Environmental Engineering Reference
In-Depth Information
Table 1.1
Glossary of common terms used in study design
Accurate
Having low bias and variance; where resulting estimates are repeatable and
close to the true value of a population
Alternative
hypotheses
Alternative explanations for an observed pattern or process that are usually
represented in competing statistical or predictive models
Bias
Difference between long-term average of a sample estimate from true
population value
Conceptual
models
Abstractions of reality based on observation of an ecological pattern or
process envisioned by an investigator but not typically formalized
graphically or mathematically
Control
Group of experimental units for which the factor of interest is excluded or
otherwise accounted for in study design
Descriptive
inference
Using observations from a study to learn about or predict other unobserved
facts
Deterministic
Completely predictable, not involving any random components
Effect size
Magnitude of a measurable effect due to a treatment of interest
Empirical models
Models in which data are used to estimate parameters or test predictions
Experiment
A process that imposes a
treatment
on a group of elements or subjects
(experimental units) to measure a response and quantify an effect
Experimental
design
A plan for assigning experimental conditions to subjects and experimental
units
Experimental
error
The inherent variation among experimental units treated alike or variation
not explained by treatments or other variables
Experimental
unit
Subjects (elements) to which individual experimental treatments are applied
Fixed effect
A variable in which levels are not subject to random variation under repeti-
tion of the experiment
Fundamental
objective
What a decision maker wants to accomplish
Hypothesis
Specific statement of reality that is frequently testable by comparing
predictions to data
Independence
Organisms, samples, experimental units, or other objects that can be
represented by a statistical distribution one at a time, without dependence
on the values of other objects
Independent
variables
Those variables hypothesized (including treatments) to contribute to varia-
tion in
dependent
or
response variables
, the values of which depend on
levels or types of independent variables
Means objective
Intermediate objectives that must be accomplished to achieve or address a
fundamental objective
Metapopulation
When the target population of interest is subdivided into discrete patches
across a landscape but movement among patches continues
Model
An abstraction or perceived representation of nature
Objectives
Statements of desired achievements by investigators and decision makers
Random effect
Where repetition of the experiment will result in different levels within the
analyses unless the same experimental units are used
Randomization
Assignment of treatments to or section of experimental or sampling units at
random
Replication
Assignment or selection of multiple experimental units to an individual
treatment
(continued)
