The tongfen R package is now on CRAN, so it’s time for an overview post. Tongfen has changed a bit since it’s inception and is now a lot more flexible but slightly more abstract to use. What is tongfen? Tongfen, 通分 in Chinese, generally denotes the process of bringing two fractions onto the least common denominator. This is akin to the problem of making data on different but congruent geographies comparable by finding a least common geography.
Geographic data often comes on different geographic breakdowns. A prime example is census data, where the underlying census geographies can change from census year to census year. This makes it difficult to compare census data across censuses. But comparing census data across censuses at fine geographies is important for many applications. There are two main ways how people deal with this problem. Estimate data for one of the two geographies by (usually at some point) relying on area-weighted interpolation.