Math Is Fun Forum

  Discussion about math, puzzles, games and fun.   Useful symbols: ÷ × ½ √ ∞ ≠ ≤ ≥ ≈ ⇒ ± ∈ Δ θ ∴ ∑ ∫ • π ƒ -¹ ² ³ °

You are not logged in.

#26 2011-04-06 22:57:01

gAr
Member
Registered: 2011-01-09
Posts: 3,482

Re: Urgent Assignment Help Needed!

Hi,

How about taking exponential of the data you already have and transform that? wink


"Believe nothing, no matter where you read it, or who said it, no matter if I have said it, unless it agrees with your own reason and your own common sense"  - Buddha?

"Data! Data! Data!" he cried impatiently. "I can't make bricks without clay."

Offline

#27 2011-04-06 22:58:42

Alive
Member
Registered: 2010-08-14
Posts: 92

Re: Urgent Assignment Help Needed!

Wait.. select what??

Should I make the y axis the population and the x axis the land area???? and where will I label the country when putting it into my scatter...........................

edit: I need two transformations.

Last edited by Alive (2011-04-06 22:59:45)


All things can be forgiven if we can progress.
Yusuf Islam (formerly known as Cat Stevens)

Offline

#28 2011-04-06 23:37:57

Bob
Administrator
Registered: 2010-06-20
Posts: 10,626

Re: Urgent Assignment Help Needed!

y=pop x = area will do fine.  I don't think it matters.

Oh yes, I'd forgotten you want two transforms.

I'll have a closer look at the data and available transforms.

Back in a tick,

Bob


Children are not defined by school ...........The Fonz
You cannot teach a man anything;  you can only help him find it within himself..........Galileo Galilei
Sometimes I deliberately make mistakes, just to test you!  …………….Bob smile

Offline

#29 2011-04-06 23:45:21

Bob
Administrator
Registered: 2010-06-20
Posts: 10,626

Re: Urgent Assignment Help Needed!

ok.

If you've got data that needs compressing then log is the obvious choice.

But try y versus 1/x first and then log second.  This is the one that is likely to be most useful but if you get a chance to criticise the former choice that should be extra credits.

In the end, choice of statistics is down to what works and what doesn't.

As you are discovering, you don't know until you try it.  That's part of the assignment I think, so do it, and say if it's been useful or not.

If the assignment is 'just' a homework then I'm sure that all you have done meets the targets.  If it is part of an exam assessment it might be wise to check with your teacher at this stage.

Bob


Children are not defined by school ...........The Fonz
You cannot teach a man anything;  you can only help him find it within himself..........Galileo Galilei
Sometimes I deliberately make mistakes, just to test you!  …………….Bob smile

Offline

#30 2011-04-06 23:45:56

Alive
Member
Registered: 2010-08-14
Posts: 92

Re: Urgent Assignment Help Needed!

It will be WONDERFUL if you can bob bundy.

By the way, to get the residual.. for example:
1.4216915 (1965) - 2475.611
= 318
= y data - y pred
= 320 - 318
= 2
Is that the right method????

1.421695 (1966) - 2475.611
= 319.44137
= 321 - 319.4
= 1.6

Is that the way we get the residuals for each of them???

Edit: I might not change my data, just go through with it...

Last edited by Alive (2011-04-06 23:48:00)


All things can be forgiven if we can progress.
Yusuf Islam (formerly known as Cat Stevens)

Offline

#31 2011-04-06 23:55:05

Bob
Administrator
Registered: 2010-06-20
Posts: 10,626

Re: Urgent Assignment Help Needed!

It will be WONDERFUL if you can bob bundy.

Sorry I've lost track on this thread.

What would be wonderful?

dunno

Bob


Children are not defined by school ...........The Fonz
You cannot teach a man anything;  you can only help him find it within himself..........Galileo Galilei
Sometimes I deliberately make mistakes, just to test you!  …………….Bob smile

Offline

#32 2011-04-06 23:55:44

Alive
Member
Registered: 2010-08-14
Posts: 92

Re: Urgent Assignment Help Needed!

