Does it make sense to control for nonlinear time trends in every state?
Here Lott makes a very strange argument–that including nonlinear trends for regions is reasonable but including nonlinear trends for individual states makes no sense. If it reasonable for crime rates to follow nonlinear trends in regions, then surely it is reasonable for crime rates to follow nonlinear trends in individual states. Lott argues that a crime rate that was rising before the carry law and as a result of the law started falling after the law would be fitted by a nonlinear trend, making it look like the law had no effect. Equally, you could argue that if a crime rate that following a nonlinear trend which peaked before the carry law, Lott would fit it with a model that showed an increase until the law was passed and then a decrease afterwards, making it look like the law had an effect when nothing special happened to crime rates when the law was passed. To resolve the situation it would be necessary to fit a model with both individual nonlinear trends and a parameter that al
Related Questions
- If an employee leaves state service, is there any time period during which he or she cannot submit a bid for a contract for service currently performed by state employees?
- Is it ok to permit the use of state time and resources in bid development by EBUs?
- Does it make sense to control for nonlinear time trends in every state?
