The 4 types of methods
- Lab, field, natural and quasi
- All have the same basic mechanics, looking at an IV and measuring its effect on the DV, but they differ in the levels of control the researcher has over the variables
- Lab - Highly controlled environment, IV manipulated by researcher to determine causation
- Field - more natural, IV manipulated to get DV
- Natural - Natural environment, IV indirectly manipulated as it occurs naturally
- Quasi - Can be lab or field, with IV not directly manipulated but is predetermined - the researcher can select the IV of study but it occurs naturally and is not
The strengths and limitations of laboratory experiments
Strengths -
- Highly controlled - easier to determine cause and effect
- The IV and other variables are easy to manipulate and control, with more precise control over extraneous variables
- It is easier to replicate
- Easier to establish cause and effect
Limitations -
- Lacks ecological validity
- More likely to create demand characteristics
- Experimenter bias
- Ethical issues with deception
- Difficulty in operationalizing variables
The strengths and limitations of field experiments
Strengths -
- Take place in natural setting - less artificial and therefore has more ecological validity
- No demand characteristics - if participants are unaware of the investigation they may less likely alter their behaviour
Limitations -
- More difficult to control extraneous variables, so confounding variables may be causing the effect on the DV not the IV
- Cannot involve informed consent, right to withdraw or debrief - ethical issues
- Sample bias as participants are not randomly allocated to groups
The strengths and limitations of Quasi experiments
Strengths -
- Ecological validity - natural settings should allow for natural behaviour and so can be generalised to other settings
- Methodology - can be used when it may be unethical to do so otherwise
- Few demand characteristics - when covert participants are unaware of being watched and so there are no demand characteristics
Limitations -
- Participants cannot be randomly allocated to conditions as the IV could be gender or age, leading to a lack of control in extraneous / confounding variables, making causation harder to infer
- Bias - observers see what they want to see, reducing reliability
- Replication - no control over variables means it can never be repeated again
- Ethics - the issue of invasion of privacy and informed consent is high
- Methodology - it may be difficult to not be seen observing or recording all behaviours seen in a period of time; categorising behaviours in lots of different situations can also cause issues
Types of observation - Non-experimental design
Observations are used to gather data through observing particular behaviour or events within a specific scientific research plan. There are two types of observational methods:
- Naturalistic observation
- Controlled observation
Once a researcher has decided on their observational method they will then need to make a number of decisions about how they will conduct their observation. Whether to carry out a:
- Naturalistic or controlled observation
- Overt or covert observation
- Participant or non-participant observation
When planning an observation, the researcher must also consider:
- Categories of behaviour / operationalisation
- sampling techniques
- testing for inter-observer reliability
Naturalistic vs controlled observation
- Naturalistic Observations involve observing behaviour in a natural environment. The observer tries to be unobtrusive and does not interfere with the behaviour in any way.
- Controlled Observations (also known as laboratory observations) involve the researcher setting up the situation to be observed. Controlled observations do not necessarily take place in a laboratory.
Natural -
- Natural observations study people behaving in their normal environment, so have high ecological validity
- Lack of control over extraneous variables makes it difficult to establish patterns of behaviour and difficult to replicate
Controlled -
- Controlled observations are easy replicate and the effect of extraneous can be minimised
- The artificial environment means that the findings lack ecological validity
Covert vs overt observation
- Having decided whether to conduct a natural or controlled observation, the researcher needs to decide whether the investigation will be carried out overtly or covertly.
- An overt observation is where the participants are aware that they are being observed, whereas in a covert observation the participants are not aware that they are being observed.
