Found in "A Note on the Theme of Too Many Instruments" by David Roodman
"(...) a tendency among researchers to view with complacency p values on specification tests above ‘conventional significance levels’ of 0.05 or 0.10. Those thresholds, thought conservative when deciding on the significance of a coefficient estimate, are liberal when trying to rule out correlation between instruments and the error term. A p value as high as, say, 0.25 should be viewed with concern."
What would be a reasonable level of significance to inspect the result of a Hansen J test? 25%?
"(...) a tendency among researchers to view with complacency p values on specification tests above ‘conventional significance levels’ of 0.05 or 0.10. Those thresholds, thought conservative when deciding on the significance of a coefficient estimate, are liberal when trying to rule out correlation between instruments and the error term. A p value as high as, say, 0.25 should be viewed with concern."
What would be a reasonable level of significance to inspect the result of a Hansen J test? 25%?
