TOPIC: RESEARCH METHODS Flashcards

Question

OBSERVATIONAL TECHNIQUES: What is observations and how can reliability be improved?

Answer 1

Where a researcher observes and records participants' behaiour, with no manipulation or condition can be used as part of an experiment The reliability of observations can be improved by: ensuring that the behavioural categories are operationalised measure only observable behaviour are distinct, with no overlapping

Answer 2

- Involves observing subject in their natural environment PROS: - High ecological validity as the researcher records naturally occuring behaviour in a natural environment, without any outside interference from the researcher CONS: - Cannot be replicated to check reliabilty, as the researcher is not in control of variables

Answer 3

-Where researchers watch participants in a contained environment such as laboratory PROS: - Can be replicated to check reliability, as the researcher is in control of variables and therefore can repeat the method as they wish CONS: - Low ecological validity as the researcher records behaviours in an artificial ( manipulated ) environment, with potential outside interference from the researcher

Answer 4

- Where those being observed are aware of the fact PROS: - It is possible to inform participants in advance and obtain informed consent CONS: - Behaviour can be distorted through invetigator effects in which the participants changes their behaviour through social disirability bias

Answer 5

- Where the researcher is "undercover " the ppts are unaware they are being observed PROS: - Investigators effects are unlikely meaning that participants' behaviour will be genuine CONS: - Less ethical as participants are not aware they are taking part and cannot give fully informed consent

Answer 6

- When the researcher is immersed in the day - to - day activities of the participants PROS: - The researcher can obtain in-depth data as they are in close proximity to the partcipants and so are unlikely to overlook or miss any behaviours CONS: - The researchers' presence might influence the partcipants' behaviour due to evaluation apprehension

Answer 7

- Obersing ppts without actively participating PROS: - Investigator effects an evaluation apprehension are less likely as the researcher is not visible CONS: - Due to lack of proximity the researcher might overlook or miss behaviour of interest

Answer 8

- The behaviours that the researcher is interested in need to be clearly defined ( operationalised ) [usually producing a behaviour checklist or behaviour categories] so that the observer knows what to look out for and measure - Data collected could lack internal validity and if there is more than one oberserver it may lack inter observer reliability

Answer 9

- An observation study using predetermined coding scheme to record the partcipants behaviour PROS: - Easier to record data and easier to establish inter-observer reliability CONS: - Reductionist - reduces behaviour to basic units. Open to observer bias - may only record what they want to see

Answer 10

- An observation where there is no checklist so every behaviour seen is written down in an much detail as possible PROS: - Increase validity as more detail is collected - Can be used in a number of contexts CONS: - Harder to record what is observed - Harder to establish reliabilty as hard to repeat - Open to observer bias - may miss things

Answer 11

- Where there are behavioural trends that occur over a particular time periods PROS: - Effective in reducing the number of observations that have to be made CONS: - Sample may be unrepresentive of the observation as a whole

Answer 12

- Where you simply tally all co-operative behaviour over the full 1 hour lesson to gather an overall impression of the amount of co-operative behaviour. PROS: - Useful when target behaviour or evnt happens quite infrequently, and could be missed if time sampling was used CONS: - It is too complex, the observer may overlook important details if using event sampling

Answer 13

Reliability - When using two observers, to ensure that they are observing and recording behaviour in the SAME way >> to check inter-observer reliability TO DO THIS: - Plot data from one observer against another - if carried in a similar way = strong positve correlation

Answer 14

- Behavioural categories not being operationalised enough - Observer bias where what the observer sees is influenced by their expectations IMPROVEMENTS: - Using double blind techniques where the observer doesn't know the aim of the reseacher and so can't have any expectations - Can be checked and improved by using more than one observer

Answer 15

- Ecological validity - where the observation takes place ( naturalistic VS controlled ) but it will depend on the particular study and what was being observed - Population validity - can be a problem if the observation is only done on a limited sample IMPROVEMENTS: - By carrying out the observation on a variety of people in different environments

Answer 16

- People can be observed in an environment where they would expect to be observed by strangers without any informed consent - CAN'T observe people in their homes or other private places without their consent << confidentiality should be maintained at all times, where possible consent should be obtained - COVERT observations do not necessarily breach informed consent ethics because you can observe people without consent in areas where they expect to be observed

Answer 17

Aim : The general statement of what the researcher intends to investigate or the purpose of the study e.g. We want to investigate whether there is a difference in the short-term memory of children aged 10yrs and 6yrs . Hypotheses : Defined as a clear, precise, testable statement

