Research Methods Flashcards
What is an aim?
It’s a general statement which describes what a psychologist intends
to investigate.it states the purpose of the study.
What are examples of an aim?
- to see whether a person’s confidence level has an effect on the likelihood of them obeying.
- to find out if a collector’s appearance would affect the donations to charity
- to investigate the effect of group size on conformity
What is a hypothesis?
It’s a clear, precise, testable statement that states the relationship between the variables to be investigated. It predicts what the results of a piece of research will be.
What is a Directional Hypothesis (one tailed)?
States the direction of the predicted difference between the two groups. Predicts the direction in which the results are expected to go.
Example. people who eat fish will score significantly more on an
intelligence test than those who do not eat fish.
What is a Non-Directional Hypothesis (two tailed)?
It predicts simply that there is a difference between two conditions or two groups of participants, without stating the direction of difference.
Example There will be a difference in scores on an intelligence test
between people who eat fish and those who do not.
What is a variable?
A variable is anything that can vary or change within an investigation.
They are generally used in experiments to determine if changes in
one thing result in changes in another.
What is an Independent Variable (IV)?
Is the variable which the researcher/experimenter manipulates to see what effect it has on the dependent variable.
An IV has two conditions- experimental condition and the control condition.
What is a Dependent Variable (DV)?
Is the variable which is affected by the changes in the independent variable and is what is measured by the researcher/experimenter.
What are Operationalising Variables?
Operationalisation refers to the process of making variables physically measurable or testable.
This is done to make the hypothesis clear, testable, objective and replicable.
This can be done by recording some aspect of observable behaviour
that is assumed to be indicative of that variable.
What is an Alternative/Research Hypotheses
It predicts that there will be significant difference or relationship between two conditions you are investigating.
What is an Experimental Hypothesis?
A hypothesis used only in experiments which predicts the changes in the IV will cause an effect on the DV.
Example :There will be a significant difference in the number of words recalled by 16-19 year old students from a list on a Monday morning than on a Friday afternoon.
It predicts differences and not relationships between groups.
What is a Correctional Hypothesis?
- Used in correlational research
- It predicts there will be a relationship or association between two variables.
Example: There will be a relationship between the amount of studying a student does and their mark in the exam.
What is a Null Hypothesis?
States that results are due to chance and are not significant in terms of supporting the idea being investigated.
Remember it predicts that nothing is going on, there is no difference or relationship between variables you are investigating and any link which your results show is just a ‘blip’ due to chance.
What is an Experimental Design?
The way participants are distributed between different conditions in an experiment
What is an ‘Independent Group’?
- Involves using different participants in each condition of the experiment.
- The performance of the two groups is then compared.
- This is usually random
Example: To study the effect of noise on performance in a memory test- one group are given a memory test in no noise condition and the other group is given the same memory test in a noise condition
What are ‘Repeated Measures’?
- Involves using the same participants in each condition of
the experiment - The two sets of data from each condition would then be
compared.
What are ‘Matched Pairs’?
- Involves using different but similar participants in each condition of the experiment
- Participants are matched on some variable that may affect the DV other than the IV e.g. age, sex, intelligence, ability
- Then one member of the pair is assigned to condition A and one to condition B.
- The performance of the two groups would then be compared.
- E.g. Twins
What is an Advantage of Independent Groups?
- different participants so they aren’t similar, results are diverse
What is a Disadvantage of Independent Groups?
- time consuming
- less economic (expensive)
What is an Advantage of Repeated Measures?
- more controlled + compare results
- fewer people, less expensive
What is a Disadvantage of Repeated Measures?
- participants might not come back
- participants weren’t chosen at random, researcher bias
- they might change their behaviour
- angry, agitated, tired
What is an Advantage of Matched Pairs?
- order effect isn’t a problem
- no demand characteristics
What is a Disadvantage of Matched Pairs?
- hard to find similar participants
- time consuming
- they might not be the same
What is attrition?
When participants drop out of the study – more
problematic when same participants in both conditions
since you lose data for both conditions as well as
matched pairs as pairing is difficult.
When PPs drop out of a study (attrition) data are lost so fewer data = less powerful study. This can be a problem with matched PPs (and repeated measures if there is a gap between conditions)
Loss of a PP in these designs means losing their data from both conditions
How do you reduce participant variables in independent groups?
- use random allocation
- helps give each participant an equal chance of being in any condition of the experiment to evenly distribute participant characteristics across the conditions of the experiment.
- This can be done using random techniques- put all the participants names in a hat and select them one at a time - one goes to condition A and the next to condition B and so on till all of them have been allocated.
- Participant variables are reduced
How do you reduce order effects counterbalancing?
- Important control when using repeated measures
- Reduces ‘carry over’ effects
- Half PPs do condition A then B
- Other half do condition B then A
- Order effects are shared by both conditions or balanced out
- Imp: reduces order effects but does not remove them
What are extraneous variables?
Any variable other than the IV which can affect the DV and need to be controlled
What are confounding variables?
If the extraneous variables are not controlled they may confuse the results and cause an experimental error. We would not be able to say that only the IV cause the changes in the DV.
So it is any variable other than the IV that may have affected the DV so we cannot be sure of the true source of the changes to the DV.
What is randomisation?
The use of chance in order to control the effects of bias when designing materials or deciding the order of conditions e.g. pick names from a hat etc
What is standardisation?
Using exactly the same formalised procedures and instructions for all the participants in a research study e.g. same time, same room, same written instructions
What is counterbalancing?
It’s a technique used to control for the potential effects of order and sequence in experiments
What is a single blind procedure?
Participants may not be told about the aim of the
research at the beginning of the study.
What is a double blind procedure?
Neither the participant nor the researcher who conducts the study is aware of the aims of the investigation ( get a third party to conduct the study)
What are types of extraneous variables?
- participant variables
- situational variables
- investigator effect
- order effects
- demand characteristics
What are participant variables?
They are individual differences between participants such as levels of intelligence, age, gender, social class, fitness etc. A researcher can do little to control these, but careful selection of participants can reduce these.
What are situational variables?
These are outside influences on the experiment such as time of day, weather, noise, type of room experiment takes place in etc.
e.g. if you were trying to test a person’s ability to complete a jigsaw puzzle on their own as compared to when in competition with someone else. If the experiment took place at the end of the day, the person could be tired and therefore unable to perform to the best of their ability. Another situational variable could be the noise in the room where the experiment was done.
What are investigator effects?
Any effect of the investigator’s behaviour ( conscious or unconscious on the research outcome ( The DV). This could include the design of the study ( e.g. designing materials, order of the condition, the instructions), selection of participants, interaction with the participants during the study, leading questions, expectancy effects.
What are order effects?
usually in a repeated measures deign such as fatigue, boredom, practice
What are demand characteristics?
Participants try and work out what the purpose of the experiment is due to participant reactivity ( they are not passive in the study through cues from the researcher and the research situation. They try and second guess the researcher’s intentions and aim of the study. This may lead the participant to change their behaviour within the research process- behaviour is not hafural. This is known as demand characteristics and they affect the validity of the results.
