ABSTRACT
The process of making scientific observations starts with an important realization that naturally occurring phenomena and processes are very complex and as data scientists, we must come up with simple and creative ways to effectively measure and represent them. In spatial analysis, the strategies for collecting and processing data are the keys to scientific success, and many of these analytical strategies have been inspired by several schools of thought. Chief among them are the logical positivists who recommend the use of research designs that rely on direct observations with the help of our senses, established protocols, artificial sensors, or instrumentation to validate research hypotheses. While data generated from primary sources are the most ideal in such designs, the increasing availability of secondary data sources has made it possible for a variety of spatial analyses to be done using computer programs and without necessarily conducting any taxing experiments. The purpose of this chapter is to underscore the relevance of data collection, how and why data are collected, potential gaps in the data collection, and the accompanying processing needed to ensure quality and accuracy in the observations. Studies that are carefully designed with the appropriate mix of data and analytical strategies used for execution, analysis, and interpretation will yield meaningful scientific conclusions and recommendations. Studies drawn from reliable and scientifically valid measures are often the ones that are easily verifiable and replicable, yielding a solid body of evidence and new knowledge for use in policy formulation and scientific decision making.
