6.23 probability and significance 💚

Null hypothesis - suggests no causal relationship between the independent and dependent variable

Alternative hypothesis - suggests a causal relationship

Variability - the researcher must decide if the data is strong enough before rejecting the null and accepting the alternate. Use probability to minimise the chance of error from natural variability

Probability - must be less than 5% probability that the results are due to chance (0.05%)

Type 1 error

• False positive

• When researchers incorrectly accept the alternate hypothesis

• Around 1 in 20 studies

• Reduce this by using a smaller level of significance (0.01%), but this increases the chance of a type 2 error

Type II error

• False negative

• When researchers incorrectly reject the alternate hypothesis

• Use a larger level of significance (0.05%), but this increases the possibility of a type 1 error