RESEARCH METHODS 2 Flashcards
Define research methods
The process by which information or data is collected usually for the purpose of testing a hypothesis and/or a theory
Define correlation
A mathematical technique in which a researcher investigates an association between two variables, called co-variables.
What type of variables for the two co-variables have to be
Continuous variables
What type of graph is correlation usually plotted on
Scattergram
What does each axis represent in a scattergram
One of the variables investigated
Define correlation coefficient
A number between -1 and +1 that represents the direction and strength of a relationship between co-variables
What two things does a correlation coefficient tell us about the relationship between co-variables
The direction and strength of correlation
What does a coefficient of +1 represent
A perfect positive correlation
What does a coefficient of -1 represent
A perfect negative correlation
The closer the coefficient is to +1 or -1 the ——-
Stronger the relationship between the co-variables is
Which correlation coefficient is stronger -0.5 or +0.5
They are as strong a relationship as each other
Can coefficients that appear to indicate weak correlation still be statistically significant
What does it depend upon
Yes - the side of the data set
Define case studies
An in-depth investigation, description and analysis of a single individual, group institution or event
What data does connecting a case study usually involve
Qualitative data
Hat might researchers construct of the individual concerned
A Case history
What three things may be used to construct a case history
Interviews, observations and questionnaires
What two things might a person be subject to to assess what they are (are not) capable of
Experimental or psychological testing
What type of data would experimental or psychological testing produce from a case study
Quantitative data
What do you call a case study if it takes place over a long period of time
Longitudinal
Who else might data be gathered from rather than just the individual in a case study
Family and friends
Define content analysis
A research technique that enables the indirect study of behaviour by examining communications that people produce.
Give 5 examples of examined communication that people produce
Texts, emails, tv, film or other media
What type of research is content analysis
Observational
What is the aim for content analysis to have conclusions draw
For it to be summarised and described in a systematic way so overall conclusions can be drawn
Define coding
The stage of a content analysis in which the communication to be studied is analysed by identifying each instance of the chosen categories.
What stage is coding in content analysis
The initial stage
What would large data sets be categorised into
Meaningful units.
How might words in text be manipulated to produce quantitative data
Counting up the number of times a word is used
Define thematic analysis
An inductive and qualitative approach to analysis that involves identifying implicit or explicit ideas within data.themes will often emerge once the data has been coded.
When will themes often emerge form data
Once the data has been coded
Is the outcome of thematic analysis qualitative or quantitative
Qualitative
What does a theme in content analysis refer to
Any idea, explicit or implicit that is recurrent.
Are themes more likely to be more or less descriptive than coding units
More descriptive
What might researchers do after they are happy with the themes they have developed
May collection a new set of data to test the validity of the themes and categories.
What will the reseracher do if the themes explain the new data adequately
Write up the final report
What will a final report typically use in thematic analysis to illustrate each theme
Direct quotes from the data to illustrate each theme
What are the four strengths of case studies
Offer detailed insights on very unusual and atypical forms of behaviour.
Contribute to our understanding of ‘typical’ functioning.
Generation of hypothesis for future study
One solitary contradictory instance may lead to the revision of an entire theory.
What are the three limitations to case studies
Generalisation of findings on research of small sample sizes.
Information in the final report is based on the subjective selection and interpretation of the researcher.
Personal accounts from participant, family or friends may be prone to inaccuracy and memory decay.
What are the three strengths of content analysis
Avoids many ethical issues, no issues with obtaining permission.
Such communications have the benefit of being high in external validity.
Can produce both qualitative and quantitative data
What is the limitation of content analysis
May suffer from a lack of objectivity, especially when more descriptive forms of thematic analysis are employed
What do modern analysts do to evaluate and show their own biases
Clear about how their own biases and preconceptions influenced the research process.
Often make references to them as part of their final report
What is the name given to the process of referencing biases in final reports
Reflexivity
Define reliability
Refers to how consistent a measuring device is - and this includes psychological tests or observations which assess behaviour
If a test or measure in psychology assessed some ‘thing’ on a particular day what would we expect to be the case on another day
If this is not the case what do we assume has happened
Expect it to be the same
The thing has changed
What do psychologists tend to measure rather than concrete things
(4 examples)
Abstract things
Attitudes, aggression, memory and IQ
What have psychologists developed to assess whether their measuring tools are reliable
Test-retest
Define test-retest reliability
A method of assessing the reliability of a questionnaire or psychological test by assessing the same person on two separate occasions. This shows to what extent the test produces the same answers.
What is the method for test-retest
Administering the same test or questionnaire to the same person on different occasions.
