Reply
Tue 15 Jan, 2019 12:52 pm
Hi! I need to statistically show whether or not the number of trials my animals needed to reach the learning criterion dropped as they went through more tasks (in total 10 transfers). It seems like there really is not too much correlation between the number of trials needed to learn and the number of tasks they had gone through, but I don't know how to statistically show it i.e. how to make a correlation analysis of this (I was suggested to perform a Spearman test, but after making research maybe also one way repeated measures ANOVA would work? ).
Do I have to have the same individuals in each step ? I mean, does it matter if in the first 4 transfers I have 5 individuals, then for the transfers 5-8 I have 3 of those ones left and then for the transfers 9-10 I only have one of those individuals left? Or do I have to have the same individuals in every "phase"? This would mean that I can only analyze the first 4 transfers using all individuals or analyze the first 8 transfer, using only the three individuals that went through 8 tasks. Thank you so much if you can help me, the most hopeless person what it comes to statistics...
@protankatto,
If I understand your question, you are trying to test whether the process of learning tasks makes the individuals better at learning tasks. The independent variable is the number of tasks learned. The dependent variable is the number of trials required to learn a given task. You should be able to do this by plotting the dependent variable against the independent variable, fitting a line to the data and looking at the t variable. It would be best if all individuals performed all the tests, but you should be able to add individual as a new independent variable and run an ANOVA.
Stumble It!
Tweet This
Bookmark on Delicious
Share on Facebook
Share on MySpace