The next phase was to detect the outliers of the data, setting the threshold at two standard deviations from the mean. The results were interesting and surprising, having the five outliers with the highest number of permits issued being zip codes in Staten Island and Rockaway, Queens. Similar results were obtained in the building violations complaints sense. Understanding that in each of NYC borough the analyzed phenomena might perform differently, I re-conducted the analysis on a shortened dataset including Manhattan and Brooklyn only. The results of the new linear models were even less significant than the whole city's, with R-squared of 0.047 in Brooklyn and an insignificant p-value and R-squared of 0.022 for Manhattan and even a less significant p-value.