If the test is reliable what should be the case in the test-retest method
The results obtained should be the same or very similar each time they are administered
What is the test-retest method most likely to be used on
What is another example of where it can but usually wont be applied
Psychological tests and questionnaires
Interviews
What 2 reasons are there for leaving the right amount of time between test and re-test
The participant cannot recall their answers to the questions to a survey
Not so long that the participant’s attitudes, opinions or ability’s might have changes
How would two data sets from test-retest be manipulated
Two sets of scores would be correlated to make sure they are similar
What correlation should be present to indicate a reliable measuring instrument
Significant and positive correlation
Define inter-observer reliability
The extent to which there is agreement between two or more observers involved in observations of a behaviour.
How is inter-observer reliability measured
By correlating the observations of two or more observers
What is the maths sum applied to inter-observer reliability
(Total number of agreements) / (total number of observations)
What number does the result from the maths sum for inter-observer reliability have to be higher than to have a good reliability
+0.80
What type of research is inter-observe reliability important in
Observational reserach
What is the main issue in observational research
One observers interpretation may differ greatly form anothe s
What 3 negative things are introduced into data collection if one observers interpretation is different from another’s
Subjectivity, bias and unreliability
How can inter-observer reliability be tested before the actual experiement
With a pilot-study
In the pilot-study what is being checked to be applied in the same way
Behavioural categories
What is the reliability test called when applied to content analysis
Inter-rater reliability
What is the name of the reliability test done on interviews
Inter-interviewer reliability
What should the correlation coefficient exceed in both test-retest and inter-observer reliability for them to be deemed reliable
Exceed +0.8
What two things can be done to improve a questionnaire if it produces a low test-retest reliability
Some of the items to be ‘deselected’ or rewritten
What type of questions can be replaced with another type of question in questionnaires to make them more reliable
Why
Open questions can be changed to closed questions
Will be less ambiguous
What is the best way to ensure reliability in interviews
To use the same interviewer each time
What should be done if the same interviewer cannot be used every time
What does this prevent
Interviewers must be trained
Prevents one particular interviewer from asking too leading or ambiguous questions
What two words describe a type of interview that is less likely to be reliable
Unstructured and more free-flowing
What can be properly operationalised to improve the reliability of observations
Behavioural categories
What two things must behavioural categories be
Measurable and self-evident
What must behavioural categories do
Overlap
All possible behaviours must be ____
Covered on a check list
What will happen if categories are not operationalised well, or are overlapping or absent
Different observers have to make their own judgements of what to record where and may end up with different and inconsistent records.
What two things can the observers do if reliability is low
Training in using behavioural categories
May wish to discuss their decisions with each other so they can apply categories more consistently
In an experiment was is the focus for reliability
The procedure
What is the goal in an experiment to ensure a high reliability
Standardised procedures
Define validity
The extent to which an observed effect is genuine - does it measure what it is suppose to, and can it be generalised beyond the research setting within which it was found.
For high validity what must represent what is out in the real world
Observed effects
What is the word given to whether the researcher had managed to measure what they intended to
Internal validity
What is the word that refers to the extent to which findings can be generalised beyond the research setting
External validity
Give an example of how reliable data from a research might not be valid
(study on weight is it reliable? Is it valid?)
A broken set of scales may tell someone’s weight consistently but it may always be 5kg more than their actual weight.
The scales are reliable but the weight is not true so lacks validity.
What does internal validity refer to
Whether the effects observed in an experiment are due to the manipulation of the independent variable and not other factors
What is one major threat to the internal validity of a study
If participants respond to demand characteristics - acting in a way they think is expected
Give an example of a study in which demand characteristics are expected to have influenced results
Milgram’s shock study
What does external validity refer to
(What are the 3 others)
Factors outside the investigation.
Generalising to other settings, other populations of people and other areas.
What type of validity does ecological validity come under
It is a type of external validity
Define ecological validity
The extent to which findings from a research study can be generalised to other settings and situations
What type of experimental setting would have a high ecological validity
A more natural setting - one that is likely to be seen in everyday life
E.g. a field study
What is one example of a setting that people believe will have low ecological validity
A lab setting
In an experiment a task that is used to measure the ____ variable will have low ecological validity
What term is given to this
Dependent variable
Low mundane realism
Give an example of a field study in which you would expect high ecological validity but it is actually low
(Memory)
A list of words to remember in a shopping mall.
Using a word list makes the study lack ecological validity.
What must be looked at to decide whether findings can be generalised beyond the setting of reserach
All sorts of aspects of the research
Define temporal validity
The extent to which findings from a research study can be generalised to other historical times and eras.
What type of validity does temporal validity fall under
External validity
Give an example of a study that have low temporal validity.
Why is it the case
Asch’s research having high rates of conformity
They took place in a particularly conformist era in American history (1950s / post WW2)
Define face validity
A basic form of validity in which a measure is scrutinised to determine whether it appears to measure what it is suppose to.
What two things can be done to determine face validity
By simply ‘eyeballing’ the measuring instrument or by passing it to an expert to check
Define concurrent validity
The extend to which a psychological measure relates to an existing similar measure
How can concurrent validity be tested (example with intelligence)
The new-intelligence test will be given to participants alongside a well-established test and IQ scores they achieve may be compared.
