Module 5- Spatial Statistics
This lab required to complete the Explore Spatial Patterns in Your Data Using ArcGIS web course via ESRI training. It consists 5 exercises in order to determine which areas in western and central Europe should issue a freeze advisory based on the current readings provided by weather monitoring stations across the region.
Ex. 1- Explored the spatial distribution of data: I learned how to calculate the mean center, median center, and examine directional trends of a spatial data set.
Ex. 2- Explored the values of the data: this consisted of learning how to interpret data from a Histogram and Normal QQ plot in order to determined that the data set consists of characteristics of normal distribution.
Ex. 3- Explored spatial relationships on data: here I used a Voronoi map to identify outlier data points.
Ex. 4- Validated spatial autocorrelation using a Semivariogram to determined that there is an outlier in the data set by analyzing the data points in 3d space as means to better identity notable trends.
Ex. 5- Explored trends in data via Trend Analysis.
In the end, it was concluded that a geostatistical interpolation would be the most appropriate analysis technique for this data set.
This map looks at the distribution of all 431 weather monitoring stations in Western Eruope.
Overall, this was a straightforward lab to follow, but it was dense with information about how to properly interpret a data set we're working with. Before this course I had only taken Introduction to Statistics while in college. Being familiar with some of the terminology helped. But I feel like I've definitely learned a lot from this exercise in terms of applying it to the real world and how to review any conclusions made.
Ex. 1- Explored the spatial distribution of data: I learned how to calculate the mean center, median center, and examine directional trends of a spatial data set.
Ex. 2- Explored the values of the data: this consisted of learning how to interpret data from a Histogram and Normal QQ plot in order to determined that the data set consists of characteristics of normal distribution.
Ex. 3- Explored spatial relationships on data: here I used a Voronoi map to identify outlier data points.
Ex. 4- Validated spatial autocorrelation using a Semivariogram to determined that there is an outlier in the data set by analyzing the data points in 3d space as means to better identity notable trends.
Ex. 5- Explored trends in data via Trend Analysis.
In the end, it was concluded that a geostatistical interpolation would be the most appropriate analysis technique for this data set.
This map looks at the distribution of all 431 weather monitoring stations in Western Eruope.
Overall, this was a straightforward lab to follow, but it was dense with information about how to properly interpret a data set we're working with. Before this course I had only taken Introduction to Statistics while in college. Being familiar with some of the terminology helped. But I feel like I've definitely learned a lot from this exercise in terms of applying it to the real world and how to review any conclusions made.
Comments
Post a Comment