Quantitative Research Methods (DP IB Psychology)

Quantitative Research Methods

• Quantitative research is theory-based and deductive

• Quantitative research focuses on generating general laws of behaviour via the use of large samples and controlled conditions

  • It is objective rather than subjective and personal

• Paper 3 has six relevant quantitative research methods:

  • Lab experiments

  • Field experiments

  • Quasi experiments

  • Natural experiments

  • Correlational research

  • Surveys

Experiments

Lab experiments

• Lab experiments use a standardised procedure in controlled conditions to ensure replicability and reliability

• All variables are kept the same/constant: only the independent variable (IV) changes between conditions

  • the experiment is run in the same room/space per condition

  • the light, heat, sound levels are kept constant per condition

  • the researcher treats the participants in the same way (e.g. tone of voice, body language, clothing) per condition

• Keeping all variables constant means that the dependent variable (DV) can be measured exactly 

Field experiments

• A field experiment takes place in a natural setting, away from the lab

• The researcher can control the environment to some extent but they have to acknowledge the fact that many extraneous variables are part of field experiments e.g.

  • if the experiment takes place outdoors the weather will be a factor (e.g. people's mood lifts in the sun and is less positive in the rain)

• Field experiments still involve the implementation of an IV and DV

• Any qualitative data collected could be used to comment on the quantitative findings and shed light on the actions of the participants 

Quasi experiments

• A quasi-experiment is a research method which does not manipulate the IV; similar to a natural experiment it uses naturally occurring phenomena e.g.

  • Age e.g. an experiment in which digit-span recall is tested between a group of young people compared to a group of older people

  • Gender e.g. the performance of girls is compared to the performance of boys in an experiment testing emotional intelligence

• The researcher has less control over what happens as part of the experimental process as they cannot randomly allocate participants to condition

  • The participants are the conditions of the IV e.g. either young/old, female/male, trained/untrained

Natural experiments

• Natural experiments consist of research in naturally occurring phenomena e.g.

  • living in a war zone

  • suffering from a specific mental illness

• Often naturally occurring phenomena would be highly unethical for a researcher to impose on participants, hence they look for people who have experienced/are experiencing the specific phenomenon

• The research takes place in the participant's natural setting

• As part of a natural experiment, the researcher:

  • cannot manipulate the IV

  • cannot randomly allocate participants to condition (due to the naturally occurring IV)

  • observes, measures and records the natural changes and responses which have occurred due to the naturally occurring phenomena

  • determines the DV and then designs their research to investigate the effects of the IV on the participants

Correlational research

• A correlation is not a research method, rather it is an analysis of the relationship between two co-variables 

• One or both of the co-variables could be pre-existing e.g.

  • school attendance measured as days present at school in Year 11 (co-variable) and number of GCSEs achieved (co-variable)

• One or both of the co-variables could be measured for the research itself e.g.

  • number of arguments with your partner in a month (co-variable) and self-reported stress levels for the same month (co-variable)

• A correlation uses two scores e.g. number of cups of caffeine and the number of hours of sleep

• The researcher submits the two scores to statistical analysis to look for a relationship

• The relationship may show one of three correlations:

  • Positive correlation

    • One co-variable increases as the other increases e.g. calories consumed and weight gained

  • Negative correlation

    • One co-variable increases while the other co-variable decreases e.g. hours spent sitting down and level of fitness

  • Zero correlation

    • There is no relationship between the co-variables e.g. hair colour and IQ

• The correlation coefficient is the calculated value which represents both the direction and the strength of the correlation between the co-variables, expressed as a value between -1 and +1

  • A perfect positive correlation would be expressed as  +1

  • A perfect negative correlation would be expressed as  -1 

  • No relationship would be expressed as 0 

Surveys

• Surveys use the self-reporting method of questionnaires to amass large amounts of data

• Surveys are generally large-scale, reaching high numbers in terms of sample size

• Surveys tend to use predominantly closed questions as these generate quantitative data e.g. Do you enjoy meeting new people? Yes/No

• Surveys are a good way of examining behaviour cross-culturally as participants are asked a set of standardised questions; their answers are then compared to highlight cultural differences

• Data analysis of surveys is straightforward - the data can be 

  • converted to percentages

  • presented graphically

  • statistically analysed

Research design

• Experiments use one of three research designs:

• Independent measures/groups

  • Two groups of participants each experience one condition of the IV 

  • Either the experimental condition or the control condition 

  • The groupings are achieved via random allocation to condition

• Repeated measures

  • One group of participants each experience both conditions of the IV

• Matched pairs

  • Two groups of participants are matched according to specific criteria e.g. gender, age, IQ, memory ability, skill set

Sampling scenarios

• Sampling methods are ways of selecting participants for a study

• There are five types of sampling methods relevant to Paper 3:

  • Random sampling

  • Convenience/opportunity sampling

  • Volunteer sampling

  • Purposive sampling

  • Snowball sampling

Random sampling

• This is the process where every member in the target population has an equal chance of being selected

• The sample may be obtained via the names-out-of-a-hat technique or using specific software random name-generator software

Convenience/opportunity sampling

• This is the process of selecting people who can participate in the study at a given time e.g. whoever is in the common room at 11 am

• This is the most well-used and popular form of sampling method used by researchers

Volunteer/self-selecting sampling 

• This is when individuals choose to participate in the study as a result of the researcher advertising for them e.g. by putting up a poster or ads on social media etc

Purposive sampling

• This is when participants are chosen because they possess characteristics salient to the research study e.g. 18-25 year-old heroin addicts who have attended rehab at least once

• This is used when other forms of sampling cannot be relied on to produce the right sample for the study

Snowball sampling

• This is used to find participants who may be otherwise difficult to locate

• The researcher asks people to help them recruit more participants through their social network/contacts

• This is particularly true of socially sensitive research where the researcher cannot easily gain access to participants e.g. people who have been involved in crime, people who are or who have been drug addicts etc.