# research methods

What is a correlation?
Measuring the relationship between two variables.
1 of 180
whats in an aim for a correlational study?
To measure the relationship between VARIABLE 1 and VARIABLE 2.
2 of 180
whats in a nul hypothesis for a correlational study?
There will be no significant correlation between VARIABLE 1 (measured…) and VARIABLE 2 (measured…). Any correlation which does occur will be due to chance.
3 of 180
whats in a alternate/ one tailed hypothesis for a correlational study?
There will be a significant positive/ negative correlation between VARIABLE 1 (measured …) and VARIABLE 2 (measured…).
4 of 180
whats in a alternate two tailed hypothesis for a correlational study?
There will be a significant correlation between VARIABLE 1 (measured…) and VARIABLE 2 (measured…).
5 of 180
whats a positive correlation?
it is when two variables increase together, though not necessarily at the same rate.
6 of 180
whats a negative correlation?
it is when one variable increases as the other decreases, though not necessarily at the same rate.
7 of 180
what is no correlation?
it is when there is no relationship between the two variables, and is represented by a correlation coefficient close to 0.
8 of 180
stregnths of correleational research?
Shows the strength of a relationship between two variables which indicates the extent to which a factor influences behaviour.
9 of 180
second stregnth of correlation?
Allows data to be collected that perhaps could not have
10 of 180
example from second strength?
. I.e. getting people to take illegal drugs to test their effect would be unethical, but carrying out a correlation between grams of cocaine consumed per week and severity of paranoia, in existing users is acceptable.
11 of 180
argument against second strength example?
Equally, Maguire used a correlation to investigate how navigation experience was related to the volume of the hippocampus as getting people to practice navigational skills over many years would have been difficult without paying them= is very costly.
12 of 180
third strength of correlation?
Is often cheaper than an experiment as variables do not have to be manipulated or controlled, so can allow us to identify potential factors of a behaviour which can then be tested experimentally. If no relationship is found, experiment isnt needed.
13 of 180
fourth strength of correlation?
is often cheaper and quicker than an experiment as variables do not have to be manipulated or controlled, so more participants can be tested, increasing the population validity of results, and therefore the generalisability of the conclusions.
14 of 180
weaknesses of correletional research?
Correlations do not show causation: No cause and effect relationship can be determined as the relationship between A and B, may be caused my other untested variables.
15 of 180
second weakness correlation?
Bidirectional ambiguity: Correlations do not reveal which variable influences the other, for example a researcher might find that children who watch more television also display more aggressive behaviours on a school playground.
16 of 180
explinantion of second weaknesss?
This would be a positive correlation, however, it would not be possible to say whether the television viewing caused the aggression, or if it was the aggression which led the child to watch more television.
17 of 180
other explination for second weakness?
, could also be that there is no cause-and-effect relationship at all, but that another variable might be responsible for the behaviour
18 of 180
own experience correlation experiment?
At AS, we carried out a correlation on narcissism (self-love) and creativity.
19 of 180
what are examples of experimental methods?
Laboratory , field, quasi
20 of 180
Laboratory definition?
controlled enviroment
21 of 180
feild definition?
Natural environment for that task/ the participants
22 of 180
quasi definition?
Conditions of IV are naturally occurring. Experimenter doesn’t decide who is in which condition.
23 of 180
labatory stregnths?
It’s controlled so Ps are tested in consistent/ same environment so the results should have internal reliability.
24 of 180
second labatory stregnth?
Extraneous variables are identified and controlled so they cannot confound the results, improving the internal validity, and demonstrating clearer cause and effect.
25 of 180
feild stregnths?
Good ecological validity because it is set in the participants’ natural environment. Results are generalisable to explain the phenomenon in its real-world setting. * Experimenter effects are less likely to occur as the researcher is not controlling t
26 of 180
quasi stregnths?
Experimenter doesn’t decide who is assigned to which condition so there is less experimenter bias, improving the internal reliability. * This method can be used to demonstrate cause and effect when it would be unethical or impractical (too expensive,
27 of 180
labatory weaknesses?