Answer 18

- States the direction in which we expect the results to go >> we use this when we are confident about what will happen in the study H1[ Children aged 10yrs will recall significantly more words correctly from a list than children aged 6yrs ] Operationalised IV = whether children are 6yrs or 10yrs Operationalised DV = Number of words correctly recalled

Answer 19

- State that there will be a significant difference between our two conditions - An alternative hypothesis must contain an operationalised IV and DV - ( operationalised means clearly defined )

Answer 20

- States that there will be a difference between the two conditions but doesn't state the direction in which it will go H1 = There will be a significnt difference in the number of words correctly recalled from a list by children aged 6yrs and those aged 10yrs. Operationalised DV - number of words correctly recalled Operationalised IV - whether children are 6yrs or 10yrs

Answer 21

- States that there will be no significant difference between our two conditions and that any difference wwe did find was due to chance H0 - There will be no significant difference in the number of words correctly recalled from a list b children aged 6yrs and those aged 10yrs. Any difference found will be due to chance.

Answer 22

- You put it through a stastical test, which will tell us if the difference we have found is significant or not - If the difference is significant = accept alternative hypothesis - If the difference is NOT significant = accept null hypothesis

Answer 23

- Sample is a smaller group selected from a target population. A target population is all the people a psychologist wants to study. - A population is the entire group of people that you want to draw conclusions about

Answer 24

- A sample for which everyone in the target population has an equal chance of being chosen PROS: - No bias > evryone has an equal chance of being selected > drwas a representative sample and a good cross- section of people - High internal validity as the sample is representative CONS: - No control over who is being selected - Not always practical, especially when the population is large - Difficult to get a list e.g a list of homeless people

Answer 25

- A sample drawn from the target population because they are avilable and conveinient PROS: - Quick,easy and straightforward as the researcher selects people who are available at that time - Convenient because people take part who are willing at the time CONS: - The sample does not tend to be representative because some participants ahve chosen because they're friends/family of the researcher or they were in a certain locality - May not be represenative as they may use psychology students, and may be keen to please the researcher ( show demand characteristcs ) and therefore comprise the results of the study >> giving it low internal validity

Answer 26

- Also called as self-selecting. Individuals who ahve chosen to be involved in the study. Often find out about the study through some sort of advertisement PROS: - Often achives a large smaple size through reaching a wide audience e.g. online advertisement CONS: - Those who respone to the call for voluteers may display similar charateristics // increasing the chances of yielding and unrepresentative sample

Answer 27

- Dividing the target population into important subcategories. Then selcting members in proportions that they occur in the population PROS: - It avoids the problem of misrepresentation sometimes caused by purely random sampling CONS: - It takes more time and resources to plan - Care must be taken to ensure each key characteristic present in the population is selected across strata otherwise this will design a biased sample

Answer 28

- Systematic sampling is a sampling technique that uses a predetermined system to select the participants from a target group. PROS: - Assuming the list order has been randomised, this method offers an unbiased chance of gaining a representative sample CONS: - If the list has been assembled in any other way = bias may be present e.g. is every fourth perosn in the list was male, you would have only males in your sample

Answer 29

-Pilot studies are small, trial versions of proposed studies to test their effectiveness and make improvements. - Helpful in identifying potential issues early - Allows the validity and reliability of the test to be assessed in advance which then gives the opportunity for improvement to be made - Problems can be talkd before running the main study > save money + time

Answer 30

-Different participants are used in each condition of the experiment -Should be done by random allocation, which ensures that each participant has an equal chance of being assigned to on group or the other PROS: ~ Avoids order effects > which means they are less likely to guess the aim of the experiment CONS: ~ More participants are required ~ Participants variables e.g three of the participants in one of the condtion, might be super intelligent

Answer 31

- The same participants take part in both conditions of the experiment - This means that eachcodtionof the experiment includes the same group of partcipants PROS: ~ Fewer participants are required, as they take part in all condtions CONS: ~ Order of effects - the order of the conditions may have an effect on the participants behaviour e.g. the performance in condi.2 might be better, because the participants know what to do >> researchers avoid this by "counterbalancing "

Answer 32

- Pairs of participants are matched in terms of key variables such as age. One member of each pair is then placed in two different conditions. PROS: ~ Reduces participant variables because th researcher has tried to match the participants in each condition ~ Avoids order effects as the participants are ony in one condition CONS: ~ Very time consuming and expensive ~ Impossible to match people exactly, unless idenical twins

Answer 33

Is the thing that is diferent between the two conditions, what has been manipulated by the researcher

Answer 34

- Is what is being measured by the resercher

Answer 35

- These are variables other than the independent variable that may have affected the dependent variable

Answer 36

- If we do not eliminate or control the EVs they can become CONFOUNDING variables > they affect the results (DV)

Answer 37

- The process of defining and measuring variables in a study Steps for operationalizing variables: Identify the concepts to be studied Choose a variable to represent each concept Select indicators to measure each variable e.g. Anxiety A researcher might measure anxiety levels using a questionnaire or by observing physiological changes like heart rate

Answer 38

Situational variables - Control of the setting where the experiment takes place Participant variables – minimizing differences between participants (e.g. their ability such as IQ). Researcher variables – factors such as researcher behaviour, appearance or gender could affect participant responses, so should be made consistent throughout the experiment.

