We wanted to know where children in NYC are thriving – and why. Which community NYC districts exceed expectations? Which are falling short? And why?
When working with a non-profit on NYC, we wanted to understand how to best allocate our resources. We also wanted to have some good data to use with advocating our local policy makers.
Using the open data collected from Data To Go NYC, we built a statistical model to define the relative contribution of a number of factors on children’s experiences at the neighborhood level. Using this model, we were able to create a holistic picture of how well young people are thriving in terms of education, health and safety. These are complicated factors to measure, yet they are critical aspects of a child’s everyday wellbeing. Looking at how these factors work together in the lives of the children in the neighborhoods we studied, we can get a glimpse into the success of some neighborhoods in comparison to others, and how well they measured up to the expectations for those neighborhoods based on their socio-demographic profile.
Our performance measure was derived by calculating the difference between the predicted likelihood of the community district’s level of performance and the empirically estimated community district’s performance. With this approach, we can also then see which factors are most likely driving the performance.
The methodological steps that we used, in a nutshell, were:
- Download data from Data2Go NYC
- Standardized indicator values
- Determined indicator weighting through a series of principal component analysis and expert consultation
- Calculation of the Index Score
- Deriving the difference between predicted score and actual score
- Using the model to identify the possible drivers of difference
- Visualization of the communities and their drivers
- Share with policy makers