Lacks ecological validity because the real world is not so controlled. Results are less generalisable to explain the phenomenon in its real-world setting. Experimenter effects are more likely to occur as the researcher is controlling - environment
28 of 180
feild weaknesses?
It’s uncontrolled so Ps are tested in an inconsistent/ changing environment so the results lack internal reliability. * Extraneous variables aren’t controlled so they could confound the results, reducing the internal validity, making cause and effect
29 of 180
quasi weaknesses?
Individual differences between conditions can confound the results, reducing the internal validity. * Shares the weaknesses of lab or field, depending on where it is conducted.
30 of 180
expermental design examples?
independant, repeated, matched pairs
31 of 180
independant definition?
Different participants take part in each condition
32 of 180
repeated definition?
Same participants take part in all conditions
33 of 180
matched pairs definition?
Participants are pre-tested so they can be paired/matched on shared traits the researcher wants to control for, and divided between the conditions.
34 of 180
independant stregnths?
No order effects confounding results (i.e. fatigue, boredom or practice from the 1st condition affecting the 2nd), improving the internal validity
35 of 180
repeated stregnths?
No individual differences between conditions confounding the results, increasing the internal validity. * Half as many participants must be recruited compared to independent measures, which is economic in time and money.
36 of 180
matched pairs stregnths?
Controls for some individual differences, which have been matched so they are the same across conditions, improving internal reliability.
37 of 180
independant weaknesses?
Individual differences between conditions can confound the results, reducing the internal validity. * Twice as many participants must be recruited compared to repeated measures, which is uneconomic in time and money.
38 of 180
repeated weaknesses?
Order effects may confound results (i.e. fatigue, boredom or practice from the 1st condition affecting the 2nd), reducing the internal validity
39 of 180
matched pairs weaknesses?
Some individual differences may still occur between conditions, as they have not been matched on, so internal reliability may be reduced.
40 of 180
counterbalancing definition?
order effects in repeated measures design can be controlled for by randomly allocating half your participants to do condition 1 first followed by condition 2 and half to do condition 2 first followed by condition 1.
41 of 180
whats the independant variable?
the variable which is manipulated by the researchers, or that the participants are grouped by. It is the variable they are investigating to see if it is the cause of a phenomenon.
42 of 180
what are the conditions?
These are what changes in the experiment (may be manipulated by the experimenter, or may be naturally occurring groups). It is what the researchers are investigating the difference between.
43 of 180
whats the dependant variable?
the variable which researchers are measuring. It is the variable researchers believe will be effected by the IV.
44 of 180
what is control?
This is something which has been kept the same for all participants so it cannot affect results.
45 of 180
how to write experimental aim?
The aim is to investigate whether [state IV] affects [state DV]
46 of 180
how to write for experimental research questions?
Does [state IV] affect [state DV]?
47 of 180
how to answer how has the IV been operationalised?
Copy from the scenario every detail on what happened in the different conditions. Do NOT refer to the DV or you may get 0 marks.
48 of 180
how to answer how has the DV been operationalised?
Copy from the scenario every detail on how the DV was measured. Do NOT refer to the IV/ what happened in the condition or you may get 0 marks.
49 of 180
how to answer evaulate how the IV has been operationalised?
Consider the ecological validity of how the conditions were manipulated (not the ecological validity of the environment itself)
50 of 180
how to answer evaulate how the DV has been operationalised
Consider how standardised the measure was which will affect its reliability Consider whether bias would affect responses to the measure, confounding the results and reducing internal validity.Consider what type of data was collected + its strength/ w
51 of 180
writing frame for null hypothesis?
write out
52 of 180
writing frame for two-tailed hypothesis?
write out
53 of 180
writing frame for one tailed hypothesis?
write out
54 of 180
what is a participant observation?
The person observing actually joins in with the group of people they want to watch, this can be overtly or covertly.
55 of 180
participant observation stregnths?
As the observer is part of the group being observed, they are able to gather a greater insight into the behaviour of the group and the reasons behind those behaviours, increasing the validity.
56 of 180
participant ovbservation weaknesses?
