The summary of specification tests in panel data models
| Specification test | Null hypothesis | Hypothesis (Basu) | Hypothesis (B&R) | Test result |
|---|---|---|---|---|
| F-limer | OLS model is appropriate | 1, 2, 3 & 4 | 1, 2, 3 & 4 | Preference of panel data model |
| F-limer | OLS model with time effects is appropriate | 1, 2, 3 & 4 | 1, 2, 3 & 4 | Preference of panel data model |
| Hausman | Random effects model is appropriate | 1, 2, 3 & 4 | 1, 2, 3 & 4 | Appropriate |
| LM | Pooled OLS model with individual effects is appropriate | 1, 2, 3 & 4 | 1, 2, 3 & 4 | Inappropriate |
| LM | Pooled OLS model with time effects is appropriate | 1, 2, 3 & 4 | 1, 2, 3 & 4 | Appropriate |
| LM | Pooled OLS model with individual and time effects is appropriate | 1, 2, 3 & 4 | 1, 2, 3 & 4 | Inappropriate |
| Breusch–Godfrey/Wooldridge | No serial correlation in idiosyncratic errors | 1, 2, 3 & 4 | 1, 2, 3 & 4 | The residuals are serially correlated |
| Specification test | Null hypothesis | Hypothesis (Basu) | Hypothesis (B&R) | Test result |
|---|---|---|---|---|
| F-limer | OLS model is appropriate | 1, 2, 3 & 4 | 1, 2, 3 & 4 | Preference of panel data model |
| F-limer | OLS model with time effects is appropriate | 1, 2, 3 & 4 | 1, 2, 3 & 4 | Preference of panel data model |
| Hausman | Random effects model is appropriate | 1, 2, 3 & 4 | 1, 2, 3 & 4 | Appropriate |
| LM | Pooled OLS model with individual effects is appropriate | 1, 2, 3 & 4 | 1, 2, 3 & 4 | Inappropriate |
| LM | Pooled OLS model with time effects is appropriate | 1, 2, 3 & 4 | 1, 2, 3 & 4 | Appropriate |
| LM | Pooled OLS model with individual and time effects is appropriate | 1, 2, 3 & 4 | 1, 2, 3 & 4 | Inappropriate |
| Breusch–Godfrey/Wooldridg | No serial correlation in idiosyncratic errors | 1, 2, 3 & 4 | 1, 2, 3 & 4 | The residuals are serially correlated |
Sharing content requires targeting cookies to be enabled. Please update your cookie preferences to use this feature.