- Participants may behave in a way they think is expected and this leads to a please U’ effect
- Participants may deliberately underperform to sabotage the results
- ‘screw U effect’
- Act unnaturally due to social desirability
How can you control participant variables?
Randomisation
How can you control situational variables?
Standardisation
How can you control investigator effects?
Double blind procedure
How can you control order effects?
Counterbalancing
How can you control demand characteristics?
Standardised procedures or single- blind procedure
What is a lab experiment?
- IV manipulated
- Lab experiments are highly controlled environments
- The conditions must be controlled
- Pay particular attention to eliminating the effects of other, extraneous variables, by controlling them (i.e. removing or keeping them constant) in an artificial environment.
This makes it more likely for researchers to find a causal effect, having confidence that no variables other than changes in an IV can affect a resulting DV.
What is a field experiment?
- IV manipulated
- Field experiments are conducted in a natural setting
- Some variables cannot be controlled due to the unpredictability of these real-life settings
-The independent variable will still be altered for a dependent variable to be measured against.
What is a natural experiment?
- When a researcher takes advantage of a naturally occurring IV
- This experiment is called natural because the variable would have changed even if the experimenter was not interested. The change is taking place anyway
- Has situational variables as the independent variable
- IV occurs naturally
- situational IV (e.g. care)
What is a Quasi Experiment?
- Naturally occurring characteristic that decided what
condition the participants go into e.g Autism - The IV is based in participants variables
- The IV cannot be randomly allocated (occurs naturally)
- participant IV e.g. gender
What are Advantages of Lab Experiments?
- High control over extraneous variables means that they cannot confound the results, so a ‘cause and effect’ relationship between the IV and DV is often assumed.
- Results of laboratory experiments tend to be reliable, as the conditions created (and thus results produced) can be replicated (high internal validity)
- Variables can be measured accurately with the tools made available in a laboratory setting, which may otherwise be impossible for experiments conducted ‘in the field (field experiments)
What are Disadvantages of Lab Experiments?
- Data collected may lack ecological validity, as the artificial nature of laboratory experiments can cast doubt over whether the results reflect the nature of real life scenarios.
- There is a high risk of demand characteristics, i.e. participants may alter their behaviour based on their interpretation of the purpose of the experiment.
- There is also a risk of experimenter bias (investigator effects) e.g. researchers’ expectations may affect how they interact with participants (affecting participants’ behaviour), or alter their interpretation of the results.
What are Advantages of Field Experiments?
Higher mundane realism as the
environment is more natural and so may produce behaviour that is more valid and authentic. This may be the case as participants are unaware that they are being studies
* Demand characteristics are less likely to be an issue as participants are less likely to adjust their natural behaviour according to the interpretation of the studies purpose
What are Disadvantages of Field Experiments?
- Extraneous variables could confound results due to the reduced control experimenters have over them in non- artificial environments, which makes it difficult to find truly causal effects between independent and dependent variables.
- Ethical principles have to be considered, such as the lack of informed consent; if participants are not made aware of their participation in an experiment, privacy must be respected during observations and
participants must be debriefed
appropriately when observations come to an end. - Precise replication of the natural environment of field experiments is understandably difficult, so they have poor reliability, unlike laboratory experiments where the exact conditions can be recreated.
What are Advantages of Natural Experiments?
- Behaviour in a natural experiment is more likely to reflect real life because of its natural setting, i.e. very high ecological validity.
- There is less likelihood of demand characteristics affecting the results, as participants may not know they are being studied.
- Can be used in situations in which it would be ethically unacceptable to manipulate the independent variable.
What are Disadvantages of Natural Experiments?
- They may be more expensive and time consuming than lab experiments.
- There is no control over extraneous variables that might bias the results. This makes it difficult for another researcher to replicate the study in the same way.
What are Advantages of Quasi Experiments?
- Can be used in situations in which it would be ethically unacceptable to manipulate the independent variable.
- Studies the ‘real effects’ so there is increased realism and ecological validity
What are Disadvantages of Quasi Experiments?
*Confounding environmental
variables are more likely= less
reliable
*Must wait for the IV to occur
*Can only be used where conditions vary naturally
What is the definition of ‘population’?
The population Is the large/ whole group of people whose behaviour we wish to study. This is often known as the target population.
What is the definition of ‘sample’?
However it is not possible to test everyone in the target population therefore sampling techniques are used to choose a select group.
A sample is a small portion of individual cases selected from a greater population.
What are the characteristics of a sample?
It should be representative group drawn from the target population so that generalisation of the findings from the research to the target population becomes possible.
This however is difficult to achieve since sample may contain some degree of error or bias.
What is the Generalisation?
The extent to which findings and
conclusions from a particular investigation can be applied
to the target population. This is only possible when the
sample is typical of the population.
What is a bias?
When certain groups may be over or underrepresented within the sample selected. This limits the extent to which inferences can be made to the target population.
What is the Opportunity Sampling?
The researcher selects whoever is available and willing from the target population to participate in their research.
How would you carry out an Opportunity Sample?
Researcher simply takes a chance and asks whoever is around at the time of their study.
What is an Advantage of an Opportunity Sample?
Quick, convenient – saves the researcher time and effort
What is a Disadvantage of an Opportunity Sample?
Unrepresentative sample of the target population – since sample drawn from a very specific area
Biased on part of the researcher who may chose subjects who will be helpful
What is Random Sampling?
Every member of the target population has an equal chance of being selected in the sample.
How do you carry out an Random Sample?
- Complete list of all members of the target population is obtained.
- All the names are assigned a number.
- Sample generated using a lottery method- computer generated or names from a hat.
What is an Advantage of an Random Sample?
Free from researcher bias because they have no influence over who is selected. They cannot choose people who they think may support their hypothesis
What is a Disadvantage of an Random Sample?
Difficult to achieve in a large population where compiling a list of everyone is impractical – difficult and time consuming to conduct.
Subject to laws of chance – freak sample . Therefore not representative
Difficulties for researcher if participant refuses to participate – you may end up with more like a volunteer sample
What is Systematic Sampling?
Where every nth member of the target population is selected for example 5th student on the school register.
How would you carry out a Systematic Sample?
A sampling frame is produced – a list of the target population
A sampling system is nominated – every 3rd, 6th person etc.
Researcher works through the sampling frame till the sample is complete
What is an Advantage of an Systematic Sample?
Avoids researcher bias- once the system is established the researcher has no influence over who is chosen.
Fairly representative
What is a Disadvantage of an Systematic Sample?
Only possible where a full list of target population exists (college class lists contain all enrolled students)
May not be representative due to chance factor
What is Volunteer Sampling?
This is where participants select themselves to be part of the sample, hence it is a self selection.
How do you carry out a Volunteer Sample?
- place an advert in the paper or notice board
- willing participants will select themselves
What is an Advantage of a Volunteer Sample?
Convenient and less time consuming– minimal input from the researcher
Ethical if volunteering is by informed consent
Not biased by researcher choice
What is a Disadvantage of a Volunteer Sample?
