research methods overview Flashcards
define aim
- doesn’t make a prediction but instead it states what is it that we want to look at.
- it is a statement of what the researcher intends to find out in a research study
what is a directional hypothesis
- indicates the direction of the prediction
- e.g. ‘music will negatively effect recall’
what is a non-directional hypothesis
- states something is going to happen but not the direction of the prediction.
- e.g. ‘there will be a difference in recall between the music and no music condition’
what is a null hypothesis
-predicts that there will be no difference, only difference is just due to chance
independent variable
- the thing the researcher is able to manipulate between the different conditions
- the thing that is changed
dependent variable
-the thing that is measured
how do you operationalise hypotheses/IV’s/DV’s . How do you make it measurable ?
ask yourself can I count this easily? If the answer is no then it is not operationalised
situational variables
- things to do with the situation
- e.g. lighting, instructions, time of day.
- overcome by standardisation (making everything the same for all conditions)
participant variables
- things to do with the participants
- e.g. age, Intelligence, gender, personality
- overcome by random allocation or measured/matched participants
what are the two extraneous variables
situational variables
participant variables
confounding variable
a type of IV that varies systematically between conditions
investigator effects
-an experimenter may accidentally give cues to make partisans respond in a certain way
- can be over come by;
1. using standardised instructions to stop the experimenter leading the participant.
2. using a double blind technique where both the participants and the experimenter don’t know the aim of the experiment
independent measures
-group of participants, split them in half. Half of the participants do the first condition of the IV and the second half do the 2nd condition of the IV. Compare the performance of both groups.
evaluation of independent measures
advantage = you don’t get order effect as participants are only doing one condition of the IV so they don’t get use to what’s happening.
disadvantage =no control of participant variables and you need twice as many participants
overcoming these problems = random allocation of participants which theoretically distributes participant variables evenly.
repeated measures
-group of participants take part in all levels of the IV. Same participants in all conditions of the IV
evaluation of repeated measures
Advantage = fewer participants. No individual differences as participants are taking part in all conditions of the IV
Disadvantage = you might get an order effect. Participants may do better on 2nd test due to practice effect. May guess experiment purpose and change their behaviour.
overcoming these problems = use 2 different tests to reduce practice effect. Counterbalancing can be used to deal with order effect- cover story can be presented to the participants about the purpose of the test.
matched Paris design
- 2 groups of participants but match them on key characteristics believed to effect performance on the DV
- 1 member of pair is allocated to group a and the other group b. Procedure is then the same for independent groups.
evaluation of matched pairs design
advantages = controls some participant variables, participants won’t guess the studies aim. As a result of having different participants for each condition there is no order effect.
disadvantages = achieving matched pairs is difficult and time consuming. May not control all participant variables
overcoming these problems = restrict the no. of variables to the matched one. A pilot study to show key variables that need to be matched
random sampling
- everyone in the target population has an equal chance of being selected.
- can be done through generating random numbers of simply picking names out of a hat.
opportunity sample
-people who are available at the time the study is carried out. e.g. people in the common room.
volunteer sample
-participants are recruited for through an advert, newspaper, Internet etc
systematic sample
- a system is used to select participants e.g. every 4th person to leave the canteen. The numerical interval is applied consistently.
stratified sampling
- subgroups within the population are identified e.g. gender.
- participants are obtained from each of the subgroups in proportion to their occurrence in the population
- selection from the strata is done using a random technique
1 strength and 1 weakness of random sampling
strength = least biased weakness = difficult to achieve in practice as target population could be huge so time consuming
1 strength and 1 weakness of volunteer sampling
strength = gives access to a variety of participants weakness = tends to be a certain type of person that volunteers. e.g. highly motivated, so could be biased
1 strength and 1 weakness of opportunity sampling
strength = easy and less time consuming to allocate sample
weakness = biased as sample is drawn from a small part of the population
1 strength and 1 weakness of stratified sampling
strength = less biased as proportional and randomly selected representation of subgroups weakness = time consuming to identify subgroups and then randomly select participants
1 advantage and 1 disadvantage of systemic sampling
advantage = unbiased as participants are selected using an objective system weakness = not truly unbiased unless you select a number using a random method and start with this person and then selected every nth person.
lab experiment
- involves manipulation of IV whilst trying to keep all other variables content.