The observer is in danger of interpreting behaviour based on their own reasoning or relationships with the participants, which may not reflect participants’ reasons, reducing the validity of their conclusions.
57 of 180
what is a Non- participant observation?
The person observing does not join in with the group of people they are observing; they observe from afar.
58 of 180
non-participant observation stregnths?
It is easier for the researcher to remain impartial and unbiased as they are not participating in the behaviour being observed, meaning the validity of the data being recorded is increased.
59 of 180
non- participant observation weaknesses?
The researcher has less insight into why the behaviour is occurring because they are not fully experiencing what the participants are experiencing and are not fully engaging with them, which means the validity of their interpretations will be reduced
60 of 180
what is a naturalisitic observation?
Observing the behaviour in participants’ own environment.
61 of 180
naturalistic observation stregnths?
High in ecological validity as it is a naturally occurring event and the researcher has not in any way tampered with the situation.
62 of 180
naturalistic observation weaknesses?
Low in external reliability as it is difficult to replicate because the researcher has no control over the environment/situation.
63 of 180
what is a controlled observation?
Involves the recording of behaviour under conditions controlled by the researcher, i.e. an artificial or simulated environment.
64 of 180
controlled observation stregnths?
The researcher can control important elements of the study which limits the influence of external factors which may affect the behaviour of the participants. This means these variables cannot confound results, increasing- internal validity of data
65 of 180
controlled observation weaknesses?
As the situation is artificial participants may be aware that the situation is being manipulated so demand characteristics may occur, which confound the results reducing the validity.
66 of 180
what is an overt observation?
Participants know they are being observed.
67 of 180
overt observation stregnths?
Participants can choose to withdraw from the observation. Consent can be obtained. * Data can be recorded openly making it more likely all behaviour can be recorded as it happens so nothing is missed, making the data more valid.
68 of 180
overt observation weaknesses?
Demand characteristics may occur as participants may change their behaviour when they know they are being watched. This means that their behaviour may no longer be natural which reduces the ecological validity.
69 of 180
what is a covert observation?
Participants do not know they are being observed. Researchers may use one way mirrors, video cameras, or pretend to be doing work, when observing behaviour.
70 of 180
covert observation stregnths?
There should be less demand characteristics and higher ecological validity as participants are more likely to display natural behaviours because they do not know they are being observed.
71 of 180
covert observation weaknesses?
There are ethical issues (lno consent, deception). Can only ethically be conducted in a public place. * It may also be difficult to record data (as it would raise suspicions) and therefore data could be missed would decrease the validity of findings.
72 of 180
what is an unstructured observation?
This involves the researchers recording everything they see happen during the course of the observation. No system for recording behaviour is planned. This tends to produce qualitative data.
73 of 180
unstructured observation stregnths?
Allows the researcher to record other important behaviours which may occur but would not be recorded using a planned system, increasing the validity of conclusions.
74 of 180
unstructured observation weaknesses?
It is difficult to record all behaviour that is occurring and makes replication difficult (i.e. checking for reliability). *
75 of 180
what is a structured observation?
This is where the researcher designs a replicable procedure, using well-defined systems, like event sampling, to record behaviour. It is carried out in an objective way, so no participant observation.
76 of 180
structured observation stregnths?
Generally provides quantitative data (frequencies) which is easier to analyse and compare with other populations, increasing generalisability of results.
77 of 180
strutured observation weaknesses?
Does not allow the researcher to record behaviours which do not occur in their planned observation schedule, which means the data may be less valid.
78 of 180
what is event sampling techniques?
When a checklist of behaviours the researchers expect to see are pre-determined (coding system). Over a continuous period of time, researchers tally every instance of the pre-determined behaviours.
79 of 180
event sampling technique stregnths?
All behaviours are recorded because the researcher is continuously looking at the event, making the data collected more valid. • A coding system makes it easier for all observers trecord data in the same way, increasing-inter-rater reliability