Unrepresentative since the sample is self selected
Volunteer bias - They are biased on part of the participant (volunteers are unlike non volunteers in many ways – they are keen, curious, helpful) – can’t generalize the findings.
What is Stratified Sampling?
In this composition of the sample reflects proportions of people in certain subgroups within the target population.
How do you carry out a Stratified Sample?
Involves dividing the target population into relevant subcategories or strata e.g. age, gender,
Calculate the proportions need from each strata (subpopulation) for it to be representative Selecting people randomly from these subcategories in the
proportion that they occur in target population
Example: If the survey population has 75%men and 25% women then
the sample of 20 should have 15 men and 5 women
What are the Advantages of a Stratified Sample?
Representative sample since it accurately reflects the composition of the population. This means findings can be
generalised.
Avoids researcher bias – no influence of the researcher since participants are selected randomly from each strata.
What are the Disadvantages of a Stratified Sample?
Difficult and time consuming since the subcategories have
to be identified and their proportions in the target
population calculated
What is the BPS Code of Ethics?
A quasi-legal document produced by the British Psychological society instructs psychologists in the UK about what is and what isn’t acceptable when dealing with participants.
What is the BPS Code of Ethics built around?
It is built around the four major principles of Respect, Competence, Responsibility and Integrity. They must follow certain moral principles and rules of conduct, which are designed to protect both participants and the reputation of psychology.
What are the Ethics Committee?
A group of people within a research institution that must approve a study before it begins
What do the Ethics Committee do?
They do a cost-benefit analysis (weigh up the positive and negatives) of research proposals to decide whether the research study should go ahead. This can be done from: - the p’s point of view - distress/ loss of time vs feeling of having contributed to scientific research.
- the point of view from society - possibility that individuals may be harmed vs value in improving people’s lives
What are the 6 BPS ethical principles that all research has to abide by?
- protection from harm
- right to withdraw
- confidentiality
- informed consent
- debriefing
- deception
What is informed consent?
Informed consent is ensuring p’s have a clear understanding of what it’s about and what they are and what they will have to do. Once they know, they’ve given informed consent.
How can p’s give informed consent?
They will be given a consent form.
What are the limitations of asking for informed consent?
- if under 16, you need a parent/ guardian to give consent.
- asking for informed consent may make study meaningless, p’s might not act naturally
If you cannot get informed consent because it may lead to demand characteristics what are the alternative ways to obtain consent?
- debriefs p’s
- research after the study/ ask them if you can contact them after the study
- get general prior consent
What is deception?
Deception is where certain information is withheld from the p’s to avoid demand characteristics. Deception means that p’s can’t give informed consent.
When is deception considered inappropriate?
Psychological + physical harm
What is the right to withdraw?
It allows p’s to leave if they feel uncomfortable or if they don’t want to continue. They can leave at anytime (before, during or after the study)
What is Protection from Harm?
When p’s are put under psychological or physical harm and the level of risk should be no more than they experience in every day life.
What does protection from harm include?
Made to fee embarrassed, inadequate or placed under the stress
What’s a limitation of Protection from Harm?
It’s difficult to predict the outcomes of research to guarantee protection from harm
How do they put Protection in Harm in place?
Researchers must put in safeguarding.
Being reminded of the fact that they have the right to withdraw
What is confidentiality?
P’s have the right to control information about themselves. Must be kept confidential through letters or numbers to ensure anonymity under data protection
What is the purpose of a debrief in psychology research?
P’s must be given a full debrief. P’s should be aware of the true aims of the investigation + any details they weren’t supplied with during the study
What happens if the participants show distress?
If p’s show distress then should receive counselling.
What is briefing and de-briefing?
Briefing participants before the study begins and debriefing them after the end is one of the most important opportunities psychologists have to make sure they are handling all the ethical issues.
How do you write a briefing document?
• Greet participant and introduce yourself.
• Include as much information about the experiment as you can without creating too many demand characteristics - remember you may wish to keep the hypothesis concealed. It would be reasonable to tell the participant key facts like how long it will take and whether it includes anything unpleasant.
• Let participants know that you will keep their results confidential - explain what steps you will take.
• Inform the participants that they have the right to withdraw at any point if they change their minds.
• Ask for their consent - or ask the parents for written consent if the participants are under 16.
• Thank them and ask if they have any questions.
How do you write a de-briefing document?
• Explain the aim and hypothesis of the study using language and terminology which your participants (non-psychologists) will understand. If your participants were divided into different groups explain what each group did (“you ate a banana while the other group ate an orange before completing the jigsaw”).
Remind them that they still have the right to withdraw their results from the study if they change their mind about participating now that they know the purpose of the study.
• Remind of other ethical issues such as confidentiality.
• Ask if they have any questions or worries and deal with these as well as you can.
• Thank them for their time.
What is Qualitative data?
Qualitative is likely to be expressed in words, rather than numbers or statistics. It may be a written description of the thoughts, feelings and opinions of participants
What are examples of Qualitative data?
a written account of an unstructured observation, a transcript from an interview, an extract from a diary
What are strengths of Qualitative data?
- Offers data which is in depth and detailed than quantitative data because it lets the participant develop their thoughts, feelings and opinions on a given subject. Due to this they have greater external validity than quantitative data. This increases the validity of the data.
- They provide the researcher with a more meaningful insight into the participant’s viewpoint than quantitative data.
What are weaknesses of Qualitative data?
- It is difficult to analyse and because it is difficult to summarise statistically, patterns and comparisons within and between data may be difficult to identify.
- Conclusions depend on the subjective interpretations of the researcher and these may be biased — the researcher may have expectations of what he/she may find and this will influence the interpretations they make. This decreases the reliability of the data.
What is quantitative data?
This is data that is expressed numerically. The data is usually collected in numerical form from individual scores of participants. E.g. from experiments, structured interviews, questionnaires.
What are the Strengths of Quantitative data?
Strengths
- Can be analysed and summarised statistically using bar charts and graphs and so comparisons between groups can easily be made.
- Data in numerical form tends to be more objective and less affected by researcher bias. It is therefore more reliable.
What are the Weakenesses of Quantitative data?
- Narrower in scope and meaning so may not provide meaningful insights into the participant’s viewpoint.
- It may lack external validity- may not represent real life since the participants cannot develop and expand on their feelings, opinions.
What is primary data?
Information that has been collected first hand by the researcher for the purpose of a research project. It is the original data collected by the researcher first- hand from the participants themselves. e.g. data gathered by conducting an experiment, interview, observation.
What are strengths of primary data?
- It is data that is fit for purpose because it is authentic data obtained from the participants themselves for the purpose of a particular investigation. it targets the information the researcher wants for that research
What is a weakness of Primary data?
- Collecting the data requires planning, resources, time and effort so may not be cost effective as compared to secondary data that can be accessed in minutes.
What is secondary data?
This is data that has been collected by someone other than the person who is conducting the research. This data already exists before the psychologist began the research. Also known as ‘desk research’. e.g. data in journals, books, websites, government statistics like the census
What is a Strength of Secondary data?
- Is inexpensive and easily accessed requiring minimal effort unlike primary data.
What is a Weakness of Secondary data?
The information may seem valuable at first but may be outdated or incomplete. The content of the data may not match the researcher’s needs, There may be substantial variation in the quality and accuracy of the data available.
What is Meta- Analysis?
It is a particular form of research method that uses secondary data. In this ‘Research about research’ refers to the process in which data from a large number of studies, which have involved the same research questions and methods of research, are combined to provide an overall view. The researchers may simply discuss the findings and conclusions in a qualitative analysis:
They may additionally use a quantitative approach and perform a statistical analysis of the combined data.
This may involve calculating the effect size - which is the dependent variable of a meta-analysis t- to assess overall trends by giving an overall statistical measure of difference or relationship between variables across a number of studies.
What is a Strength of Meta Analysis?
Reviewing the results from a group of studies rather than from one study can increase the validity of the conclusions drawn because they are based on a wider sample of students and it gives us more confidence to generalise results across larger populations.
What is a Weakness of Meta Analysis?
It may be prone to publication bias, sometimes known as file drawer problem. The researcher may not select all relevant studies, choosing to leave out those with negative or non-significant results. This makes the data of meta-analysis biased because it represents some of the relevant data and incorrect conclusions are drawn.
What are Self-Report methods?
Self Report methods are in which the person is asked to state or explain their own feelings, opinions, behaviours and / or experiences related to a given topic. These can be written in the form of a questionnaire or asked, orally, an Interview.
What is do all study need?
It is very difficult to write good questions and all surveys need a pilot study (a practice run) to check that the questions are unambiguous and easy for participants to
understand. This increases the reliability and validity of the data collected.
What is the main problem with surveys?
The main problem with surveys is that participants may lie (demand characteristics). Surveys can also be affected by researcher or investigator effects. This is when the researcher influences the participants, often unconsciously. For example, body language such as nodding or smiling could encourage the participants to answer in a particular way.
What are surveys good for?
surveys are a very efficient and ethical manner of collecting data.
What is a pilot study?
A pilot study is a small scale trial run of the procedures to be used in an actual investigation with a
small group of participants and it takes place before the real investigation takes place
Why would someone conduct a pilot study?
It allows the researcher to identify any potential issues and modify the design or procedure, saving and money in the long run.
What are examples of pilot studies?
- It can identify any flaws in design of questionnaires and interviews ( offensive, leading, language too difficult to understand, takes too long to complete or test before the main study begins
- To check for and prevent
Floor effects: This is when the task is too difficult and all participants perform badly
- Ceiling effects: This is when the task is too easy and all participants perform well. - To check for ambiguity/confusion in standardized instructions given to the participants, or in the procedure so as to ensure reliability and to ensure that ethics are addressed.
- In observations a pilot study provides a way of checking coding systems before real observations are carried out. This may be an important part of training observers.
What is a questionnaire?
They contain a list of written questions (sometimes referred to as items) to which the respondents are asked to supply answers. They are used to assess a person’s thoughts and /or feelings. They may collect quantitative or qualitative data depending on the types of questions asked.
What are Close Ended questions?
- Closed Ended -Individuals are asked a number of preset questions with the choice of a limited number of answers
• Yes/no answers
• Checklists where participants tick any item which applies from a preset list
• Putting a preset list of items into rank order
•Likert Scales where statements are rated on a numeric scale
What is a Strength of Close Ended questions?
Provide quantitative data by limiting the answers the respondents can give, which is easy to score and analyse and summarise.
What are the Weaknesses of Close Ended questions?
• It may lack the detail and depth associated with open questions - since the participants cannot explain their answers- respondents may be forced to select answers that do not represent their real thought or behavior. This means that the data collected lacks validity.
• Partcipants may display a response bias and therefore the data collected may not be informative.
What are Open-Ended questions?
They have preset questions but there is no preset choice of answers. This allows the respondents to
reply in their own words
What are the Strengths of Open Ended questions?
• Collects data containing rich and detailed information since it allows the respondent the opportunity to elaborate on answers given - may be more valid data
• Can provide unexpected answers, allowing the researchers to gain new insights into people’s feelings and attitudes.
What are the Weaknesses of Open Ended questions?
• Produce qualitative data which is difficult to score and collate, analyse and summarise because it has such a wide range of answers.
• Conclusions drawn may be open to bias- lack reliability.
What are overall Strengths of Questionnaires?
- They are cost effective after they have been designed for the following reasons
- They can gather large amounts of data quickly because they can be distributed to large numbers of people - can gather large volume of data.
- A questionnaire such as a postal questionnaire can be completed without the researcher present, which reduces the effort involved as well. - The data produced by questionnaires is straightforward to analyse especially if closed questions have been used. Statistical analysis can be applied to this numerical data and comparisons between groups of people can be made using graphs and charts.
- Can explore sensitive topics and areas as they can be anonymous and there is no interviewer hearing their answers, so people may be more willing to reveal personal/confidential information.
- Help gather data attitudes, beliefs that cannot be observed because you can ask people about their feelings and opinions directly instead of making inferences.
What are overall Weaknesses of Questionnaires?
- Since the data is self report it may be invalid. Responses given may not always be truthful.
Respondents may want to present themselves in a positive light and this may influence their answers. This is a form of demand characteristic called social desirability bias. - Questionnaires often produce a response bias which is where respondents tend to reply in a similar way, example always ticking ‘yes’ ( acquiescence bias) or answering at the same favoured end of the rating scale regardless of the content of the questionnaire. This maybe because respondents complete the questionnaire too quickly and read the questions properly. This decreases the validity of the findings.
- They can only be filled by people who can read and write and who are also willing to spend time filling them in. This makes the sample biased.
What are the 3 guidelines when writing good questions?
- Clarity
- Bias
- Analysis
What comes under Clarity?
- Clarity: questions need to written so that the respondent understands what is being asked.
- Ambiguity Questions which can be interpreted in various ways should be avoided. For example ‘Do you drink coffee often?’ can mean different things to different peoole. How often is often? Questions should be clear and precise. For example ‘How many cups of coffee do you drink a day?”
- Jargon Technical jargon should be avoided, simply because most respondents will not know what it means. For example, psychological terms like ‘role conflict and ‘role ambiguity’ are likely to confuse many people.
- Double-barrelled questions These contain two options within a single question. For example ‘Do you think crime is due to bad housing and poor education?’ A respondent who blames bad housing but not poor education would have difficulty answering this question. It should be rewritten as two separate questions.
Negatives The use of negatives can often confuse respondents. For example I am not unhappy in my job? Agree/disagree
Complex questions Respondents can get lost with long, complicated questions. For example ‘While equal opportunity legislation may reduce discrimination against minority groups, it may have the reverse effect by antagonising those who are responsible for discrimination, so reinforcing the very behaviour it was designed to eradicate. Do you agree?’ - Impossible questions Some questions are just impossible to answer accurately. For example ‘How many Mars bars have you eaten in the last five years?’ Probably, the only people who can answer this question accurately are those who can’t stand Mars bars and never eat them!
What comes under Bias?
- Avoid leading questions: This may make the respondent more likely to give a particular answer because they can guess the attitude of the author through the question asked. Example: Is it not obvious that student fees should be abolished?
Loaded questions These are questions which contain emotive language, i.e., language which is likely to produce an emotional reaction in the respondent. For example ‘Do you think right wing extremists should be allowed to stand for parliament?’ Emotive language can encourage respondents to give particular answers.
What comes under Analysis?
Analysis: Write questions that will be easy to analyse. Preferably ask questions where the range of possible answers is limited
How to write a Good Questionnaire?
- Standardised instructions which should be easy to follow and complete. Not too many questions
- Decide on the sequence of questions. It is best to start with easy questions, saving the ones that make someone more defensive or anxious until the respondent has relaxed.
- Use some filler questions- irrelevant ones to distract the respondent from the main purpose of the survey. This reduces demand characteristics.
- Conduct a pilot study to test the questionnaire on a small sample so that you can refine the questions in response to any difficulties encountered. Clearly laid out and well printed
- There should be enough alternative answers so the participants may be able to express their view.
What is an interview?
An interview is a research method that involves a ‘live’ encounter (face to face- or on the telephone) where one person ( the interviewer) asks questions to assess the interviewee’s thoughts and / or experiences.
What are the 3 types of interview?
- structured
- semi-structured
- unstructured
What is a Structured interview?
Contains fixed predetermined questions and in some highly structured interviews fixed ways of replying - yes/no or multiple choice. These questions are asked in a fixed order. This is like a questionnaire but conducted in real time where the interviewer asks the question and waits for a response.
What is a Strength of a Structured Interview?
Can easily be repeated because the questions are standardised. T that the answers from different people can be compared and are analyse than the unstructured interview because the answers are m predictable.
What are Weaknesses of a Structured Interview?
- It is however not possible for interviewers to deviate from the topic or elaborate their points. This may be a source of frustration for some interviewees.
- Due to their inflexible nature they may not provide insight into the interviewees viewpoint. Information collected may not be valid.
What is a semi-structured?
In this there is a list of questions that have been worked out in advance but interviewers are also free to ask follow up questions when they feel it is appropriate. This falls in between the structured and unstructured interview.
e.g. job interview.
What is a unstructured?
This may contain a topic area for discussion but no fixed questions or ways of replying.
The researcher or interviewer can ask any questions that are appropriate. He/she listens carefully and is free to follow any unforeseen lines of questioning that may arise. This is a general aim that a certain topic has to be discussed and the interaction tends to be free-flowing.
What are Strengths of a Unstructured Interview?
- There is much more flexibility in an unstructured interview than in a structured one. The interviewer can follow up on points that arise and so is much more like to help gain insight into the interviewee’s feelings and thoughts.
- In an unstructured interview a skilled and experienced interviewer should be able to establish sufficient rapport with the participant so that even when sensitive topics are discussed, any responses given are more truthful.
What are Weaknesses of a Unstructured Interview?
- It is difficult to analyse that data from an unstructured interview since the researcher has to sift through much irrelevant information and drawing conclusions from so much information may be difficult.
- The requirement for well trained interviewers makes unstructured interviews more expensive to produce in comparison to structured interviews.
- They require interviewers to have more skill than a structured interview because they have to develop new questions on the spot-they may not have time to reflect on what they are going to say
What are the Overall evaluation of Interviews?
In all interviews the interviewer’s expectations may influence the answers the interviewee gives - this type of investigator effect is called interviewer bias.
What is an Interview Schedule?
this is a list of questions that the interviewer intends to cover. This should be standardised for each participant to reduce interviewer bias.
How do Design an Interview?
The interviewer should be taking notes throughout but this may interfere with listening skills and may also make the respondent feel a sense of evaluation.
Alternatively the interview may be audio or video recorded.
3. In 1-1 interviews the interview should be conducted in a quiet room away from other people so that the interviewee may open up.
4. Begin the interview with neutral questions to make the participants feel relaxed and to establish rapport.
5. Interviewees should be reminded that their answers will be confidential especially if discussing sensitive/ personal topics.
6. Since an interview involves the presence of an interviewer they need to be aware of behaviours that demonstrate interest so that the interviewees may provide the information required. This can be non verbal communication such as knowing to not to sit with arms crossed or frowning and knowing that head nodding and leaning forward encourage the respondent to speak. It is also awareness of listening skills - not to interrupt too often, use a range of encouraging comments to show that they are listening.
7. Develop questioning skills - what follow up questions to ask, not to repeat questions, not probe too much, ask focussed questions for ease of analysis later.
What do observations provide psychologists with?
Observations provide psychologists with a way of seeing what people do without having to ask them ( as in interviews and questionnaires - the self-report methods). They allow researchers to study observable behaviour.
They do not establish cause and effect since the IV is not being manipulated. Behaviour is lust watched and recorded (Assess the DV).
What are Naturalistic Observations?
Watching and recording behaviour in the setting within which it would normally occur. The researcher does not interfere and everything in the situation is left as it is normally.
e.g. if the researcher wanted to study playground aggression then he/she would observe children in a school playground.
What is a Strength of Naturalistic Observation?
Have high external/ecological validity since behaviour is being studied in an environment where it would normally occur. This gives a realistic picture of natural behaviour and so the findings from this research can often be generalised to everyday life.
What is a Weakness of Naturalistic Observation?
Since there is lack of control over the research situation, replication of the investigation is difficult. There may be many uncontrolled extraneous variables, so something unknown to the observer may account for the behaviour observed.
What are Controlled Observations?
Watching and recording behaviour within a strucfured environment i.e. one where some variables can be managed and extraneous variables can be controlled. This reduces the ‘naturalness’ of the environment.
e.g. record how children react to their mothers and to strangers within a specially designed playroom. A two way mirror could be used to watch and record the behaviour so as to not disturb the children.
What is a Strength of Controlled Observation?
Extraneous variables may be less of a problem due to the controlled environment. This makes replication of the observation easier.
What is a Weakness of Controlled Observation?
Artificial and controlled environment so may produce findings that cannot be readily applied to real life settings. Low external validity.
What are Covert Observations?
Participant’s behaviour is watched and recorded with their knowledge or consent. Participants do not realise they are being studied.
What is a Strength of Covert Observations?
Since the participants do not know they are being watched there is no possibility of their behaviour being affected by demand characteristics ( participant reactivity) or the need to gain approval by behaving in socially acceptable ways.
Their behaviour will be natural and this will increase the validity of the data gathered.
What is a Weakness of Covert Observations?
Raises ethical issues redarding privacy as people do not know that they are being watched. Even in public people may not wish to have their behaviour noted down. Example shopping may be seen as a public activity, but the amount of money people spend on a shopping trip is probably their own business.
What are Overt Observations?
Participants’ behaviour is watched and recorded with their knowledge and consent. The observer themselves or their purpose is disclosed to the participants.
What is a Strength of Overt Observations?
Ethical since participants are able to give consent to taking part in the research. Privacy is not invaded.
What is a Weakness of Overt Observations?
Observer effect: when people know they are being observed they may change their behaviour. Behaviour may not be natural. Decreases the validity of the data collected.
What are Participant Observations?
The observer becomes a member of the group whose behaviour he/she is watching and recording.
What is a Strength of Participant Observations?
The researcher can experience the situation as the participants do; this gives them increased insight into the lives of the people being studied. This may increase the validity of the findings.
What is a Weakness of Participant Observations?
There is danger that the researcher may identify too strongly with those they are studying and lose objectivity. This is also referred to as ‘going native’ when the lines between being a researcher and the participant become blurred.
What are Non - Participant Observations?
The observer watches and records behaviour from a distance and does not interact with the people being observed
What is a Strength of Non - Participant Observations?
Allow the researcher to maintain a psychological distance from their participants so there is less danger of them going native’.
What is a Weakness of Non - Participant Observations?
They may lose valuable insight since they are too far removed from the people and behaviour that they are studying.
What are the Overall evaluation of Observations?
- Observations help capture spontaneous behaviour which other methods may not be able to do so. What people say they do is often different from what they actually do.
- They may suffer from observer bias. What people observe is distorted by their expectations of what they would hope to see. It makes the observations subjective reducing the reliability of the observations. This can be reduced by using more than one observer who independently makes their observations. Their findings can then be compared and if they are similar (80% similarity), it raises inter observer reliability.
What are the steps to check reliability of observations - inert-observer reliability?
i) Observers familiarise themselves with behavioural categories used. They should have a recording sheet with the categories with space where a tally mark can be placed when the behaviour is observed.
ii) They observe the same behaviour at the same time independently
iii) Compare the data they have collected and discuss any differences in interpretations.
iv) Analyse the data to find out if their findings are similar- have a positive correlation. If there is a similarity of 80% or above then the data is reliable.
What information do observations provide?
Observations provide information about what people do but not what people think or feel. Interviews or questionnaires (self-report methods) may be a better way to find out about what people think or feel.
What is the design for Unstructured Observation?
In this the researcher records all relevant behaviour but has no system.
What is a Strength for the design of Unstructured Observations?
Produces detailed accounts of behaviour but may be appropriate when observations involve few participants and are on a small scale.
What is a Weakness for the design of Unstructured Observations?
- However there may be too much to record and this may not be possible. Also the behaviours recorded may be the most visible or eye catching but may not be the most visible.
- May suffer from observer bias.
What is the design for Structured Observation?
These are objective and rigorous. They use two techniques- Behavioural categories and Sampling procedures to make observations more organised.
What are Behavioural Categories?
Break the target behaviour to behaviour checklist or behaviour categories that are observable and measurable.
What are the characteristics of Behaviour Categories?
- These behaviour categories should be objective and measurable.
e.g. if target behaviour is affection- the observational categories could be hugging, kissing, smiling, holding hands. - They should be explicit actions. There should be no need to make inferences and two observers should be interpret the behaviour category in the same way, E.g, a category for affection cannot be ‘ being loving’.
- The researcher should ensure that all possible forms of target behaviour are included in the checklist. This is to avoid having a ‘ dustbin category’ into which many different behaviours are deposited.
- Categories should be mutually exclusive and not overlap. For example it may be difficult to differentiate between smiling and grinning.
What are Sampling Procedures?
Structured observations do not use continuous recording of behaviour unlike unstructured observations. The researchers instead use a systematic way of sclecting the behaviours in the observation through two sampling procedures.
What are the two Sampling Procedures?
Event Sampling- A target behaviour or event is first established. Then the researcher records this event every time it occurs. Counting the number of times behaviour occurs in a target individual or group.
Useful when the target behaviour is infrequent and may be missed in time sampling.
Time sampling: A target individual or group is first established. Then their behaviour in a fixed timeframe e.g. every 60 seconds is recorded.
Those instances when behaviour is sampled might however be unrepresentative of observation as a whole
What is correlation?
Correlation is a mathematical technique to assess the strength and direction of an association or relationship between two or more co-variables ( things that are being investigated - they are not called IV and DV because we are measuring the association between the variables and not cause and effect).
What is positive correlation?
This occurs when values of one co-variable increases, the values for the other also increases. High values are paired with high values and low values are paired with low values
E.g. As temperature increases, ice cream sales increases.
What is negative correlation?
When values of one co-variable increases, the values for the other variable decreases. High values are paired with low values.
E.g. As temperature decreases, sales of woolly jumpers increases.
What is zero correlation/ no correlation?
This means there is no correlation (positive or negative) between the co-variables.
So if we knew the scores on one variable we would not be able to predict the person’s performance on the other variable.
E.g. Ability in mathematics and how clean a person’s shoes are.
What is correlation plotted on?
A scattergraph
What is a scattergraph?
This is a type of graph on which one co-variable forms the x-axis and the other the y-axis. You always need to have two scores which have been paired in some way. It can be two scores from each participant. It does not matter which variable goes on which axis. A cross is put where the values of the two scores for each individual being tested intersects. The pattern that results indicates the relationship between the measurements. This can be seen by drawing a line of best fit.
What are Strengths of a Correlation Study?
• It is useful preliminary tool for research. By assessing the strength and direction of relationship or association between variables they provide a quantitative measure of
how two variables are related. This may suggest ideas for possible experimental research if the variables are strongly related. E.g. can be used as a starting point to identify patterns between variables before conducting an experiment.
• Can be used where an experiment would not be ethical since no manipulation of variables is
required in correlation analysis. You cannot do an experiment to study the effect of smoking on health but can study the correlation between smoking and cancer from hospital records (difference between experiments and correlations).
• They are cheaper and more practical to carry out than experiments since there is no need for a controlled environment or manipulation of variables and they can use secondary data.
What are Weaknesses of a Correlation Study?
• A correlation study cannot establish cause and effect between one co- variable and another - only an experiment can do that. It only identifies if the two variables are positively or negatively correlated with each other. There may be several variables that are interrelated and it is difficult to know whether or not the two which have been chosen are related by cause and effect. The experiment on the other hand states that one variable has caused the other (major difference between experiments and correlations).
Example: In the summer you might find a positive correlation between ice cream sales and degree of sunburn. That is more the sunburn, higher the ice cream sales. Neither is the cause of the other. They have both been caused by an extraneous variable or an intervening variables - such as temperature
Example: For example we can say the Bad health is positively related to Lower income. We cannot say that bad health caused lower income because there may be other factors involved.
This means that the hypothesis in a correlation study should not predict that one variable will have an effect on the other. It should predict a relationship between variables.
• Scattergram does not reveal curvilinear relationships. Things that may increase for some time and then decrease. Example, relationship between student alertness and time of day.
• Correlational research has the potential for misuse and this is quite often done in the media or by politicians where correlations are used to imply cause when in reality they may not be.
