7. Data Analysis

Data Collection and Analysis:

     The key to good data collection and analysis is good observation. You should be collecting measurable numerical data throughout the course of your experiment. Measurements in metric need to be part of the data collection and should be represented in charts or tables that are clearly labeled and contain relevant information. The data collected should also be represented in a pictorial form through a graph. The graph can be a bar graph, line graph, scatter plot, pie graph or point (coordinate) graph. The graph should clearly show the relationship between the data.  In other words, your data should be in numbers, not just what you see in words. It can be amounts of water used, how long something is, the time something took, etc… If you are not taking any measurements, you are probably doing a demonstration rather than a true science experiment.

     For example, say that some of your plants grew 1 centimeter the third day. Don't say that the plants “look bigger today than they did yesterday.” Words like “bigger” mean different things to different people, so reporting your results using only words can lead to confusion. You want to tell people exactly how much your plants grew. Keep all your results in your notebook.

     Often data must be analyzed before it can be graphed. Analyzing your data means figuring out what the numbers mean to the overall experimental results. Often it is simply a matter of averaging experimental groups or different trials. You should then look for patterns and trends in the data to help you draw general conclusions about your experiment.

     For example if you launched a rocket and the altitude was your collected data, you will have three sets for each of the three times you repeated the experiment. You should create a fourth set that shows the average altitude by averaging your data.