research methods pt2 Flashcards

Question

what is a population?

Answer 1

a large population of individuals that a researcher is interested in studying e.g. students

Answer 2

a subset of the general population and these smaller groups will be representative of the target population and findings can be generalised however some samples can cause bias

Answer 3

a sample that reflects that characteristics of the people in the target population, so results can be a higher validity

Answer 4

the extent to which results from research can be generalised to other groups of people

Answer 5

- random sampling - systematic sampling - stratified sampling - opportunity sampling - volunteer sampling

Answer 6

- this is when all members of the target population have the same equal chances of being selected

Answer 7

- no researcher bias - unbiased as the confounding and extraneous variables will be divided between groups equally, enhancing internal validity

Answer 8

- time consuming as you need a list of members of the population - unrepresentative as some participants may refuse to take part meaning you can end up with a volunteer sample

Answer 9

a predetermined system where every nth member is selected from the sampling frame

Answer 10

- objective, as once the system for selection has been established the researcher has no influence over who is picked, so avoids researcher bias

Answer 11

- time consuming - participants may refuse resulting in a volunteer sampling

Answer 12

a sampling technique that reflects the varying proportions of people in particular subgroups ( strata ) withing the wider population

Answer 13

- no researcher bias as the selection within each stratum is done randomly - representative data as it is designed to accurately reflect the composition of the population, so generalisation is possible

Answer 14

- time consuming to identify strata and contact people from each - not completely representative of the target population as the strata cannot reflect all the difference between the people of the wider population

Answer 15

this is when the researcher selects anyone who happens to be willing and available, they take the chance to ask whoever is around at the time of their study

Answer 16

- easy method of recruitment as no sample list is needed - less time consuming and less costly

Answer 17

- unrepresentative of the target population as it is drawn from a very specific areas so findings cannot be replicated - researcher bias as they have complete control over the selection of participants and can avoid people they do not want

Answer 18

involves participants selecting themselves to be part of the sample e.g. the researcher may place an ad in a newspaper

Answer 19

- less time consuming as there is quick access to willing participants - participants are more engaged and more likely to cooperate in the study

Answer 20

- volunteer bias as the study may attract a particular profile of a person, meaning generalisability is then affected - demand characteristics are created as volunteers are more likely to change their behaviour to please the researcher

Answer 21

- a small-scale version of an investigation which is done before the real investigation is undertaken - they are carried out to allow potential problems of the study to be identified and the procedure to be modified to deal with these, this saves money and time

Answer 22

- instructions / questions may be unclear and unnecessary - the procedure could be too much for one researcher to cope with on their own - observation could be poorly operationalised or nothing worth observing at the time sampled

Answer 23

- check that the questions are clear and make sense - check questions relate to the research aim - can you complete all questions in the time given

Answer 24

- do your behavioural categories work - are the observers trained to notice the behaviour - does the time / event sampling work for the study

Answer 25

- does your method match your aim - have you got enough stimuli to fill the time - do you have too much to do in your method - do your instructions make sense to the participants

Answer 26

single-blind procedure double-blind procedure

Answer 27

- a research method in which the researchers do not tell the participants the aim of the research until the end of the study to reduce demand characteristics

Answer 28

- a research procedure in which neither the participants nor the experimenter knows the aims of the study - these procedures are normally administrated by someone who is independent of the investigation, this reduces the investigator effect

Answer 29

- sets a baseline where the results from the experimental condition can be compared to the control condition - if there is a significantly greater change in the experimental group compared to the control than the researcher is able to conclude that the cause of effect was the IV

Answer 30

- a way of seeing or listening to what people do without having to ask them - observation if often used within an experiment as a way of assessing the DV

Answer 31

- can capture authentic behaviour, so there is less risk of demand characteristics

Answer 32

- observer bias, as different people interpret situations differently - the observers interpretations of the situation may be affected by their expectations. this can be fixed by having more then one observer

Answer 33

- an observation that takes place where the target behaviour would normally occur

Answer 34

- high external validity as in a natural context behaviour is likely to be more spontaneous - ecological, so can be more generalisable to every day life

Answer 35

- there is no control over confounding and extraneous variable, so there is no clear cause and effect

Answer 36

- an observation that takes place in a structured environment e.g. control over variables

Answer 37

- can be replicated due to standardised procedures, so has a high internal validity