Answer 39

- Random allocation of participants to their groups - Decreases the possibility of participant variables in the form of individual differences, such as mathematical ability = affects results

Answer 40

- Used to deal with order of effects when using repeated measures design - When the sample is split in half completing the two conditions in the reverse order -Any order effects should be balanced out E.g., the first 10 participants would complete condition A followed by condition B, and the remaining 10 participants would complete condition B and then A. Any order effects should be balanced out by this technique.

Answer 41

Randomisation is used in the presentation of trials in an experiment to avoid any systematic errors that might occurs as a result of the order in which the trials take place

Answer 42

- Standardisation refers to the process in which procedures used in research are kept the same - Changes in data can be attributed to the IV. - It is far more likely that results will be successfully replicated on subsequent occasions.

Answer 43

- A high risk that participants will change their natural behaviour in line with their interpretation of the aims of a study = affects the results - Controlled by not allowing the participants to guess the aim/ identify the IV = achieved by using single blind experimental technique - Measure of deception has been used / so they can't easily guess the aim

Answer 44

* Investigator effects occur when a researcher unintentionally, or unconsciously influences the outcome of any research they are conducting * These are best controlled by not allowing both the ppts and the researcher to know the aim of the research . This is achieved by double blind technique. -Measure of deception has been used as the researcher and ppts don't know the aim.

Answer 45

Is a document produced by the BPS, which details the general principles that apply to the use of human participants in all research contexts. It focuses on four major principles: respect, competence, responsibility and integrity.

Answer 46

- Need to be informed of what will happen, what they are expected to do, told of risks - Ppts decide and give their consent - Issue >> informed about the aims of the study and may show demand characteristics = invalid results ... ppts may not be given all the facts of the study = deception - Some research methods require that ppts are unaware that they have been in a study - Researchers do need to be careful that their methods do not evade privacy of the ppts except in public.

Answer 47

- Giving a ppt information concerning the nature and purpose of the study may invalidate the results - Even if the researcher has gained informed consent, ppts may not understand what they are doing - No universal agreement about what constitutes a public place

Answer 48

- Sometimes necessary to deceive parents, as if they knew the full aims of the study = alter behaviour > invalid results - Deception is unethical as ppts have the right not to be lied to - If information about the aims of the study is withheld to the ppts = unable to give informed consent > could lead to distress as the ppts don't know what they have volunteered for. - Causes no harm as its minor

Answer 49

- PPTS may feel bad or embarrassed - Weighing up the costs-benefits of deception is sometimes hard as the cost are not always apparent until after the researcher has been carried out

Answer 50

Confidentiality refers to the protection of the ppts' data

Answer 51

It is sometimes possible to work out who the ppts were by the information that is provided

Answer 52

When ppts take part in an experiement, the experimenter is obliged to disclose to the ppts the real and actual nature of the experiment and to answer any questions the ppts may have . This occurs AFTER the experiment is completed

Answer 53

Harder to debrief in field or natural experiment The damage is already done, the ppts may feel bad or embarrased

Answer 54

Making sure design studies which ensure the ppts come to no more harm than they would in everday life Any potential harm needs to be communicated to the ppts so that they can give informed consent Ppts should leave a study in the same state that they entered it

Answer 55

Researchers are not always able to predict accurately the risks of taking part in the research

Answer 56

Part of the scientific process of carrying out research and getting work published Also referred to as refereeing Is the assessment of scientific work by another expert in the same field

Answer 57

Idea, theory, hypthesis --> Research and Write --> Manuscript (proposed article) --> Send to Jornal editor --> Reviewed by 3-5 experts in the field --> Decision is made to accept, revise or reject

Answer 58

- To ensure that work being published is of high quality - Peer review process checks: - Validity of the research - Orginality checks for plagarism, falsification and fabrication of data - Quality of the procedure and methodology - Importance of the researcher to the wider community

Answer 59

Any research that is published should be of high quality It helps to allocated research funding - the UK government currently spends £5.8 billion on research, and this needs to go to worthwhile studies In order to be published in a journal, articles must be peer reviewed Peer review also contributed to the research rating of university departments It is meant to spot fraudulent research, so that any research that is published can be trusted by the general public