What would close agreement between a set of data using an old test and a set of data from a new test mean
The new test has high concurrent validity
Close agreement between the new and old test is indicated if the correlation between two sets is what
Exceeds +0.80
What are two examples looked in more detail of things that can be done to improve validity
Control group
Standardised procedures
What can a control group allow researchers to better assess when looking at validity
Whether changes in the dependent variable were due to the effect of the independent variable
The impact of what two things are minimised when standardising procedures
Participant reactivity and investigator effects on the validity if the outcome
What two types of procedures may help achieve minimised participant reactivity and investigator effects
Single-blind
Double-blind
What is the case in single-blind procedures
What does it reduce the effects of
Participants are not made aware of the aims of a study until they have taken part to reduce the effect of demand characteristics
What is the case in a double-blind study
What two things does this reduce the effects of
A third party conducts the investigation without knowing its main purpose
Reduces demand characteristics and investigator effect
What two things does the introduction of a lie scale into questionnaires and psychological tests assess
The consistency of a respondent’s response
Control for the effects of social desirability bias
What can be promised to respondents to further enhance reliability
Why
Data submitted will remain anonymous
They wont hide negative truths
What type of observations can produce high ecologically valid findings due to minimal intervention by the researcher
Covert observations - behaviour of those observed is likely to be natural and authentic
What can have a negative impact on the validity of observational data collection if they are too broad or overlapping
Behavioural categories
Which method of data collection and research is thought to have a higher ecological validity than the otehr
Qualitative methods have higher ecological validity than quantitative
Why is detail and depth associated with case studies and interview more likely to have higher ecological validity
It is better able to reflect a participants reality
Define interpretive validity
The extent to which the researcher’s interpretation of events matches that of their participants.
What two things can interpretive validity be demonstrated through
Coherence of the researcher’s narrative
The inclusion of direct quotes from participants within report
Define triangulation
The use of a number of different sources as evidence
What does triangulation do to validity
Enhances it
Give 3 examples of what can be combined and used in triangulation
Data complied through interviews with friends and family, personal diaries and observations
What two words and one phrase can be used to describe validity
Whether a test is legitimate and genuine
Whether findings can be generalised
Define statistical testing
Used in psychology to determine whether a significant difference or correlation exists.
What does a statistical test determine about null hypothesis
Whether it should be rejected or retained
What are the three factors to consider when deciding which statistical test to use
Whether the researcher is looking for a difference in correlation
In the case of a difference, what experimental design is being used
The level of measurement
Define levels of measurement
Quantitative data can be classified into types or levels of measurement
What are three example types of measurement quantitative data can be classified into in levels of measurement
Nominal, ordinal and interval
What is the first thing to consider when deciding which statistical test to use
Is the researcher looking for a difference or correlation
Where should it be obvious if the researcher is looking for a difference or correlation
In the wording of the hypothesis
What is not an issue if the investigation is looking for a correlation rather than a difference
Experimental design
What are the three types of experimental design
Independent groups
Repeated measures
Matched pairs
Which two types of experimental designs are referred to as related designs
Repeated measures and matched pairs
What is the case with participants in a repeated measures design
Is this classed as related
Same participants are used in all conditions of the experiment
Yes
What is the case with participants in a matched pair design
Is this classed as related
Participants in each condition are not the same but have been matched on some variable that is important for the investigation.
Yes
What is the case with participants in a independent design
Is this classed as related
Participants in each condition are different
No - unrelated
What must the researcher choose between in decision 2 of experimental design
Whether participants will be related or unrelated
What is the third factor influencing the choice of statistical tests
The levels of measurement
How is nominal data represented
In the form of categories
why is nominal data discrete
One item can only appear in one category
Give an example of a question asked in nominal data and the possible answers
Do you like dogs?
Yes or no
How is ordinal data represented
It is data that can be ordered in some way
Give an example of a question asked for ordinal data and potential answers
Rate how much you like dogs on a scale of 1 to 10
10 - i love dogs
Does ordinal data have to have equal intervals between each unit
No
Which type of data has to have equal intervals between each unit
Interval data
Why does ordinal data lack precision
It is based on subjective opinion rather than objective measures
Why does an IQ test lack precision when looking at ordinal data
IQ test questions are derived from a view of what constitutes intelligence rather than any universnl measurement.
Why is ordinal data not used as part of statistical testing
What is done with ordinal data instead, can this be used
Due to its unsafe nature
Raw scores are converted to ranks and ranks are used in the calculation
How is interval data represented
Based on numerical scales that include equal units, precisely defined size.
