Ch. 7: The Experimental Research Strategy Flashcards
the experimental research strategy
establishes the existence of a cause-and-effect relationship between two variables
how does the experimental research strategy accomplish its goal?
the experiment manipulates one variable while a second variable is measured and other variables are controlled
true experiment
attempts to show that changes in one variable are directly responsible for changes in a second variable
independent variable
the variable that is manipulated by the research
independent variable in the behavioural sciences
it usually consists of two or more treatment conditions to which participants are exposed
treatment condition
a situation or environment characterized by one specific value of the manipulated variable
how many treatment conditions do expiments contain?
Experiments contain two or more treatment conditions that differ according to the values of the manipulated variable
levels
the different values of the independent variable selected to create and define the treatment conditions
dependent variable
the variable that is observed for changes to assess the effects of manipulating the independent variable
dependent variable in behavioural research
Typically a behaviour or a response measured in a treatment condition
extraneous variables
all the variables in the study other than the independent and the dependent variable
4 basic elements of experimental studies
- manipulation
- measurement
- comparison
- control
manipulation
the researcher manipulates one variable by changing its value to create a set of two or more treatment conditions
measurement
a second variable is measured for a group of participants to obtain a set of scores in each treatment condition
comparison
the scores in one treatment condition are compared with the scores in another treatment condition. Consists of differences between treatments provide evidence that the manipulation has caused changes in the scores
control
all other variables are controlled to be sure that they do not influence the two variables being examined
what studies are considered “real experiments”
ones that satisfy all 4 elements
what elements are unique to experimental studies?
Control and manipulation
how do you determine statistical significance?
you must conduct a hypothesis test and determine that the difference is statistically significant
significant result
the difference is large enough and consistent enough for a hypothesis test to rule out chance as a plausible explanation, and thereby conclude that the difference must have been caused by the treatment
if there is a difference between scores does that mean the treatment has caused the difference?
not necessarily
causation and the third variable problem
- Just because two variables are related doesn’t mean that they have a causal relationship
- It is always possible that a third variable is controlling the two variables and is responsible for producing the observed relation
causation and the directionality problem
- Although a research study may establish a relationship between two variables, the existence of a relationship doesn’t always explain the direction of the relationship
- The remaining problem is to determine which variable is the cause and which is the effect
controlling nature
To establish a cause-and-effect relationship, an experiment must control nature by creating an unnatural situation wherein the two variables being examined are isolated from the influence of other variables
why do experimental studies control nature?
- it’s a necessity
- just because an experiment takes place in an unnatural environment doesn’t imply that the results are unnatural
two specific goals of experimental research
- Demonstrating that the cause (independent variable) happens before the effect (dependent variable). To accomplish this, a researcher manipulates the independent variable and then observes the dependent variable to see if it also changes
- Rule out that the changes are caused by an extraneous vairbale
purposes of manipulation
- To allow researchers to determine the direction of a relationship (the directionality problem)
- To help researchers control the influence of outside variables (the third-variable problem)
purpose of control
Eliminating confounding variables
confounding variable
a third variable that is allowed to change systematically along with the two variables being studies
two important characteristics of a confounding variable
- It influences the dependent variable
- It varies systematically with the independent variable
what is most important when controlling extraneous variables
Identifying those that are most likely to influence the dependent variable
3 main methods of controlling extraneous variables
- Holding a variable constant
- Matching values across treatment conditions
- Control by randomization
holding a variable constant
- Holding an extraneous variable constant can eliminate it
- This can be done by standardizing the environment and participants
- Often it is unreasonable to hold a variable completely constant
- It can limit the external validity of an experiment
matching values across treatment groups
- Matching the levels of an extraneous variable across treatment conditions can help eliminate it
- This can be done by ensuring that the averages of participant, environmental, and time-related vairables (ex. Age, order of treatment conditions) are the same across conditions
- The demands of this technique are impractical for all extraneous variables
counterbalancing
the process of matching treatment conditions
randomization
the use of a random process to help avoid a systematic relationship between two variables
what does randomization involve?
using an unpredictable and unbiased procedure to distribute different values of each extraneous variable across the treatment conditions
random process
all the different possible outcomes are equally likely
example of a random prcoess
random assignment
random assignment
the use of a random process to assign participants to treatment conditions
advantages of control by randomization
- Randomization is the primary technique for controlling the huge number of extraneous variables that exist in any experiment
- It offers a method of controlling a multitude of variables simultaneously
- It does not require specific attention to each extraneous variable
limitations of control by randomization
- It doesn’t guarantee that extraneous variables are really controlled; it uses chance to control variables
- In the long run, with large numbers, it will guarantee a balanced result, but not in the short term, especially with small numbers
advantages and disadvantages of active control methods
- Holding constant and matching require some extra effort
- They are usually only used with one or two specific variables identified as real threats for confounding
- Holding a variable constant can limit external validity
experimental condition
the condition in which the treatment is administered
control condition
the condition in which the treatment is not administered
no-treatment control condition
a condition in which the participants do not receive the treatment being evaluated
the placebo effect
a positive response by a participant to an inert medication that has no real effect on the body. It occurs simply because the individual thinks the medication is effective
placebo control condition
a condition in which participants receive a placebo instead of the actual treatment
outcome research
investigates the effectiveness of a treatment
goal of outcome research
to determine whether a treatment produces a substantial or clinically significant effect
placebo research
attempts to identify the active components of a treatment
the placebo effect in placebo research
The placebo effect must be separated from other, active components of the treatment
manipulation check
an additional measure to assess how participants perceived and interpreted the manipulation and/or to assess the direct effect of the manipulation
two ways to check manipulation
- An explicit measure of the independent vairable
- Embed specific questions about the manipulation in a questionnaire that participants complete after they participate in the experiment
four situations in which manipulation checks are particularly important
- Participant manipulations
- Subtle manipulations
- Placebo controls
- Simulations