Finding the features you’re interested in is one thing, but the fun truly begins when you get to dig into the numbers. Summarizing your data with statistics isn’t just about crunching numbers; it also helps to reveal patterns and stories hidden within, like spotting climate shifts over decades or understanding where wildlife habitats overlap with developed urban areas.
When you look at a map, what kinds of patterns or trends do you hope to find by analyzing the underlying data?
Getting Simple Statistics
GIS is powerful not only for finding and visualizing features but also for its capability to quickly generate basic statistics, revealing patterns and characteristics of your data. For instance, if you’re a city planner, knowing the average elevation across the city can help inform flood management strategies.
Simple statistics, like minimum, maximum, mean, median, and mode, give you a quick look at trends across your dataset, and standard deviation can help you understand variations in your data. These basic statistics are essential for interpreting everything from temperature changes to vegetation density. Here’s a brief look at each type of statistic:
- Minimum and maximum: These values give you the range of your data. If you’re working with elevation data, you can get an idea of the landscape’s overall variation by knowing the lowest valley (minimum) and highest peak (maximum). Understanding these extremes can be crucial for risk assessment and environmental planning.
- Mean (average): The mean gives you the average value across all pixels in raster. If you’re working with temperature data across a region, the mean can give you a sense of the area’s general temperature. The mean is particularly useful for comparing regions or time periods because you can see how one area’s average compares to another’s.
- Median: When you arrange your pixel values in order from lowest to highest, the median is the one that falls exactly in the middle. In contrast to the mean, the median isn’t affected by extreme values at one end or the other, making it useful for datasets with outliers, like a generally flat area with just a few very high elevation points.
- Mode: The mode is the value in your dataset that occurs most often. This statistic is helpful when working with categorical data such as land cover types. Knowing the mode in a land-cover dataset might tell you which type of vegetation is most common across an area, whether it’s forest, grassland, or desert scrub.
- Standard deviation: This statistic shows how much variation there is from the mean. If you’re working with temperature data, a high standard deviation indicates large swings in temperature across the area, whereas a low deviation means that temperatures are more uniform. This information can help you identify regions with consistent conditions versus those with high variability.
These simple statistics give you a way to summarize raster data in a meaningful, digestible way. Many GIS programs will compute these values for you on the fly, saving time and providing insights at your fingertips for use in planning, analysis, and further studies.
NASA’s freely available Earthdata portal offers global temperature and climate data—an excellent resource to practice calculating and visualizing raster statistics.
Try experimenting with each of these statistics on sample raster data to see how they shape your interpretation. Summarizing data in this way doesn’t just answer questions about individual features but also helps you grasp the larger patterns and variations across your data. Check out NASA’s Earthdata online portal for global temperature and climate data.
Raster data consists of grid-based cells (pixels), each containing a value representing a geographic attribute such as elevation, temperature, or land cover.
A statistical measure that indicates how much values in a dataset vary from the average (mean); higher values mean more variability.
Want to go deeper? The science behind these statistics
Mean, median, and mode each summarize data differently: the mean is sensitive to outliers, the median resists them, and the mode reveals the most common value. Standard deviation quantifies spread, helping analysts quickly spot regions with stable vs. highly variable conditions. Understanding these distinctions is vital when interpreting environmental or urban data—choosing the right statistic can change your conclusions!
Download a sample raster dataset (such as elevation or temperature) and calculate basic statistics using your preferred GIS software.
- Open your sample raster dataset in a GIS program.
- Locate the statistics or summary tool (often found in the layer properties or analysis menu).
- Record the minimum, maximum, mean, median, mode, and standard deviation values.
- Reflect on what these values reveal about your data’s characteristics.
How might the range (minimum and maximum) of your data influence planning decisions for a city or conservation project?
Exploring Advanced Statistical Techniques
If you want to dig deeper into your raster data, advanced statistical techniques like map algebra and its component, zonal statistics, help you go beyond individual data layers to see how they interact.