80 of 180
event sampling techniques weaknesses?
Hard to ensure all behaviours are recorded if they happen in quick succession or many behaviours occur at one time. The observers may miss some due to human error, leading to the data being lower in validity.
81 of 180
what is time sampling technique?
The researcher specifies the duration for which all observers will record behaviour, and the duration they will have rest breaks/ intervals for. I.e. recording behaviour for 30secs every 5mins for an hour.
82 of 180
time sampling techique strengths?
Easier to record data as the researchers can stay more focused when observing because they have “rest periods” where they are not observing; this means when looking at the scene they should be “fresher” and able to pay more attention.
83 of 180
time sampling technique weaknesses?
• Behaviours may be missed during the set intervals/ breaks between observations, meaning that the findings on the behaviour being investigated may not be valid/ representative of typical behaviour researchers intended to investigate. • As behaviours
84 of 180
what is a self report?
A self-report is any method which involves asking participants about their feelings, attitudes, and beliefs etc...
85 of 180
what are interviews?
A type of spoken questionnaire: The interviewer records the responses
86 of 180
whats a structured interview?
Predetermined set of questions are asked to all participants
87 of 180
whats an unstructured interview?
Questions are not decided in advance – the researcher has a general theme they would like the participant to talk about and questions may be generated by the interviewer during the course of the interview.
88 of 180
whats a semi-strcutured interview?
Some pre-determined questions are asked to all participants, but there is potential for follow-up questions to be asked as the interviewer sees fit.
89 of 180
what are questionaires?
Consists of a set of questions usually in a highly structured written form, participants record their own answers.
90 of 180
things you need for desiging a good questionaire?
When designing questionnaires, the researcher should ensure there is clarity in the way the questions are being asked. There should be no ambiguity; to help with this, key terms should be operationalised. Researchers should try to avoid bias.
91 of 180
whats an open question?
they allow the participant to choose their own response, and collect qualitative data
92 of 180
what are closed questions?
they mean that the participant makes a forced choice, which makes it easier to analyse the responses.
93 of 180
what are rating scales?
they get the participant to assign a numerical value to their opinion, which means they collect quantitative data. However, the scales are often interpreted differently by different participants leading to a lack of internal reliability in the data
94 of 180
what are semantic differentail rating scales?
they are a bipolar scale where words/statements with opposite meaning are printed at either end of the scale, like introvert/extrovert.
95 of 180
what are likert rating scales?
they are 5 or 7 point scale which assesses how much an individual agrees or disagrees with a statement. Allows for the response to be neutral or neither agree/disagree. Ranges from Strongly agree to strongly disagree.
96 of 180
what are filler (distracter) questions?
some irrelevant questions to mislead the respondent from the main purpose of the survey. This may reduce demand characteristics.
97 of 180
what is a pilot study?
The questions can be tested on a small group of people. This means that you can refine the questions in response to any difficulties encountered.
98 of 180
self report stregnth?
Useful as it gives insight into the participants' attitudes, beliefs, feelings, memories or thoughts, which cannot be measured in other ways.
99 of 180
self report weaknesses?
Responses can be confounded by participant biases, reducing the validity of results. * The reliability can be lowered as the wording of the question/scales, or participants' use of language can be interpreted in different ways.
100 of 180
questionaire stregnths?
Standardised meaning all participants are asked the same questions, increasing reliability, and their responses can be compared more easily to allow conclusions to be drawn about a phenomenon.
101 of 180
questionaire weaknesses?
May miss out on important information about how/why a phenomenon occurs, as questions are pre-determined. Lowers validity.
102 of 180
interview stregnth ?
Allows rapport/ a relationship to be built with the interviewee, which may encourage them to give greater insight into the phenomenon being investigate.
103 of 180
interview weaknesses?
More possibility of social desirability bias because responses are not anonymous, and the participant may be worried the interviewer will judge them. This could confound results, reducing validity.
104 of 180
strcutured interview stregnths?
