Skip to content

Webinar on Using GIS to Improve Sampling

by on May 18, 2015

gis-sampling

Guest post by Peter Lance, MEASURE Evaluation Research Associate

On May 21 at 10am (EDT), MEASURE Evaluation will host a webinar discussion motivated by the recent MEASURE Evaluation manual on geographic information systems (GIS) and survey sampling. I and fellow authors John Spencer and Aiko Hattori will discuss the possibilities for GIS to make sampling far more precise and efficient.

There is rapidly increasing demand for survey-derived information (values for critical indicators, program impact estimates, etc.) for particular, policy-sensitive subpopulations. Straightforward sampling from conventional national (e.g. census-derived) sampling frames often results in insufficiently small samples from such subpopulations even in the face of huge and costly overall samples.

However, sometimes these subpopulations of interest exhibit predictable patterns of spatial distribution. In these cases, a well-crafted GIS can, often at modest expense, tremendously increase the yield from the subpopulation of interest for a given overall sample size. In other words, such a GIS can greatly reduce the cost per individual successfully sampled from the subpopulation. Moreover, with the explosion in the range and richness of available geo-referenced information, the possibilities for modelling the spatial distributions of subpopulations of interests are expanding at a breathtaking pace.

Please join us for a discussion of the powerful possibilities offered by applying GIS to sampling.

gis-sampling-banner

Leave a Comment

Leave a Reply

Fill in your details below or click an icon to log in:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out / Change )

Twitter picture

You are commenting using your Twitter account. Log Out / Change )

Facebook photo

You are commenting using your Facebook account. Log Out / Change )

Google+ photo

You are commenting using your Google+ account. Log Out / Change )

Connecting to %s

%d bloggers like this: