Jump to content

Type II - Fish Production


Noxen

Recommended Posts

you can't simply plot the data points to get the best fit regression, because there isn't any actually. split the data into probably 3 parts and use a combination of functions.

I'd put years on the x axis and mass on the y axis.

What do you mean by split the data into 3 parts?

Is that that some years works with some function an some other with another function, etc. ?

Furthermore does "combinations of functions" (from the assignment) mean composite functions or as you said actually some different functions? :o

Link to post
Share on other sites

  • 2 weeks later...
  • 2 weeks later...

Ok, I have a question. Do you have to split it into three tables to get overall equation or can you just take the three tables and combine them into one to get the model? Also, what does it mean by defining suitable variables. What are the general parameter/constraints? And, do we graph the whole thing or each individual table?

Thanks for helping. I know it is a little demanding but help me if you can please! :hang:

Link to post
Share on other sites

  • 3 weeks later...

So I get that we should split the data into three parts. But one of the prompts on the task sheet asks us to compare models and basically, draw the model again in one full graph. How do I then combine those three models? Will they just look like three disjointed lines on one graph?

Link to post
Share on other sites

  • 3 weeks later...

Has anyone figured out a model for the third table for the first part? And can anyone explain the last part about the fish farms. Am I suppose to do combination of functions again? And what trends do I look for?

for the sea: i didnt divide the function into 3 different sections, i just used a damping sine wave for the entire thing

for the farms: I think that it is a cubic function, but am i not sure, because of the fluctuation towards the end, anybody else have an idea?

Link to post
Share on other sites

I ended up figuring out how to do it. Turns out it is not as hard as I thought it to be. Making a model can be as easy as modifying some of the parameters of a regression function smile.gif. Also, I am going to post the task paper below for anyone who is interested.

Thanks for all your help,

-Noxen

How do you do it? I plugged in the sine regression equation that I recieved from my calculator into excel and all I got were negative numbers. Could you explain your proccess of how you figured it out please?

Link to post
Share on other sites

I can't seem to find a program that can graph the tan curve. Can anyone point me in the right direction?

There are a lot of good graphing softwares. The easiest would be just to use your calculator.

You could also use GeoGebra (I love it!!), AutoGraph or LoggerPro. If you need any help with GeoGebra, feel free to PM me.

Link to post
Share on other sites

Ok, I've read the whole topic and I'm still much confused. I want to divide the first data into three, so having three functions. So I'm trying to 'guess' which type of functions will bu useful here (plus I tried the ideas of people here). So starting with the first one from 1980 to 1988 and there are two ideas, my classmate proposed a linear and that is what I found also somewhere when googling the task and here there are people saying it is cubic. So I tried a trend estimation

1) for linear http://scr.hu/0hj9/xok06

2) for cubic http://scr.hu/0hj9/0x5k7

And my question is - how any of this would be correct if only a few points lie on the line? I'm confused, but I guess this is due to my lack of some knowledge as I read through a full task, and a guy drew a line which was not at all perfectly going through all the points and still it is summarized by "as we can see, the line fits the graph perfectly".

Any hints, please?

(Is it possible to do this task without trigonometry?)

Edited by lilianna009
Link to post
Share on other sites

Can anyone please help define the domain and range for the first set of data points? I don't know what number set to use, and is it discrete, or continuous...? Also, what is the best model for the last graph for part 1? And also I don't understand how trends from the second model can be used to explain the trends in the first model. Can anyone please help?

Edited by dish_network123
Link to post
Share on other sites

And also I don't understand how trends from the second model can be used to explain the trends in the first model. Can anyone please help?

Draw the two models on the same set of axis and try to notice any relationship maybe, one increases, the other decreases?

But I don't know, I'm still stuck at the very beginning as I mentioned :(.

Link to post
Share on other sites

The hardest part in this portfolio is doing polynomial regression by hand. Our class was never taught how to do this, and trying to teach myself such a hard concept is not going too well.

If only we were allowed to use the calculator for this. But they ask for analytical approaches, meaning no use of technology...

Link to post
Share on other sites

  • 1 month later...

Ok, I've read the whole topic and I'm still much confused. I want to divide the first data into three, so having three functions. So I'm trying to 'guess' which type of functions will bu useful here (plus I tried the ideas of people here). So starting with the first one from 1980 to 1988 and there are two ideas, my classmate proposed a linear and that is what I found also somewhere when googling the task and here there are people saying it is cubic. So I tried a trend estimation

1) for linear http://scr.hu/0hj9/xok06

2) for cubic http://scr.hu/0hj9/0x5k7

And my question is - how any of this would be correct if only a few points lie on the line? I'm confused, but I guess this is due to my lack of some knowledge as I read through a full task, and a guy drew a line which was not at all perfectly going through all the points and still it is summarized by "as we can see, the line fits the graph perfectly".

Any hints, please?

(Is it possible to do this task without trigonometry?)

MAJOR NO NO, NEVER DO LINEAR. I did that for my Type 2 - Gold Medals Height and that basically made me a lord of marks. (come on, this shouldn't be spoiling... I classify this as common knowledge)

I honestly doubt you will respond because you're probably done but for those looking at this thread last minute like me haha. I'm doing another Math Portfolio so that explains why I'm doing this again.

Use concepts learned from Grade 11 and 12, never use anything simplistic as linear.

Also you're trying to find a model for your graph, if your model is close to your data points then you can basically say its a good match. Your model does not have to be perfect, it just has to be close and/or hit your data points if its going to be valid. By then you could say there is a relationship or what that guy said is that the line fits perfectly.

Also, how does trigonometry help make a model? I can only think of trigonometry for the Type 1 - Circles IA, not for this.

Edit -

I don't want to double post so I'm posting extra of my own opinion on this thread.

Thank you people for helping me generate ideas for this IA. :D I'm pretty sure I'm on the right track. Also, anyone else doing this last minute?

Edited by RedTopHats
Link to post
Share on other sites

Join the conversation

You can post now and register later. If you have an account, sign in now to post with your account.

Guest
Reply to this topic...

×   Pasted as rich text.   Paste as plain text instead

  Only 75 emoji are allowed.

×   Your link has been automatically embedded.   Display as a link instead

×   Your previous content has been restored.   Clear editor

×   You cannot paste images directly. Upload or insert images from URL.

×
×
  • Create New...