Residualization is not the answer: Rethinking how to address multicollinearity

Here I show that a commonly used procedure to address problems stemming from collinearity and multicollinearity among independent variables in regression analysis, “residualization”, leads to biased coefficient and standard error estimates and does not address the fundamental problem of collinearity, which is a lack of information. I demonstrate this using visual representations of collinearity, hypothetical experimental designs, and analyses of both artificial and real world data. I conclude by noting the importance of examining methodological practices to ensure that their validity can be established based on rational criteria.     

Linking Housing Changes to Crime

Housing figures prominently in debates about crime in Britain. It has become commonplace to comment on the increasing associations between crime and council housing. This paper explores some of the issues which link housing and crime. It argues that it is important to recognize how the social base and geography of housing have changed and to understand processes which lead to an increasing concentration in council housing of those with least choice in the housing market and fewest resources elsewhere. At the same time there is a danger in overstating the associations between crime and council housing and neglecting other associations with housing, and homelessness. In view of the associations between crime and council housing, considerable effort has been expended on developing management and other responses designed to reduce crime. The general view is that a broad approach is required in such initiatives and the limited research evidence does not suggest that housing management action alone is effective in reducing crime. The association which exists between council housing and crime requires a policy response which relates to why the most deprived sections of the community are increasingly concentrated in parts of the housing market and exposed to increased risks, and one which relates to the pattern of opportunities and choices in the housing system and not just to housing management.