image description

Glossary

Below are some terms you'll find throughout this application.


TermDefinition

Accuracy A property of a set of Measurements or estimates of being close to the exact or true value of what you're trying to measure. (Source: OECD). When playing darts, Accuracy is hitting the bullseye; whereas Precision is repeatedly hitting the same area of the board.

Action Effectiveness Monitoring A type of monitoring (or research) that attempts to establish “cause and effect” or inferential relationships between fish conditions, habitat conditions, and/or management actions. It pertains to evaluation of projects and programs meant to protect or enhance habitat conditions or fish production. These studies are complex and technically rigorous, and often require measuring many parameters under a very structured statistical design to detect the variable affecting change. From PNAMP Strategy document.

One of the options when identifying the Monitoring Purpose for a Protocol.

Area of Inference A geographical area or biological population on which you are deriving Indicators from Metrics according to the Inference Design.

Attribute A property that describes a data element or entity. In a database, this is often stored as a "field" in a table for a specific entity. For example sites within a master sample have a wide range of attributes (may be continuous or categorical), which can be used to winnow or select a subset of the sites. Attributes can also be used to stratify a sample design.

While some people refer to data collected in the field or created as a result of analyzing or synthesizing field data as "attributes", in Monitoring Resources we use the terms measurements, metrics, and indicators to differentiate these types of data.

Auxillary variable If a variable that is known for every unit of the target population is not a variable of interest but is instead employed to improve the sampling plan or to enhance estimation of the variables of interest, it is called an auxiliary variable. (Source: Encyclopedia of Survey Research Methods)

Auxiliary variables are "extra" variables measured in association with the desired response variable that might be used to increase precision of the estimate, by for example developing a modeled relationship between the response variable and auxiliary variables that might be measured at more sites than can be monitored for the primary response variable. Auxiliary variables are used in model assisted surveys to guide the selection of the sample sites.

Bias An effect which deprives a statistical result of representativeness by systematically distorting it, as distinct from a random error which may distort on any one occasion but balances out on the average. The bias of an estimator is the difference between its mathematical expectation and the true value it estimates. In the case it is zero, the estimator is said to be unbiased. (Source: OECD).

Biased Sample A sample obtained by a biased sampling process - a process which incorporates a systematic component of error, as distinct from random error which balances out on the average. Non-random samples are often, though not inevitably, subject to Bias, particularly when entrusted to subjective judgement on the part of human being. Source: OECD

Opportunistic Samples are a type of Biased Sample. Contrast with Unbiased Samples -- both Probability Samples and Census.

Category A classification rank used for summarizing and reporting that is below Subject, above Subcategory. For example, Fish or Water Quality.
Category belongs to a Subject and has Subcategories
The Subject -> Category -> Subcategory taxonomy provides a series of pick lists for Protocol authors. After selecting a Subcategory, authors then enter a title for their specific Metric or Indicator.

Causal Mechanism The process by which a cause or treatment (i.e., stressor or set of stressors) results in a change.

Census A survey conducted on the full set of observation objects belonging to a given Target Population or universe (aka {Statistical Population}. Source: OECD.

A Monitoring Project conducting a "partial (or restricted)" census observes only members within its study area. For example, all members of a salmonid population within a subwatershed.

Contrast with Probability Sample and Opportunistic Sample.

Confidence Interval A confidence interval is an interval which has a known and controlled probability (generally 95% or 99%) to contain the true value. Source: OECD

Continuous random variable A random variable where the data can take infinitely many values. For example, a random variable measuring the time taken for something to be done is continuous since there are an infinite number of possible times that can be taken. Contrast with discrete random variable.

Control In an experiment, a control group is a baseline group that receives no treatment or a neutral treatment. To assess treatment effects, the experimenter compares results in the treatment group to results in the control group.

From: stattrek.com/Help/Glossary.aspx


Customized Method A modification of an existing Method (owned by a user other than you) to describe minor changes necessary to meet the needs of your project or program. The original Method details are preserved, along with annotations of the changes you will make when implementing the method. Customized Methods can only exist in the context of a specific Protocol.

For example, you may see an existing method describing a technique for measuring substrate that matches most of what you do, except the existing method measures substrate at 10 intervals along each transect and your method only measures substrate at 5 intervals along each transect. Rather than create a new method, you can add the existing method to your protocol and then customize the method and make a note about the change from 10 to 5 intervals.

Data Repository A storage space or container for monitoring or research data that may include Measurements, Metrics, and/or Indicators. Typically repositories are set up by Organizations to hold data generated by one or more Monitoring Programs; however, some repositories hold data from multiple organizations and/or monitoring programs and some don't hold raw data, but instead offer summaries of data, such as technical reports, publications, or figures/graphs displaying data.

Ideally, these repositories are online relational databases (not just text files or spreadsheets) and accessible to the public, or at least accessible via a user account (that requires logging in). A single data set generated by a Method does not constitute an Data Repository.

Note: In monitoringresources.org, we now call these "Environmental Information Repositories" the updated name more accurately reflects the types of data the monitoring community is interested in tracking. You can view the full list of Environmental Information Repositories.

