Project 2 – review 1

Dataset 2 – Armed Conflict Location and Events Data
This week we are being introduced to a new dataset
* Some things we have in thought are
  * Can we get a map of the locations (does that tell us how they are distributed)
  * Locations data
     * Is the data clustered, in what sense?
     * clustering does not necessarily mean geographical, just being part of a subgroup is considered a cluster
     * k-means clustering
     * Spatial data – is it random?
   * What kind of questions do we think about upon seeing that data
   * Where, when, why
   * How much data does the region you pick have
   * Why is the violence there high/low
   * How does the size of the data affect the analysis
   * What factors affect how much data we have on a specific region
   * Can we identify the labels and how they are distributed
   * Cause – what assumptions are made of law enforcement or perpetrators or even victims, who was wrong?

Leave a Reply

Your email address will not be published. Required fields are marked *