- participants are aware they are taking part in an experiment but may be unsure of the true aims of the study
field experiment
- the IV is manipulated in a natural setting e.g on a train
- participants are often unaware that they are taking part in the experiment
natural experiment
- study in which a naturally occurring IV is investigated
- the IV is not deliberately manipulated by the researcher
- generally used when it’s not possible/practical ethically to manipulate the IV
Quasi experiment
- IV is naturally occurring
- DV can be measured in a lab
- key feature is that the IV isn’t actually ‘manipulated’ or made to vary by anyone-it is simply a difference that exists.
- e.g, gender as the IV
naturalistic observation
- carried out in everyday setting
- investigator doesn’t interfere in any way but just observes the behaviours
controlled observation
-behaviour is observed but under conditions where certain variables have been organised by the researcher
overt observation
participants are aware that their behaviour is being studied
covert observation
observing people without their knowledge
participant observation
observations made by someone who is also participating in the activity being observed
non participant observation
the observer is separate from the people being observed
unstructured observation
- researcher records all relevant behaviours but has no system
- problem is that there may be too much to record and the behaviours recorded will often be those which are most visible
structured observation
- likely to use behavioural categories (operationalised behaviours that you are likely to see)
- tally each time you sport these behaviours
behavioural categories
- e.g. when observing infant behaviour, we can have a lost including things like smiling, crying, sleeping etc
- behavioural categories should be objective, cover all possible component behaviours and be mutually exclusive.
sampling procedures
event sampling= counting the number of times a certain behaviour occurs in a target individual/individuals
time sampling = recording behaviours in a given time frame. e.g. noting what a target individual is doing every 30 seconds
structured interview and evaluation
pre determined questions
strength = easily be repeated as the questions are standardised so answers from different people can be compared and it is easier to analyse
weakness = comparability may be a problem if the same interviewer behaves differently on different occasions. Low reliability
unstructured interview and evaluation
starts off with general aims but the interviewee’s answer quint subsequent questions
strength = provides more detail
weakness = require interviewers with more skill as they have to develop questions of the spot
two types of questionnaires
open questions (qualitative data) closed questions (quantative data)
two strengths of questionnaires
- sample a lot of people in a short space of time as researcher doesn’t need to be there
- doesn’t produce investigator effect
1 weakness of questionnaire
- some groups in society that can’t answer questionnaires -those who can’t read or write
- sample is therefore biased
correlation co-efficient
a numbers cal measure of some type of correlation, meaning a relationship between two variables
3 strengths of correlations
- can allow us to study naturally occurring variables
- can measure things we can’t experimentally (due to ethics)
- can suggest patterns which then lead to experiments
2 weaknesses of correlations
- just because there is a relationship it doesn’t necessarily mean a cause and effect relationship
- may be a third intervening variable that is responsible for the relationship
case study
an in-depth investigation, often of a single individual. They are often longitudinal (over time)
3 strengths of case studies
- give very detailed information
- can be used to investigate very rare behaviours
- interaction of many different things
4 weaknesses of case studies
- each case is unique so can’t be generalised
- may have to recall past (introspective recall). Not reliable
- bias of researcher
- problems of confidentiality due to personal information
what are the three measures of central tendency
mean
median
mode
advantage and disadvantage of mean
advantage = most useful as it is made up of all of the values in the data set
disadvantage = sometimes produces a value that can’t work with certain data. e.g. 2.4 children
advantage and disadvantage of median
advantage = less effect by extreme scores than the mean
disadvantage = not very useful on smaller data sets
advantage and disadvantage of mode
advantage = can be used for categorical data
disadvantage = useless if you have lots of modes within the data
primary data
- first hand
- collected directly by researcher for that study
secondary data
- second hand
- data originally collected for another purpose other than the current one
internal validity
does the research measure what it intends to measure ?
external validity
the extent to which the findings can be generalised
population validity
how results cans be generalised to other groups of people
ecological validity
if it reflects real life
time validity
if results can be generalised to other time periods
external reliability
- whether a experiment measures consistently over time/people
- e.g. an IQ test on Monday should produce the same results a week later if it has external reliability
internal reliability
- whether an experiment is consistent within itself
- e.g. scales should measure the same weight between 50 and 100g and 150 and 200g
when to use a sign test
- when looking at paired or related data
- the 2 pieces of data could come from a repeated measures design, I.e. the same person is tested twice.