Dataset A collection of data, usually presented in tabular form. Each column represents a particular variable. Each row corresponds to a given member of the data set in question. It lists values for each of the variables, such as height and weight of an object. Each value is known as a datum. The data set may comprise data for one or more members, corresponding to the number of rows. Nontabular data sets can take the form of marked up strings of characters, such as an XML file. Source: Wikipedia

Deconvolution Procedure to remove impact (bias) of metric uncertainty on an indicator estimated cumulative distribution or percentiles estimated for target population and sub-populations.

Discovery Level Metadata Metadata records that typically provide a minimum of essential information to enable a user to find out if a particular dataset exists, its location and ownership, and how to obtain further information.

Contrast with full metadata include additional information on such aspects as data quality and lineage (provenance) and technical details for access and exploitation. Source: GBIF

Discrete random variable A variable that may assume any of a specified list of exact values that are numerical outcomes of a random phenomenom (Source Yale Stats) Contrast with continuous random variable.

Element of a Population Elements of a population refer to the ‘parts’ that make up the target population. Elements of a discrete population are easy to describe in that they are the individuals that make up the population. Each lake or wetland in a population of lakes or population of wetlands is a population element. For continuous resources, population elements are points on the target resource, e.g., points on a stream network. An important rule in the definition of the population elements is its explicit definition so that members of a field crew can determine whether the site visited is a member of the target population.

Endorser Organization An Organization that reviews and sanctions a Protocol.

Environmental Information Repository A storage space or container for monitoring or research data that may include Measurements, Metrics, and/or Indicators. Typically repositories are set up by Organizations to hold data generated by one or more Monitoring Programs; however, some repositories hold data from multiple organizations and/or monitoring programs and some don't hold raw data, but instead offer summaries of data, such as technical reports, publications, or figures/graphs displaying data.

Ideally, these repositories are online relational databases (not just text files or spreadsheets) and accessible to the public, or at least accessible via a user account (that requires logging in). A single data set generated by a Method does not constitute an Environmental Information Repository.

Note: In monitoringresources.org, we used to call these "Data Repositories" but updated the name to more accurately reflect the types of data the monitoring community is interested in tracking. You can view the full list of Environmental Information Repositories.

Experimental Design The process of planning a study that uses manipulation and controlled testing to understand causal processes. Planning an experiment properly is very important in order to ensure that the right type of data and a sufficient sample size and power are available to answer the research questions of interest as clearly and efficiently as possible.

From: www.experiment-resources.com/experimental-research.html
and www.stat.yale.edu/Courses/1997-98/101/expdes.htm


Frame Evaluation In advance of the field season, sample sites are reviewed individually to ensure that they are a member of the design’s target population. For example, a point that lies upstream of an impassable fish barrier would be rejected in a design where the target population included all anadromous stream reaches. May involve a visit to the site in advance of data collection activities to determine whether the site is target or not.

Full Metadata Metadata records that include additional information on such aspects as data quality and lineage (provenance) and technical details for access and exploitation.

Contrast with discovery level metadata which typically provides a minimum of essential information to enable a user to find out if a particular dataset exists, its location and ownership, and how to obtain further information. Source: GBIF

Funder Organization An Organization that pays for the development of a Protocol or that simply funds Monitoring Programs or individual projects that use Protocols. In monitoringresources.org, a Funder Organization can "approve" one or more Protocols for use within its program.

Generalized Random-Tessellation Stratifed (GRTS) Design The generalized random-tessellation stratified design is an algorithm that creates a spatially well-balanced, random selection of sites across 1-dimensional systems (e.g., linear resources such as stream networks), 2-dimensional systems (e.g., areal resources such as forests), or 3-dimensional systems (3-D resources such as oceans or lakes). Source Stevens & Olsen 2004

Geostatistics A branch of statistics focusing on spatial or spatiotemporal datasets (Source Wikipedia). The term was introduced by Matheron (1962) for the study of ‘regionalized variables’; that is, variables supposed to follow some spatial stochastic process (ISI).

GRTS Generalized Random Tessellation Stratified.

The spatial distribution of a natural resource is an important consideration in designing an efficient survey or monitoring program for the resource. Generally, sample sites that are spatially balanced, that is, more or less evenly dispersed over the extent of the resource, are more efficient than simple random sampling. GRTS is a technique for selecting random, spatially balanced probability samples over large extents.


Horvitz-Thompson (HT) Estimator A method of estimating the population total when sampling without replacement from a finite population and when unequal probabilities of selection are used. The estimator is unbiased, linear and can be used with a variety of basic sample designs (ISI; Horvitz and Thompson, 1952).

Hydrologic Unit Code (HUC) The United States is divided and sub-divided into successively smaller hydrologic units which are classified into four levels: regions, sub-regions, accounting units, and cataloging units. The hydrologic units are arranged within each other, from the smallest (cataloging units) to the largest (regions). Each hydrologic unit is identified by a unique hydrologic unit code (HUC) consisting of two to eight digits based on the four levels of classification in the hydrologic unit system. (Source USGS)

Implementation and Compliance Monitoring The monitoring of management actions to determine if they were implemented properly according to the project design or comply with established standards or with laws, rules, or benchmarks. This is normally associated with a restoration project where an engineered solution has been constructed, or where a best management practice (BMP) has been implemented. Implementation monitoring documents the type of action, the location, and whether the action was implemented successfully. It also assesses whether the project remained functional over the life of the monitoring. It does not require environmental data and is usually a low-cost monitoring activity. From PNAMP Strategy document.