Answer 60

The peer review process is not infallible and sometimes the system breaks down. Cases of fraud are rare but they have included plagiarism, falsification of data and fabrication of data EXAMPLE ONE: Andrew Wakefield published a study staying that the MMR vaccination was linked with the development of autism It turned out that he was wrong - his method were faulty, and the conclusions based on unscientific work. There was a conflict of interest He has been struck off the medical council, and can no longer be a doctor However, the rumours about MMR persist, and many parents chose not to vaccinate their children. The rate of measles infections has shot up, and it can be fatal in young children Smith 1999 - Gender bias: male researchers tend to be favoured - Institution Bias: Research from prestigious universities is favoured - Reviewers doesn't always habe suffcient expertise - The publication of postive results tends to be favoured, but negative results can be just as important = file draw effect - Allows for obejectivity, however rivalry between clinicians could be a motive for foul play - Many reviewers will ensure that research they are reviewing is in line with existing theory, thus can prevent a resolution of paradgim in science

Answer 61

First check if they are asking about the process or the purpose of peer reveiw PROCESS: What happens during a peer review - the different stages PURPOSE: Why do we do per reviews? Consider things like funding, university ratings etc

Answer 62

The implications of psychological research for the economy are concerned with how the knowledge and understanding gained from psychological research (theories and studies) may contribute towards our economic prosperity.

Answer 63

Memory --> EWTs + Use cognitive interviews -no leading questions, gather more correct information --> Arrest the correct the person -> saves money and time Attachment --> Ideas of John Bawley are inccorect --> Women can go back to work men can stay at home --> Children can go to nursery -> creates jobs --> good for the economy Stress --> Stress causes people to become ill = off work --> If we can treat/manage stress people can continue to work --> good for the economy Psychpathology --> Treatment of disorders e.g phobia --> If treated, people are able to go to work, good for the economy -> paying taxes, spending money Biopschology --> use of brain scans to diagnose disorders e.g. cancer --> Can treat earlier + learn more about the illness --> People happier for longer --> can work more + less pressure in the NHS Social influence --> Process of social change can get people to change behaviour --> e.g if we can get people to eat healthier food + exercise they are less ill e.g Jamie Oliver --> Less pressure in NHS --> Saves money Forensic Psychopathology --> custodial sentencing --> if ineffective people reoffend --> is it good use of money? { Expensive to put people in prison --> miscarriage of justice --> Compensation Restorative justice --> Cheap alternative Offender profiling --> Arrest correct person quicker --> saves polices time + money

Answer 64

The test-retest method measures external reliability: The same participants are given the same questionnaire at separate time intervals (e.g. with a 6-month gap between testing sessions) If the same result is found per participant then external reliability is established and see if there is a positve correlation between the two

Answer 65

It is very important to establish inter-observer reliability when conducting observational research. It refers to the extent to which two or more observers are observing and recording behaviour in the same way. All observers must agree on the behaviour categories and how they are going to record them before the observation begins The observation is conducted separately by each observer to avoid conformity (i.e. one observer may be influenced by one or more other observers) After the observational period: The observers compare the two independent data sets (often designed as a tally chart) They then test the correlation between the two sets If there is a strong positive correlation between the sets then this shows that there is good inter-observer reliability and that the behaviour categories are reliable Establishing good inter-observer reliability means that there is less chance that researcher bias has interfered with the observation

Answer 66

Reliability refers to the consistency of research study or measuring test. Reliability can be divided into two categories: internal and external reliability. Internal reliability describes the internal consistency of a measure, such as whether the different questions (known as ‘items’) in a questionnaire are all measuring the same construct. External reliability assesses consistency of a measure from one use to another. For example, if a participant took an IQ test one year, and then took the same test a year later and gained a very similar score, this would show external reliability.

Answer 67

The reliability of interviews can be improved by using the same interviewer for each separate interview using trained interviewers (which is particularly important for the cognitive interview used with eyewitnesses) ensuring that leading questions or ambiguous, double-barreled questions are omitted from the questioning

Answer 68

Refers to whether something is consistent

Answer 69

This is about whether something is consistent within itself

Answer 70

This is about whether an observed effect is an accurate one

Answer 71

This is concerned with control

Answer 72

This is concerned with generalising

Answer 73

- Temporal - Ecological - Population

Answer 74

If we are referring to whether a study mirrors the real world or everyday experiences = mundane realism If we are asking whether the results of the study can be generalised to other settings = generalisability

Answer 75

RESEARCH METHODS: SELF-REPORT TECHNIQUES ASSESSING EXTERNAL RELIABILITY : Test retest reliability , Inter-interview reliability IMPROVING EXTERNAL RELIABILITY: Ensures items on the self-report are not ambiguous - rewrite questions if necessary, training of interviewers

Answer 76

RESEARCH METHODS: OBSERVATIONS ASSESSING EXTERNAL RELIABILITY : Inter-observer reliability IMPROVING EXTERNAL RELIABILITY: better operationalisation of behavioural categories, Training of observers

Answer 77

RESEARCH METHODS: EXPERIMENTS ASSESSING EXTERNAL RELIABILITY : Is the measurement of the DV consistent IMPROVING EXTERNAL RELIABILITY: Ensure procedures are detailed so research can be replicated, Ensure procedures are standardised

Answer 78

RESEARCH METHODS: Split-half ASSESSING INTERNAL RELIABILITY : Split-half reliability IMPROVING INTERNAL RELIABILITY: Remove some questions and then retest the correlation between the two halves of questions

Answer 79

Face validiy - does it look valid Concurrent validity - how does it compare to an existing measurement

Answer 80

- Investigator effects - Demand characteristics - Confounding variables - Social desirability bias - Poorly operationalised behavioural categories

Answer 81

- Poor face validity - revise questions and rewrite if necessary - Poor concurrent validity - remove irrelevant questions and then check the concurrent validity again - Tighter controls of extraneous varaibles will increase internal validity - Can also use double blind techniques to avoid demand characteristics and investigator effects

Answer 82

Carrying out research in more natural settings or with different populations or in different time periods will help to improve the external validity if the results are the same

Answer 83

Science tries to explain how and why things happen It tests hypotheses adn contruct theories by asking questions A theory can only be scientifit it it can be tested Science has a number of key features e.g. empirical evidence, objectivity, replicability, theory construction, hypothesis testing and falsifiability

Answer 84

Empical evidence is collected through direct observations or experiment; it does not rely on opinion or belief Experiments and observations can be repoted in detail so that other investigatiors can repeat and attempt to verify the work

Answer 85

Researchers remain unbiased in theory observations and all sources of bias such as personal or subjective ideas are eliminated If they manage to maintain objectivity, then they should be able to establish cause and effect

Answer 86

Procedured are carefully recorded so that other researchers can repeat the research to see it the results are the same Replication of research is vital in establishing a scientific theory The peer review process is used to test for replicability

Answer 87

Theories are explanations of observations and findings They emerge from observations or hypothesis testing Once a scientific theory has been contruucted, it must be subjected to testing to see if its possible to gather eveidence to support or challenge it A theory can never be regarded as the absolute truth - it is provisional and can be supported, modified or abandoned in light of new research evidence

Answer 88

A hypothesus serves as a prediction and comes from a theory Hypotheses are stated in a form that can be tested i.e operationalised If a hypothesis is supported then the theory will be strengthened If the hypothesis is rejected, then the theory needs to be amended or rejected

Answer 89

Karl Popper (1935) suggested that in science theories should come first and then from these we generate hypotheses which can then be falsified by observations and experiments He believed you could not confirm a theory only disconfirm it e.g. seeing lots of white swans does not prove the alternative hypothesis that "all swans are white" as the sighting of just ine black swan would disprove this Therefore we must test the null hypothesis that 'not all swans are white' and if we cannot support this null hypotheisi then we can accept the alternative hypothesis According to Popper a scientific theory must be falsifiable which means approached like Freudian gender developement (Oedipus complex etc) is not scientific as it is not falsifiable - it can' t be proved wrong as it is based on the unconscious mind and we cannot objectively test that

Answer 90

- Kuhm believed that for something to be a science, it needed to have a paradigm ( a world view or general theoretical orientation that is accepted by the majority of scientists working in a given discipline, such as psychology ) 3 stages to the developement of any scientific discipline: Prescience - the subject isn't a true science because it has lots of different, competing approaches Normasl science - an overall paradigm is established. This means there's general agreements about theories, and appropriate research is used to develop knowledge Paradigm shift - Research evidence that challenges the current paradigm ends up changing the paradigm and then the subject returns to the normal science stage These ideas resulted in two different opinions as to whether psychology is truly a science: - Some belive that psychology has a paradigm - It was initially behaviourism, but then it underwent a change to cognitive psychology - This change in principles and practices is known as a paradigm shift - Others argue that psychology might be made up of mini-paradigms, and so psychology is in the prescience stage and not yet a normal science scientific revolution - Researcher evidence that challenges the current paradigm ends up changing the paradigm, so the subject returns to the normal science stage

Answer 91

Should say what the study's about and include the IV and the DV e.g. An investigation into the the effects of hunger on reaction times

Answer 92

- Concise summary of the report - brief description of aims and hypotheses - method - summary of the results - interpretations of the findings and any significant flaws in the study - all written in third person

Answer 93

General overview of the area being studied Include existing theories Discuss a few studies closely related to the current study

Answer 94

Aim is a sentence stating the purpose of the study Hypothesis is what's actually going to be tested, should include IV and DV

Answer 95

Describes how the research was carried out Someone should be able to replicate the study by following the method, needs to be detailed

Answer 96

The study can be reported as descriptive or inferential statistics

Answer 97

- The implications of the study - An explanation of the findings - The limitations and modifications of the study - The relationships to background research

Answer 98

Contains a list of: Books Articles Websites References should be presented in alphabetical order of first author's surname

Answer 99

Any materials used Raw materials and statistical test calculations also go here

Answer 100

surname(s), date,title,city and publisher e.g. Eysenck,H.J. (1947). Dimensions of Personality. London. Routledge and Kegan Paul

Answer 101

- Quantative data is data that is numerical and it is easy to compare and anaylse and find patterns in PROS: - Relatively simple to analyse - Less open to bias and more subjective CONS: - May fail to represent 'real-life'

Answer 102

- Qualitative data is data that can't be reduced to numbers and have lots of detail PROS: - To have greater validity - provides more meaningful insight into the ppts CONS: - Often difficult to analyse - Patterns and comparisons may be hard to identify - May be bias

Answer 103

Primary data is collected by the researcher dealing directly with the ppts. Can be done via observation experiments, surveys etc PROS: - Authentic data obtained - Can be designed to specifically target information that the researcher requires CONS: - Requires time and effort - Needs planning, preparation and resources

Answer 104

- Secondary data is collected form external sources such as television, radio, magazines, internet etc.. Also often used in correlations PROS: - Inexpensive and eaily acced requiring minimal effort CONS: - The substantial variation in the quality and accuracy of secondary data, therefore could be out of data

Answer 105

- Meta-analysis is when using a particular for of research method that uses secondary data - This refers to a process in which data from a large number of studies, which involve the same research questions and methods of research, are combined - May involve quantitative analysis of the conbined data - this produces an effect size - May also involve a qualitative review of the conclusions of the different studies - A problem with meta-analysis is publication bias > This is when the researcher may not select all relevant studies, just the ones that have positive or significant results, meaning the meta-anaylis is biased

Answer 106

the mean is calculated by adding up all the avilable data scors, and dividing by the number of actual data scores EXAMPLE: 6,5,2,4,6,5,1,4,4,3 Mean = 40 /10 = 4 PROS: The mean uses al available data in the caluclation which means that no data or participant contribuions to a study are left out CONS: The mean can be skewed by anomalies, such as a particularly high or low score. Since the mean uses all data, even these anomalies have to be included

Answer 107

- To calculate the mode, you look for the most frequently occuring score in a data set, and this becomes your mode EXAMPLE: 5,3,6,4,3,6,6,4,4,6,6,7 Mode = 6 PROS: The mode is not affected by anomalouse scores because the most frequent score is not rare or extreme CONS: On most occasions, the mode only uses one figure to work out an average of data set, which means that this single number is used to represent a whole set of results

Answer 108

It is calculated by ranking all scores from smallest to largest, and then working out which is the middle value If there are two score that sit in the middle, then the median is the sum of the two scores, divided by two EXAMPLE: 4,4,5,6,6,7,7,8,9,9,9 Range = 7 PROS: The median only uses the middle figure in a data set, which means that by nature, it does not become skewed by anomalous results in a study CONS: The median does not use all available scores in the calculation, which mean that it may not always be as representative as other methods such as the mean

Answer 109

- A measure of dispersion - Calculated by looking at the highest score and the lowest score and working out the difference EXAMPLE: 10,13,5,2,8,9,11,4,7 Range = 11 PROS: The range is easy to calculate and can provide an insight into the variance of results quicker than other methods such as standard deviation CONS: The range only uses two sets of data in the calculation, and both of these could potentially be extreme scores - low or high. This means the range may not be the most accurate measure of dispersion

Answer 110

Do not need to calculate for exams but displayed on graphs like normal distribution graphs PROS: Unlike the range, the full data set is used to calculate standard deviation, so more data is taken into account CONS: It is more complex to work out than the range, and relies on the mean calculation being accurate and unaffected by anomalous results

Answer 111

Tally marks are used for counting things These are used in content analysis and observations They record the number of times something is seen

Answer 112

Can be used to represent the data from tally charts, mean scores or the totals They are used with norminal or ordinal levels of measurement The bars must be seperate from each other

Answer 113

Are used when we have percentages in categories (norminal data) Each segemnt represents a percentage of the total

Answer 114

Should be used to present continious/interval data such as weight, height and temperature Histograms unlike bar charts also have no gaps between the bars Histograms always have equal sized intervals of data on the x axis and the y axis always represents the frequency within each interval

Answer 115

Are used with continuous/ interval data and use points connected by lines to show how something changes in value, for instance over time Line graphs do not need to have equal sized intervals of data on the X axis, like histograms Typically the IV will be on the X axis and the DV on the y axis

Answer 116

Are used with correlations where the relationship of two variables is summarised They illustrate the direction of the relationship (postive, negative or zero correlation) and can indicate the potential strength of the relationship

Answer 117

Shows us the frequency if something as it occurs in the population Distribution graphs are histographs with the measured variable along the bottome and the frequency up the side normal: In the normal distribution mean,mode and median will all be at the same point The data is symmetrical about the mean (50% of scores are above and 50% are below) It will also be a bell shaped curve - this can look different from above but still be a normal distribution curve

Answer 118

These are non-symmetrical as the scores are not equally distributed above and below the mean A postive skew results from scores that are mainly below the mean A negative skew from scores that are mainly above the mean

Answer 119

Means association - more precisely it is a measure of the extent to which two variables are related

Answer 120

Where it an be expressed numerically as a coeffecinet, ranging from -1 to +1 Gives us the information about the strength (weak, moderate, or strong) and direction (positive or negative) of the correlation

Answer 121

An experiment isolates and manipulates the independent variables to observe its effects on the dependent variable, and controls the environment in order that extraneous variales may be eliminated, experiments establish cause and effect A correlation identifies variables and looks for a relationship between them. An experiement tests the effect that an independent variable has upon a dependent variable but a correlation looks for a relationship between two variables Correlation = predict relationships Experiment = can predict cause and effect

Answer 122

Correlation hypothese are written differently than ones where we are looking for a difference Hypothesis will still either be directional or non directional Directional = positive or negative Non-directional = just a significant correlation Null hypothesis = no significant correlation

Answer 123

- Allows to investigate naturally occuring variables that maybe unethical or impractical to test experimentally. For example, it would be unethical to conduct an experiment on whether smoking causes lung cancer - Correlation allows the researcher to clearly and easily see if there is a relatioship between variables. This can be displayed in a graphical form

Answer 124

- Is not and canot be taken to imply causation. Even if there is a very strong association between two variables we cannot assume that one causes the other - Correlation does not allow us to go beyond the data that is given

Answer 125

The most precise Uses standardised unots where the intervals between data pointes are always exactly the same EXAMPLE: How far in cm did each of the aeroplanes go Heart rate in babies The time taken for ppts to complete questionnaire

Answer 126

Means the data points can be put into rank order However, with data that is ranked we don't knw how big the gap is between each scores EXAMPLE: patients ratings of satisfaction with the service of their dentists Ratings of how happy each student feels about their psychology test score

Answer 127

The lease precise form of data collection; here we are simply counting up frequencies Sometimes called category data or naming data EXAMPLE: A study of the main mode of transport to school of YR7 How many boys and girls each choose to do either an apprenticeship or a degree

Answer 128

Measure of central tendency: Norminal - Mode Ordinal - Median Interval/Ratio - Mean Measure of dispersion Norminal - N/A Ordinal - Range Interval/ Ratio - Standard deviation

Answer 129

It is an observation Studies human behaviour indirectly, usually observing the things we produce e.g web sites, television programmes Used to analyse qualitative data Allows a researcher to take quanlitative data and to tranform it to quantitative data The counting serves two purposes: - to make analysis more objective - to identify trends

Answer 130

Content is something that peole have created = called artefacts EXAMPLES OF ARTEFACTS: Books Drawings Films Newspaper items

Answer 131

Data is collected Researcher reads through or examines the data, making themselves familiar with it The researcher identifies coding units The data is analysed by applying the coding units A tally is makde of the number of times that a coding unit appears Sample: artefacts that are to be analysed. needs to be representative Coding systems: researcher creates a coding system, breaks down the information into coding units or behavioural categories - units vary depending on the artefact used Results: The reasearcher then looks at the data and draws conclusions