Answer 38

- has a low external validity, as behaviour may be contrived as a result of the setting so findings cannot be applied to everyday experiences ( generalised )

Answer 39

- this is an observation where participants are NOT aware that they are being studied

Answer 40

- reduced demand characteristics as ppts do not know they are being watched so their behaviour will be more natural, this increases the internal validity of the findings

Answer 41

- ethically questionable, as people may not want behaviour recorded even in public, so ppts right to privacy may be affected through: deception and a lack of informed consent

Answer 42

- an observation where participants know they are being studied

Answer 43

- more ethically acceptable as ppts have given their consent to be studied, so they have the right to withdraw

Answer 44

- higher chance of demand characteristics as the ppts have the knowledge of being studied which influences behaviour and reduces the internal validity of the findings

Answer 45

- when the researcher becomes a member of the group whose behaviour they are observing

Answer 46

- can lead to a greater insight as the researcher experiences the situation as the ppts do, this enhancing the external validity of the findings

Answer 47

going native, meaning the researcher may identify too strongly with those they are studying, which threatens the objectivity and internal validity of the findings

Answer 48

- an observation where the researcher remains outside of the group whose behaviour they are observing

Answer 49

- more objective as the researcher maintains an objective distance so less chance of bias, and an increase in the internal validity of the findings

Answer 50

- lack of insight as the researcher may be too far removed from those they are studying and that may reduce the external validity of the findings - the observation is open to the observer bias for example stereotypes the observer is aware of

Answer 51

- unstructured observations - structured observations

Answer 52

- an observation in which the researchers simply write down everything they see, so the observations are rich in detail

Answer 53

- more richness and depth of detail throughout the data

Answer 54

- this observation produces qualitative data ( non-numerical ) and this makes it more difficult to record and analyse - there's a risk of observer bias as objective behavioural categories are not present in this type of observing, so the researcher may only record behaviours that catch their eye

Answer 55

- an observation used when there is too much going on in a single observation for the researcher to record everything, so they focus on target behaviours using behavioural categories

Answer 56

- recording is easier as it produces numerical discussions of quantitative data, so analysing and comparing the behaviour is straightforward - there is less risk of observer bias

Answer 57

- not much depth of detail within the data - difficult to achieve higher interobserver reliability as filling the predetermined lists in is subjective

Answer 58

- this is when a target behaviour, which is being observer, is broken up into more precise components which are observable and measurable e.g. aggressive behaviour can be broken down to shouting, punching, swearing etc

Answer 59

- data collection of behavioural categories are structured and objective

Answer 60

- researchers have to ensure categories are observable, measurable and self-evident- if not data collection is unreliable - categories have to be exclusive and not overlap e.g. smiling and grinning

Answer 61

- event sampling - time sampling

Answer 62

- involves counting the number of times a particular behaviour occurs in a target individual / group

Answer 63

- is useful when the target behaviour happens quite infrequently and could be missed if time sampling was used

Answer 64

- if complex behaviour is being observed, important details of the behaviour may be overlooked by the observer - if the behaviour is very frequent there could be counting errors and can be difficult to judge the beginning and ending of a behaviour

Answer 65

- involves recording behaviour withing a pre-established time frame e.g. may note down the observations of a target individual every 30 seconds

Answer 66

- it reduces the number of observations that has to be made, so it is less time consuming

Answer 67

- the small amount of data that you collect withing that time frame ends up being unrepresentative of the observation as a whole

Answer 68

- this is when single observers may miss the important details or only notice events that confirm their hypothesis ( investigator bias ) - so inter observer reliability help to reduce biasness and make data objective, by having 2 observers and having the data checked for consistency

Answer 69

1. observers can familiarise themselves with behavioural categories 2. observe behaviour at the same time, perhaps in a small-scale pilot study 3. they can compare the data they have recorded and discuss any differences in interpretation 4. observers analyse the data and inter observer reliability is calculated by correlating each pair of observations made, and an overall figure is produced

Answer 70

- these are pre set lists of written questions ( or items ) to which a participant responds - they are used to assess thoughts and feelings of ppts - they can also be used as part of an experiment to assess the DV

Answer 71

cost effective- can gather large amounts of data quickly and researcher does not have to be present when completed, this reduces the effort involved and makes questionnaires cost effective straightforward to analyse- especially if closed fixed-choice questions are used, meaning statistical data can be easily converted to graphs and charts for comparison