Don't worry lol, I thought you were going to find the data that can be transformed exactly but that's going to take long. Could you help me with the residuals part?


All things can be forgiven if we can progress.
Yusuf Islam (formerly known as Cat Stevens)

Offline

#33 2011-04-07 00:16:00

Alive
Member
Registered: 2010-08-14
Posts: 92

Re: Urgent Assignment Help Needed!

Thanks for the help guys but for goodness sakes could you just help me with the residuals, thanks!


All things can be forgiven if we can progress.
Yusuf Islam (formerly known as Cat Stevens)

Offline

#34 2011-04-07 00:26:34

bobbym
bumpkin
From: Bumpkinland
Registered: 2009-04-12
Posts: 109,606

Re: Urgent Assignment Help Needed!

Hi Alive;

I already explained to you the residuals, you should remember.

It is the difference between the data value of y and the computed value of y.

Also you did it right 4 posts up.


Here is a contrived problem perfect for school work.

Raw data

When you transform the data with y = ln(y) you get this:

The graph on left shows how the data was linearized. You can use linear regression on it. The right graph is the raw data. It will not have a good linear fit. You can see it is not a straight line.


In mathematics, you don't understand things. You just get used to them.
If it ain't broke, fix it until it is.
Always satisfy the Prime Directive of getting the right answer above all else.

Offline

#35 2011-04-07 00:51:06

Bob
Administrator
Registered: 2010-06-20
Posts: 10,626

Re: Urgent Assignment Help Needed!

hi Alive, hi bobbym,

Here's my calcs for the residuals

I'm signing out on this thread now.  My vacuum cleaner has just blown up (real sparks!) so I've got to get it sorted.  wave

Bob


Children are not defined by school ...........The Fonz
You cannot teach a man anything;  you can only help him find it within himself..........Galileo Galilei
Sometimes I deliberately make mistakes, just to test you!  …………….Bob smile

Offline

#36 2011-04-07 00:53:30

bobbym
bumpkin
From: Bumpkinland
Registered: 2009-04-12
Posts: 109,606

Re: Urgent Assignment Help Needed!

Hi Bob;

Get it sorted it out. See you tomorrow or later if you are not incinerated.


In mathematics, you don't understand things. You just get used to them.
If it ain't broke, fix it until it is.
Always satisfy the Prime Directive of getting the right answer above all else.

Offline

#37 2011-04-07 02:54:05

Bob
Administrator
Registered: 2010-06-20
Posts: 10,626

Re: Urgent Assignment Help Needed!

hi bobbym,

Still in the land of the living.  Had to pay out for a new machine as the old one was definitely and fatally beyond hope.  It's in the garden cooling down and letting the bad smell of burning dissipate.  New one is great.  Almost makes vacuuming the house into a pleasure!

smile

Bob


Children are not defined by school ...........The Fonz
You cannot teach a man anything;  you can only help him find it within himself..........Galileo Galilei
Sometimes I deliberately make mistakes, just to test you!  …………….Bob smile

Offline

#38 2011-04-07 03:47:09

Alive
Member
Registered: 2010-08-14
Posts: 92

Re: Urgent Assignment Help Needed!

Thanks a bunch guys! There's only one question I couldn't do. 2(Regression)c) Does it just want how much linear it is? Should I just say that it has a strong positive linear relationship? Thanks.


All things can be forgiven if we can progress.
Yusuf Islam (formerly known as Cat Stevens)

Offline

#39 2011-04-07 06:36:55

bobbym
bumpkin
From: Bumpkinland
Registered: 2009-04-12
Posts: 109,606

Re: Urgent Assignment Help Needed!

Which regression are you talking about? Your CO2 data? That is strongly correlated. It has a correlation of over .99. This means that y is almost fully explained by x.

Hi Bob;

That happens with a new machine. Using it the first few times is a sheer joy. That quickly wears off.


In mathematics, you don't understand things. You just get used to them.
If it ain't broke, fix it until it is.
Always satisfy the Prime Directive of getting the right answer above all else.

Offline

Board footer

Powered by FluxBB