probability and significance Flashcards
What is a null hypothesis?
States that there will be no difference between the conditions of the IV.
What is the usual significance level in psychology research?
0.05 (5%)
Why is it good to have a 5% significance level in research?
We can never be 100% certain about results. Results could be down to chance.
What is a one-tailed hypothesis?
A directional hypothesis
What is a two-tailed hypothesis?
A non-directional hypothesis
What are the two types of errors?
Type 1 error
Type 2 error
What is a type 1 error?
Claiming that there is an effect when there isn’t
i.e rejecting the null hypothesis and accepting the experimental hypothesis.
What is a type 2 error?
Claiming that there isn’t an effect when there is.
i.e accepting the null hypothesis and rejecting the experimental hypothesis.
At a probability of 0.01 are we more or less likely to make a type 1 error?
Less
At a probability of 0.10 are we more or less likely to make a type 1 error?
More
At a probability of 0.01 are we more or less likely to make a type II error?
More
At a probability of 0.10 are we more or less likely to make a type II error?
Less
How can we avoid a type I error?
Increase stringency of significance level.
E.g move from p=0.05 to p=0.01
How can we avoid a type II error?
Decrease stringency of significance level.
E.g move from p=0.01 to p=0.05
What are the consequences of a type I error?
-The researcher publishes false data and other researchers waste precious time and resources trying to replicate the study.
-Scientific journals waste resources in publishing replicating research.
What are the consequences of a type II error?
-Researchers may think that their study was not good enough to find an effect so may improve their technique e.g larger sample etc. but they may not find the funding for this.
-Researcher gives up research that might have provided important findings and others do not hear about these new ideas.