Answer 72

responses may not always be truthful- respondents tend to present themselves in a positive light and this may influence their answers response bias- respondents may favour a particular kind of response e.g. they always agree, this means that all respondents tend to reply in a similar way

Answer 73

- closed questions - open questions

Answer 74

- a question in which respondents have limited options e.g. yes or no

Answer 75

easy to analyse- produces qualitative data that can be turned into quantative data this makes it easier to draw conclusions however responses are restricted and ppts are forced into an answer that may not represent true feelings so may reduce the validity of the finding

Answer 76

- this is a question in which ppts have a whole range of answers and respondents can answer in any way - produces qualitative data

Answer 77

- responses are not restricted so answers are more likely to provide detailed, unexpected information. this means there is likely to have more external validity than statistics - responses are difficult to analyse so there will be a wider variety of answers produced compared to closed questions. this means that it may be forced to reduce data to statistics

Answer 78

- likert scales - rating scales - fixed choice option

Answer 79

- this is a scale in which the respondent indicates their agreement or otherwise a statement using a scale usually five points - the scale ranges from strongly agree to strongly disagree

Answer 80

- a rating scale gets respondents to identify a value that represents their strengths of feeling about a particular topic e.g. how entertaining do you find zombie films on a scale of 1-5, 1 being very entertaining 5 being not at all entertaining

Answer 81

- this option includes a list of possible options and respondents are required to indicate those that apply to them e.g. for what reasons do you watch zombie films A. entertainment B. amusement C. to escape D. education

Answer 82

- this is a list of pre determined questions that are asked in a fixed order

Answer 83

- easy to replicate because of a standardised format, the format also reduces differences between interviewers - interviewers cannot elaborate so they cannot deviate from the topic or explain their questions therefore this may limit the richness of data collected

Answer 84

- an interview with no set questions, there is a general topic to be discussed but the interaction is free-flowing and the interviewee is encouraged to elaborate

Answer 85

- there is greater flexibility where points can be followed up as they arise, so there is more chance of gaining insights into interviewees worldwide view and collect unexpected information - increased chance of interviewer bias as there is closer dialogue between interviewer and interviewee meaning more opportunity for unconscious cues

Answer 86

- an interview with a list of questions that have been worked out in advance but interviewers ask further questions based on previous answers

Answer 87

1) 1-1 interviews should be in a quiet room to then allow the interviewee to open up 2) interviewers should have a standardised list of questions that they need to cover to reduce interviewer bias 3) should be a rapport, meaning interviewers should begin with some neutral questions to make ppts relaxed 4) interviewees should be reminded that answers are treated with strictest confidence

Answer 88

1. overuse of jargon 2. emotive language and leading questions 3. double barrelled questions and double negative

Answer 89

- this is the overuse of technical terms that are only familiar to those within a specialised field

Answer 90

- a researchers attitude towards a particular topic can be clear from the way in which the question is phrased - this can be leading which guides respondents towards a particualr answer or words can be too emotive and should be replaced with neutral alternatives

Answer 91

- a double barrelled question contains two questions in one, the issue being that respondents may agree with one of the questions and not the other - a double negative can be difficult for ppts to understand e.g. I am not unhappy with my job ( agree / disagree )

Answer 92

- this is non-numerical data expressed in words, thoughts, feelings etc. advantages- richness of detail and more meaningful so has a greater external validity disadvantages- difficult to analyse and draw conclusions from as it is hard to identify patterns and make comparisons so leads to subjective interpretation and researcher bias

Answer 93

- this is when data is analysed statistically and converted into graphs e.g. reaction time advantages- easier to analyse and draw conclusions as you can draw graphs and calculate averages, so comparisons between groups can be made disadvantages-expresses less detail so has a lower external validity and may be less like 'real life'

Answer 94

primary- 'first-hand' data collected for the purpose of the investigation advantages- information is directly relevant to research aims disadvantages- requires time and effort secondary- data collected by someone else so is pre-existing and already subject to statistical testing advantages- inexpensive, requires minimal effort making it expensive (more economical) disadvantages- quality may be poor as information may be outdated or incomplete so challenges the validity of the study

Answer 95

- this is a type of secondary data that involves combining data from a large number of studies to draw an overall conclusion

Answer 96

advantages- increases validity of conclusions as the eventual sample size is much larger than individual samples , therefore the extent to which generalisations can be made disadvantages- publication bias as researchers may not select all relevant studies, leaving out negative or non-significant results, therefore conclusions may lack validity

