Experiments Flashcards
Advantages of lab experiments
- will produce scientific research
- ensures variable is only thing affecting behaviour
Disadvantage of lab experiments
-reduces ecological validity due to artificial settings which do not reflect real life behaviour
Advantages of field experiments
- offer more realistic setting for study
- has more ecological validity
Disadvantage of field experiments
-lack of control over extraneous variables
Advantage of quasi experiments
-allows us to study effects of the variables psychologists can’t manipulate
Disadvantage of quasi experiments
-no control over participants e.g: social setting, upbringing, lifestyle
Advantage of repeated measures design
- uses fewer participants so cost and time effective
- less likely that individual differences confound the study
Disadvantages of repeated measures design
- can be affected by order effects
- if subjects are tested multiple times they may guess the IV
Advantages of independent measures design
- not affected by order effects
- less likely to be affected by demand characteristics
Disadvantages of independent measures design
- individual differences may confound study or findings
- large samples often needed
Advantages of matched groups design
- can avoid order effects
- can reduce participant variables
Disadvantages of matched groups design
- always some sort of variation between pairs or groups
- time consuming
Participant variables
Characteristics of individual participant that may influence the result
Situational variables
Any feature of the research situation which influences a participant’s behaviour and therefore the result
Controlling participant variables
- use repeated measures design or matched pairs design
- if using IMD, allocate participants to conditions on a random basis so PV more likely to be distributed evenly between conditions
Controlling situational variables (order effects)
- use an independent measures design or a matched pairs design
- if repeated measures design used, it should be counter balanced
Controlling situational variables (environmental factors)
-impose controls to ensure there are as few differences between the groups as possible
Controlling situational variables (demand characteristics)
-do not tell participants of the aim of the investigation (a single blind procedure)
Single blind procedure
If the participant is left blind to the aim of the study
Double blind procedure
If both the participant and the researcher is left blind to the aim of the study
Researcher bias
When a researcher allows their hopes/or expectations for the study’s results to influence what data they choose to hold onto
Researcher effects
When a researcher’s expectations of a participant’s behaviour actually influences the participant’s behaviour.
Alternative hypothesis
Predicts how one variable (the IV) is likely to affect another variable (the DV). An alternative hypothesis predicts the IV will affect the DV
Null hypothesis
Predicts the IV will not affect the DV. Predicts that any difference seen will be due to chance factors rather than the independent variable
Two-tailed hypothesis
Predicts the IV will have a significant effect on the DV (there will be a significant difference in the results from the different conditions of the experiment) but doesn’t predict the direction of the effect
One-tailed hypothesis
Predicts the IV will have a significant effect on the DV but also predicts the direction (e.g: men who have beards are perceived as being significantly older than clean-shaven men)
Operationalising variables
Refers to the process of making variables physically measurable or testable
Strengths of a self-selecting sample
This often achieves a large sample size through reaching a wide audience, for example with online advertisements
Weaknesses of a self-selecting sample
Those who respond to the call for volunteers may all display similar characteristics (such as being more trusting or cooperative than those who did not apply) thus increasing the chances of yielding an unrepresentative sample
Strengths of an opportunity sample
Quick and easy method of collecting data
Weaknesses of an opportunity sample
Similar sort of people will be in any one place, e.g: a club on a Saturday night will not be filled with old people - sample may be unrepresentative
Strengths of a random sample
Sample will be completely unbiased
Weaknesses of a random sample
It can be impractical (or not possible) to use a completely random technique, e.g. the target group may be too large to assign numbers to
Strengths of a snowball sample
Quick way of obtaining information from difficult-to-locate people
Weaknesses of a snowball sample
Sample is biased due to the type of people people know - e.g: if you ask someone who goes to a gym, its likely they will ask lots of other people who work out or go to the same gym, which might reduce validity for a questionnaire or experiment that is about health
Strengths of qualitative data
- very detailed and contains a lot of information
- gives a richness to the details and data
Weaknesses of qualitative data
-hard to analyse and compare because you can’t find measures of central tendency
Strengths of quantitative data
- easy to analyse
- can be summarised
- good way of telling if results are replicable
Weaknesses of quantitative data
- not detailed - lacks reasoning or explanation
- not descriptive
- can lack ecological validity
Advantages of using the mean
All data is included - nothing is missed out
Disadvantages of using the mean
- ‘spurious accuracy’ - impossible to remember 19.95 items for example
- anomalies can skew overall result
Advantages of using the median
-less affected by extreme scores/anomalies so results won’t be skewed
Disadvantages of using the median
- distorted by small samples
- can take a while to calculate because you must order the numbers
Advantages of using the mode
-allows you to use it for non-numerical data
Disadvantages of using the mode
- impossible to calculate if all data is different
- there may be more than one mode
Three measures of dispersion
- the range
- variance
- standard deviation
Variance calculation
Calculate the mean score per condition in the experiment
- for each participant, subtract the mean score from their score - this ‘d’ is the difference
- square each ‘d’ score
- add all your d^2 scores together to get the sum of all differences squared
- calculate the mean of these d^2 scores by dividing this figure by n-1 (which is the number of participants in the sample for that condition minus 1)
Standard deviation calculation
-simply the square root of the variance
Advantages of the range
-quick and easy to calculate
Disadvantages of the range
- data can be skewed by outliers
- top or bottom values could be extremes
Advantages of variance
- takes into account all values
- less likely to be affected by outliers
Disadvantages of variance
- figure calculated is not in the same unit s the original data - it is squared when the original is not
- time consuming and more difficult to calculate than the range
Advantages of standard deviation
- takes into account all data
- expressed in the same unit as the original data
Disadvantages of standard deviation
-time consuming and more difficult to calculate than the range
