Dotti22 Posted July 15, 2017 Report Share Posted July 15, 2017 (edited) Hi Everyone, So I had the idea for my maths IA to model my sleep cycle (an example is shown in the picture) to determine the average length of my individual cycle & try and determine the best points to wake/sleep. Any feedback/expansions on the topic would be greatly appreciated! Thanks in advance! Edited July 15, 2017 by Dotti22 Reply Link to post Share on other sites More sharing options...
kw0573 Posted July 15, 2017 Report Share Posted July 15, 2017 You should quantify the vertical axis. Also give units on both axes. Reply Link to post Share on other sites More sharing options...
Dotti22 Posted July 15, 2017 Author Report Share Posted July 15, 2017 (edited) 5 hours ago, kw0573 said: You should quantify the vertical axis. Also give units on both axes. Yep I definitely will do that Do you have an possible expansions on this topic as first I am going to try and model it just by eye, then try to find a curve of best fit. Then I can determine the time periods where the lightest sleep occurs & therefore the best times to wake up. But I feel like I need some more maths involved, so any suggestions would be greatly appreciated Edited July 15, 2017 by Dotti22 Reply Link to post Share on other sites More sharing options...
kw0573 Posted July 15, 2017 Report Share Posted July 15, 2017 Often it's better if you explain the formula/concept behind linear regression (or other best fit techniques) rather than just applying them. I think if you do that and quantify effectively then there should be enough math. Examiners also suggest that people explain graphs and any trends observed rather than just include a graph for no reason and not talk about it. Reply Link to post Share on other sites More sharing options...
Dotti22 Posted July 15, 2017 Author Report Share Posted July 15, 2017 (edited) Okay thank you! Just to clarify quickly, what do you mean by "quantify effectively" Edited July 15, 2017 by Dotti22 Reply Link to post Share on other sites More sharing options...
kw0573 Posted July 15, 2017 Report Share Posted July 15, 2017 Now I don't have a solution in mind, but if you assign discrete values of awake = 0, sleep = 1, deep sleep = 2, then for something like 1.5, it becomes completely meaningless. An effective way to quantify the vertical axis is allow meaningful numbers on a continuous scale. Reply Link to post Share on other sites More sharing options...
Dotti22 Posted July 15, 2017 Author Report Share Posted July 15, 2017 1 minute ago, kw0573 said: Now I don't have a solution in mind, but if you assign discrete values of awake = 0, sleep = 1, deep sleep = 2, then for something like 1.5, it becomes completely meaningless. An effective way to quantify the vertical axis is allow meaningful numbers on a continuous scale. Okay, I get where you are coming from, but I am a bit confused on how to make the numbers "meaningful". Do you mean doing something like sleep is from 1 < x < 2? Thanks Reply Link to post Share on other sites More sharing options...
kw0573 Posted July 15, 2017 Report Share Posted July 15, 2017 Just now, Dotti22 said: Okay, I get where you are coming from, but I am a bit confused on how to make the numbers "meaningful". Do you mean doing something like sleep is from 1 < x < 2? Thanks I mean that the vertical axis should take values from a continuous scale, not specific values of 0, 1, or 2. And every point plotted should have some physical meaning regards to level of sleep. This is a key component of your IA and I leave you to figure out the details. 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.