Research methods

• Laboratory experiments: Takes place in a highly controlled environment

  Strength:

  • High internal validity
  • High replicability

  limitation:

  • low external validity
  • risk of demand characteristics
• Field experiment: Takes place in a everyday setting but the IV is still manipulated.

  Strength:

  • High ecological validity
  • High external validity

  Limitation:

  • Low internal validity
  • difficult to replicate
• Natural experiment: The IV occurs naturally rather than being manipulated by researcher.

  Strength:

  • Can be useful in situations where you cannot manipulate independent variables
  • High ecological validity

  Limitation:

  • participants may not be randomly allocated to experimental conditions
• Observations:

  Covert: participants do not know they are being observed

  Strength:

  • reduce demand characteristics

  Limitation:

  • could be unethical due to issues with consent, right to withdraw
• Observations:

  Overt: participants know they are being observed and have given consent

  Strength:

  • more ethical as participants know they are being studied

  Limitation:

  • Increased demand characteristics
• Questionnaires:

  Open questions: No fixed answers and responders can answer freely

  strength:

  • Richer in depth answers so gain better understanding of response

  Limitation:

  • Time consuming to analyse
• Questionnaires: AO3

  Strength:

  • can be distributed to large number of participants
  • Researcher doesn’t have to be present

  Limitation:

  • participants may not be truthful
  • response bias
  • Social desirability
• Questionnaire:

  Closed questions: Fixed responses through yes/no answers

  strength:

  • easier to analyse than qualitative data

  Limitation:

  • less depth of detail in answers
• Interviews: AO3

  Strength:

  • Can be distributed to large numbers of participants

  Limitation:

  • Participants may not be truthful
  • Social desirability bias
• Interviews:

  Structured: Questions are pre-determined and in a fixed order.

  Strength:

  • Easily repeated,
  • Less chance of interviewer bias
  • higher inter-interviewer reliability.

  Limitation:

  • Interviewers cannot deviate from the questions which reduces the richness of their data.
• Interviews

  Unstructured: No pre-determined questions but a general aim of the interview.

  Strength:

  • More detail than a structured

  interview as the interviewer can explore different avenues of questioning.

  Limitation:

  • Higher risk of interviewer bias
  • time-consuming
• Correlations: designed to test the strength and direction of a relationship between co-variables. Theres no IV and DV

  Negative correlation:

  • As one co-variable increases the other decreases.

  Positive correlation:

  • As one co-variable

  increases so does the other.
• Correlation: AO3

  strength:

  • They can be used when it is unethical or impractical to manipulate.
  • It can tell us is further research is justified.

  Limitation:

  • There may be extraneous variables that influence results and so we cannot establish cause and effect
  • As with experiments they may lack internal/external validity.
• Content and Thematic analysis:

  content analysis: is used to analyse qualitative (non-numerical) data and convert it into quantitative (numerical) data.

  Thematic analysis: assesses the source/material for common themes. These themes are then coded, like content analysis.

  AO3:

  Strength:

  • Good for studying and analysis qualitative data in a numerical way

  Limitation:

  • Could have low inter-rater reliability
• Hypotheses:

  Directional: Predicts the direction of the difference or relationship e.g increase, decrease

  Non-directional: predicts that there is a difference but not a direction

  Null: There’s no difference or relationship
• Sampling:

  Random: Everyone has an equal chance of being picked

  AO3:

  • potentially unbiased
  • Difficult and time consuming
• Systematic sampling: Participants are chosen from a sampling frame which is a list of people from the target population in a particular order. E.g every 5th person

  AO3:

  • Objective system
  • Not everyone has an equal change of being selected
  • time consuming
• Opportunity sampling: Use whoever happens to be willing and available. Most commonly used by researchers.

  AO3:

  • Quick, convenient and economical
  • Researcher can be bias in who they select
  • Not representative or generalisable
• Volunteer sampling: Participants self select themselves to take part. Usually in response to an advert.

  AO3:

  • Less time consuming
  • Participants are motivated and engaged
  • Volunteer bias means the sample is hard to generalise from
• pilot study: A smaller version of a larger study that is conducted to prepare for that study and 'iron out' any problems.
• Observational designs:

  Time sampling: The researcher records the behaviour that is happening at regular time intervals e.g. every 30 seconds.

  Event sampling: The researcher records every time the behaviour is observed by keeping a tally.
• Experimental design:

  Independent groups: Different participants take part in each condition.

  AO3:

  Strength:

  • No order effects
  • Quickest and easiest way to allocate participants

  Limitation:

  • Different participants are needed for each condition which takes more time and expense.
• Repeated measures: The same participants are used in each condition.

  AO3:

  Strength:

  • The dependent variable will not be affected by participant variables
  • It requires less participants

  Limitation:

  • Order effects may affect the participants performance
  • Participants may guess the aim of the study and cause demand characteristics
• Matched pairs: Participants only take part in one condition but are paired with a participant in the other condition based on important characteristics

  AO3:

  Strength:

  • No order effects
  • Reduced participant variables

  Limitation:

  • More expensive and time consuming
• Independent variable: The variable that is manipulated by the researcher to see the effect it has on another variable.

  Dependent variable: The variable that is measured as a result of the effect of the independent variable.
• Counterbalancing: The sample is divided in half, with one half completing the two conditions in one order and the other half completing the conditions in the reverse order
• Test-retest: Giving the same test/ questionnaire on two occasions and correlating the results.

  Inter-observer reliability: Use more than one observer and correlate their recordings.
• Quantitative data: Numerical data which is easily analysed.

  Qualitative data: Non-numerical data, usually in word format.

  Meta- analysis: Researchers combine data from several studies and combine them to give an over all conclusions.
• Nominal data:is in categories i.e. Tall' and 'Short. Each category has a frequency count of how many items/people are in it. Measured in Mode

  Ordinal data: that is usually scores in rank order. Measured in mean and median

  Interval data: that is a continuous scale with equal intervals.
• Sign test:

  1. Insert data into the table
  2. score from condition B is subtracted from Condition A
  3. Add up all the number of + and -
  4. ignore the same score
  5. The S value is the lower number out of the + and -
• Ethics

  • informed consent
  • deception
  • debriefing
  • right to withdraw
  • protection from harm
  • privacy
  • confidentiality
• Informed Consent

  • should be given at the start of the study

  Contains:

  • tells aims of experiments
  • details + procedures + what is required
  • ethics: can withdraw any time + kept anonymous + receive full debrief
  • sign + date
• Independent groups design

  + less demand characteristics

  + no order effects

  • double participants needed
  • researcher cannot control the effects of participant variables
• Distribution curves

  • normal distribution
  • negatively skewered distribution(mean = lowest, mode = highest)
  • positively skewered distribution(mean = highest, mode = lowest)
• Type l error

  • a false positive
  • researcher's results are wrongly stated as being significant when may be due to chance
  • so they reject the null hypothesis in error
• Type ll error

  • a false negative
  • data is overlooked and wrongly said to be not significant
  • so they accept the null hypothesis in error
• Ecological validity

  • type of external validity, refers to the extent to which findings can be generalised to a real-life setting
• Features of a Science

  • Theory construction (highly controlled evidence
  • Hypothesis testing (operationalisation)
  • Empiricism (control variables)
  • Paradigm
  • Reliability / Replicability (sample size/generalisation)
  • Objective
  • Operationalisation
  • Falsifiability
• Falsifiability

  • principle that a theory cannot be scientific unless it admits the possibility of being proven false
  • Karl Popper challenges the psychodynamic approach for being unfalsifiable as Freud's theories cannot be proven false e.g.repression in defence mechanisms