Get 2 days of unlimited access
Class Notes (1,000,000)
US (420,000)
UB (3,000)
GEO (30)
Lecture 10

GEO 446LEC Lecture Notes - Lecture 10: Stratified Sampling, Design Of Experiments, Statistical Unit

Course Code
Adam Wilson

This preview shows page 1. to view the full 5 pages of the document.
Chapter 10: Insights from Experimentation
Experimental design
Experimental design
Manipulative experiments: A hypothesis is tested by altering a factor hypothesized to be the
cause of a phenomenon.
Natural experiment: An approach to hypothesis testing that relies on natural variation in the
Treatment: The factor that we want to manipulate. Example: Cages that exclude birds from
Control: A treatment that includes all aspects of an experiment except the factor of interest.
Example: Trees without cages
Replication: Being able to produce a similar outcome multiple times.
Randomization: An aspect of experiment design in which every experimental unit has an equal
chance of being assigned to a particular manipulation.
Microcosm: A simplified ecological system that attempts to replicate the essential features of an
ecological system in a laboratory or field setting.
Designing studies
Why, what, and how?
Why collect the data?
What type of data to collect?
How should the data be collected in the field and then analyzed?
Clear objectives help relate all three components.
Why? Clear objectives
How will the data be used to discriminate between scientific hypotheses?
How the data will be used to make management decisions?
For example:
Determine overall level of occupancy for a species in particular region.
Compare the level of occupancy in two different habitat types within that region.
What? Many kinds of data
Population size/density
Immigration & emigration
Colonization & extinction
Species richness/diversity
How? Sampling and Modeling
Interest lies in making inference from a sample to a population
Want it to be repeatable and accurate
You're Reading a Preview

Unlock to view full version

Only page 1 are available for preview. Some parts have been intentionally blurred.

Others should understand what you have done and be able to replicate
Many different modeling/analysis approaches
Distance sampling, multiple observer, capture-recapture, occupancy modeling…
Purposes Of Sampling
Estimate Attributes (Parameters)
Abundance/ density
Occurrence probability
Allow legitimate extrapolation from data to populations
Provide measures of statistical reliability
Sampling Needs To Be
Accurate leading to unbiased estimates
Repeatable estimates lead to similar answers
Efficient do not waste resources
How Good “On Average” An Estimate Is
Cannot Tell From A Single Sample
Depends On Sampling Design, Estimator, And Assumptions
Precise (repeatable)
Imprecise (less repeatable)
Imprecise & unbiased
Precisely Biased
Imprecise And Biased!
Accurate = Unbiased & Precise
Striving for accuracy
Keep Bias Low
Sample To Adequately Represent Population
Account For Detection
Keep Variance Low
Replication (Adequate Sample Size)
Stratification, Recording Of Covariates, Blocking
Sampling principles
What is the objective?
What is the target population?
You're Reading a Preview

Unlock to view full version