RESEARCH METHODS

RESEARCH METHODS

1. Planning Research

   • Quantitative research
     • Data in the form of numbers
     • Not as informative as qualitative research
   • Qualitative research
     • Data in the form of words
     • Based usually on opinions
     • More detailed compared to quantitative research
   • Formulating research questions: Research starts with a research question: something that psychologists want to find out i.e. How do phobias occur?
   • Formulating aims: An aim is a general statement a psychologist wants to investigate i.e. To investigate whether people recall more words depending on whether they are presented acoustically or visually.
   • Formulating a hypothesis: A testable statement making predictions about what will happen in an investigation
     • Experimental: Used only in experiments which predicts a difference and has a IV and DV
     • Alternative: Predicts a difference or correlation following a null hypothesis
     • Research: Predicts a difference in the measured variables
   • Sampling techniques
     • Random: Every person has an equal chance of being chosen i.e. Choosing names out of a hat
       • Strength: Avoids bias as researcher has no control over who is chosen
       • Strength: Law of probability states researcher will normally get a representative sample
       • Limitation: There is a chance of a freak sample which would not be representative
       • Limitation: Compared to other methods it is time consuming as all the potential partcipants have to be identified before the draw can be made
     • Stratified: Participants are selected after the sampling frame has been stratified or layered
       • Strength: Avoids the problem of freak samples by more or less guaranteeing a representative sample
       • Strength: Relatively subjective as once the sampling frame is stratified it is normally left to chance who is selected from each strata
       • Limitation: More time consuming than other techniques because all potential participants need to be assesed and catergorised
       • Limitation: Researcher may not identify all the key characteristics for stratification meaning the sample is still not representative.
     • Systematic: Taking every Nth person in the sampling frame for the sample i.e. Selecting every 5th person from a sampling frame of 100 in alphabetical order
       • Strength: Avoids bias once the researcher has chosen what number they are going to use for selection, they have no control over who is selected
       • Strength: Law of probability says that the researcher will normally get a representative sample
       • Limitation: There is a chance a freak sample will be obtained which is not representative.
       • Limitation: It is not as objective as random sampling because the researcher may decide on how people are listed before selection and what number to use for the system
     • Opportunity: Participants have been chosen due to convenience
       • Strengths: Less time consuming than other sampling techniques
       • Limitation: Quite likely sample will be bias because only certain types of people will volunteer to be chosen
       • Limitation: Researcher may show bias when selecting the participants

2. Experimental Methods

   • Experiments
     • Field: An experiment carried out in a natural environment
       • IV is still manipulated by the experimenter
       • Gives findings more ecological validity as the people are in real-life settings and more likely to behave as they normally would do
     • Laboratory: An experiment carried out in a controlled environment
       • Allow researchers to manipulate one stimulus to elicit a response while keeping all other stimuli the same
       • Makes it easier to reliably establish cause and effect
     • Quasi-experiments: An experiment where the experimenter does not directly control the IV
       • Can take place in either a laboratory or field setting
       • Cannot manipulate the IV so would have to wait for it to occur naturally
   • Variables
     • Independent: Something manipulated or set up in an experiment
     • Dependent: Something that is measured after the independent variable may have had an effect on it
     • Extraneous: A variable besides the IV which could affect the DV. (Noise, poor eyesight of participant)
       • Standardisation: The process of keeping variables the same
       • Counterbalancing: Ensuring variables occur in all possible combinations an equal number of times
       • Randomisation: Process of deciding the order of use of variables by chance
     • Confounding: A variable besides the IV which could affect the DV. (Balancing the number of men and women in an experiment)
   • Effects
     • Order: Where behaviour is affected because participants take part in two or more conditions in a particular order
     • Practice: Where participants performance improves over time across conditions through familiarity with a task/environment
     • Fatigue: Where participants performance worsens across conditions because of tiredness/boredom
     • Demand characteristics: Features or cues which help participants figure out what is expected of them