Standardised meaning it is reliable and easier to compare participants' responses to draw conclusions about a phenomenon.
105 of 180
structured invterview weaknesses?
No opportunity to ask further questions-clarify the meaning of a participants' response, results in lowered validity of interpretations, less insight is gained into the phenomenon as further questions concepts interest of participants cant be asked
106 of 180
unstructured interview stregnth?
Opportunity to ask further questions to clarify the meaning of a participants' response, resulting in increased validity of interpretations, and greater insight gained into the phenomenon as further question on participant intrests cant be asked
107 of 180
unstructured interview weaknesses?
Not standardised meaning it is unreliable and more difficult to compare participants' responses to draw conclusions about a phenomenon.
108 of 180
semi- strcutured interview stregnths?
Opportunity to ask further questions to clarify the meaning of a participants' response, resulting in increased validity of interpretations, greater insight gained into phenomenon as further question - concepts of participants intrests cant be asked
109 of 180
semi- strutured interview weaknesses?
Lacks standardisation, which reduces the reliability, and makes the responses more difficult to analyse than in a structured interview.
110 of 180
diary stregnths?
Can note down thoughts/ behaviours/ feelings as they happen which reduces the likelihood of retrospective bias confounding the results, increasing the validity.
111 of 180
diary weaknesses?
Participants may forget to fill it in or rush their responses because of other commitments which reduces the amount of insight into a phenomenon that can be gained.
112 of 180
open questions stregnths?
Allows participants to record their responses in their own language, making it more representative of how they actually feel/think/behave, and therefore more valid.
113 of 180
open questions weaknesses?
It can be difficult to interpret participants' use of language, reducing the validity of conclusions drawn about the phenomenon.
114 of 180
closed questions stregnths?
Easier to compare participants' answers, which makes it easier to analyse and draw conclusions about a phenomenon.
115 of 180
closed question weaknesses?
May not represent participants' actual response, as it is forced-choice, and therefore the results may be invalid.
116 of 180
rating scale stregnths?
As it's quantitative, it is easier to compare participants' answers, which makes it easier to analyse and draw conclusions about a phenomenon.
117 of 180
rating scale weaknesses?
Doesn't provide as much detail on how or why a phenomenon occurs.
118 of 180
likert rating scale stregnths?
Allows participant to opt for a neutral response which may be representative of how they truly feel and therefore more valid.
119 of 180
likert rating scale weaknesses?
Participants may be indecisive or feel safer not expressing an opinion so may opt for the middle value, reducing the validity of the data.
120 of 180
semantic differntial rating scale stregnths?
Allows attitudes, behaviours, or traits to be measured on a dimension, which should be more representative of how participants really behave/think/feel.
121 of 180
sematic differntial rating scale weaknesses?
Bipolar adjectives may be misunderstood by participants, reducing the validity of their responses
122 of 180
reliabillity in self reports?
Reliability refers to how consistent a measuring device is. A measurement is said to be reliable or consistent if the measurement can produce similar results if used again in similar circumstances.
123 of 180
what is the split half method?
This involves splitting a test into two and having the same participant doing both halves of the test. If the two halves of the test provide similar results this would suggest that the test has internal reliability.
124 of 180
what is test retest method?
This involves giving participants a questionnaire/interview/test and then giving them the same questionnaire/interview/test at another time, e.g. a month later. If the scores on the test give similar results then has external reliability.
125 of 180
procedure questions, own experiance self reports?
In AS, we did a questionnaire on attitudes towards crime.
126 of 180
what is the probability in results?
Probability that the results are due to chance is set at 0.05 for Psychology; this can be expressed as a 1/20 or 5% likelihood the results are due to chance. It gives us a 95% confidence interval (certainty our results are significant)
127 of 180
what is a type 1 error?
it is a false positive (reject the null when we should have accepted it). More likely to occur if you set your probability higher, i.e. 0.10 as your confidence in your results is reduced to 90%
128 of 180
what is a type 2 error?
a false negative: false negative (accept the null when we should have rejected it). More likely to occur if you set your probability lower, i.e. 0.01 because you’re being overly-cautious
129 of 180
what must parametric tests be?
