Sarthak Garg Posted December 4, 2015 Report Share Posted December 4, 2015 HelloI am currently finishing up my IA for Biology HL. I have 5 conditions one of which is control. Each with 5 trials measured over 4 time periods. With 3 dimensions to my research, I was wondering what statistical tests I should use. I was thinking of doing ANOVA and HOC test to check the difference between the conditions with each trial. 4 times ofcourse due to 4 time periods. Is this a good choice? What else should I use. Can I simply use a online calculator for this test, reference it and give the table that shows the results and then explain what the results tell me for the ANOVA and the HOC test?Some details: I tested the antimicrobial properties of turmeric at different concentration. Measuring radius of influence over 4 time periods.Also, what are the ethical concerns associated with microbials - bacteria? (not safety but ethical because I heard from my teacher that they were very strict about ethical concers even for microbials but i cant seem to think a reason for so)Thank You Reply Link to post Share on other sites More sharing options...
Surutham Posted December 4, 2015 Report Share Posted December 4, 2015 Hello, firstly considering your experiment, I think you should do a t-test to make sure that your values are different due to the factor being measured. I also think you should do standard deviation - pretty sure that is default. As for the ethical considerations - As far as I know, I don't think you require ethical considerations for the microbes. However, my hunch is that you should make sure that you add in that the microbes were not put through any physical harm (i don't think psychological matters here haha). Reply Link to post Share on other sites More sharing options...
batool Posted December 4, 2015 Report Share Posted December 4, 2015 Hello, firstly considering your experiment, I think you should do a t-test to make sure that your values are different due to the factor being measured. I also think you should do standard deviation - pretty sure that is default. As for the ethical considerations - As far as I know, I don't think you require ethical considerations for the microbes. However, my hunch is that you should make sure that you add in that the microbes were not put through any physical harm (i don't think psychological matters here haha). I was having the same problem as Sarthak Garg and I didn't quite understand how to approach t-testing... T-testing should be done between two samples so how many t-tests do I really need to do? I don't understand how a t-test would be applicable in this certain scenario..? 2 Reply Link to post Share on other sites More sharing options...
Sarthak Garg Posted December 4, 2015 Author Report Share Posted December 4, 2015 Hello, firstly considering your experiment, I think you should do a t-test to make sure that your values are different due to the factor being measured. I also think you should do standard deviation - pretty sure that is default. As for the ethical considerations - As far as I know, I don't think you require ethical considerations for the microbes. However, my hunch is that you should make sure that you add in that the microbes were not put through any physical harm (i don't think psychological matters here haha). I was having the same problem as Sarthak Garg and I didn't quite understand how to approach t-testing... T-testing should be done between two samples so how many t-tests do I really need to do? I don't understand how a t-test would be applicable in this certain scenario..? This is also my question, isn't t test for 2 groups so would I need to do 10 X 4 (4 time periods) = 40 t tests? Reply Link to post Share on other sites More sharing options...
batool Posted December 4, 2015 Report Share Posted December 4, 2015 Hello, firstly considering your experiment, I think you should do a t-test to make sure that your values are different due to the factor being measured. I also think you should do standard deviation - pretty sure that is default. As for the ethical considerations - As far as I know, I don't think you require ethical considerations for the microbes. However, my hunch is that you should make sure that you add in that the microbes were not put through any physical harm (i don't think psychological matters here haha). I was having the same problem as Sarthak Garg and I didn't quite understand how to approach t-testing... T-testing should be done between two samples so how many t-tests do I really need to do? I don't understand how a t-test would be applicable in this certain scenario..? This is also my question, isn't t test for 2 groups so would I need to do 10 X 4 (4 time periods) = 40 t tests? Mine is even crazier because I have 17 conditions and 5 trials and 9 different time periods!!! So I really hope that isn't true.... Reply Link to post Share on other sites More sharing options...
batool Posted January 10, 2016 Report Share Posted January 10, 2016 This is just an update for anyone going through statistical analysis hardships! Look into the one-way ANOVA or the two-way ANOVA for your data (they are both extremely useful when it comes to analyzing statistics typically used in IB IA's). Good luck everyone! x 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.