frankinafishtank Posted March 9, 2011 Report Share Posted March 9, 2011 I missed the lesson where my teacher explained inferential statistics we have to use for our IA, and now she refuses to explain it again.So my question is: what exactly are inferential statistics, how do i use them, and how do i know which one to pick? Please help Reply Link to post Share on other sites More sharing options...
blindpet Posted March 10, 2011 Report Share Posted March 10, 2011 I missed the lesson where my teacher explained inferential statistics we have to use for our IA, and now she refuses to explain it again.So my question is: what exactly are inferential statistics, how do i use them, and how do i know which one to pick? Please help What are inferential statistics?Inferential statistics are used to test whether the differences you observe between two experimental groups/conditions occurred by chance. They use probability to see what the likelihood of the results you got happening by chance are. If the probability is very low then you can be fairly certain that the difference between the groups is due to the independent variable.How do I use inferential statistics?Inferential statistics can be calculated by hand but it's pretty cumbersome. You can find websites that will allow you to input your data and it will calculate the values you need and tell you if they are significant based on the p-values (probability values). I would recommend using a plugin for Excel since it facilitates the whole process. A good program that provides a 30-day trial is Analyse-it, no need to pay just uninstall it when the trial runs out (but make sure you run the test within the 30 days).How do I know which inferential statistical test to use?The test you run depends on the design you use (repeated or independent measures) and the level of measurement of the data (nominal, ordinal, interval/ratio).Repeated measures is when the same group of participants perform different tasks and essentially act as their own control.Independent measures is when you have one group do one task and another group another task and compare the differences.In IB you will usually have dependent variables that are either categories (nominal), ratings on a scale (ordinal) or reaction times (interval/ratio). Here is a generic guide on which test to use.Nominal - Chi-squareIndependent measures (2 groups)Reaction times - Independent t-testRatings on a scale - Mann-Whitney U TestRepeated measures (2 conditions)Reaction times - Related t-testRatings on a scale - Wilcoxon t-testMore than 2 groupsReaction times - ANOVARatings on a scale - Kruskall-Wallis TestMore than 2 conditionsReaction times - ANOVARatings on a scale - Friedman TestIf you need more info just ask . 2 Reply Link to post Share on other sites More sharing options...
Recommended Posts
Join the conversation
You can post now and register later. If you have an account, sign in now to post with your account.