Probability Flashcards
what is a null hypothesis (H0)?
an assumption that there is no relationship (difference, association, etc) in the population from which the sample is taken
a statement of no effect (e.g. there is no gender difference in map reading)
a statement of no difference or no correlation
what is an alternative hypothesis (H1)?
a statement that there is an effect (populations under study are different, etc)
a testable statement about the relationship (difference, association, etc) between two or more variables
the alternative hypothesis should be stated in terms of people rather than participants because we are interested in making a statement about the populations from which the samples are drawn rather than just stating something about the samples themselves
what is probability?
a numerical measure of the likelihood or chance that certain events will occur
a statistical test gives the probability that a particular set of data did not occur by chance
what do researchers look for in results?
researchers should expect small differences between samples, simply because things do vary and this might simply be random variation or chance
they should look for a sufficiently large difference between the samples to be sure that a difference actually exists and it’s not simply down to chance
statistical tests are used to work out whether a difference is significant or not
what are statistical tests used for?
statistical tests are used to work out whether a difference is significant or not
they enable researchers to work out how probable it is a pattern in research data could have arisen by chance or how probable it is that the effect occurred because there is a real difference in the populations from which the samples were drawn
what is chance?
chance refers to something with no cause and something that just happens
researchers can never be 100% certain that an observed effect was not due to chance but they are able to state how certain they are
a 95% probability rate means that researchers are fairly confident that they are right but nevertheless have a little doubt
which probability level is used in psychology and what does it mean?
psychologists use a level of probability of 95%
which means….
• they have a degree of uncertainty
- there is a 5% chance/probability of the results being down to chance
- there is a 5% probability that the results would occur even if there was no real difference between the populations from which the samples were drawn
psychologists tend to use the 5% probability level because this is a good compromise between being too strict or too lenient about excepting the hypothesis
how is a 5% probability level recorded?
p = 0.05
a probability of 5% or less is recorded as p < 0.05
the chosen value of p is the significance level
why might psychologists use a different probability level?
in some cases, psychologists want to be more certain about their findings
for example, when they are conducting a replication of a previous study or considering the effects of a new drug on health
in these cases, researchers use a probability of 1% or less (p < 0.01)
type 1 error
occurs when the researcher rejects a null hypothesis that is true
false positive
type 2 error
occurs when the researcher accepts a null hypothesis that was not true
accepting the null hypothesis when the alternative hypothesis is true
false negative
