00:01
Reliability is a crucial aspect of research and refers to the consistency and accuracy of measurements or instruments used in a study.
00:11
There are several types of reliability, three of which are, number one, parallel forms reliability.
00:36
So parallel forms reliability assesses the consistency of measurements obtained from two different versions of a test or instrument that are designed to measure the same construct.
00:51
An example of this would be in an educational setting where researchers develop two parallel forms of a math assessment to evaluate students ' problem -solving abilities.
01:28
Both versions contain similar difficulty levels and content, i'll call it a similar type, and if they administer form a to one group and form b to another group, there's a high correlation between scores on both forms.
01:57
High correlation between both of these tests.
02:06
And that indicates good parallel forms reliability.
02:11
There's also split half reliability.
02:14
Split half reliability evaluates the consistency of measurements obtained from two values of a single test or instrument.
02:34
An example would be in psychology, if you're doing a study that involves a personality questionnaire with 40 questions.
02:51
Let's say you divvy that up 20 questions apiece.
02:59
And so if you give the 20 questions each to a different group or a different person, they should have a high correlation between results.
03:11
And that means that if you split this 40 question questionnaire down to 20 each, they both have a high correlation or similar results...