Hello,
I am making a research on job satisfaction determinants. While checking job satisfaction between groups of "Work experience Current Position" and " Total work experience" in Univariate/two-way ANOVA , I got significant results for each, although when repeating the same process in One-way ANOVA results become statistically insignificant. What am I doing wrong, and which analysis should i trust?
I have an idea, but can you send the data or show the results? A two-factorial ANOVA can have more power if the added factor reduces the error term.
I think the reason for that is multicollniarity or singularity. Because the independent variables not indepenent from each other. total working experience is also include working experience in current position. Because two way ANOVA uses regression to construct ANOVA equation. This may lead wrong conclusion related to your data. (Type I error). conducting one way ANOVA is more suitable.
Hi,
There are two possibilities:
1. The variances are inflated by multicollinearity (you can assess multicollinearity by examining tolerance and the Variance Inflation Factor/VIF), entry error or outliers that could be inflating the variance of one or more variables.
2. Potential negative dependence between factors
If the two independent variables are related and/or the ANOVA is not balanced, then a two way ANOVA shows you the effect of each variable controlling for the other one.
Hope it helps!
- Badges
- Science topic
- Similar topics
- Biological Science
- Botany
- Pharmaceutical Botany
- Plant Extracts