A Researcher Investigating the Determinants of Crime in the United

Essay

A researcher investigating the determinants of crime in the United Kingdom has data for
42 police regions over 22 years.She estimates by OLS the following regression $$\ln ( \mathrm { cmrt } ) _ { i t } = \alpha _ { i } + \phi _ { t } + \beta _ { 1 } \text { unrtm } _ { i t } + \beta _ { 2 } \text { proyth } _ { i t } + \beta _ { 3 } \ln ( p p ) _ { i t } + u _ { i t } ; i = 1 , \ldots , 42 , t = 1 , \ldots , 22$$
where $\mathrm { cmrt }$ is the crime rate per head of population, unrtm is the unemployment rate of males, proyth is the proportion of youths, $p p$ is the probability of punishment measured as (number of convictions)/(number of crimes reported). $\alpha$ and $\phi$ are area and year fixed effects, where $\alpha _ { i }$ equals one for area $i$ and is zero otherwise for all $i$ , and $\phi _ { t }$ is one in year $t$ and zero for all other years for $t = 2 , \ldots , 22 . \phi _ { 1 }$ is not included. (a) What is the purpose of excluding $\phi _ { 1 }$ ? What are the terms $\alpha$ and $\phi$ likely to pick up? Discuss the advantages of using panel data for this type of investigation.