One of the options when identifying the Monitoring Purpose for a Protocol.

Inclusion Probability The probability of an element or member of the statistical population (e.g. a site) becoming part of the sample during the drawing of a single sample. Inclusion Probability is the inverse of the statistical weight.
(Source: OECD).

Indicator Value resulting from the data reduction of Metrics across sites and temporal periods based on applying the procedures in the Inference Design. A reported value used to indicate the status, condition, or trend of a resource or ecological process; intended to answer questions posed by the Objectives of the Protocol. Contrast with Metric.
Metric J + Metric K = Indicator X

Per the Inference Design, Metrics are combined or reduced to produce Indicators.


Inference Design Component of the Study Design that defines the process of determining Indicator values based on Metric values observed at sites during specific temporal units over the course of the study. Contrast with Response Design.
Interface Design belongs to Study Design

NOTE: monitoringresources.org will not support detailed documentation of Inference Design; however users may add Data Analysis/Interpretation Methods to their Protocol that explain how Metrics are combined to produce Indicators.


Key Assumption Something that is accepted as true or as certain to happen, without proof. When describing a Protocol's Study Design it is important to document its Key Assumptions. Examples:
  • My frame is accurate
  • Gear (smolt trap, seine, weir, etc.) is functioning properly
  • Gear is calibrated

Landowner Permission Evaluation For sample sites on private lands or sample sites that require traversing private lands, the landowner must be contacted to obtain permission to access the site. A landowner permission evaluation documents the results of the landowner contact.

Local Neighborhood Variance (LNV) Estimator The LNV is an alternate to the Horvitz-Thompson (HT) Estimator or other variance estimators applied to sample surveys. The LNV provides an unbiased estimate of variance if spatial designs (such as GRTS) are used, especially if the response of interest exhibits spatial pattern.

Margin of Error "Radius" (or half the width) of a confidence interval for a particular statistic from a survey. Source: Wikipedia

Master Sample The full list of sites that would be sampled with a complete Census used to generate a Random Sample of sites for a Probability Sample. These sites can be used for comparable, complementary monitoring among separate monitoring organizations and across geographic scales. A Master Sample retains the principles of Randomization and Spatial Balance. For further reading:

Larsen, D.P., A.R. Olsen, and D.L. Stevens. 2008. Using a master sample to integrate stream monitoring programs. JABES 13: 243-254.

Measurement A value resulting from a data collection event at a specific Site and temporal unit. Measurements can be used to produce Metrics using a Response Design.
Measurement A + Measurement B = Metric J

Per the Response Design, Measurements are combined or reduced to produce Metrics.


Metadata Literally, "data about data;" provides information on such aspects as the ‘who, what, where and when’ of data and can be considered from the perspective of both the data producer and the data consumer. Source: GBIF

Descriptive or contextual information which refers to or is associated with another object or resource. This usually takes the form of a structured set of elements which describe the information resource and assists in the identification, location and retrieval of it by users, while facilitating content and access management.

Here in Monitoring Resources, we have a prototype of a "Metadata Builder" which helps users create a discovery level metadata record based on information already provided in monitoring project and protocol documentation systems. This prototype does not attempt to create full metadata records.

For more information, see:

Metadata Record A metadata record is a file of information, usually presented as an XML document, which captures the basic characteristics of a specific dataset, data entity, monitoring project, or other item. For more on this topic, see our definition for metadata.

In Monitoring Resources' Metadata Builder, we attempt to only generate ISO 19115: 2003 compliant discovery level metadata records for one dataset at a time rather than full metadata records.

Method A systematic, standard operating procedure for collecting data (Measurements) or analyzing data (deriving Metrics from Measurements). Method descriptions are part of the Response Design. Methods must be: 1. described in documentation, 2. repeatable by others.

In monitoringresources.org Methods have "State" - to learn more, see our State Diagram.

Methods are associated with a Protocol through a Study Design

Methods belong to a protocol (technically, they are associated through the Study Design of the Protocol, but we wanted to simplify the picture here). Our system has both Data Collection and Data Analysis/Interpretation Methods.


Method Type A classification of a Method based on its function, such as Data Collection or Data Analysis.

Method Unit The standard unit of measure used by the method. Options include Metric, English, or Mixed. We urge Method Owners to not use the "Mixed" option if at all possible.

Metric A value resulting from the reduction or processing of Measurements taken at a Site and temporal unit at one or more times during the study period based on the procedures defined by the Response Design. Metrics can be used to estimate an Indicator using an Inference Design. Note that a variety of Metrics can be derived from original Measurements.
Metrics are part of a Response Design, which is a part of a Study Design

Per the Response Design, Measurements are used to produce Metrics. Per the Inference Design, Metrics are used to produce Indicators.


Model A formalized expression of a theory or the causal situation which is regarded as having generated observed data. Source: OECD

Monitoring Metadata Exchange (MMX) The Monitoring Metadata Exchange (MMX) is a data exchange standard used to define and exchange metadata and location information associated with data collection events. The MMX enables better integration of information from disparate efforts across time and space by providing data seekers with more than just a location of monitoring efforts; it helps answer the 'who', 'what', 'where', 'when', and 'how' about specific projects. Any project can use the MMX standard to exchange data with MonitoringResources.org and any website with map services can use the exchange to increase their content. If your project is interested in using the MMX standard to automate the exchange of information, please contact pnamp.info@gmail.com, or find the full documentation on the MMX standard here.