Covert -
- Participants do not know they are being watched so will behave naturally, removing the problem of participant reactivity and giving valid results
- There are ethical issues as the research cannot involve informed consent
Overt -
- Ethical issues are reduced as participants know they are being observed
- Participants know they are being observed, so may alter their behaviour. This is known as observer effects and leads to unreliable results
Participant vs non-participant observation
- In addition, the researcher also needs to decide whether they will take part in the situation as part of the observed group, known as participant observation - however, this is not always possible and for some investigations non-participant observation may be more practical and ethical, such as with studying drug abuse
Participant -
- The researcher experiences the situation first hand, gaining valuable insight which increases the validity of the findings
- Researcher may become too involved and lose objectivity, and it is also difficult to record data
Non-participant -
- The researcher can remain objective as they are not involved in the research situation
- The researcher will lose valuable insight gained from taking part
Self-Report Techniques
Self-report techniques involve asking participants about their behaviour, attitudes, emotions etc. There are two main types of self-report technique:
- Questionnaires
- Interviews
Questionnaires
- Questionnaires ask a representative sample of people the same questions about particular attitudes, opinions, values and beliefs.
- They can be carried out face-to-face, over the phone, by post or by internet and can be used on their own or with other research methods
- When researching, they need to decide whether to use open or closed questions
- Closed questions involve a fixed response, which the participant must choose from. For example yes or no questions or attitude scales, such as the Likert scale, which involve the participant giving self-report ratings on a 5-point scale. These produce quantitative data that is easier to analyse and interpret.
- Open questions encourage participants to answer freely, for example; what did you like about the film? These open questions produce qualitative data that is detailed and more meaningful than closed questions. Open questions also avoid participants becoming frustrated by a long list of closed questions.
Evaluation of Questionnaires - Strengths
- They are cheap, easily administered and easy to replicate
- A large amount of data can be gathered from a lot of people in a fairly short time, so is more representative of the wider population and has high population validity
- They are very flexible using both open and closed questions, which gather quantitative and qualitative data about people’s real-life experiences, feelings and emotions.
- The data gathered is easy to analyse and interpret
Evaluation of Questionnaires - Weaknesses
- Researcher bias can lead to certain questions being set that will generate a particular response in support of the research hypothesis. Therefore, reducing the validity of the research
- Participant reactivity is a problem as participants often provide answers that portray them in a positive light, this is known as social desirability bias
- Participants may chose the first option or simply agree with the question because they are short on time or cannot be bothered to answer truthfully. This is known as responder bias
- The self-report questionnaire needs to be reviewed to ensure that -
1) there was no misunderstanding
2) sample was not biased towards volunteer personalities / certain demographics
3) response rates are not too low
4) Sensitivity of questions / ethical considerations
5) Social desirability issues
Interviews
This method of research is a one-to-one conversation with the purpose of collecting information
from an individual, usually about their personal thoughts, feelings and behaviours.
Types:
1. Structured interview – this method has a standardised format of questions, which means the same questions are asked in the same order for each participant.
2. Semi-structured interview – this method also uses specific questions, but the order is not fixed. This means that questions can be selected to suit the flow of the interview, which encourages participants to be more open.
3. Unstructured interview – this method is participant-led. Further questions are based on the
answers that are given. This is the format taken in the clinical interview.
Evaluation of Interviews - Strengths
- The interview can yield rich, detailed data, which has high validity because it reveals more about how the participant makes their experiences meaningful. Especially when an unstructured interview is used
- The pre-planning of the questions and the standardisation of a structured interview allows for replication and increases the reliability of the results and conclusions. This means that the findings can be generalised to the wider population
- The interview can be more flexible as the more unstructured interviews can be participant-led rather than researcher-led
Evaluation of Interviews - Weaknesses
- Researcher bias can lead to certain questions being set that will generate a particular response in support of the research hypothesis. Therefore, reducing the validity of the research.
- Participant reactivity is a problem as participants often provide answers that portray them in a positive light, this is known as social desirability bias
- Ethical issues may be an issue as a participant is less likely to withdraw in a one-to-one situation
Similarities between interviews and questionnaires
In both questionnaires and interviews it is very important to construct good questions, as answers cannot be compared if participants have interpreted the same questions differently. Therefore, to improve validity ambiguity must be avoided and questions need to be clear, concise and terms need to be well operationalised.
Correlational Studies
- A correlational study is probably the most common type of non-experimental design. It is used where you are specifically looking at the relationship between two variables.
