitable procedure to analyze the influence of categorical predictors on an ordinal dependent variable, OLR requires two main assumptions: (1) absence of multicollinearity and (2) proportional odds (Osborne, 2016). For the absence-of-multicollinearity assumption, we verified that our predictors were not correlated with each other, by dummy coding our categorical variables (experience, satisfaction, age, and academic year) and by running a linear regression including all the independent variables.…”
Section: Multivariate Analysis: Ordinal Logistic Regressionmentioning
confidence: 92%
“…This assumption was validated for all the predictors except for gender (p = .010). The rejection of this assumption for gender is likely due to the large size of our data set (Osborne, 2016).…”
Section: Multivariate Analysis: Ordinal Logistic Regressionmentioning
confidence: 98%
“…To do this, we used a quadratic model in the regression; quadratic equations use "a squared term to produce a curve with one inflection point or point where the slope changes direction" (Osborne, 2017, p. 27). The squared term is added to the regression equation (Osborne, 2017).…”
Section: Resultsmentioning
confidence: 99%
“…R explained the correlation between the observed and predicted Y (outcome) scores. R 2 explained the overall variance accounted for (Osborne, 2017). Finally, the F statistic explained whether or not R 2 (variance explained) was statistically significant (Osbourne, 2017).…”
Section: Discussionmentioning
confidence: 99%
“…The model assessed the change in the model R 2 to determine whether any of the variable blocks contributed to explaining additional variance in work performance scores (Osborne, 2017). Block 1, included each of the moderating variables age, gender, and job function.…”
Section: Discussionmentioning
confidence: 99%