probability and significance - A-level Flashcards
probability definition
measure of likelihood that a particular event will occur where 0 indicated statistical impossibility and 1 statistical certainty
significance definition
statistical term that tells us how sure we are that a difference or correlation exists. a significant result means that the researcher can reject the null hypothesis
critical value definition
when testing a hypothesis, the numerical boundary or cut-off point between acceptance and rejection of the null hypothesis
type 1 error definition
false positive as the alternative hypothesis has been accepted and null hyporthesis rejected when null hypothesis should have been accepted
type 2 error definition
false negative as null hypotheis has been acepted and alternative hypothesis rejected, when the null hypotheis should have been accepted
what is the directional or non directional hypothesis sometimes called
alternative hypothesis
what does the null hypothesis state
there is no difference between the conditions
how do you determine which hypothesis is correct and therefore if to reject or accept the null hypothesis
statistical tests
how do statistical test work
based of probability rather than certainty so show a significance level
what is the significance level
point at which the researcher can claim to have discovered a large enough difference or correlation within the data to claim an effect has been found (if the null hypothesis can be rejected and alternative hypothesis accepted)
what is the usual significance level
0.05 or (5%)
how is the significances level written
p<_ 0.05
what does level of significance mean
the probability of the observed effect occurred when there is no effect in the population is equal to or less than 5%. this means when a researcher has claimed to found a significant difference or correlation there is still up to a 5% chance that isn’t true for the target population form which the sample was drawn
why can psychologists never be 100% certain about a particular result
haven’t tested all members of the population under all possible circumstances, so have settled on a conventional probability where they are prepared to accept the results may have occurred by chance
what happens once the calculated value is decided
checked for statistical significance so calculated value is compared with the critical value which shows if we can reject null hypothesis and accept alternative hypothesis
how is a table of critical values used
each stat test has its own table of critical values and for some tests the calculated value must be greater than or equal to critical value ans for some it must be smaller than or equal to
3 criteria for using critical value tables
-one tailed or two tailed test
-number of participants in the study
-level of significance
how is a one or two tailed test used in a critical value table
directional hypothesis is one tailed and non-directional is two-tailed. probability levels double when two-tailed tests are being used as they are a more conservative predication
how is number of participants in a study used in a critical value table
usually appears as the N value on the table. for some tests degrees of freedom are calculated instead
how is level of significance used in a critical value table
the 0.05 level of significance is the standard level for psychological research
what is the usual level of significance
0.05 level
when is a more stringent level of significance used
0.01 is used in studies where there may be a cost to human life such as in drug trials or in one off studies where for practical reasons it could not be repeated in the future
what happens if there is a large difference between calculated and critical values in preferred dircetion
researcher will check more stringent levels and the lower the p value os, the more statistically significant the result
what is a type 1 error
null hypothesis has been rejected and alternative accepted when it should be the other way round, an in reality the null hypothesis is true
how is type 1 error often referred to
optimistic error or false positive as researcher claims to have found a significant difference or correlation when one doesn’t exist
what is a type 2 error
null hypothesis is accepted when it should have been the alternative hypothesis accepted, and in reality the alternative hypothesis is true
what is a type 2 error often referred to
pessimistic error or false negative
when are you more likely to make a type 1 error
if significance level is too lenient (too high) such as a 10% not 5%
when is it more likely to make a type 2 error
if significance level is too stringent (too low) such as 0.01, as significant values could potentially be missed
why do psychologists favour the 5% level of significance
best balances risk of making type 1 or type 2 error
what is the R rule
stats test that have the letter R in the name, calculated value must be greater than critical value
