3. experimentation Flashcards
what is validity?
variables controlled so that any measured effect is likely due to the independent variable
what is reliability?
consistent values in replicates (repeated or independent)
what is accuracy?
data/mean sets of data are close to the true value
what is precision?
measured values are close to each other
what is a pilot study used to do?
help plan procedures, assess validity and check techniques
what do pilot studies allow for?
evaluation and modification of experimental design
the investigator to establish the number of repeat measurements required to give a representative value for each datum point
what can the use of a pilot study ensure?
an appropriate range of values for the independent variable
what can independent and dependent variables be?
continuous or discrete
what do simple designs involve?
one independent variable
what do multifactorial designs involve?
more than one independent variable
what are observational studies able to detect?
correlation
what are observational studies unable to detect and why?
causation, as they do not directly test a hypothesis
what are confounding variables?
variables that may affect the dependant variable other than the independent variable being investigated
how should confounding variables be handled?
held constant, or monitored so that their effect on the results can be accounted for in the analysis
what is an advantage of lab work?
it allows simpler experiments to be conducted more easily as lab conditions can be controlled
what is an advantage of field work?
the findings can be applied to a wider setting
what is a disadvantage of lab work?
organisms may alter their behaviour when removed from their natural habitat
what is a disadvantage of fieldwork?
it may not be as accurate of an observation
what is an observational study?
a study in which the independent variable is not directly controlled by the investigator for ethical or logistical reasons
how do randomised block designs work?
blocks of treatment and control
groups are distributed in such a way that
the influence of any confounding variable is
likely to be the same across the treatment
and control groups
what do controls allow?
scientists to make comparisons with the results of treatment groups
what is a negative control?
gives results in the absence of treatment