Answer 132

generalisability - if the artefacts are limited to a particular culture or group then the findings won't be generalised to wider society reliability - can be easily replicated by others - as long as artefacts are available to others, the analysis could be repeated and reliability measured using inter-rater reliability application - easy technique and not too time consuming , allows a statistical analysis to be conducted as there is usaully quantatie data as a result of the procedure which can be anlaysed using the mode and chi-squared test validity - tends to have high ecological validity because they are based on observations of what people actually do; real communication that are current and relevant -no chance of demand characterisitcs as the artefacts that are being analysed already exist - observer bias: different observers might interpret the meanings of the categories in the coding system differently - can be culture bias as the interpretation will be affected by the language and culture of the observer and the coding system used Ethics - no risk to content analysis - artefacts are normally public documents like news articles, TV shows or music videos - no need for consent and no one will be harmed - social responsibilty is important in some content analyses -> hate material might infalme anger and offence and might be emotionally difficult for the researcher

Answer 133

The data is transcibed The data is reviewed repeatedly so that the researcher can identify trends in the meaning conveyed by language The themes identified are re-analysed so that they become more refined and relevant and given short hand codes. The researcher can then annotate the transcript with the codes that have been identified The themes identified can ebused to support or challenge exisiting theories, with specific examples of data or quotes being used as supporting evidence

Answer 134

Thematic analysis is a method for analysing qualitative data that involves identifying and reporting patterns within the material to be analysed. The material to be analysed might be a diary, TV advertisements, or interview transcripts.

Answer 135

Is the probability that the results reported happened by chance e.g. a level of significance of 0.05 means that there is a 5% chance that the results is insignificant, or that it just happened by chance alone

Answer 136

When we use the p<_ 0.05 signifcance level we are saying that probability of our results occuring by chance is equal to or less than 5% In other words, we are at least 95% confident that the results we have obtained are due to the manipulation of the independent variable rather than chance factors

Answer 137

occurs when we conclude that there is a significant difference or significant correlation when really ther isn't accept the alternative hypothesis but we should have accepted the null hypothesis this occurs when the significant level is too lenient Caused by poor experimental design or confounding variables

Answer 138

occurs when we conclude that there isn't a difference or correlation when really there is accept the null hypothesis but we should have accepted our alternative hypothesis occurs wehn the level of significance is too stringent

Answer 139

More stringent >>>> TYPE 2 ERROR MORE LIKELY Confidence level, that result was due to IV Risk result was due to chance p = 0.001 99.9% result due to IV 0.1% result due to chance p = 0.01 99% result due to IV 1% result due to chance p = 0.5 95% result due to IV 5% result due to chance MORE LINIENT >>>>> TYPE 1 ERROR MORE LIKELY p = 0.1 90% result due to IV 10% result due to chance p = 0.2 80% result due to IV 20% result due to chance

Answer 140

Parametric tests are prefered as they are more powerful but in order to use them the data must: - be interval or ratio - must be drawn from a population which must be normally distributed - the two sets of data must be similarly spread out

Answer 141

we are looking for a difference between two conditions we have repeated measures or match-pairs design we have collected norminal (category)

Answer 142

1. Work out the 'sign'. Has the score gone up ( + ) or down ( - ) 2. Calculated the value of 'S'. The lowest score, excluding any 'nill' scores 3. Calculated the value of 'N'. The total number of scores, excluding any 'nill' scores 4. Find the critical 'S' value ... using the critical value table 5. Determine whether the results are significant is your calculated value for S less than or equal to the critical value for S?

Answer 143

For a ONE/TWO tailed test with p value of p = ... and a sample size of N=.... , the critcal table value is .... As the observed value of S= .... is LESS THAN/ EQUAL TO/ MORE THAN the critical table value, it is SIGNIFICANT/ NOT SIGNIFICANT and so the ALTERNATIVE/NULL hypothesis is accepted and the ALTERNATIVE/NULL hypothesis is rejected

Answer 144

df = (number of rows - 1) X (number of columns - 1)

Answer 145

Are you looking for a difference or a correlation? If yes... What kind of data was collected?

Answer 146

Using critical values table Ppts will perform better in a memory test in the afternoon than in the morning ppts : 28 students observed value: 153 ( ppts scored higher in the afternoon) - Direction - S = Critical Value = 130 - Non-significant For a one tailed with a P value of 0.05 and a sample size of N = 28, the critical value 130. So it is non- significant Ppts will achieve a different score on self-esteem test after eating a packet of Hob Nobs ppts: 9 women observed value : 4 ( ppts self- esteem was lower) - one tailed - S = 4 - Critical value = 8 - Significant

Answer 147

Research is carried out to see of boys run faster than girls. They are timed running a 100m course Which test do you use and why? Difference Interval/Ratio Independent measures Unrelated t-test A study to see if there is a link between calories consumed and risk of coronary heart disease - Correlation - Ordinal - Spearman Rho

TOPIC: RESEARCH METHODS Flashcards

(173 cards)