Map algebra is, as the name implies, a way to perform math with raster layers by adding, subtracting, or multiplying values in each cell. Map algebra lets you calculate across layers, like combining temperature and elevation to pinpoint frost-prone zones. For example, to assess climate impact, use zonal statistics to calculate the average temperature in different vegetation zones. Both map algebra and zonal statistics are powerful tools for raster analysis.
Advanced statistics add a new layer of analysis, allowing you to connect data across different themes, examine trends over time, and understand the relationships between features.
City planners use zonal statistics to determine which neighborhoods are most vulnerable to flooding by overlaying elevation and rainfall data, allowing for targeted interventions and resource allocation.
Think of a real-world challenge—how could combining multiple raster data layers help create better solutions?
- You can now identify and interpret basic statistics (mean, median, mode, etc.) for raster datasets.
- You’ve been introduced to advanced techniques like map algebra and zonal statistics for deeper analysis.
Visualizing and Interpreting Raster Data
Generating statistics is just one part of analyzing your data. The other part is visualizing it. Visualization methods help you interpret and communicate your data. You can display raster data in a variety of ways. Hillshades, gradients, and classifications are popular options for displaying raster data because they show patterns in a way that’s easy to understand at a glance. Visualizing land cover data on a map lets you quickly spot agricultural areas within and around wetlands, making patterns that might be missed in raw data easily visible to both you and your audience.
Visualization is a powerful way to communicate patterns in your data, showing where values cluster or spread. Visualization tools make complex results accessible, helping others quickly grasp the big picture of your analysis.
Visualizing data is just for making pretty maps and doesn’t affect analysis.
Visualization is essential for interpreting and communicating the patterns and insights revealed by statistical analysis—making complex data accessible and actionable.
Reporting and Sharing Results
After all your hard work of collecting, tabulating, and preparing statistics, it’s time to share your findings! Whether you’re preparing a printed report or creating an interactive dashboard, clear visuals and summaries ensure that your analysis is accessible to all. With GIS, you have options like color-coded maps, interactive dashboards, and web maps, making it easy for anyone to view your data — no special software required.
Imagine that you’ve calculated areas at risk for flooding. Instead of presenting a bunch of text and detailed tables of raw data, you bring your data to life by creating a report with color-coded maps, clear charts, and summary tables. These visual aids make it easy for your audience to spot high-risk zones and understand your recommendations.
When you tailor your reports to your audience — whether by creating a printed report for planners, an interactive dashboard for local officials, or an online interactive map-based app for the public — you’re helping your audience not only understand but also act on what you’ve found. A great report doesn’t just look good; it makes your data meaningful.
Summarizing your data with statistics isn’t just about crunching numbers; it also helps to reveal patterns and stories hidden within.
Think about a recent decision you’ve made (personal or professional). How might using statistical summaries and visualization in GIS have improved your understanding or influenced the outcome?
Calculating and visualizing statistics in GIS transforms raw data into meaningful insights, helping you reveal patterns, inform decisions, and communicate results effectively.
Simple and advanced statistical techniques together allow for both rapid data summarization and deep, multi-layered analysis, empowering you to address complex geographic questions.
What is the median in a dataset?
Tap to revealThe median is the value that falls exactly in the middle when data points are arranged from lowest to highest; it is less influenced by outliers than the mean.
Define “map algebra” in the context of GIS.
Tap to revealMap algebra is a technique for performing mathematical operations across raster layers, allowing for combined analysis such as adding, subtracting, or multiplying cell values.
What does a high standard deviation indicate in raster data?
Tap to revealA high standard deviation indicates there is a large amount of variation in the data values, or big swings between low and high values in the dataset.
Which statistic is least affected by extreme values (outliers) in a raster dataset?
How confident are you that you can calculate and interpret simple statistics (mean, median, mode, range, and standard deviation) for raster data in GIS?
If you’re interested in further analysis, explore how spatial statistics and time series can help uncover trends and anomalies in evolving geographic datasets.