week 5 Flashcards
holding a variable constant is a technique for removing one threat (choose internal or external validity) but it can limit the (choose internal or external validity)
internal validity but it can limit external validity
holding a variable constant means…
matching characteristics like gender, SES, across treatment conditions.
We try to match the groups so that the groups have a similar distribution of each of these factors between the two conditions.
or
control by randomly assigning participants into a treatment condition, or one treatment condition or the other. random characteristic not systematic.
When they’re systematic, it offers an alternative explanation of the findings. So random assignment is another important piece of experimental design.
the zimbardo prison study is an extreme example of a simulation experiment. Researchers often use simulation experi in an attempt to increase the (internal or external) validity of the results
external
field studies tend to have (higher/lower) internal validity and (high/lower) external validity than experimental research studies.
lower internal validity and
higher external validity
what are the four basic elements that an experimental design contains?
M - manipulate IV
M - measure DV
C - comparison or control group
C - strict control
in non-experimental and quasi-experimental designs how are the groups or conditions defined? How does it differ from an experimental design
The difference is the level of manipulation and control.
non/quasi experimental uses naturally occurring characteristic of a person that defines what group they’re going to be in. no randomization
differs from experimental design which uses manipulation from researcher to to assign groups/conditions/variables - use randomization or match individual differences.
also experimental design does establish causality which non/quasi do not
non experimental and quasi-experimental studies always contain a threat to internal validity (true or false)
true
because these designs are always going to have a confounding variable or potential threat to internal validity.
there are two types of developmental research. __________ design evaluates changes in behavior related to age by examining different groups of individuals with each group representing a different age.
cross sectional
There are two types of development research. _______ design evaluates changes in behavior related to age by examining one group of participants who are roughly the same age, at different times
longitudinal
Identify 3 problems in establishing causation
third-variable problem:
- In natural situations, changes in one variable are accompanied by changes in many other variables
Easy to establish relationship between variables but difficult to establish causality bc many potential variables related to outcome
- 3rd variable may be controlling the way the two variables act
directionality:
- determining which is cause and which is effect
- Even if you can establish relationship, difficult to establish which is cause and which is effect
controlling nature:
- must employ STRICT controls to establish causation but can impact external validity
- When applying very strict contols on extraneous variables that would normally coexist in a natural setting we are limiting the ability to generalize
researchers indicate that people who suffer from depression also tend to experience insomnia. However it is unclear whether the depressions causes insomnia or the lack of sleep causes depression. what problem is demonstrated by this example?
directionality
What is directionality problem
- determining which is cause and which is effect
- Even if you can establish relationship, difficult to establish which is cause and which is effect
what is third-variable problem
third-variable problem:
- In natural situations, changes in one variable are accompanied by changes in many other variables
Easy to establish relationship between variables but difficult to establish causality bc many potential variables related to outcome - 3rd variable may be controlling the way the two variables act
explain how extraneous variables can become confounding variables
there are endless numbers of factors that may have an influence. so we would have to control for as many of these factors as we could because we want to prevent these extraneous factors from becoming confounds.
If we demonstrate that they affect or they have the potential to affect how the variables perform systematically, they’ll become a confound.
- If an extraneous variable influences the independent variable/dependent variable.
- Some extraneous variables do not have systematic influence on the independent variable and instead might have random influence.
identify the three methods of actively controlling for extraneous variables
- hold a variable constant (no variation in factors like time of day and environment)
- match characteristics across treatment conditions
- control by randomly (randomization) assigning participants into a treatment condition, or one treatment condition or the other.
non experimental and correlational designs tend to have less control than experimental design. How does this affect internal and external validity of non experimental and correlation studies?
Less control means lower internal validity and higher external validity, thus, nonexperimental and correlational studies tend to have lower internal validity and higher external validity.
correlational - – - – quasi - – - – experimental
lower inter valid - - - - - - - - - - - - - - higher