- can be used in matched pairs design as participants are paired and count as 1 person tested twice
how to do a sign test
- state hypothesis. Directional means one-tailed test, non directional means two-tailed test.
- record the data and work out the sign (either + or -)
- find calculated value. Add up pluses, add up minus and select smaller value. E.g. if there are 3 minus which is the less frequent sign then S = 3. This is the calculated value
- find critical value of S. N = total no. of scores ( not including any zeros). E.g. one-tailed test is used. Use table of critical values. Locate the column headed 0.05 and the row which begins with N value.
- check result is in the right direction
Quantative
represents behaviour in numbers
Qualitative
descriptive data that represents the quality of something
how to turn qualitative into quantitative
place into categories then count up
bar charts
- height of each bar represents the frequency of each item
- space left between each bar
histogram
- the area within the bars must be proportional to the frequencies represented.
- no gaps between bars
normal distribution
- bell shapes curve
- it is the predicted distribution when considering an equally likely set of results
- mean, median and mode are all in the exact mid point
- the distribution is symmetrical
- the dispersion of scores either side of the mid point is consistent and can be expressed in SD
skewed distribution
-when there is a number of extreme values to one side or the other of the mid point
negative skewed distribution
most of the scores are bunched towards the right
positive skewed distribution
most of the scores are bunch towards the left
what are the 6 ethical issues
P = privacy C = confidentiality D = deception R = right to withdraw I = informed consent P = protection from harm
informed consent
- from the researchers point of view it means revealing the true aims of the study.
- from the participants point of view they should be told what they will be required to do so the can make an informed decision about whether they want to take part
- to deal with it particles ta have to sign a document which contains info about the nature and purpose of the experiment
deception
-from the researchers point of view it can be necessary to deceive participants about true aims of study otherwise participants may alter their behaviour.
-from the participants point of view it is unethical as researcher
.should not deceive anyone without good cause. Deception prevents participants being able to give informed consent.
-to deal with it participants should be fully debriefed afterwards
the right to withdraw
- from the researchers point of view if participants leave then this will make the findings biased as those who stay are likely to be more obedient.
- from the participants point of view if they feel uncomfortable then they should be able to withdraw themselves. Especially important if participant has been deceived about aims.
- to deal with it participants should be informed at the beginning of the study that they have the right to leave.
protection from physical and psychological harm
- from researchers point of view studying some of the more important questions in psychology may involve a aspect of distress in participants.
- from participants point of view nothing should happen in a study to cause them harm.
- to deal with it avoid any risks greater than experienced in everyday life
confidentiality
- from researchers point of view it may by difficult to protect confidentially as they will want to publish findings.
- from the participants point of view the data protection act makes confidentiality a legal right
- to deal with it researcher should not record any names of participants but instead use fake names or numbers
privacy
- from researchers point of it it may be difficult to avoid invasion of privacy when studying participants without their awareness like in a field experiment
- from participants point of view they do not expect to be observed by others in certain situations like in the privacy of their own homes
- to deal with this researcher shouldn’t study anyone without their consent unless it is in a public place and public behaviour
2 examples of how psychology has been used in the economy
memory: cognitive interview used to reduce crime by catching the correct criminals
social influence: reducing smoking and alcoholism, so costing NHS less
purpose of peer review
- allocation of research funding
- publication of research in journal articles
- assessing the research rating of university departments
issues in peer review
- finding an expert
- anonymity
- publication bias
- preserving the status quo
How do you know what the value of s is when calculating the sign test
S is the total for the least frequently occurring sign