What is the most precise and sophisticated for of data in psychology
Interval data
What type of test is interval data a necessary criterion for
Parametric tests
What type of measurement is taken to produce interval data based on accepted units of measurement
Public scales of measurement
Give three examples of accepted units of measurement used in interval data
Time, temperature and weight
What is nominal data’s measure of central tendency
Mode
What is ordinal data’s measure of central tendency
Median
What is interval data’s measure of central tendency
Mean
What is ordinal data’s measure of dispersion
Range
What is interval data’s measure of dispersion
Standard deviation
What is nominal data’s measure of dispursion
There is not one
What are the 2 tests used for nominal data
Chi-squared. Sign test.
What are the 3 tests used for ordinal data
Mann-Whitney. Wilcoxon. Spearman’s rho
What are the 3 tests used for interval data
Unrelated t-test. Related t-test. Person’s r
What are the 6 tests of difference
Chi-squared. Sign test. Mann-Whitney. Wilcoxon. Unrelated t-test. Related t-test
What are the three tests of associated or correlation
Chi-squared. Spearman’s rho. Pearsons r.
What are the 3 unrelated design tests
Chi-squared. Mann-Whitney. Unrelated t-test
Hat are the three related design test
Sign test. Wilcoxon. Related t-test
Define Spearman’s rho test
(A test for what, data at what level)
A test for correlation when data is at least ordinal level
Define Pearson’s r test
(A test for what, data at what level)
A parametric test for a correlation when data is at interval level
Define Wilcoxon test
(A test for what, data at what level, what design)
A test for difference between two sets of scores.
Data should be at least ordinal level using a related design
Define Mann-Whitney test
(A test for what, data at what level, what design)
A test for a difference between two sets of scores.
Data should be at least ordinal level using a related design
Define related t-test
(A test for what, data at what level, what design)
A parametric test for difference between two sets of scores.
Data must be internal level with a related design
Define unrelated t-test
(A test for what, data at what level, what design)
A parametric test for a difference between two sets of scores.
Data must be interval level with an unrelated design
Define Chi-squared test
(A test for what, data at what level, what design)
A test for an association between two variables or conditions.
Data should be nominal level using an unrelated design
What are the three criterion for the use of the parametric test
Data at interval level
Data must be drawn from a normally distributed population
Homogeneity of variance
What three tests are known as parametric tests
Related and unrelated t-test and pearson’s r
What does homogeneity of variance mean
The set of scores in each condition should have similar dispersion or spread.
Why will researchers always choose a parametric test if able to
Able to detect significance within some data sets that non-parametric tests cannot
What do researchers begin their investigation with writing
A hypothesis
What two things might the hypothesis be depending on how confident the researcher is in the outcome of the investigation
Directional or non-directional
What does a null hypothesis state
There is ‘no difference’ between the conditions
What is the name given to the alternative of a null hypothesis
An alternative hypothesis
What is an alternative hypothesis
A hypothesis that states there is a difference between conditions
What does a statistical test determine about the hypothesis
Which hypothesis is true and whether we accept or reject the null hypothesis
What do statistical testes work on the basis of rather than certainty
Probability
Define probability
A measure of the likelihood that a particular event will occur where 0 indicated statistical impossibility and 1 statistical certainty
What does a 0 result for a statistical test indicate for probability
Statistical impossibility
What does a number 1 result form a statistical test indicate about probability
Statistical certainty
What is the usual level of significance in psychology
P < 0.05 or 5%
What does a significant result mean for the null hypothesis
It is rejected
What is significance level
The point at which there is a large enough difference or correlation within the data to claim an effect has been found.
Define significance
A statistical term that tells us how sure we are that a difference or correlation exists.
What does p stand for in p < 0.05
Probability
What does p < 0.05 mean within a population
The probability that the observed effect occurred when there is no effect in the population is equal to or less than 5%
What does p < 0.05 mean for the chances that the correlation isn’t true for the target population from which the same was drawn
There is still up to a 5% chance
Why is the probability 5% or less for the chance it is not true and not 0%
Or 95% or more true and not 100% true
Psychologists can never be 100% certain about a particular result they have not tested on all members of the population under all possible circumstances
What is the name given to the number calculated at the end of a statistical test
Calculated value
What must be the calculated vale be compared to at the end of statistical test to check statistical significance
Critical value
Define critical value
When testing a hypothesis the number boundary or cut-off point between acceptance and rejection of the null hypothesis
What does each statistical test have for critical values
Its own table of critical values
For some statistical tests the calculated value must be what to the critical value
For others the calculated value must be what to the crictal value
Equal to or less than
Equal to or greater than
What are the three criteria for deciding which critical value to use
One-tailed or two-tailed test
The number of participants in the study
The level of significant
If a one-tailed test was used what is the hypothesis like
Directional
If using a two-tailed test what is the hypothesis like
Non-directional
What happens to probability levels when two-tailed tests are used and why
Probability levels double
They are a more conservative prediction
What does the number of participants usually appear as on a table of critical values
N
What might need to be calculated using number of participants in some statistical tests
Degrees of freedom
What two things might cause a more stringent level of significance to be used such as 0.01
Studied where they may be a human cost - drug trials
One-off studies that could not be repeated in the future
What will all researchers do if there is a large difference between the calculated and cricital values in the preferred direction
Why
They will check more stringent levels, as the lower the p value the more statistically significant the result
Define type I error
The incorrect rejection of a true null hypothesis (a false positive)
What are the two other names given to type I errors
Optimistic error or false positive
Define type II error
The failure to reject a false null hypothesis
What are the two other names given to a type II error
Pessimistic error or false negative
When is a type I error more likely to be made
When the significance level is too lenient or too high
When is a type II error more likely to be made
If the significance level is too stringent or too low
Why do psychologists favour the 5% level of significance when it comes to type I and II errors
It best balances the risk of making a type I or type II error
How many and what type of groups are used in Mann-Whitney
Two independent groups
What type of design is in Mann-Whitney
Unrelated
What is the level of measurement of data in Mann-Whitney
Ordinal data
What are the 3 steps to a Mann-Whitney calculation
Step 1: table of ranks
Step 2: working out the value of U
Step 3: the calculated and critical values
How do you produce a table of ranks in step 1 of a Mann-Whitney test
Data in both groups are ranked together.
