Evaluating Policies Quantitatively as an Economic Consultant

Question 1: Evaluating the Effect of Youth Curfew on Juvenile Crime in Philadelphia

As an economic consultant, evaluating policies quantitatively for clients, if you are not able to do random controlled trials, all you have to rely on is existing data.

The data provided by your client includes time-series data and cross-sectional data. Cross-sectional data is a type of data in which data are collected on a sample population, at a particular point in time, for example, in a survey conducted in a particular year. Time-series data, on the other hand, is data collected over a period of time, for example, from 1990-2020.

For quantitatively robust answers, you could use econometric modeling. Econometric modeling is a quantitative method that uses statistical techniques to estimate economic way and predict future outcomes. It is used to analyze data and test hypotheses in economics. Econometric modeling typically includes three steps: Model specification: Here, you select the variables that you want to include in your model and decide how to specify way between these variables.

To know more about economic consultant please refer to:

Simplest OLS Regression Equation:

OLS Regression Equation: Number of Juvenile Crime Incidents = β0 + β1(Curfew Implementation)

Bias Explanation:

The OLS regression equation above would have bias in this context because it does not account for other factors that may influence juvenile crime incidents, such as socioeconomic status or police presence in different neighborhoods. An omitted variable in this case could be the level of parental supervision, as areas with stricter curfews may also have parents who are more vigilant in monitoring their children's activities. This omitted variable could lead to an overestimation of the effect of the curfew on reducing crime incidents.

Method Proposal: Difference-in-Difference

Implementation Details: To conduct a difference-in-difference analysis, you would need data on juvenile crime incidents before and after the curfew implementation in Philadelphia. You would also need data on a control group of similar cities without a curfew, to compare the difference in crime incidents over time. Potential sources to get the data include crime statistics from city police departments.

Pros and Cons: Difference-in-difference can help control for time-invariant unobserved heterogeneity in the data, but it relies on the assumption that the treatment and control groups would have followed similar trends in the absence of the treatment. It works well when this assumption holds true, but it can fail if there are significant differences in trends between the groups.

Intuition: The idea behind difference-in-difference is to isolate the effect of the treatment (curfew) by differencing out the trends in crime incidents that are common to both the treatment and control groups, before and after the intervention.