correlation + extra bits Flashcards
what do correlation studies investigate
whether there are relationships between different co-variables
how do you write hypothesis as opposed to experimental ones
there will be a significant correlation/relationship
there will be a significant positive/negative (one tailed)
how do you tell in stats if correlation is positive or negative
+1 positive
-1 negative
advantages of correlation studies
-a useful technique when either practical/ethical reasons mean that variables cannot be manipulated so use secondary data
-good starting point for research, can be developed further
disadvantages of correlation studies
-do not tell us cause and effect
-stats tests will not always pick up on a relationship between two co variables
-no qualitative data
when would a parametric stats test be used in psychology
-data is interval/ratio
-variance should be similar
-data has curve of normal distribution
independent measures, nominal data stats test
chi square test
independent measures, ordinal data stats test
mann whitney u test
repeated measures, nominal data stats test
binomial sign test
repeated measures, ordinal data stats test
wilcoxon signed ranks test
correlation, ordinal data stats test
spearman’s rho correlation coefficient
what should p value be for alternative hypothesis to be supported
p< or equal to 0.05
what is a type 1 error
alternative hypothesis accepted and null hypothesis rejected, behaviour shown was due to chance
what is a type 2 error
alternative hypothesis rejected and null hypothesis accepted, independent variable is having a significant impact on dependent variable
what does normal distribution graph look like
peak in middle, symmetrical
what does negatively skewed distribution look like
peak lies to right of graph
what does ~ mean
approximately
what does fish symbol mean
proportionality
what is internal reliability
the consistency of a measuring device e.g how standardised it is
what is external reliability
consistency of a study’s findings e.g is there a pattern to a study’s findings that has not been distorted by outliers
3 methods to test for reliability of a study
-split half method
-test retest method
-inter rater reliability
how to use split half method to test reliability
test one half of questions and obtain a score and then the other half to see if the same level of score was achieved on both halves
how to use test retest method to test reliability
retesting scores to see how standardised the experiment is due to the similarity in results
how to use inter rater reliability to test reliability
2 observers consistently observe or rate the same behaviour and the 2 sets of ratings are correlated
what are the different types of internal validity
face
concurrent
criterion
construct
what are the different types of external validity
population
ecological
what is face validity
whether a test appears on the face of it to be measuring what it intends to
what is concurrent validity
where a test or study measure gives the same results as another test or study that is measuring the same concept
what is criterion validity
how much one test or measure predicts future performance on another test or measure
what is construct validity
refers to whether a test or study actually measures the concept it sets out to measure (and extraneous variables are controlled for)
what is population validity
refers to the degree to which the sample used in the research is representative of a diverse group of people
what is ecological validity
refers to how accurately a piece of research reflects real-life situations
difference between representativeness and generalisability
representativeness - is sample representative
generalisability - are results generalisable
what are demand characteristics
participants guess aim of research and show behaviours they think the researcher wants to be shown
what is social desirability bias
participant behaves in a way that reflects society’s norms to present themselves as a good member of society
what is researcher bias
researcher may want to see a particular behaviour and therefore interpret it differently
what are researcher effects
participant is influenced by researchers presence
what should citing academic references contain
-author or authors, surname first then initials of first name
-year of publication in brackets
-article title in single inverted commas
-journal title in italics
-volume of journal
-issue number of journal in brackets
-page range of article
what is peer review
used to assess whether recently completed research has been carried out in an acceptable manner with appropriate methodology
strengths of peer review
-checks research is useful before funded
-validity ensured
weaknesses of peer review
-long process
-may not be possible to detect research that has used false data
what is falsification
the ability to prove a claim wrong
what is replicability
to be able to repeat and support or reuse the findings from another piece of research
what is objectivity
when a claim is a matter of fact, rather than opinion
what is induction
empirical research is carried out and then a theory is developed to make sense of findings
what is deduction
a theory is developed and then empirical research is carried out to see if the theory is correct e.g Bandura
what is hypothesis testing
once a theory has been identified then a hypothesis is formulated and can be tested in empirical research
independent measures nominal data stats test
chi squared
independent measures ordinal data
mann whitney u test
independent/repeated measures interval/ratio data stats test
t test
repeated measures/ MP nominal data stats test
binomial sign test
repeated measures/ MP ordinal data stats test
wilcoxon signed ranks
correlation ordinal data stats test
spearmans rho