3. Non-experimental methods

   • Experimental design
     • Repeated measures: Same participants are used in each condition
       • Strength: Any differences in conditions are due to changes in the IV and not participant variables
       • Strength: Fewer participants are recruited as they are used twice
       • Limitation: Order effects-Fatigue, practice, demand characteristics (Can be reduced by counter-balancing or randomising)
     • Matched pairs: Different participants are used in conditions but are related in the sense they are matched up on important psychological characteristics.
       • Strengths: No order effects as different participants are used
       • Strengths: Individual differences are reduced between conditions as participants have been matched up
       • Limitations: Time consuming and expensive to match participants
     • Independent groups design: Different participants are used in each condition, no attempt to match participants across conditions
       • Strengths: No order effects as participants only take part in one condition
       • Strength: Allows task conditions to be controlled i.e. participants can be given same list of words in both conditions so it doesnt become a confounding variable.
       • Limitations: Any differences between conditions could be due to the individual differences of participants (Larger the sample the less likely)
   • Self-report methods
     • Questionnaires: Pre-determined list of questions to which participants may respond can occur: face-to-face, through the post, via the telephone and on the internet
       • Strength: Can be filled in at once making it more cost-efficient and less time-consuming than interviews
       • Limitation: Relies on respondents returning them, response rates make it difficult to generalise.
       • Limitation: Researchers often get a response bias
       • Strength: Filled in anonymously so more honest responses are given
       • Limitation: Can lead to less honest answers as no researchers are monitoring
       • Limitation: Respondents may mis-interpret the questions.
     • Interviews: Involve researcher asking questions directly to participant
       • Structured: Pre-determined questions
         • Strength: Make it easier to compare answers
         • Limitation: Researcher cant go into much depth
       • Unstructured: General topic which researcher wants to cover
         • Strength: More detailed questions, follow up new lines of enquiry
         • Limitation: Answers cant be compared
     • Open questions: Participants are free to answer a question however they want and in more depth
     • Closed questions: Fixed responses to questions, not much depth or detail
   • Pilot studies: A small scale trial study
     • Help researchers test their questions to make sure they are valid
     • Identify any factors that might negatively affect the outcome of the study, saves researcher wasting time and money on research that could be unreliable
   • Correlation studies: Analysis of data to test for a relationship between two variables
     • Are not like experiments because they cannot establish cause and effect (due to the fact they occur after the event)
     • There's no IV or DV
     • Allow researchers to statistically analyse situations that cannot be manipulated experimentally for ethical or practical reasons.
   • Observational studies: Simply involve watching and recordings peoples behaviour
     • Natural setting
       • High ecological validity, easier to generalise to real life
     • Laboratory setting
       • High levels of control, easier to establish cause and effect
     • Covert: Undercover, people are not aware they are being watched
       • Ethical concerns, is it right to watch someone without there consent?
     • Overt: Open, people are aware they are being watched
       • Observer effect: Participants don't behave normally
     • Participant: Researcher joins in with the group
       • Allows researcher to experience a situation participants do
     • Non-participant: Researcher is not directly involved
       • Researcher remains objective as they are not directly involved
   • Content analysis: Process of interpreting secondary material as a means to understand people
   • Case studies: In-depth investigation of one person or group
     • Based on small samples so is difficult to generalise
     • Allow researchers to study events they could not practically or ethically maniuplate

4. Representing data and descriptive statistics

   • Representing data
     • Bar graphs: Used to represent data which is divided in categories, sometimes known as discrete data
     • Line graphs: Used to represent data which is in numerical form, sometimes known as continuous data
     • Histograms: Alternative to line graphs as they also represent continuous data.l
     • Scattergrams: Used to show relationships between variables. Different from other graphs which display differences
   • Descriptive data
     • Mode: Most common score in data set
     • Mean: Average score (Add all scores together and divide by total number of scores
     • Median: Middle score in data set (once data is organised in ascending order)
     • Range: Measure spread of data (Highest score minus the lowest score)
     • Standard deviation: Calculates spread of scores away from the mean
     • Positive correlation: As one variable increases so does the other variable
     • Negative correlation: As one variable increases the other decreases
     • Zero correlation: No clear relationship between two variables
   • Ethics
     • Confidential: Anonymous, private
     • Consent: Agreement
     • Deception: Misleading of participants through lies or withholding information
     • Right to withdraw: Ability to not continue with the investigation
     • Debrief Inform participants of the aim of the research after the event