This site will look much better in a browser that supports web standards, but it is accessible to any browser or Internet device.

Skip Navigation skip menu and banner
University of Wyoming


Analysis of Data: Common Types of Data for Assessing the Effectiveness of a BMP

Common types of data:
    Time series
    Before After Control Implementation (BACI)
    Paired watersheds
The selection of analysis method or methods should reflect the objectives of your project. Often, more than one analysis method will be needed to assess water quality data to determine the effectiveness of a BMP. Data analysis assumes that the data have been properly managed and organized (Section 9)and the data are in a format for conducting analyses.

The following information needs to be considered prior to data analysis (often before the monitoring program has begun):
  • QA/QC – need to know if the data are defensible before data analysis. Adding bad data to a good data set compromises the entire data set.

  • Has the intensity of the sampling changed from intensive monitoring to trend (or vice versa)?

  • It is important to know how the data were collected and by whom. It is important to know if the same methods were used or if the data needs to be separated by method.

  • Is there a large enough data set or sample size (n) to evaluate the project? How much data is available? How many monitoring stations? How many years and how often per year?

  • It is important to know the details of the data and to investigate inconsistencies when necessary. For example, when analyzing streamflow data, are height or discharge measurements being analyzed? Were the data collected under similar precipitation? Are they event, seasonal, or annual flow data? If water quality data are collected along with streamflow, are you in the rising or falling limb of the hydrograph? Is spring runoff or baseflow being measured? And are you in the upper or lower reaches of a watershed?

  • There are significant differences between no data, zero, and data that are below detection limits; these differences should be clearly defined in datasets and be taken into account in the analysis process.

  • In the analysis process, it is important to be able to distinguish between independent (explanatory) and dependent (response) variables.
Due to the large variability in the types of water quality data collected and questions that can be answered, it is difficult to identify specific tools that will be needed. Some very common data analysis techniques are listed below; however, it is highly recommended to contact a statistician to assist with data analysis and interpretation. Additional information on selecting the “appropriate” analysis tool can be found in the NRCS’s National Water Quality Handbook at w2q/water_qual/docs/NatWQhandbookNRCS.pdf.