The lowest number has a rank of 1
Calculate the sum of the ranks for Group A (Ra)
Calculate the sum of the ranks for Group B (Rb)
What do you do in the ranking step of a Mann-Whitney test if two data items are the same
Do an example with a number appearing 4 times
Add up the rank they would get and give the mean for those ranks
The rating of 12 appears 4 times in the table at rank positions 7,8,9 and 10
They are all given a rank of 8.5
Do you need to calculate the smallest or largest value of U in a Mann-Whitney test
The smallest value
What group do you use to calculate the smallest value of U in a Mann-Whitney test
The group with the lowest sum of ranks
If the group with the smallest number of ranks is group A in a Mann-Whitney what will the value of U now be called
Ua
If the group with the smallest sum of ranks is Group A in a Mann-Whitney what will the number of participants now be called
Na
What is the main task in step two of the Mann-Whitney test
Input the data found from the table of ranks into the given equation and calculate the smaller value of U
What is the calculated value in a Mann-Whitney test
The smaller value of U
How would you obtain the critical value of U in a two-tailed Mann-Whitney test
Use the table.
Find the number in the column corresponding to the number of participants in one group and the row of the number of participants in the other
What must the calculated value be in comparison to the critical value for the result to be significant in a Mann-Whitney test
The calculated value must be equal to or less than the critical value
If the calculated value is equal to or less than the critical value in a Mann-Whitney test what happens to the null hypothesis
It is rejected
What type of measure design is used in Wilcoxon
Repeated measure design
What type of data is used in a Wilcoxon test
Ordinal data
What are the 3 steps to completing a Wilcoxon statistical test
Step 1: calculate a difference and rank the difference
Step 2: working out the T value
Step 3: the calculated and critical values
In step 1 of the Wilcoxon test what is ranking based on
The difference between two sets of data
Are signs taken into account during ranking in Wilcoxon test
No they are ignored
What happens if the difference is zero in a Wilcoxon test
The data is not included and is deducted from the N value
How do you calculate the valence of T in Wilcoxon test
Adding up the numbers with the less frequent sign
(Minus or plus)
How do you find the critical value for the Wilcoxon test
Go down the column for the level of significant and across the row for number of participants (N)
The number that lines up with these is the critical value.
What must the calculated value be in comparison to the critical value for the result to be significant in a Wilcoxon test
The calculated value needs to be equal to or less than the critical value
What happens to the null hypothesis in the Wilcoxon test if the calculated valence is more than the critical value
It is accepted
What is the unrelated t-test a test of
Difference between two sets of data
What data does the unrelated t-test use
Interval level only
The unrelated t-test is selected for what group design
Independent groups design
The criteria for what test need to be fulfilled before using the unrelated t-test
Parametric test
What can be assumed about the population and variance if the parametric test is fulfilled in unrelated t-test
Normally distributed population
Homogeneity of variance
If there is a normal distributed population and homogeneity of variance what in both groups are similar in an unrelated t-test
The standard deviation in both groups
What are the 3 steps in the unrelated t-test
Step 1: table of data
Step 2: working out the value of t
Step 3: the calculated and critical values
Outline the 4 calculations that need to be made in step 1: the table of data for the unrelated t-test
Sum of scores for group A (Xa)
Sum of scores for group B (Xb)
Square each value in Group A (Xa²) and calculate sum of all squared values.
Square each value in Group B (Xb²) and calculate sum of all squared values.
What is the equation for Sa and Sb using Xa and Xb in the unrelated t-test
Sa = sum of Xa² - (sum of Xa)² / Na
Same for Sb
How do you work out the value of t after calculating Sa and Sb in the unrelated t-test
Place Sa and Sb into the given equation.