- The outcome of the investigation is known as the correlation coefficient, which shows the direction and strength of the relationship
- Don’t manipulate an IV but look at the relationship between two co-variables
- They don’t establish cause and effect, but look at the strength of the relationship known as the correlation coefficient
- The relationship can be illustrated either graphically through scattergrams or measured mathematically with a correlation coefficient, which is always between +1 and -1.
Different types of correlation
Positive correlation - As the variable on the y axis increases, so does the variable on the x axis. A perfect positive correlation has a correlation coefficient of +1.
Negative correlation - As the variable on the y axis increases, the variable on the x axis decreases. A perfect negative correlation has a correlation coefficient of -1.
No correlation - There is no relationship between the variables and the correlation coefficient is zero.
Evaluation of Correlational Studies - Strengths
- It can be used when manipulation of the variables is impossible due to ethical or practical reasons
- Correlational analysis shows the direction and strength of relationships and so the findings can be used to generate ideas for future research
- Correlations are relatively easy and less time consuming to carry out as there is no need for a controlled environment and can use secondary data from other sources such as official statistics
Evaluation of Correlational Studies - Weaknesses
- Cause and effect cannot be established because the variables are not directly manipulated
- Only two variables are investigated, but other factors may be involved that were not known of or were not accounted for in the research, so may be too narrow and lack construct validity
- The findings are descriptive rather than explanatory, as they describe the relationship rather than explaining the effect of one variable on the other
Case Studies
- This research method was used extensively by Sigmund Freud and is favoured by Child Psychologists and Social Workers (Psychodynamic Approach)
- This is a detailed in-depth investigation into a single individual case, a group of people or event using a range of different research methods. Because of its narrow focus and individual nature it is said to be an idiographic approach.
- Examples; Rutter (quasi experiment for Romanian orphans), Kolchuva (Czech twins), Genie
Key features in the design of case studies:
- Researchers need to decide how the information will be gathered. This can be done through the use of various research methods, such as interviews, observation or experimental techniques.
- They will also need to decide if the information can be gathered retrospectively, i.e. after the event using case histories or if they need to conduct a longitudinal study, which is a study carried out over a long period of time.
Strengths of Case Studies
- A case study is useful when researching rare, unique or socially sensitive topics.
- Because it uses a range of different research methods, this increases reliability. It is a way of double-checking results.
- They involve looking at behaviour or events as they occur naturally and so has greater ecological validity than more controlled techniques.
- It generates rich in-depth information of a mostly qualitative nature
- case studies can be longitudinal and so changes can be observed over time whereas questionnaires tend to provide just a ‘snapshot’ of experience
- case studies usually involve several methods (observation, interviews, etc.), enabling checks for consistency/reliability/validity whereas a questionnaire is a single method of data collection
- case studies produce rich, detailed qualitative data, whereas questionnaires tend to produce less detailed information.
Weaknesses of Case Studies
- It is difficult to generalise the results of a case study because it is only carried out on one individual or a small number of individuals. This also makes it difficult to replicate.
- The sensitivity of many of the topics mean that the findings are subject to participant bias, as participants may lie or exaggerate in order to provide socially desirable answers.
- It is also subject to researcher bias, where they may ask certain questions or interpret findings in such a way as to support their research aim and hypothesis.
- The small scale and sample methods used in case studies, mean that they lack scientific validity.
Content analysis and thematic analysis
- Content analysis is a research tool used to indirectly observe the presence of certain words, images or concepts within the media (e.g. advertisements, books films etc.). For example, content analysis could be used to study sex-role stereotyping. Content analysis is usually carried out on secondary data e.g. data already published.
- Researchers quantify (i.e. count) and analyse (i.e. examine) the presence, meanings and relationships of words and concepts, then make inferences about the messages within the media, the writer(s), the audience, and even the culture and time of which these are a part.
- To conduct a content analysis on any such media, the media is coded or broken down, into manageable categories on a variety of levels - word, word sense, phrase, sentence, or theme and then examined.