Monitoring Program An activity led/sponsored by an Organization with stated objectives and that implements one or more Monitoring Projects. Monitoring Programs use a set of Protocols to collect and/or analyze monitoring data for sites in multiple geographic locations in response to a research question, or to meet an agency mission or mandate. Examples: EMAP, Washington Forum on Monitoring, AREMP, BPA's RM&E Program. Program Management is concerned with doing the right projects; Project Management is about doing projects right.
Monitoring Programs can have one or more Protocols, and Protocols can be shared by many Monitoring Programs

Monitoring Programs can have one or more Protocols, and Protocols can be shared by many Monitoring Programs.


Monitoring Project A specific activity led/sponsored by an Organization to collect and/or analyze monitoring data for one or more Monitoring Purposes. Monitoring Programs have one or more Monitoring Projects which typically have budgets, durations, and specific outputs. Project Management is about doing projects right whereas Program Management is concerned with doing the right projects.
Monitoring Programs can have one or more Monitoring Projects

Monitoring Programs can have one or more Monitoring Projects. While we capture some details on Programs, we do not track Projects.


Monitoring Purpose The primary purpose of your research or Monitoring Program. In monitoringresources.org, this is limited to a few options:

Multi-Density Category Defines a subset of the sample frame that will have the same probability of selection for all elements in that subset. Multi-density categories partition the sample frame into mutually exclusive and exhaustive subsets where the probability of selection will be constant for all elements within a subset. Density refers to the density of sample points (i.e., sites) within a category. Compare to Stratum.

Non-random Sample A sample selected by a non-random method. For example, a scheme whereby units are selected purposively would yield a non-random sample. Again, a sample obtained by taking members at fixed intervals on a list is a non-random sample unless the list was arranged in a random order. Source: OECD

Objective A formal statement detailing a desired outcome of a Project. A good objective meets the criteria of being results-oriented, measurable, time-limited, specific, and practical. If the project is well conceptualized and designed, realization of a project’s objectives should lead to the fulfillment of the project’s goals and ultimately its vision.

In monitoringresources.org, an important aspect of documenting a Protocol is defining one or more Objectives. While some Monitoring Programs associate Objectives to management questions, monitoringresources.org does not track management questions.

Opportunistic Sample A type of Biased Sample. Common reasons given for opportunistic sampling are Ease of Access and/or Historic Precedent. Contrast with Probability Sample and Census.

Organization A formal business entity that typically has staff and a budget. Examples: ODFW, Nez Perce Tribe, EPA, Tetra Tech, BPA. In monitoringresources.org, some organizations have special functions: Sponsor Organization, Funder Organization, Endorser Organization.

Oversample coming soon

Owner The person responsible for maintaining a primary entity, such as a Protocol or Method, in monitoringresources.org. Normally, this is the same as the Creator and Author, but doesn't have to be.

Panel A set of Sites that have the same revisit pattern across years. For example, a set of sites visited every year would make up one panel. A set of sites visited every three years would make up a second panel.

Power In general, the power of a statistical test of some hypothesis is the probability that it rejects the null hypothesis when that hypothesis is false (ISI).

Power Analysis Power analysis is a statistical approach to determining the required sample size to obtain population estimates within a given confidence interval. Power analysis generally requires estimates of the distribution of the population to be sampled and in some cases a determination of analytical tools to be applied.

To learn more, visit http://www.statsoft.com/textbook/power-analysis or http://en.wikipedia.org/wiki/Statistical_power.

Precision A property of a set of Measurements of being very reproducible or of an estimate of having small random error of estimation. (Source: OECD). Precision is a quality associated with a class of Measurements and refers to the way in which repeated observations conform to themselves; and in a somewhat narrower sense refers to the dispersion of the observations, or some measure of it, whether or not the mean value around which the dispersion is measured approximates the "true" value. Contrast with Accuracy.

Probability Sample A sample selected by a method based on the theory of probability (random process), that is, by a method involving knowledge of the likelihood of any unit being selected. Source: OECD

Examples of probability sample include Simple Random Sample and GRTS. Contrast with Biased Sample and Census.

Project Scale Effectiveness Monitoring Most salmon or watershed projects are implemented at a small scale, with defined sets of actions intended to protect or enhance specific habitat features or habitat-forming processes. Project scale effectiveness monitoring measures environmental parameters to ascertain whether the actions implemented were effective in creating a desired change in habitat conditions or fish populations. From PNAMP Strategy document.

One of the options when identifying the Monitoring Purpose for a Protocol.

Protocol "A detailed plan that explains how data are to be collected, managed, analyzed, and reported, and is a key component of quality assurance for natural resource monitoring programs" (Oakley et al. 2003). Protocols are necessary to ensure that changes detected by monitoring actually are occurring in nature and not simply a result of measurements taken by different people or in slightly different ways. Required sections of protocols are: Background/Rationale to explain why you use these particular methods to meet your specific Objectives, and Methods and Metrics to describe how you meet the objectives. Also required is Metric-Method Mapping. Sections not required, but important for future repeatability, and metadata accessibility, are: Key Assumptions, Literature Cited, and a self-citation. Protocols can belong to many Monitoring Programs. Protocols have "States" or a status of Draft, In Review, or Published (State Diagram).

