Methods Flashcards
What are the two types of experiment?
Laboratory
Field
How do lab exp work?
Manipulate IV
Measure DW
In a contrived setting so can control confounding variables
How do field exp work?
Done in a more natural setting
Set up the experiment and measure the DV
As it is in a more natural setting researchers do not have as much control over potential extraneous variables
+ of lab exp
More control
Highly repeatable = highly reliable
Control allows for a causal relationship to be established
- of lab exp
Not in the pp natural environment so may not measure natural behaviour, reducing validity
Pp are aware they are in a study -> could lead to demand characteristics
+ of field exp
Good ecological validity (if pp remain unaware they are in a study)
Less likely to have demand characteristics (if they remain unaware they are in a study)
Can still create a standardised procedure which increases reliability
- of field exp
Less control over confounding variables which could impact the study
In order to study natural behaviour, pp have to be deceived, otherwise they are conducting the exp in a natural environment but it may not be real life behaviour due to Social desirability
Independent variable
The variable you change
Dependent variable
The one you measure
Experimental hypothesis
States there will be a relationship between the two variables, if accepted rejects the null hypothesis
Can be directional or non-directional
Null hypothesis
States there will be no relationship and any relationship that occurs will be due to chance, if accepted it rejects the experimental hypothesis
Directional (one tailed) hypothesis
States there will be a significant relationship between the two variables and that it will be this…
If accepted rejects the null hypothesis
Non-directional (two-tailed) hypothesis
There will be a significant relationship between the two variables but you are not sure what the relationship will be
If accepted it rejects the null hypothesis
What are the 3 types of experimental and research design
Repeated measures
Matched pairs
Independent groups
Describe repeated measures
A type of experimental design where each participant takes part in every condition
How can order effects be reduced
Counterbalancing
What is counterbalancing
Half the participants do A then B and half do B then A
ABBA
+ of repeated measures
No pp variables
Fewer amount of pp needed than other experimental designs
- of repeated measures
Order effects
What are order effects and how can they be overcome?
It is where pp get better or worse as they go from one condition to the next, due to fatigue or practice
Counterbalancing
Describe independent groups
Where each pp only takes part in one condition, normally pp are randomly allocated a condition
+ of independent groups
No order effects
- of independent groups
Pp variables
Number of pp needed
Describe matched pairs
An experimental design where pp are matched on key variables such as age, then split into two groups
One member of the pair is in one condition and the other member is in the other condition
+ of matched pairs
No order effects
Minimises pp variables
- of matched pairs
Hard to do
Time consuming
Pp not exactly the same so not removing pp variables necessarily
What is randomisation
Where the pp are randomly allocated, normally via a computer into one of the two conditions
Situational variables
Factors in the environment that should be controlled
An extraneous variable that could affect the results of the study
Participant variables
Characteristics of individual pp that might influence the outcome of a study
E.g. More motivated
If something is objective it is
Not open to interpretation
Not able to be misinterpreted
What is reliability
Refers to consistency
If you did the same study again with the same people would you get the same result sort of thing
What is validity
Are you measuring what you think you are measuring
Similar to but not necessarily the same as accuracy
What is ecological validity
Whether the findings can be applied to a real life setting
What is predictive validity
If you say someone is going to behave in a certain way and they do, your findings/theory have a high predictive validity
What is internal validity
How well is the study conducted, is there anything else effecting the results
What is external validity
Does the task represent the real world activity
Experimenter effects
Ways in which the experimenter might influence the outcome of an experiment
Can be due to design or presence etc
Demand characteristics
Pp changed their behaviour to meet what they perceive to be the demands of the experimenter
What are control issues
Have you controlled all of the variables that could impact the experiment
Why would you choose a Mann Whitney U test?
Independent groups experimental design
Ordinal (rankings) data
Test of difference
Why would you choose Wilcoxon
Repeated measures experimental design
Ordinal data
Test of difference
Type 1 error in inferential stats
Accepting alternative hypothesis when it’s false
Type 2 error in inferential stats
Accepting the null hypothesis when it’s significant
What is Normal distribution
What measure of central tendency should be used to assess
Where mean median and mode are all in the middle of the data set
Mean
What is skewed distribution
What measure of central tendency should you use to assess
Where mean median and mode are not all together
Median