The result is t
What is the calculated value in the unrelated t-test
T
What is the calculated value in the Wilcoxon test
T
When will t be a negative value in the unrelated t-test
When the mean for group b was larger than group a
When you check the critical values table in the unrelated t-test do you take into account the sign for T
No - ignore it
What do you have to calculate before using the critical values table in unrelated t-test
Degrees of freedom
What is the equation for degrees of freedom
Df = (No. of participants in group A + No. of participants in group B) - 2
How do you obtain the critical value in the unrelated t-test
Use critical value table
Find the type of tailed test you completed.
Go down the corresponding column for level of significance to the number that is in the row for the correct degrees of freedom
What must the calculated value be in comparison to the critical value for the result to be significant in the unrelated t-test
The calculated value must be greater or equal to the critical value
If the calculated value is greater or equal to the critical value what happens to the null hypothesis in the unrelated t-test
The null hypothesis is rejected
A related t-test is selected when what design is being used
Repeated design
What type of data is used in a related t-test
Interval level data only
What type of population and variance are required for the related t-test
Normally distributed population
Homogeneity of variance
What are the 3 steps for the related t-test
Step 1: the table of data
Step 2: working out the value of t
Step 3: the calculated and critical values
What are the 4 calculations that need to be made for step 1: the table of data in the related t-test
The difference between scores for group A and B (d)
Square each difference (d²)
Add up the values of d to give the sum of d
Add up the values of d² to give the sum of d²
What happens in step 2: working out the value of t for the related t-test
Input sum of d and sum of d² into the given equation and calculate
What is the calculated value in the related t-test
T
What needs to be calculated before finding critical value in related t-test
Degrees of freedom (Df)
How do you find the critical value for related t-test in step 3
Use critical value table
Find the type of tailed test you completed.
Go down the corresponding column for level of significance to the number that is in the row for the correct degrees of freedom
What must the calculated value be in comparison to the critical value for a significant result in the related t-test
Calculated value must be equal or greater than the critical value
What happens to the null hypothesis if the calculated value of t is less than or equal to the critical value in the related t-test
It is accepted
What is Spearman’s rank a test of between two sets of values
Correlation
The spearman’s rank test is selected when one or both of the variables are what level of data
Ordinal
Can the spearmans rank test also be used with another type of data
Is so which
Yes
Interval data
What does not need to be considered with the spearmans rank test and why
Design type
Investigation is correlation and not experimental
What are the 4 steps for Spearman’s test
Step 1: the table of ranks
Step 2: calculate the difference
Step 3: working out the value of rho
Step 4: the calculated and critical values
What must be done in step 1 of spearmans rho test
Scores need to be ranked separately in each group from lowest to highest.
Are groups/conditions ranked separately or together in spearmans test
Separately
Are groups ranked together or separately in Mann-Whitney
Together
What do you do in step 1 of the spearmans test if two or more scores share the same rank
Find the mean of their total ranks
What 3 things must be done in step 2 of spearmans ranks
Find the difference between each individual pair of ranks (d)
Square the difference for each pair (d²)
Calculate the sum of the squared differences ( sum of d²)
What happens in stage 3 of spearmans rank to calculate rho
Input sum of d² into the given equation and complete the calculation to get rho
What is the calculated value in spearmans
Rho
How do you find the critical value in spearmans rho
Use critical value table
Find the type of tailed test you completed.
Go down the corresponding column for level of significance to the number that is in the row for the correct number of participants
What must the calculated value be in comparison to the critical value in spearmans rho for the result to be significant
The calculated value must be greater than or equal to the critical value
What happens to the null hypothesis in spearmans rho if the calculated value is greater than or equal to the critical value
It is rejected
What type of data is a pearson’s test selected for
Interval level
What is not an issue for selection for a persons test
Why
Design
Investigation is correlational rather than experimental
Can a pearon’s test meet the criteria for a parametric test
Yes
What are the 3 steps for a pearson’s test
Step 1: the table of data
Step 2: working out the value of r
Step 3: the calculated and critical values
What 3 stages of calculations must be made in step 1: the table of data for a Pearsons test
Calculate the sum of the scores for X (sum of X) and Y (sum of Y)
Square each x value and each y value. Calculate the sum of X² and Y²
Multiply X and Y for each participant. Add these values together (sum of XY)
What happens in stage 2: working out the value of r in pearson’s test
Input the calculated sum of X, sum of Y, sum of XY, sum of x² and sum of Y² into the given equation.
Solve the equation to get r.
What is the calculated value in Pearsons
R
What must be calculated before the critical value in Pearsons
Degrees of freedom
How do you find the critical value in stage 3 in pearson’s
Use critical value table
Find the type of tailed test you completed.