In November 2017, Study Designs were extracted from Protocols. If you owned a draft protocol at that time, your Study Design information was saved, extracted and can be found in the list of Study Designs or under your account name.


Purposive Sample A sample in which the individual units are selected by some purposive method. It is therefore subject to biases of personal selection and for this reason is now rarely advocated in its crude form. Source: OECD

Random Sample A sample which has been selected by a method of random selection. Source: OECD Random sampling allows each element of the target population (as represented by the Sample Frame) a positive chance of being selected in the sample. This likelihood of being selected is the inclusion probability (or inclusion density for continuous populations); its inverse is the sample weight.

Randomization An important technique in probability samples or designs that has two functions: guards against selection bias, intentional or otherwise, and it provides an objective, inferential basis for extrapolating from the sample to the target population level. (Source: Sample Design, Execution, and Analysis for Wetland Assessment, Stevens and Jensen, 2007.)

Reference Site A reference site (aka 'control site') is a spatial/temporal location that is similar (ideally identical) to another site, the only difference being that the other site is affected to a greater (or lesser) extent by some mechanism. Of course, no two sites can be identical, but the careful choice of one or more reference sites will permit reasonably rigorous conclusions about differences in responses at those sites to the Causal Mechanism. More information on reference and control sites and the different uses of these terms can be found in Downes et al. (2002, page 122) and Roni et al. (2005, page 22).

Remote Sensing The acquisition of information about an object or phenomenon, without making physical contact with the object. In modern usage, the term generally refers to the use of aerial sensor technologies to detect and classify objects on Earth (both on the surface, and in the atmosphere and oceans) by means of propagated signals (e.g. electromagnetic radiation emitted from aircraft or satellites).

From: wikipedia


Replicate In engineering, science, and statistics, replication is the repetition of an experimental condition so that the variability associated with the phenomenon can be estimated. ASTM, in standard E1847, defines replication as "the repetition of the set of all the treatment combinations to be compared in an experiment. Each of the repetitions is called a replicate." Replication is not the same as repeated measurements of the same item: they are dealt with differently in statistical experimental design and data analysis."

From: en.wikipedia.org/wiki/Replication_(statistics)


Resilience The capacity of a natural system to recover from disturbance. Source: OECD

For instance, imagine two lakes, one that includes only a small number of species and/or functional groups of phytoplankton, zooplankton, and fish, and another thathas multiple species and/or functional groups in each of those categories. The simple lake ecosystem will probably be less able to maintain its previous structure and function after major disturbances such as massive nutrient loading, warming, or changes in seasonal timing of events than the second lake. An often-forgotten second component to the resilience concept that Holling (1972) described is that frequent disturbances help select for characteristics among component populations that lead to greater resilience.

Response Design The Response Design is a component of a Study Design: what and how Measurements will be made (field or laboratory methods) and data analysis/interpretation Methods used to derive Metrics from Measurements as determined by the Spatial Design and Temporal Design. In MonitoringResources.org, describe the response design in the background of the Study Design. Describe detailed methods in the Protocol, and describe the spatial and temporal designs in the Sample Design


Response Design includes Methods, Measurements, and Metrics

Response Design includes Methods, Measurements, and Metrics. In MonitoringResources.org, Methods and Metrics are components of the Protocol.

Want to learn more? check out monitoringadvisor.org

"There are two conceptually separate and distinct design activities involved here. One design effort is determining what to measure, count, or observe given that we are at some point in the population domain, and how to combine or synthesize the measurements, counts, or observations collected. This effort is response design: the process of deciding what to measure and how to measure it; of designing and giving substance to the quantity or quantities we associate with the point. The other design activity is sampling design: the process of specifying how and where to select population units or points on the response surface. The response at these points will be used to estimate attributes of the response surface, which, if we have done the response design correctly, will bear some known relationship to the attributes of the population of real interest.These two processes are conceptually distinct, but often are confused in practice.

The task of finding suitable and efficient ways to sample a spatial environmental population by exploiting its spatial component is greatly simplified if we keep these two processes operationally distinct. The benefit of doing so is that we can develop efficient and practical response designs that exploit the local characteristics of the population, and develop efficient sampling designs that exploit the regional characteristics of the population. We then appeal to sampling theory to establish design-unbiasedness of proposed estimators of the response surface parameters, and appeal to the response design to establish the link between the response surface parameters and population parameters." --- Stevens and Urquhart, 2000. Environmetrics

Safety Evaluation In advance of the field season, sample sites are evaluated by crew members to ascertain whether the site can be safely accessed by the crew. Reasons for rejecting a site for safety reasons could include hazardous terrain, excessive distance from an access road or trail, or other conditions where crew safety cannot reasonable be assured.

Sample Design Provides information on the target and final sample sizes, strata definitions and the sample selection methodology. The usage is not uniform as regards the precise meaning of this and similar terms such as "sample plan", "survey design", "sampling plan" or "sampling design". These cover one or more parts constituting the entire planning of a sample survey inclusive of processing, etc.