Normally distributed (roughly equal mean, median, and mode): no positive skew (when the tail is on the positive side) or negative skew (when the tail is on the negative side)
130 of 180
independent second strength?
Less chance of demand characteristics confounding results, as Ps don’t observe the change in the IV, which improves the internal validity.
131 of 180
matched pairs second strength?
No order effects confounding results (i.e. fatigue, boredom or practice from the 1st condition affecting the 2nd), improving the internal validity.
132 of 180
repeated second weakness?
More chance of demand characteristics confounding results, as Ps observe the change in the IV, which reduces the internal validity.
133 of 180
matched pairs second weakness?
Uneconomic in time and money as participants must be pre-tested in order to match them. This may result in smaller samples being recruited, reducing population validity.
134 of 180
what does counter balancing do?
by doing this the results of both conditions will be equally affected by order effects.
135 of 180
examples of experimental methods?
labatory, feild and quasi
136 of 180
examples of experimental designs?
independent, repeated and matched pairs
137 of 180
when is a lab or field experiment quasi?
if the conditions of the IV are naturally occurring/ not manipulated by an experimenter
138 of 180
how to answer evaluate how the Iv has been operationalised? part 2
Consider whether every participant experienced the same within each condition, i.e. whether it was standardised (not whether the environment was standardised). This effects internal reliability.
139 of 180
how to answer how the DV has been operationalised part 2?
Consider whether bias would affect responses to the measure, confounding the results and reducing internal validity. Consider whether the measure was an ecologically valid way of testing the DV
140 of 180
second strength of participant observation?
Is more appropriate to observe sensitive groups, such as people with mental health issues, additions, or criminals, as trust can be built with the group.
141 of 180
particpant observation second weakness?
It is difficult to record behaviour as it happens because it may disrupt interactions with the participants, meaning behaviours may be missed reducing the validity of the data.
142 of 180
non- participant observation second strength?
It is easier to record behaviour as it happens (as it won’t disrupt interactions with the participants), which means less behaviours will be missed, making the data more valid.
143 of 180
naturalistic observation second strength?
It may be the only practical way to observe certain behaviours when the situation cannot be artificially re-created in a controlled environment.
144 of 180
naturalistic observation second weakness?
Can result in more practical difficulties gathering data, as people can obscure your line of sight/ unexpected events can get in the way of recording, meaning the data is incomplete so less valid.
145 of 180
controlled observation second strength?
The observation is more replicable because situational factors can be kept constant, making the results more externally reliable.
146 of 180
controlled observation second weakness?
There may also be a reduced level of ecological validity as participants are not studied in their natural environment.
147 of 180
overt observation second weakness?
May not be appropriate to observe sensitive groups, such as people with mental health issues, additions, or criminals.
148 of 180
unstructured observation second interview?
t provides rich qualitative data which may provide greater understanding of behaviour (why it occurs and how it is carried out) and increase the validity of the findings.
149 of 180
unstructured observation second weakness?
Bias may occur as the researcher may not think some behaviour is worth recording, and therefore only records behaviours that fit their expectations, confounding the results and reducing the validity.
150 of 180
structured observation second stregnth?
A system makes it easier to record behaviour, which means it is less likely behaviours will be missed, improving the validity of results.
151 of 180
structured observation second weakness?
Is more objective than unstructured which means it often lacks the insight into behaviour, reducing its validity.
152 of 180
event sampling second weakness?
The observers are restricted to just recording the types of behaviours they’ve pre-determined, meaning other, interesting behaviours can’t be recorded, making the results less valid.
153 of 180
event sampling third weakness?
If it does not use a coding system, qualitative data may be recorded which is difficult to analyse and compare to other populations to establish whether the results are generalizable.
154 of 180
time sampling what is there less chance of?
ess chance of human error affecting validity of dat
155 of 180
time sampling second stregnth?