Go down the corresponding column for level of significance to the number that is in the row for the correct degrees of freedom
What must the calculated value be in comparison to the critical valence for a significant result in Pearsons test
Calculated value more than or equal to the critical value
What happens to the null hypothesis is the calculated value is less than or equal to the critical value in pearson’s
It is accepted
What is chi-squared a test of
Difference or association
What data is in a chi-squared test
How is it recorded
Nominal
Recorded as a frequency count of categories
What are the two types of groups and therefore design in a chi-squared test
Independent groups
Unrelated design
What are the 4 steps in a chi-squared test
Step 1: A 2x2 contingency table
Step 2: the table of expected frequencies
Step 3: working out the value of x²
Step 4: the calculated and critical values
What happens in step 1 of the chi-squared test
Draw a 2x2 table showing the data that was collected in each cell and calculate the totals for each row, column and an overall total
What is an expected frequency in chi-squared
The frequency that would be expected if there was no difference between two groups
What happens in step 2 of the chi-squared test
Expected frequencies (E) are calculated
How does you calculate expected frequencies (E) in step 2 of chi-squared
Multiply the total for the row by the total for the column divided by the grand total for each cell.
(Total of row x total of column) / grand total.
What does o stand for in the chi-squared test
Observed frequencies - numbers originally recorded
What does E stand for in the chi-squared test
Expected frequencies
Give the equation used in step 3 of the chi-squared test
X² = sum of (O-E²) / E
What happens in step 3 of the chi-squared test
O and E are inserted into the equation and X² is calculated
What is the calculated value for the chi-squared test
X²
What must be calculated before finding the critical value in the chi-squared test
Degrees of freedom
How do you find degrees of freedom for the chi-squared test
Looking at the 2x2 table
(Rows -1) x (columns -1) = Df
How do you find the critical value in step 4 of the chi-squared test
Use critical value table
Find the type of tailed test you completed.
Go down the corresponding column for level of significance to the number that is in the row for the correct degrees of freedom
What is the calculated value in comparison to the critical value in the chi-squared test for a significant result
Calculate value must be greater than or equal to critical value
What happens to the hypothesis in the chi-squared test if the calculated value is greater than or equal to the critical value
It is rejected
Which statistical tests require the calculation of degrees of freedom before finding critical value
Unrelated t-test
Related t-test
Pearson’s
Chi-squared
What statistical test is a test of association
Chi-squared
What statistical tests are test of correlation
Spearman’s and pearson’s
What tests are parametric test
What other test can be parametric
Unrelated t-test
Related t-test
Pearsons
What are two non-parametric test
Mann-Whitney
Wilcoxon
What are the 6 sections of a scientific report in order
Abstract
Introduction
Method
Results
Discussion
References
What is the first section called in a scientific report
Abstract
Define abstract in terms of scientific reports
The key details of the research report including all the major elements.
How many words is an abstract on average
150-200 words
What is the second section of a scientific report
Introduction
Define introduction in terms of scientific reports
A look at past research (theories and / or studies) on a similar topic.
What type of progression should an introduction follow in scientific reports
Logical progression beginning broadly and gradually becoming more specific
What two major things are presented in the introduction of a scientific report
Aims and hypotheses
What is the 3rd section of a scientific report
The method
Define the term method in terms of scientific report
A description of what the researcher(s) did, including design, sample, apparatus, procedure, ethics
What 5 key things must a method include in a scientific report
Design
Sample
Apparatus
Procedure
Ethics
What must a scientific report include in terms of design within a method
Design is clearly stated (e.g. independent groups, naturalistic observations etc.)
Reasons / justifications given for the choices made
What must a scientific report include in terms of sample within a method
When might something not be included
Information related to the people involved in the study: how many, biographical/demographic information, the sampling method and target population.
Something might not be included if it compromises anonymity
What must a scientific report include in terms of apparatus within a method
Detail of any assessment instrument used and other relevant materials
What must a scientific report include in terms of procedure within a method
A ‘recipe-style’ list of everything that happened from beginning to end.
Includes everything said to participants - briefing, standardised instructions and debriefings
What must a scientific report include in terms of ethics within a method
An explanation of how these were addressed within the study
What is the 4th section in a scientific report
Results
Define results in terms of scientific report
A description of what the researcher(s) did, including descriptive and inferential statistics
What 5 things are likely to be included as descriptive statistics in the results section of a scientific report
Tables
Graphs
Charts
Measures of central tendency
Measures of dispersion
What 5 things are likely to be included as inferential statistics in the results section of a scientific report
Statistical test
Calculated values
Critical value
Level of significance
Final outcome for hypothesis
What statistics do graphs and tables come under in results of a scientific report
Descriptive statistics
What statistics do statistical tests come under in results of a scientific report
Inferential statistics
Where does any raw data that was collected and any calculations appear in a scientific report
The appendix
What are results in a scientific report likely to include if a researcher has used qualitative methods
Analysis of themes and/or categories
What is the 5th section in a scientific report
Discussions
Define discussions in terms of a scientific report
A consideration of what the results of the research study tell us in terms of psychological theory
What are the 3 things a researcher should discuss in the discussion section of a scientific report
Summaries results in verbal form, these should be discussed in the context of evidence presented in the introduction and other relevant research.
