Data for Social Development

Advance your mission with better decisions based on data.

Data Analysis

Affordable data analysis for public and private data. Let us help with answering your data-driven questions with charts, tables and statistics.

Data Wrangling

The hardest part of a data project is finding, cleaning and transforming data. Even if you are an expert analyst, our data wrangling services can make your next project much easier.

Indicator Websites

Data-driven indicators sites are easy, until you try to collect the indicators. Our services can ensure you have a solid library of indicators, without any of the hassle.

Projects

See All of Our Past Projects

Recent Projects

Pedestrians Rhythms By Neigborhood

Eric Busboom.

San Diego’s CityIQ system consists of about 4,400 smart street lamps, which use a variety of sensors to track parking, pedestrians, traffic and a variety of environmental conditions. This analysis reveals pedestrian paterns using time-oriented heatmaps.

`` Full notebook on github

This dataset aggregates the number of pedestrians, traveling in either direction, into 15 minute intervals, per walkway, and links the walkways to communities. Then, data is vizualized by community in a heat map with two time dimensions, known as a rhythm map. Since this data is only available for the prior 6 months, we can’t analyze long term patterns, so we only present a few types of maps, including traffic for hour of day versus day of week and for hour of day versus week of year.

Continue Reading →

Imperfect Tests and The Effects of False Positives

The US government has been widely criticized for its failure to test as many of its citizens for COVID-19 infections as other countries. But is mass testing really as easy as it seems? This analysis of the false positive and false negative rates of tests, using published sensitivities and specificities for COVID-19 rt-PCR and antigen tests, shows that even tests with slightly less than perfect results can produce very large numbers of false positives.

Continue Reading →

Modeling an Infection with Changing R for San Diego County

Eric Busboom.

The SIR infection model is a simple way of exploring the effects of a social distance policy on a large population such as San Diego County

`` Full notebook on github

The SIR infection model is a simple set of differential equations that describe how a disease can spread under very homogeneous, stable conditions. The model gets it’s name from the three “compartments” for people in diferent conditions:

Continue Reading →

Crime Rhythm Maps

Eric Busboom.

Exploring crime patterns with Ryhthm Maps, heat maps with two time dimensions.

`` Full notebook on github

A Rhythm map is a heat map with two time dimensions, which makes it much esier to find temporal patterns in some kinds of data. This example will use crime incidents from San Diego county, from 2007 to 2013..

Plotting the number of incidents for burglary versus the hour of the day, for instance, results in this dull chart:

Continue Reading →

Isochrone Analysis

Eric Busboom.

An isochrone is the area of travel from a point in a constant time, which allows for more realistic analysis of retail cachment areas than a simple radius.

An isochrone ( meaning “equal time” ) is an area that encloses the points one can travel to in a fixed time. For a bird, an isochrone would be a circle, but humans usually have to follow roads, so human isochrones have shapes that mirror the road network. Despite the name, isochrones are most often computed using a fixed distance. For instance, a 5km isochrone would be all the points that are within 5km of a point, but using distances based on a road network, not the straight distance. So, instead of a 5km radius circle, a 5km isochrone will have a non-circular shape.

Continue Reading →

All projects →