The term "sampling plan" may be restricted to mean all steps taken in selecting the sample; the term "sample design" covers in addition, the method of estimation; and "survey design" may cover also other aspects of the survey, e.g. choice and training of interviewers, tabulation plans, etc.

"Sample design" is sometimes used in a clearly defined sense, with reference to a given frame, as the set of rules or specifications for the drawing of a sample in an unequivocal manner (The International Statistical Institute, "The Oxford Dictionary of Statistical Terms", edited by Yadolah Dodge, Oxford University Press, 2003).

As a component of MonitoringResources.org, the Sample Design area contains a link to a Study Design. It is the documentation of the spatial and temporal designs applied to data collection and analysis; including a spatial design that describes where metrics will be determined and how and why locations were chosen, and a temporal design that is the total duration of the entire study, and the frequency of sampling sites.

The Sample Design component allows uploading of sampling sites, and sharing of sample sites (user sample files) that exist in the system. It has sections to characterize sampling locations, sampling event details, and specific spatial and temporal assignments of locations to rotating panels for alternating visits, treatment categories, and blocks. Several Sampling Designs are available to describe how you sample sites, including a Generalized Random Tessellation Stratified (GRTS) design. The GRTS design section uses an algorithm to generate sampling sites to randomly assign sites from a larger pool of sites.

Sample Frame Representation of the target resource used in the selection of the sample. For discrete populations, the frame is the list containing each population element, the list of lakes or streams in the region of interest, sometimes referred to as a "list frame" (e.g. list of all lakes in Alaska). For continuous resources, such as stream networks, a digital map of the stream network is the usual form of the frame. Accurate representations of stream networks therefore become critical as they become the functional target population.

Sample Survey A sample survey is a survey which is carried out using a sampling method, i.e. in which a portion only, and not the whole target population is surveyed (Source: OECD).

Sample surveys rely on selecting part of the resource of interest, characterizing that part, and then making inferences to the entirety. Sample surveys are especially useful if a census of the resource cannot be conducted (i.e., too expensive; too time consuming; technically not feasible).

Sampling Error That part of the difference between a population value and an estimate thereof, derived from a random sample, which is due to the fact that only a sample of values is observed; as distinct from errors due to imperfect selection, bias in response or estimation, errors of observation and recording, etc.

The totality of sampling errors in all possible samples of the same size generates the sampling distribution of the statistic which is being used to estimate the parent value.

Sampling errors arise from the fact that not all units of the targeted population are enumerated, but only a sample of them. Therefore, the information collected on the units in the sample may not perfectly reflect the information which could have been collected on the whole population. The difference is the sampling error (Eurostat, Quality Glossary). Source: OECD

Sampling Unit The specific area or point where Measurements are taken. For natural resources like lakes, wetlands, or streams, the Sampling Unit may be a lake, a portion of the wetland, or a point on a stream. Statisticians define these as the elements that represent the target population. The Spatial Design selects the study's Sites and Sampling Units.

Simple Random Sample Sampling in which every member of the Target Population has an equal chance of being chosen (Inclusion Probability) and successive drawings are independent as, for example, in sampling with replacement. Source: Source: OECD

One downside to simple random samples is that they tend to "clump" sample sites, producing a sample that is not spatially-balanced. To overcome this limitation, consider using a GRTS design.

Site The spatial location where one or more Measurements are taken and Metrics derived. A more generic term for this is spatial unit. The Spatial Design component of the Study Design determines the number and arrangement of Sites; the Temporal Design component determines the revisit patterns and Panel assignments for Sites. One example of a Site is a dam where fish are counted. Another example is a specific reach or length of stream where spawning salmon are counted or habitat is surveyed and summarized.

Spatial Balance The idea that sample points be distributed in some regular or nearly regular pattern, so they are more or less evenly dispersed over the extent of the resource of interest. (Source Stevens & Olsen 2004)

Spatial Design Component of Study Design that defines where in the study region metrics will be determined (how you select which sites to monitor in the study area).
Spatial Design is a component of Study Design

Categories of Spatial Design

Census
Full - All sites in the study area are sampled.
Partial (or restricted) - Only sites within a part of the study area are sampled.

Model-based
  Full - Selection of sites is based on the need to estimate parameters or coefficients of a model that will be used to make the population estimates.
Partial (or restricted) - Selection of sites in part of the study area is guided by the candidate model, and locations in other parts are selected by other methods.

Opportunistic
  Ease of Access- Sites are chosen based on their relative ease of access.
Historic Precedent - Sites are chosen because they have been studied in the past (e.g., Index Reaches).

Survey or Probabilistic
  Generalized Random Tessellation Stratified (GRTS) - Spatially-balanced random sampling.
Random Cluster Sample - Sampling in which a population is divided into clusters (or 'natural' groupings) and a random sample of those clusters is chosen for sampling. Each member of the cluster is then sampled.
Multistage Random Sample - A type of cluster sampling in which a population is divided into clusters (or 'natural' groupings) and a random sample of those clusters is chosen. Instead of sampling each member of the cluster, a portion is randomly selected and sampled.
Proportional to Size - A type of cluster sampling in which the probability of selecting any cluster depends on the size of the cluster. For each sampled cluster, the same number of members in each cluster is sampled so that each member has the same probability of being chosen .
Simple Random Sample, Stratified - A random sample of specified size is drawn from each stratum of a population. Each individual is chosen entirely by chance and each member has a known, but possibly unequal, chance of being chosen.
Simple Random Sample, Non-Stratified - A random sample of specified size is drawn from the population. Each individual is chosen entirely by chance and each member has an equal chance of being chosen.
Systematic, Non-Stratified - A random sample that selects members of the population at regular intervals, starting with a randomly chosen member.

