Statistical Inference Flashcards
what is probability?
the measure of how likely it is that some event will occur
examples of statistical use of probability
case studies and standardised reading tests- by comparing the normal distribution for population
null hypothesis
(H0) claims there is no significant difference
experimental hypothesis
(H1) claims there will be a significant difference
how can hypotheses be tested?
- must assume the null hypothesis is true
- then calculate the probability of getting a score as extreme or more extreme than the one obtained
if the probability is small…
reject the null hypothesis
if the probability is not very small…
retain the null hypothesis
what is the conventional threshold for rejecting the null hypothesis?
p=0.05
α, alpha level
what happens if the observed p value is less than the alpha value?
(p<0.05) the null hypothesis can be rejected as there is a significant difference
what are critical values?
comparing real-life scores at the threshold of statistical significance to scores that are significantly higher/lower than the population scores
how to find the lower critical score
associating z-score with p=0.05
critical z-score =
(critical value - mean) / SD
why is working out the 5% line important?
to quickly observe which results are significantly different from a cut-off point
type I error
rejects the null hypothesis when this should be accepted
type II error
accepts the null hypothesis when this should be rejected
directional hypothesis
predicts the direction of data
nondirectional hypothesis
does not predict the direction of data
__ does not differ whether the hypothesis is directional or not
(H0)
how can probability theory make inferences about a population from sample data
by generalising sample mean and SD to the general population
lack of certainty within statistical inference
cannot be certain that estimated sample mean and SD will be representative of population mean and SD
this means we can state the probability of our inference being wrong