Principles of experimental design Flashcards
The rules for psychological research
The principles of good design to set-up for data collection
The tools used in psychological research
Used to summarise and describe the data collected
Common interests in psychology
memory, perception, social behaviour, development, brain and behaviour, and non-human behaviour
Wilhelm Wundt
thought of the concept of structuralism
Structuralism
Mental events can be broken down into their components
William James
wrote the Principles of Psychology
How is the scientific method used in psychology?
to understand behaviour, to confirm the assumption that there is order to the universe, and that there is an underlying power that controls the events that occurs around us
What are the four goals reached using the scientific method?
- description
- explanation
- prediction
- control
What informs us about the accuracy of the explanation
prediction and control
The authority approach
seeking knowledge from source thought to be reliable and valid
advantages and disadvantages of the authority approach
advantage - allows us to assimilate existing knowledge
disadvantage - one shouldn’t follow advice blindly, but should evaluate it critically
The analogy approach
analogy between some new events and a amore familiar, understandable events
The rule approach
try to establish laws or rules that cover a variety of different observations
advantages and disadvantages of the rule approach
advantage - can save time and effort
disadvantage - if followed blindly, can also threaten advancement of understanding
The empirical approach
testing ideas or rules against actual events.
Hypothesis (in psychology)
formally tested expectation about behaviour
A hypothesis must be
testable and falsifiable
Causation
When one factor directly affects another factor. Change in variable 1 results in direct change in variable 2, and there is no possible cause for this change.
Population
the group of interest
Sample
a small group of members from the population of interest
Representative sample
the sample chosen reflect the behaviours and characteristics of the population
What does a representative sample allows
generalising back to the population
Randorm smapling
ensures all members of the population have an squeal change of being chosen
Descriptive statistics
the branch that summarises data collected for the sample
Inferential statistics
generalises form the sample back to the population
Dependent variable
the variable we measure and record (what the participant does)
Property of interest
indirect measure of the dependent variable
Ceiling effect
when the task is too easy
Floor effect
when the task ist too hard
What does the data type determine?
what sort of analyses to perform, what scales to use for measurement and what conclusions can be drawn
Numerical data
measured with an interval or ratio scale
Interval scale
categorises, orders and establishes an equal unit of measurement in the scale
Ratio scale
categorises, orders and establishes an equal unit in the scale, and contains a true zero
What are the two types of categorical data?
ordered data and unordered data
Ordered data
measured with an ordinal scale.
Ordinal scale
catagorises and orders the data. distance between point not considered even
unordered data
measured with a normal scale
Nominal scale
categorises the data without creating a hierarchy
Independent variable
The experimental factors that distinguish the groups and are manipulate buy the experimenter
Subject variable
a factor which is mot directly manipulated by the experimenter
True experiment
an experiment which consists of a manipulated independent variable
Quasi Experiment
an experiment which consists of a subject manipulated variable
What are the four possibilities to having independent variable X and observing dependent variable Y?
- X causes Y
- Y causes X
- A third factor Z causes Y and X (confounding)
- Chance
Control Group
A comparison group which differs form the experimental group. by the absence of the experimental treatment
Placebo effect
is very powerful, and sometimes require a special control group
Demand Characteristics
When cues in a new situation might be interpreted as demanding a certain behaviour
Single-blind Study
when the participants do not know what condition of the independent variable they are assigned to
Double-blind
when neither the experimenter nor the participant know the condition the participant is assigned to
Between-subjects
Each participant is tested in only one level of the independent variable
Within-subjects
each subject is tested in every level of the independent variable
counterbalance
each treatment condition shall be equally exposed to the practice effects and demand characteristic s inherent in the within-subjects design
control variables
any extraneous variables that are held constant during an experiment
Factorial design
When an experiment has a number of independent variables. this means the design is fully crossed, and different independent variables are called factors
Chaiken and Pilner (1987)
Studies observers perception of men and women who ate small and large meals.
Mixed study design
One independent variable is within-subjects, while the other independent variable is between-subjects
Main effects
The effects of one independent variable on the dependant variable, ignoring the other independent variables in the study
Interaction effects
The effects of one independent variable on the dependent variable, taking into account the other independent variables in the study
What effects take more information into account?
interactions effects, which is why they should be interpreted first
How many sources of variability do we haven a 2x2 factorial design?
3 sources of variability - 2 main effects and one interaction effect