Want to learn more? check out monitoringadvisor.org


Spatial Domain The geographic region over which a survey or study is to be conducted.

Spatial Unit A more technical, statistical term for Site. Compare with Temporal Unit.

Sponsor Organization The Organization that generates or develops a Protocol.

Spring Transition The time of year when productivity of phytoplankton and zooplankton at the bottom of the salmon food chain in the ocean greatly increases due to mixing of nutrient-rich waters at depth with surface waters that are exposed to sunlight.

State Diagram In monitoringresources.org both Protocols and Methods have State. The following diagram illustrates the states that each can pass through:

State diagram for Methods and Protocols

Statistical Population The total membership or population or “universe” of a defined class of people, objects or events. Source: OECD

Status The current state or condition of the indicator of interest.

Status and Trend Monitoring A type of monitoring (or research) that attemptsto estimate the status of fish populations and watershed conditions, and to track over time Indicators of habitat, water quality, water quantity and other factors that affect watershed health. The spatial scale is large and varies from watershed scale (HUC 6), to ESUs, to an entire region such as the Pacific Northwest. From PNAMP Strategy document.

One of the options when identifying the Monitoring Purpose for a Protocol.

Strahler Order In the application of the Strahler stream order to hydrology, each segment of a stream or river within a river network is treated as a node in a tree, with the next segment downstream as its parent. When two first-order streams come together, they form a second-order stream. When two second-order streams come together, they form a third-order stream. Streams of lower order joining a higher order stream do not change the order of the higher stream. Thus, if a first-order stream joins a second-order stream, it remains a second-order stream. It is not until a second-order stream combines with another second-order stream that it becomes a third-order stream. To qualify as a stream a hydrological feature must be either recurring or perennial. Recurring streams have water in the channel for at least part of the year. The index of a stream or river may range from 1 (a stream with no tributaries) to 12. (Source Wikipedia)

Stratification Target populations can be divided into discrete subpopulations, or strata, on which to increase/decrease sample size. A stream network’s elevation could be used to divide the population into elevation strata, allocating an equal number of sites per stratum (likely yielding inclusion probabilities that vary by stratum because the amount of stream length in each stratum likely would vary). Stratification is the process of grouping members of the population into subgroups before sampling. The strata should be mutually exclusive and also collectively exhaustive so that no population element is excluded. (Source: OECD).

Stratum A subset of a statistical population for which an independent sample is selected.

The term stratum is sometimes used to denote any division of the population for which a separate estimate is desired, i.e. in the sense of a domain of study. It is also used sometimes to denote any division of the population for which neither separate estimates nor actual separate sample selection is made. (Source: OECD).

Study Design Or Monitoring Design. A Study Design is the umbrella component in MonitoringResources.org for documenting metadata for your program's monitoring effort or study. Required sections are a Monitoring Program, a link to a Protocol, a Background/Rationale (abstract) to describe overarching goals for the project, and Objectives to answer management or research questions for your entire study or monitoring effort. It also includes a Monitoring Purpose, Key Assumptions, Quality Control and Reporting, Personnel and Training, and Schedule and Budget sections. The study design links to the separately documented components: a Protocol and a Sample Design. In the Protocol component of MonitoringResources.org, you document Methods to define how Measurements are taken and Metrics are calculated so that you can estimate Indicators for target population and sub-populations. Where and when are documented in the Sample Design component of MonitoringResources.org. Within the Sample Design, define where you will sample locations in the Spatial Design, and when in the Temporal Design.

In late 2017, Study Designs were extracted from Protocols. If you owned a draft protocol at that time, your Study Design information was saved with the same name as the protocol from which it was extracted and can be found in the list of Study Designs or under your account name.



Subcategory A classification rank used for summarizing and reporting that is below Category. For example, Fish Abundance or Turbidity.
Subcategory belongs to a Category

The Subject -> Category -> Subcategory taxonomy provides a series of pick lists for Protocol authors. After selecting a Subcategory, authors then enter a title for their specific Metric or Indicator.

Subcategory Focus Attributes of some Metrics and Indicators that help describe the data being collected or analyzed. For example "Fish Life Stage Strategy" is a Subcategory Fucus of the Indicator "Abundance of Fish" which allows people to differentiate juvenile from adult abundance data. Subcategory Foci then have two or more Subcategory Focus Options. For example, "Adult - Spawner" is one of the options under the Subcategory Focus "Fish Life Stage Strategy".

Subcategory Focus Option One of the possible values or selections for a given Subcategory Focus. For example, "Fish Life Stage Strategy" is a Subcategory Focus of the Indicator "Abundance of Fish" and it has various Subcategory Focus Options such as "Adult - Spawner" and "Adult-Outmigrant".

Subject A classification rank used for summarizing and reporting that identifies the broad area of study. For example, Biological or Chemical.
Subject has Categories
The Subject -> Category -> Subcategory taxonomy provides a series of pick lists for Protocol authors. After selecting a Subcategory, authors then enter a title for their specific Metric or Indicator.