Discuss limitations of the investigation and suggestions on how to address them for future studies.
Discuss the wider implications of the research - may include real-world applications.
What is the 6th and final stage of a scientific report
Referencing
Define referencing in terms of a scientific report
List of courses that are referred to or quotes in the article (e.g. books, websites) and their full details
What is the format for journal referencing in scientific reports
Author(s), date, articles title, journal name (in italics), volume (issue), page numbers
What is the format for book referencing in scientific reports
Author(s), date, title of book (in italics), place of publication, publisher
What is the format for website referencing in scientific reports
Source, date, title, weblink and date accessed
Which philosopher suggested what distinguishes scientific disciplines from non scientific disciplines
Thomas Kuhn (1962)
What did Kuhn suggest separated scientific disciplines from non-scientific disciplines
A Paradigm - A shared set of assumptions and methods
Define Paradigm
A set of shared assumptions and agreed methods within a scientific discipline
What did Kuhn suggest that social sciences including psychology lacked
What a re they therefore best seen as
They lacked a universally accepted paradigm
Best seen as ‘pre-science’ and as distinct from natural sciences like biology or physics
What two things does psychology have that marks it as a ‘pre-science’ and prevents it from qualifying as a science
It is marked by too much internal disagreement and has too many conflicting approaches.
According to Kuhn when does progress occur within an established science
When there is a scientific revolution
What are the 3 stages of scientific revolution in terms of paradigm according to Kuhn
Researchers begin to question the accepted paradigm
This critique begins to gather popularity and pace
Eventually a paradigm shift occurs when there is too much contradictory to ignore
Define paradigm shift
The result of a scientific revolution when there is a significant change in the dominant unifying theory within a scientific discipline.
What did Kuhn site as an example of a paradigm shift
Newtonian paradigm in physics towards Einstein’s theory of relativity
What is a theory
A set of general laws or principles that have the ability to explain particular events or behaviours.
Define theory construction
The process of developing an explanation for the causes of behaviour by systematically gathering evidence and then organising this into a coherent account.
What two word describe a principle that makes a good theory
What should a theory appear to reflect
Simple and economical principle that appears to reflect reality
What is an essential component of a theory
It can be scientifically tested
How many hypothesis should a theory suggest
A number of possible hypothesis
What is the term given when hypothesis are tested using systematic and objective methods
Hypothesis testing
Define hypothesis testing
A key feature of a theory is that it should produce statements which can then be tested. Only in this way can theory be falsified.
What will systematic and objective testing of a hypothesis determine
Whether it will be supported or refuted.
What is the name given to the process of deriving new hypothesis from existing theories
Deduction
Who made a different argument to Kuhn about what the key criterion is for a scientific theory
Karl Popper (1934)
What was it that Popper argued was the key criterion of a scientific theory
Falsifiability
Define falsifiability
The principle that a theory cannot be considered scientific unless it admits the possibility of being proven untrue.
What is Poppers theory of falsification
Even when a scientific principle had been successfully and repeatedly tested, it was not necessarily true.
It had not been proven false yet.
What did Popper call the science that couldn’t be falsified
Pseudosciences
What did popper suggest was the strongest theories
Those that has survived the most attempts to falsify them.
What two impacts has poppers theory of falsification had on psychology - particularly in scientific reports
Psychologists avoid phrases like ‘this proves’ and use ‘this supports’ instead
Alternative hypothesis must always be accompanied by a null hypothesis which allows for falsifying the hypothesis.
What is the name given to Poppers method of attempting to falsify theories to prove the strongest ones
Hypothetico-deductive method
What is an important element of Popper’s hypothetico-deductive method
Replicability
Define replicability
The extent to which scientific procedures and findings can be repeated by other researchers
What did popper suggest about how replication can be used to assess something else
Replication can be used to assess validity
By repeating a study over a number of different contexts and circumstances then we can see the extent to which findings can be generalised.
What must scientific researchers strive to maintain as part of their investigations
Objectivity
Define objectivity
All sources of personal bias are minimised so as not to distort or influence the research process.
What type of methods in psychology tend to be the most objective
Give an example
The methods associated with the greatest level of control
Lab experiements
What method is objectivity the basis of
Empirical method
Define empirical methods
Scientific approaches that are based on the gathering of evidence through direct observation and experiences.
What are two good examples of the empirical method in psychology
Experimental and observational methods
What did John Locke see knowledge as
What does this mean about theory
Determined only by experience and sensory perception
A theory cannot claim to be scientific unless it has been empirically tested and verified.
