Research Methods in Environmental Science

Transcription

1 Research Methods in Environmental Science Module 5: Research Methods in the Physical Sciences Research Methods in the Physical Sciences Obviously, the exact techniques and methods you will use will vary according to the type of research you are doing In this Module, I ll cover some general topics that relate to planning a research project! What kind and quality of data is needed?! What type of sampling plan should be used?! How much data should be collected?

2 Data Quality Objectives The U.S. Environmental Protection Agency developed the data quality objectives process to help organizations plan data collection activities to effectively and efficiently address environmental contamination issues Data quality objectives are a planning tool to help ensure that data collected for a study are! the right kind! the right quality! the right amount Data Quality Objectives Too often, data are collected based on! what s been collected in the past! what s easy to collect! what s affordable! what s familiar rather than focusing on what needs to be done

3 Data Quality Objectives State the problem! Understand exactly what is being studied and why! Often different stakeholders have different views of the problem! The time to come to a common understanding is prior to the data collection, not later Identify the decision! Determine what decisions will be made based on the data Data Quality Objectives Identify inputs to the decision! Decide what data is needed to make the decisions that need to be made! This involves thinking about what variables need to be measured Define the study boundaries! What is the timeframe for the study! What are the spatial boundaries of the study area Three dimensions: length, width, depth

4 Data Quality Objectives Develop a decision rule! Decide on the action limit by deciding how the data will be analyzed and what result will result in which management actions Specify limits on decision errors! Two types of decision errors can exist Do nothing when a problem exists Do something when no problem exists! Decide what probability of each type of error is acceptable Optimize the design Sampling Plans Let s start by defining population and sample The population is the entity that you want to understand. It could be a group of people, a group of animals living in a contaminated area of land, a body of water, the top 6 inches of soil in a particular area, or a body of air. The sample are the items that you actually collect and measure. The sampling plan lays out the strategy for selecting the sample from the population

5 Sampling Plans There are different ways to go about designing a sampling plan, each with pros and cons. Some common sampling plans involve:! Judgment Sampling! Simple Random Sampling! Stratified Random Sampling! Systematic Sampling Judgment Sampling This type of sampling plan involves selecting experimental conditions or taking environmental samples based on professional judgment or on the conditions observed in the field For example, you are looking for contamination on a property so you do a visual inspection and sample those spots you believe appear to be contaminated based on color, odor, surroundings, etc.

6 Judgment Sampling Judgment sampling is good as a screening tool or to find worst case conditions It s easy, it s intuitive, it s what we often do by default However, samples taken in this way are not representative of the population and shouldn t be used to make inferences about a population Simple Random Sampling A simple random sample (SRS) is one that gives each sample unit an equal chance of being selected to be in the sample. Often just called random sampling, SRS gives a sample that is representative of the population as it contains no bias It s simple and intuitive but it s possible to not collect any samples from parts of the population so you might miss something important that, later, you should have anticipated

7 Stratified Random Sampling Stratified random sampling involves splitting the population into sections, or strata, and choosing a random sample from each stratum. It is appropriate when population units are more similar within each strata than they are across strata. Populations of people are often stratified by age, sex, geographic location, political party, or other important variables. Environmental samples are often stratified by land type, terrain, geography, geology, land use, zones of contamination, and so forth. Stratified Random Sampling Advantages of stratification:! You can calculate separate estimates of the parameters for each stratum. If the strata are different from one another on the characteristic under study (contamination for example), you may make different management decisions for different strata.! Different strata can be sampled more or less intensively depending on study goals and population characteristics. For example, areas expected to be more variable should be sampled more intensively.

8 Stratified Random Sampling Disadvantages of stratification:! Usually make decisions on stratification before the study is carried out and these choices may turn out to be incorrect! Stratification can complicate later data use! Data analysis is more complicated Systematic Sampling Systematic sampling involves selecting sample units according to a specified pattern in time or space This ensures that the entire population is evenly covered. For this reason, it is intuitively appealing and often used in environmental sampling

9 Quality of Data: Bias and Precision Two ways of thinking about the quality of data are:! Although individual data points vary, are we getting the correct answer overall? This measures bias.! How much do the individual data points vary under the same conditions? This measures precision. Low Bias/Low Precision

10 High Bias/High Precision Low Bias/High Precision

11 Choosing Sample Sizes Choosing an appropriate sample size is a function of:! Study goals! Degree of precision required! Design type! Budget! and other factors Choosing Sample Sizes Often a high degree of precision is specified and calculations yield large sample sizes Iterative calculations are done until sample sizes come into a reasonable range This is okay since it ultimately leads to either! a balance between competing study requirements of cost and precision! a realignment of study requirements or resources

12 An Example Need to know, estimate, or specify the amount of variability expected in the data (σ) and the precision desired (δ) δ is half of the width of a 95% confidence interval on the mean For simple random sampling with data from an approximately normal distribution a 95% confidence interval on the mean with width 2δ will result from σ δ 2 n = 4 2 Research Methods in the Physical Sciences In summary! Spend sufficient time planning your work to ensure that you will have The right kind of data The right quality The right amount! To meet the goals of the study without wasting resources