Jump to content
Sign in to follow this  

Which tests should I apply to my data?

Recommended Posts

Hi!

 

Im doing my EE in Chemistry (HL student), with the following RQ: "How is the degree of unsaturation in fatty acids affected by exposure to high temperatures?" (Degree of unsaturation is Iodine Value) 

 

I have gathered data from 9 titrations (3 with peanut oil, 3 with olive oil, 3 blank tests), all 6 oil-samples had been exposed to ca. 300+ degrees celsius for 10minutes prior to determining the IV by Hanus' Method. This data will be measured against the secondary-data values of the exact same oils.

 

 

What tests can I do with this data, and show graphically? Chi-squared test? T-test? Pearson correlation coefficient? 

 

Any and all other tips will be appreciated as well, regarding the structure, references, citation, secondary lit. etc!

 

Sincerely,

a kind of desperate Norwegian IB-student -Panzer

 

Share this post


Link to post
Share on other sites
Guest Sonia

You could do normal scatter graphs with trend line or any graphical representation like that, maybe a graph with all the different values you got for each temperature interval so that you compare them. Statistically, you can pretty much do any statistics test to check for the significance of your results. According to your post, I'm thinking that maybe ANOVA would be a suitable test - it tests if the different 'sets' of results are indeed different or not. If this would turn out that they are not different, it means temperature has no effect (so null hypothesis is supported). But tbh I think you could do any statistical test you're comfortable with, cause in the end they pretty much tell you the same thing :)

Share this post


Link to post
Share on other sites

Might I suggest that you speak to your extended essay supervisor?

 

Of course that would be ideal. However, my supervisor has a jam-packed schedule with little to no time to spare, I've had a meeting with her just recently and she needs to prioritize the other students as well. She's very knowledgeable and a good teacher, but not the best supervisor. 

 

 

You could do normal scatter graphs with trend line or any graphical representation like that, maybe a graph with all the different values you got for each temperature interval so that you compare them. Statistically, you can pretty much do any statistics test to check for the significance of your results. According to your post, I'm thinking that maybe ANOVA would be a suitable test - it tests if the different 'sets' of results are indeed different or not. If this would turn out that they are not different, it means temperature has no effect (so null hypothesis is supported). But tbh I think you could do any statistical test you're comfortable with, cause in the end they pretty much tell you the same thing :)

 

Thanks! I'll do some research on ANOVA. You seem pretty experienced with graphical representations, what kind of software do you use?

Share this post


Link to post
Share on other sites
Guest Sonia

Thank youu! :) For my EE I did all graphs and t-tests on excel. I only had to use ANOVA once so far, which I did on an online Anova website that pretty much does it for you :P

Edited by supersonic

Share this post


Link to post
Share on other sites

Thank youu! :) For my EE I did all graphs and t-tests on excel. I only had to use ANOVA once so far, which I did on an online Anova website that pretty much does it for you :P

 

I've found several sites like that. Were you happy with the end-result? If you were; I wouldn't mind if you sent me the link in a PM :P

Share this post


Link to post
Share on other sites

Create an account or sign in to comment

You need to be a member in order to leave a comment

Create an account

Sign up for a new account in our community. It's easy!

Register a new account

Sign in

Already have an account? Sign in here.

Sign In Now
Sign in to follow this  

×

Important Information

We have placed cookies on your device to help make this website better. You can adjust your cookie settings, otherwise we'll assume you're okay to continue.