Answer 97

tables- data collected from a study can be summarised into a table and raw scores are displayed in columns and rows bar charts- categories (discreate data) are usually placed along the x-axis and frequency along the y-axis - the height of each column represents the frequency of that item line graphs- used for continuous data and to show how something changes in value e.g. overtime, weight, height)

Answer 98

histograms- used when data is continuous and bars touch each other scattergrams- used for correlational analysis, each dot represents one pair of related data - it illustrates strength and direction of correlation

Answer 99

- symmetrical, bell-shaped curve - the mean, median and mode all occupy the same mid-point of the curve

Answer 100

- distributions that lean to one side because most items are either at the lower or upper end of the distribution - there are 2 types: 1. negative skew 2. positive skew

Answer 101

- most of the distribution is concentrated towards the right side of the graph, resulting in a long tail on the left - the mode is the highest point of the peak, the median comes next and the mean is dragged across to the left - so it is negative if the mean is lower than the median and mode

Answer 102

- most of the distributions is concentrated towards the left of the graph, resulting in a long tail on the right - the mode is the highest point of the peak, the median comes next and the mean is dragged across to the left - it is positive if the mean is higher in value than the median and mode

Answer 103

- this is a non-experimental method used to measure the relationship between 2 or more co-variables

Answer 104

1. positive correlation- as one variable increases so does the other 2. negative correlation- as one variable increases the other decreases 3. null- no relationship between the co-variables in the study

Answer 105

- in an experiment, the researcher controls or manipulates the IV in order to measure the effect on the DV, so it is possible to infer that the IV caused any observed change in the DV. - in a correlation there is no manipulation of one variable so cannot establish cause and effect and it is not possible to establish a cause and effect between one co-variable and another

Answer 106

correlation- your hypothesis must be worded 'there will be a positive/ negative correlation/relationship between e.g. directional= there will be a positive relationship between anxiety and caffeine drinks non-directional- there will be a relationship between anxiety and caffeine drinks experiment- your hypothesis must be worded 'there will be a difference'

Answer 107

- it allows the relationship between 2 existing variables to be examined when a controlled experiment may not be possible due to ethical or practical reasons so correlations are less-time consuming than experiments - a correlation can be a good starting point for further research as if a relationship has been found between 2 variables, then the researcher might assume that there is something worth investigating and conduct another method to gather data, so if variables are strongly related it may suggest hypotheses for future research

Answer 108

- it is not possible to establish cause and effect between 2 co-variables as the researcher has no control over variables being measured - correlations can be misused, relationships between variables are sometimes presented as casual when they are not e.g. by the media, this leads to false conclusions about causes of behaviour

Answer 109

mean- the central value in a set of data when all the values are added up in a data set and divided by the total number of scores there are median- the middle value in a data set when scores are arranged from lowest to highest, if there are 2 scores in the middle you must take them away /2 and then tale that answer away from the lowest figure mode- the most frequently occurring value used with categorical/nominal data

Answer 110

mean advantages- it is the most sensitive measure of central tendency as it included all the values, therefore it is more representative than the median and mode disadvantages- easily distorted by extreme values so can become distorted median advantages- less affected by extreme scores so more representative of the data as a whole disadvantages- less sensitive than the mean as the actual values of lower and higher numbers are ignored mode advantages- very easy to calculate and relevant to categorical data disadvantages- not representative of the whole data and can sometimes be useless at describing data due to several modes

Answer 111

- these measures are based on the spread of scores (how far scores vary and differ from one another) - there are 2 examples: 1. range- highest to lowest value 2. standard deviation- sophisticated measure of dispersion and is a single value that tells is how far scores deviate (move away) from the mean - the larger the deviation, the greater the dispersion meaning that not all ppts were affected by the IV in the same way as data is widely spread, resulting in anomalous results - a low standard deviation value reflects the fact that data is tightly clustered around the mean, so might imply that all ppts respond in a fairly similar way

Answer 112

advantages- easy to calculate disadvantages- does not account for the distribution of the scores as the range does not indicate whether most numbers are closely grouped around the mean or spread out evenly - only takes into account the 2 most extreme values so can be unpresentative

Answer 113

advantages- more precise than the range as it included all values within the calculation therefore more accurate picture of the overall distribution of data set disadvantages- it may be misleading and it can be distorted by extreme values and extreme values may not be revealed unlike the range