If it doesn’t always involve a coding system, it means observers aren’t restricted to just recording the types of behaviours they’ve pre-determined, meaning other interesting behaviours can be recorded, making the results more valid.
156 of 180
time sampling second weakness?
As behaviours don’t have to be pre-recorded, observers may record different behaviours, lowering the inter-rater reliability.
157 of 180
event sampling second stregnth?
Tallies (frequency) data is quantitative which makes it easier to analyse and compare. The coding system can be used on other populations to test generalizability.
158 of 180
what are the most common self reports?
The most common self-report methods are questionnaires and interviews; however diary analysis can also be used as a means to gather data.
159 of 180
what happens if there is bias in a questionaire?
Any bias in a question might lead the respondent to be more likely to give a particular answer (as in a leading question)
160 of 180
what is the greatest problem with a questionaire?
social desirability bias. Respondents prefer to select answers that portray them in a positive light rather than reflect the truth.
161 of 180
what do researchers have to concider?
Researchers should also consider how they are going to analyse their data. Questions should be written so that answers are easy to analyse.
162 of 180
self report second stregnth?
Can gather qualitative and/or quantitative data meaning it explains how/why a phenomenon occurs and/or allows responses to be compared and analysed more easily.
163 of 180
self report second weakness?
The reliability can be lowered as the wording of the question/scales, or participants' use of language can be interpreted in different ways.
164 of 180
questionaire second stregnth?
Anonymous- decreasing the likelihood of social desirability bias confounding results, increasing validity.
165 of 180
questionaire second weakness?
The reliability can be lowered as the wording of the question/scales, or participants' use of language in response to open questions can be interpreted in different ways
166 of 180
interview second stregnth?
The researcher can clarify a question if the interviewee does not understand, or to ask further questions to clarify their understanding of what the participant means, which can increase the validity of responses and interpretations.
167 of 180
interview second weakness?
More possibility of interviewer effects, such as non-verbal cues or intonation guiding participants to answer in certain ways. This could confound the results, reducing the validity.
168 of 180
semi structured interview second stregnth?
More comparable responses, as the same themes are explored, than an unstructured interview, allowing for conclusions about the phenomenon to be drawn more easily.
169 of 180
diary second stregnth?
Allows participants to record their responses in their own language, making it more representative of how they actually feel/think/behave, and therefore more valid.
170 of 180
diary second weakness?
It can be difficult to interpret participants' use of language, reducing the validity of conclusions drawn about the phenomenon.
171 of 180
open questions second stregnth?
Tends to gather qualitative data which gives more insight into a phenomenon and how or why it occurs.
172 of 180
open questions second weakness?
It is more difficult to compare participants' answers as they use different language, which makes it harder to draw conclusions about a phenomenon.
173 of 180
closed questions second stregnth?
There is no chance of researchers misinterpreting the participants' responses, as only pre-determined answers can be given, so the validity of conclusions is higher.
174 of 180
closed questions second weakness?
Doesn't provide as much detail on how or why a phenomenon occurs.
175 of 180
rating scale second stregnth?
It's quicker and easier for participants to complete than descriptive answers, so more concepts can be investigated, or more participants may be willing to participate, increasing population validity.
176 of 180
rating scale second weakness?
Participants may interpret the scales differently, which reduces the reliability of responses.
177 of 180
example of reliablity in sefl reports?
For example, if a speedometer gave the same readings at the same speed it would be reliable. If it didn't it would be pretty useless and unreliable.
178 of 180
what must paramentric tests be part 2?
Equal variance in conditions or variables for a correlation (Standard deviation tells us the average amount each score varies from the mean)
179 of 180
what data must parametric test gather?
gather atleast interval level data
180 of 180

## Other cards in this set

### Card 2

#### Front

whats in an aim for a correlational study?

#### Back

To measure the relationship between VARIABLE 1 and VARIABLE 2.

### Card 3

#### Front

whats in a nul hypothesis for a correlational study?

### Card 4

#### Front

whats in a alternate/ one tailed hypothesis for a correlational study?

### Card 5

#### Front

whats in a alternate two tailed hypothesis for a correlational study?