E.g. media often quotes statistics on the relationship between being raised in a single parent family and the increased likelihood of being involved in crime. This does not mean, however that single parent households cause crime. There are intervening third variables involved e.g. poverty that may explain the link between one- parent families and crime.
What is the Correlational Hypothesis?
These are different to experimental hypothesis. They is no IV or DV. You instead have to state the expected relationship between co-variables and they must be operationalised.
What is the Directional Correlational Hypothesis?
There is a positive correlation/ relationship between the price of a chocolate bar and its tastiness rating out of 20.
What is the Non-Directional Correlational Hypothesis?
There is a correlation between the price of a chocolate bar and its tastiness rating out of 20.
What does research collect information in the form of?
Research often collects a great deal of information in the form of scores/ numbers. A reader of a report will not want to see the raw data that is the response of every participant.
What are descriptive statistics and what do they provide?
Measures of central tendency, measures of dispersion and graphs provide a summary of the results so the reader can quickly see the over all pattern of the results and any differences that may be present. This makes it easier to understand.
What is Descriptive Statistics used for?
Used to summarise and analyse numerical data to make it easier to understand.
What is Measures of Central Tendency?
Measure of the average value in a set of data
What is the mean and do you calculate it?
• This is the arithmetic in a set of data.
average
• It takes into account all the scores in the data set
of all the scores/values
Formula: To calculate the mean you add up all the scores or values of a set of data and divide by the total number of scores.
What are the Advantages of using the mean?
• It takes into account all the scores in the data within the calculation therefore it is the most_aqurate
and sensitive measure. It is the most representative of the
data as a whole.
• It is used in further statistical calculations. ( standard deviation)
What are the Disadvantages of using the mean?
• If there is a very high or a very low extreme value in the data, then the overall mean value can be distorted and misleading since it makes it unrepresentative of most of the
scores
• Sometimes it gives an unrealistically precise value
What is the median and do you calculate it?
This is the middle value in a set of data after the data has been put into rank order - from lowest to highest.
If there are two middle scores add them and divide by 2 to get the median.
What are the Advantages of using the median?
• It is not affected by extremely high or low scores so it can be used in skewed sets of data to give a representative average score.
• It is relatively easy to calculate
What are the Disadvantages of using the median?
• Does not take all the values in the data set into account therefore it is less accurate and sensitive than the mean.
• If the values are spread erratically in a small set of data, then the median may not be a representative figure. In such cases the mean would be a better measure to use.
What does it have unlike the mean?
Unlike the mean it has little use in further statistical analysis.
What is the mode?
Most often occurring score/value in a data set.
If there are 2 or 3 or more scores that occur most often then the data is bimodal.
What are the Advantages of using the mode?
• For some data- data in categories- the mode is the only method you can use. E.g if you asked the class what their favourite dessert was — the way to select the average value would be to select the modal group.
• Always an outlier from the data set therefore is more realistic and sensible and is easy to calculate
What are the Disadvantages of using the mode?
• Not very useful when there are extreme values or if there is no mode value
• Is a central measure.
What should I do if i’m asked to decide what measure of central tendency should be used with a particular set of data?
if you are asked to decide which measure of central tendency should be used with a particular set of data
- If no extreme scores use the mean.
- If there are any extreme scores use the median.
- If data in categories use the mode.
What is Measures of Dispersion used to show?
Measures of Dispersion which are used to show how SPREAD OUT
the data is. They show how
far scores vary and differ from one another.
Measures of Dispersion: What is the range?
A simple calculation of the dispersion in a set of scores which is worked out by subtracting the lowest from the highest and adding 1 as a mathematical correction.
Adding 1 is a mathematical correction - raw scores are usually rounded up or down when recorded within research- someone may complete the task in 45 seconds but it is unlikely they took exactly 45 seconds to complete the task. It could have been between 44.5 - 45.5. So adding 1 accounts for this margin of error.
What is an Advantage of the Range?
- Quick and easy to calculate
What is an Disadvantage of the Range?
- It ignores the central values of a data set so it can be misleading when there is an extreme high or low score. This would then not give a fair representation of the general spread of scores.
- Not a precise measure since it does not take into account all the values.
Measures of Dispersion: what is Standard Deviation?
- More sophisticated measure of dispersion
- This means the variability (spread) of scores around the mean. The higher the number, the greater the diversity of the scores away from the mean value - not just the gap between the highest and lowest scores.
How do you calculate Standard Deviation?
- You calculate the mean
- You then subtract the mean from each value
- You then square the results
This gives the variance. The Standard deviation is the square root of the variance.
What does a lower value and higher value of Standard Deviation mean?
- A lower value of standard deviation means that the scores are more close because they are closer together/clustered around the mean score.
- A higher value for SD means that the scores are more dispersed since they are more spread out from the mean score.
dimerted
What are the Advantages of the Standard Deviation?
- All the scores of the set of data are taken into account so it is more accurate than the range
- Used in further statistical analysis
What are the Disadvantages of the Standard Deviation?
- It is not as quick or easy to calculate as the range.
- Just like the mean, It can be distorted by a single extreme value.
What do we look at when analysing quantitative data?
When analysing quantitative data we look at central tendency, dispersion and visual display.
What are Normal Distributions?
A symmetrical spread of frequency data that forms a bell shaped pattern. The mean, median and mode are all located at the highest peak.
What are the characteristics of a normal distribution curve, also know as a bell-shaped curve or a Gaussian curve?
a) it is bell-shaped ( most people are located in the middle area of the curve with very few people at the extreme ends.
b) it is symmetrical
c) the mean, median and mode all fall on the same central point.
d) The two tails of the curve never touch the horizontal x axis ( never reach zero) as more extreme scores are always theoretically possible.
What is a Skewed Distribution?
When distributions of data is not symmetrical and the data clusters to one end (leans to one side or the other), this results in a skewed distribution
What is a Left Skewed (Negative Skewness) Distribution?
A type of distribution where the bulk of the scores are concentrated on right resulting in the long tail of anomalous scores on the left.
What is a Right Skewed (Positive Skewness) Distribution?
A type of distribution where the bulk of the scores are concentrated on left resulting in the long tail of anomalous scores on the right.
What measures of central tendency are less affected in skewed distributions ?
In skewed distributions the mode and the median are less affected because they do include all the scores when they are calculated. The mean gets affected because it includes all the scores in its calculation and gets affected by extreme values.
How to decide whether to accept or reject our experimental from the results collected from a study?
We need to ask whether the results might have been due to chance or they have been affected by the IV.
The inferential statistics would tells us whether or not it is safe to infer that the results from a particular sample of people are valid for the entire population from which the samral as drawn. That is whether the results can be generalised.
What is the aim of inferential statistics?
The aim is to discover the probability that our results are due to chance factors. If it is unlikely that they are due to chance factors, then we reject the alternative/ experimental hypothesis. That is why we use the word significant in hypothesis- there may be differences but are they significant enough)
How is probability expressed?
• It is an average value that represents the likelihood of some event happening.
• It is common practice to use the letter ‘P’ to stand for probability.