Answer 114

0.002047 1s.f- 0.002 2s.f- 0.020 3s.f- 0.0020 305,620 1s.f- 300,000 2s.f- 310,000 3s.f-306,000

Answer 115

- it is used to express very large/small numbers, using the formula (number 1-10) x 10 to the power) - the number between 1 and 10 is called the mantissa and the power is called the exponent e.g. 3.2x10⁵=320,000 and 3.2x10⁻⁵=0.000032

Answer 116

- kind of estimate using standard form and comparing the exponents

Answer 117

= equal, > greater than (3>2), < less than (2<3), much greater than >> (3000>>0.02), much less than << (0.02<<3000), proportional to ∝, weak approximation ≈ (11≈10)

Answer 118

-originally research e.g. Bowlby, followed the view that childcare was primarily a mothers role - recent research has stressed the importance of the father in a child's healthy psychological development as this may promote more flexible working arrangements in the family and modern parents are better equipped to contribute more effectively to the economy

Answer 119

- a third of all days off work are caused by mental disorders such as depression and absence from work costs the economy - psychological research into the causes and treatments of mental disorders means that people have access to therapies or psychotherapeutic drugs e.g. SSRI and therefore people with mental disorders can manage their condition effectively, return to work and contribute to the economy

Answer 120

- this is when a small group of experts in a particular field scrutinise research findings before it is published - the experts must be objective and unknown to the researcher the aims of peer review are: 1) to allocate research funding 2) validation of the quality and relevance of research 3) to suggest amendments or improvements

Answer 121

P- protects the quality of published research, so minimises possibility of fraudulent research and means published research is of the highest quality E- therefore, preserves the reputation of psychology as a science and increases the credibility and status of the subject

Answer 122

P- anonymity may be used to criticise rival research, as a minority of reviewers may use their anonymous status to criticise rival researchers E- therefore, there is often competition for limited research funding

Answer 123

P- publication bias as there is tendency for editors of journals to want to publish 'headline-grabbing' findings E- therefore, research that does not meet this criteria is ignored P- ground breaking research may be buried as reviewers may be much more critical of research that contradicts their own views E- therefore, peer review may slow down the rate of change within scientific disciplines

Answer 124

- the difference/association between 2 sets of data is greater than what would occur by change - to find out if the difference/association is significant a statistical test is needed which will estimate the probability that the results that you have obtained are due to chance - a statistical test will tell us which hypothesis is accepted and which we reject (alternative or null)

Answer 125

- probability is about how likely it is that a certain event will happen if the null hypothesis were true - the accepted level of probability is 0.05 (5%), this is the level at which a researcher decides to accept or reject the null hypothesis - if the chance between two levels of the IV being down to luck is less than 5%, the results are statistically significant (p<0.05), then the psychologist would accept the alternative hypothesis and reject the null

Answer 126

- a sign test is used to analyse the difference, rather than relationship, in scores between related items e.g. the same ppt is tested twice - therefore, the sign test is a repeated measures design - the data is organised into categories known as nominal data, and if the data is not organised into categories then it is converted

Answer 127

- there will always be a hypothesis given step 1) using the table work out the different between the 2 variables step 2) add up the total number of pluses and minuses and where there is no difference (0) cross out that ppt step 3) work out if there is more + or - and the 'S value' would be the lowest value e.g. if there was 2 pluses and 6 minuses S would be 2 step 4) work out the 'N value' which is calculated by counting the number of ppts in the data not including ppts with a difference of 0 step 5) using the hypothesis at the beginning suggest whether it is directional or non-directional and then compare the calculated value to your critical angle which is found on a critical value table - if 's' is smaller or equal to 'c' the results are significant, in which null hypothesis is rejected and the alternative is accepted - if 's' is more than 'c' then results were not significant, in which we reject the alternative and accept the null

Answer 128

hypothesis= there will be a difference in test results before and after eating breakfast 1) work out the difference between ppts score who ate breakfast and those who didn't 2) 2 pluses and 6 minuses 3) 'S value' would equal 2 as pluses were less frequent, 'N value' equals 8 as there is 8 ppts no including 0's 4) hypothesis is non-directional so is withing the two-tailed values on the critical values table - 'C value' is worked out to be 0 5) S(2) is bigger C(0) therefore the results are not significant and the non-directional hypothesis is rejected and a null hypothesis is accepted