Topic 7 (statistics) Flashcards
hypothesis
statement/idea made about the value of a population parameter
-test a hypothesis through an experiment or from taking a sample of population
test statistic
result of experiment or statistic calculated from the sample
null hypothesis
H0
default position i.e nothing is biased nothing changes or nothing works
assume to be correct/true unless proved otherwise
alternative hypothesis
H1
states there has been a change
assumption is shown to be wrong
one tailed test
states there will be a change in a specified direction
H1: p<0.5 or H1: p>0.5
two tailed test
states that there has been a change but doesnt specify direction
H1: p doesnt equal 0.5
significance level
- consider how likely the observed value of the test statistic was to occur
- probability level at which you would reject the null hypothesis
- if less than a given threshold called a significance level = can reject null hypothesis
- if not there is not sufficient evidence to reject hypothesis
typical significance levels 10&, 5% or 1%
critical region
region of probability distribution which if test statistic falls within it would cause you to reject the null hypothesis
-set of values which can lead to rejecting the null hypothesis
critical value
first value to fall inside of the critical region
p value
probability of the observed value or more extreme
two tailed you double it as you have split the significance level in half therefore need to double p-value to bring it back up
observed value
lower than expected value P(X< or equal to x) = lower tail
higher than expected value P(X> or equal to x) = upper tail