• It is measured on a scale from 0 to 1.
• Zero means it will not happen and 1 means that it will definitely happen
• Therefore probability is commonly expressed in decimals such as 0.2, 0.5, 0.01 etc.
What do psychologists use to decide whether results are significant?
- once we have applied a test on the data we get a result. We then find out whether this result is significant or not.
- psychologists use probability to decide whether or not the result is significant.
What is a significant result?
A significant result is one where there is such a probability - that the result is due to chance that we decide it is safe to reject the null hypothesis.
what is the normal level of significance used in psychology?
The normal level of significance used in psychology is 0.05 significance level or 5%
If results are significant at 0.05 level of significance, what does that mean?
If results are significant at 0.05 level of significance then it means that there is less than 5% likelihood of getting your results due to chance factors. The
researcher can be pretty sure that the difference found was because of the manipulation of the I.V.
What is another way of stating this would be that the probability of the results occurring by chance was less than 0.05.?
Another way of stating this would be that the probability of the results occurring by chance was less than 0.05.
By convention, if the probability is any greater than this ( e.g. p<0.06 or p<O.1) then the result is not significant and you must retain the null hypothesis and reject the alternate hypothesis.
A more stringent significance level of 0.01 or 1% is sometimes used. This is
in cases which involve a human cost, such as new drugs being trialled or when the investigation is a one off, with no possibility that it can be repeated in the future.
This would mean that the probability of the results occurring due to chance is less than 1%.
When a statistical test has been calculated, what is the researcher left with and does it need to be compared to?
When a statistical test has been calculated, the researcher is left with a number value. This needs to be compared with a critical value (table value) to decide whether the result is significant or not.
To use the table what info do you need?
- The significance level desired ( always 0.05 or 5% unless you want it to be stringent).
- The number of participants in the investigation ( N value)
- Whether the hypothesis is directional (one tailed) or non- directional (two tailed)
This information allows you to locate the critical value for your data.
What needs to happen to be regarded as significant?
Since you only have to know how to calculate the sign test remember that your calculated value has to be equal to or lower than the critical value in the table to be regarded as significant.
What are 3 conditions that need to be fulfilled in order to use a sign test?
- look for a difference rather than an association.
- we need to have used repeated measures design
- we need data that is organised into categories (nominal data)
How do you conduct the sign test?
- state the hypothesis
- work out the sign column of the table
- ignore any results where the results stay the same and work out the value of N = participants.
- count up the number of + and - signs. The calculated S value (observed value) will be the lower of the 2 numbers.
- find the critical value of S so we compare it to the observed value of S.
For the data to be significant the calculated value of S must be equal to or less than the critical value identified.
What is the Peer Review?
involves all aspects of written investigation being scrutinised by a small group of usually 2 or 3 experts in a field. These experts should be objective and unknown to the researcher.
What is the reviewer is often asked to do?
The reviewer is often asked to make an explicit recommendation of what to do with the manuscript or proposal.
What are the recommendations like?
Most recommendations are along the lines of the following:
• to unconditionally accept the manuscript or the proposal,
• to accept it in the event that its authors improve it in certain ways,
• to reject it, but encourage revision and invite resubmission,
• to reject it outright.
What is taken very seriously in psychology?
In Psychology the role of peer review is taken very seriously.
What are the 3 main aims of peer review?
- to allocate research funding
- validate the quality & relevance of research
- to suggest amendments and/or improvements
What is ‘to allocate research funding’?
To decide whether or not to award research funding for a proposed research project. This may be co-ordinated by government- run funding organisations such as the Medical Research Council, who have a vested interest in establishing which research projects are most worthwhile.
What is to ‘validate the quality & relevance of research’?
All elements of the research are assessed for quality and accuracy: the formulation of the hypothesis, the methodology chosen, the statistical tests used and the conclusions drawn.
What is ‘to suggest amendments and/or improvements’?
Reviewers may suggest minor revisions of the work and thereby improve the report or, in extreme circumstances, they may conclude that the work is inappropriate for the publication and should be withdrawn.
Evaluation of Peer Review
It is usual practice that the ‘peer’ doing the review remains process anonymous throughout the process so that it is more likely to produce a honest appraisal. However, a minority of researchers may use their anonymity as a way of criticising rival researchers - this may be because they are in competition for the limited research funding or may have crossed paths with them in the past.
Some journals due to this issue favour an open review system- names of the reviewer is made public.
What is a Weakness of Peer Review?
Publication - Editors of journals usually want to publish ‘headline
grabbing’ findings to increase the credibility and circulation of their publication. They also prefer to publish positive results. This means that research that does not meet these criteria is ignored or disregarded. This may create a false impression of the current state of psychology- if editors are being selective in what they publish.
What is another Weakness of Peer Review?
Burying ground breaking research:
The peer review process may suppress opposition to mainstream theories, wishing to maintain status quo within the scientific fields. Reviewers are also critical of research that contradicts their own view and favourable to that which matches it.
Established scientists are more likely to be reviewers and they are more likely to reject new and innovative researcher.
So peer review may slow down the rate of change within a scientific discipline.
What does ‘Implications of Psychological research for the economy’ mean?
Implications of Psychological research for the economy refers to how does what we learn from the findings of psychological research influence, benefit, affect, devalue our economic prosperity.
What is one example of ‘Implications of Psychological research for the economy’?
Attachment research into the role of the father:
Bowlby had asserted that a child can only ever form a secure and lasting monotropic bond with the mother. Thus at the time, childcare was seen as the mother’s responsibility, and hers alone, while the father carried out his natural role as the provider for the family.
More recent research has questioned this notion, pointing to the importance of the child forming multiple attachments; most important is that to the father. Psychological research has shown that both parents are equally capable of providing the emotional support necessary for the healthy psychological development.
This implies that children need multiple attachments. To encourage their psychological development discrediting Bowlby’s theory, changing the way in which parents can take time off (maternity and paternity)
What is another example of ‘Implications of Psychological research for the economy’?
The development of treatment for mental illness:
Absence from work costs the economy an estimated £15 billion. A third of all absences are due to mild or moderate mental health disorders such as depression, anxiety, stress. Psychological research into the causes and treatments of mental illness therefore have an important role to play in supporting a healthy workforce.
Example: many conditions are treated through psychotherapeutic drugs e.g. SSRI for depression and OCR. This means that sufferers can mange their condition and return to work. Therefore the economic benefit of psychology research into disorders such as depression is considerable.
What is another example of ‘Implications of Psychological research for the economy’?
Memory research - Any evidence relating to more efficient use of public money would be relevant. For example, research into the cognitive interview facilitates accuracy of eyewitness reporting enables better use of police time and resources and this a valuable contribution to the economy.
What is another example of ‘Implications of Psychological research for the economy’?
Research into processes that influence social change:
They demonstrate how minority, conformity and obedience can affect changes in attitudes, thinking and behaviour on a societal level. e.g. - the plastic straw ban - this saves the government millions - move towards being environment friendly through recycling - this reduces manufacturing and production costs.
