Statistical Concepts I for Ethical, Experimental, and Quantitative Biology Observational study

Statistical Concepts I for Ethical, Experimental, and Quantitative Biology
Ways t' c'llect data
Observational study: observes individuals and measures variables of interest but
does not attempt to influence the responses. (Stand back and watch.)
Experiment: deliberately imposes some treatment in order to observe the
Anecdotal Evidence: based on haphazardly selected individual cases. These cases
need not be representative of any larger group of cases. Anecdotal evidence is
NOT good science!
Experiments are better than observational studies
In principle, experiments can give good evidence for causation. Observational
studies are not as good at this.
Experiments allow us to study the combined effects of several factors.
(Interactions between factors can be very important.)
Experiments allow us to study the specific factors we are interested in, while
controlling the effects of lurking variables.
Parts of an experiment
Experimental units or subjects: the individuals on which the experiment is done
Treatments: specific experimental conditions applied to the units @independent
Factors: explanatory variables in an experiment
Levels: the specific values of the factors which will be used
Response variable: what is being measured on each unit/subject @dependent
The simplest experiment is to apply a single treatme6t and observe the resp'6seC
A common way to report the factors and response variables for an experiment is
with graphs. Learn to recognize two kinds of variables in a graph:
A quantitative variable answers a "how many?" type question. "How old are you?"
and "What is your GPA?" are both questions that would yield quantitative
responses. It makes sense to find an average for an answer to a quantitative
A categorical variable answers a question with a word response, such as "yes", "no",
"blue", "biology". "What is your major?" and "What color are your eyes?" are both
questions that would yield categorical responses. It would NOT make any sense to
find an average for an answer to a categorical question.
Review BioSkills 1 on page B-1 at the back of your textbook (Freeman, 2008,
Biological Science 3/E, Pearson Higher Education) on Reading Graphs and then
examine the kinds of variables in the following examples of graphs:
One Quantitative variable (Histogram, figure 25.4 b on p. 510)
Two Quantitative variables – to show association (Scatterplot p. 37 Fig 2.22 bottomleft graph)
One quantitative variable with separate categorical groups (Side by side plots p. 833
Fig 37.24 or dot plots p. 1061 Fig 47.7)
Two Categorical variables – to show association (bar chart p. 1200 Fig 53.6)
Time course graph - to show sequence of events over time (p. 818 Fig 37.6)
Warnings about Causation
Even a strong association between 2 variables is not by itself good evidence that
there is a cause-and-effect link between the variables.
Pou need a carefully controlled experiment to be able to show causation.
Even when direct causation is present, it is rarely a complete explanation of an
association between two variables.
Even well-established causal relations may not generalize to other settings.
Real life is messy!
To show causation, evaluate an association using the following criteria:
The association is strong.
The association is consistent.
Higher doses are associated with stronger responses.
Alleged cause precedes the effect.
The alleged cause is plausible.