Subpopulation A subset of the target population that is of interest for determining indicator value based on inference design.

Systematic Design An experimental design laid out without any randomization. The term is difficult to define exactly because in one sense every design is systematic; it usually refers to a situation where experimental observations are taken at regular intervals in time or space. Source: OECD

Related: Systematic Sample

Systematic Sample A sample which is obtained by some systematic method, as opposed to random choice; for example, sampling from a list by taking individuals at equally spaced intervals, called the sampling intervals, or sampling from an area by determining a pattern of points on a map. Source: OECD

Contrast with Probability Sample designs: Simple Random Sample and GRTS

Related: Systematic Design

Target Population The target population refers to the resource to be described. For example, it might be the number of fish in a stream network in a particular watershed, the biological condition of streams and rivers in a state, or the habitat condition of streams in a national forest. Critical in developing the design is an explicit definition of the target population.

The definition of the target population should contain specific information about the stream network: its spatial extent, its flow status (the perennial network? Includes the intermittent channels?); its size (all stream sizes? Just first order streams?). The definition should be specific enough that an individual could determine whether a location on a stream network is part of the target population; in some cases, membership in the target population might be determined after data have been collected at the site. In statistical usage the term population is applied to any finite or infinite collection of individuals. It has displaced the older term ‘universe’…(ISI).

See "Establishing the Target Population" for guidance from EPA.

Temporal Design Component of Study Design that describes the total duration of the study (Temporal Domain) and the frequency that sites will be sampled during the study (Temporal Unit). The Temporal Design describes the site revisit pattern for each temporal unit. A Panel is a set of sites that have the same temporal unit. A study may have only one panel, but can also have many if the sites need to be revisited at different times during the course of the study.
Temporal Design belongs to a Study Design

Categories of Temporal Design

Complete Revisit - Every site is revisited on each sampling occasion.

Never Revisit - A different site is visited on a given sampling occasion and never visited again.

Opportunistic - Sites are selected and visited on a convenience basis.

Complex - Sites are visited/revisited according to their assigned Panels; covers "Repeating", "Rotating", and "Split" panel designs.

Want to learn more? check out monitoringadvisor.org


Temporal Domain The temporal extent or duration of a study (aka study period). In monitoringresources.org, we ask Protocol owners to specify the planned or desired temporal domain of their study, rather than trying to keep track of the actual temporal domain which may change over time given the ups and downs of funding cycles. Temporal Domain and Temporal Unit are aspects of a study's Temporal Design.

Temporal Unit The interval during which Measurements are made at the Site, and subsequently the interval for which metric values could be determined. Inmonitoringresources.org, we ask Protocol owners to specify the minimum temporal unit of their study when documenting a complex Temporal Design which has multiple Panels. Both Temporal Domain and Temporal Unit are aspects of a study's Temporal Design.

Trend Long-term temporal pattern (i.e. change over time) in what you are monitoring.

Unbiased Sample A sample drawn and recorded by a method which is free from Bias. This implies not only freedom from bias in the method of selection, e.g. random sampling, but freedom from any bias of procedure, e.g. wrong definition, non-response, design of questions, interviewer bias, etc. An unbiased sample in these respects should be distinguished from unbiased estimating processes which may be employed upon the data. Source: OECD

Contrast with Biased Sample.

Uncertainties Research Research to resolve scientific uncertainties regarding the relationships between fish or wildlife health, population performance, habitat conditions, life history and/or genetic. This is a manipulative experiment where variables are manipulated to infer or demonstrate cause and effect relationships using statistical-designed hypothesis testing. From BPA work element attributes, Geiselman.

One of the options when identifying the Monitoring Purpose for a Protocol.

User Site Sites that are not drawn from one of the supported master samples, but have a history of data collection events that investigators wish to integrate into new sample designs. User sites may be part of an opportunistic sample or a probability sample (e.g. selected via a GRTS process).

Integrating user sites into spatially distributed probabilistic designs based on GRTS may have important implications on the validity of your statistical design. You should seek professional advice prior to using user sites in your sample design.


Variance The mean square deviation of the variable around the average value. It reflects the dispersion of the empirical values around its mean. Source: OECD

Variance Analysis (aka Variance Decomposition) The total variation displayed by a set of observations, as measured by the sums of squares of deviations from the mean, may in certain circumstances be separated into components associated with defined sources of variation used as criteria of classification for the observations. Such an analysis is called an analysis of variance, although in the strict sense it is an analysis of sums of squares. Many standard situations can be reduced to the variance analysis form. Source: OECD

Water Resource Inventory Areas (WRIA) Administrative and planning boundaries in the state of Washington. Washington Department of Ecology and other state natural resources agencies have divided the state into 62 Water Resource Inventory Areas or WRIAs to delineate the state's major watersheds. Ecology is responsible for the development and management of these areas. ((Source Dept. of Ecology)

Weight The importance of an object in relation to a set of objects to which it belongs; a numerical coefficient attached to an observation, frequently by multiplication, in order that it shall assume a desired degree of importance in a function of all the observations of the set. The statistical weight is the inverse of the inclusion probability.

While this term has many meanings, for Monitoring Resources, we use it in statistical sense.

(Source: OECD).

Links to useful definitions: