IA Type II -- G-Force Tolerance

[dropdeadgorgeous]

Hi I am currently working on this portfolio and need a little help, any kind of pointers will be appreciated. Specifically i need help finding a function. i graphed the points and want to use the general equation for a power function, what do i plug in though? for a, x, or b?

BTW is the function exponential?

[dessskris]

Hi I am currently working on this portfolio and need a little help, any kind of pointers will be appreciated. Specifically i need help finding a function. i graphed the points and want to use the general equation for a power function, what do i plug in though? for a, x, or b?

BTW is the function exponential?

Actually, I personally suggest a logarithmic function.

You first need to say that you are going to model a logarithmic function. Mention the general function, y=a+b*ln(x)

Then do some calculations to find the values of a and b.

After you get the function, plot it and comment on how well it fits the data, then use a graphing software to find a power function. Briefly describe what to do in the graphing software and put a screenshot of that software showing the power equation.

However if you still want to model a power function, the general formula would be y=a^bx+c+d

Then substitute 4 sets of values of x and y (which actually are t and G respectively) and solve for a, b, c and d

Further questions are welcomed

[mishu =D]

How did you guys get to the equation...?

I just plotted it into Excel and grabbed the exponential function.

Can someone explain to me why it isn't Power but it is Exponential?

Power seems to fit even better too.

And how would you derive that equation by hand...

I also noticed someone talking about R-squared value... what is that?

That is something that I am very confused with as well.

What is the difference between a Power function and an Exponential function?

Hey do you know something about the R-squared value?

I don not undrestand it..

[dessskris]

How did you guys get to the equation...?

I just plotted it into Excel and grabbed the exponential function.

Can someone explain to me why it isn't Power but it is Exponential?

Power seems to fit even better too.

And how would you derive that equation by hand...

I also noticed someone talking about R-squared value... what is that?

That is something that I am very confused with as well.

What is the difference between a Power function and an Exponential function?

Hey do you know something about the R-squared value?

I don not undrestand it..

R-squared value can be generated if you plot the graph in Ms. Excel.

Plot the data in XY scatter graph, add trendline, tick display R-squared value. The closer it is to 1, the more accurate your data is.

[spontaneouslyme]

Hi I'm doing this assignment too and I need help in answering two questions.

The first is "Discuss the implications of your model in terms of G-forces acting on a human being"

Does this mean I base my answers from just the graph or can I use the equation and substitute for other values? and do I just say how as time went on the force decreased or something?

and the second is "Discuss any limitations to your model and the implications of your model in terms of G-forces acting on a human being"

What does limitation mean in this assignment?

Any tips/help will be greatly appreciated!

Also would it possible to find the R values with equations solve by hand?

Edited January 23, 2011 by spontaneouslyme

[dessskris]

Hi I'm doing this assignment too and I need help in answering two questions.

The first is "Discuss the implications of your model in terms of G-forces acting on a human being"

Does this mean I base my answers from just the graph or can I use the equation and substitute for other values? and do I just say how as time went on the force decreased or something?

and the second is "Discuss any limitations to your model and the implications of your model in terms of G-forces acting on a human being"

What does limitation mean in this assignment?

Any tips/help will be greatly appreciated!

Also would it possible to find the R values with equations solve by hand?

I am not doing this task but I suppose I could help a little..

"Discuss the implications of your model in terms of G-forces acting on a human being"

You need to compare your model function and the original data right? Then I guess this asks you to describe the graph but in terms of the G-force acting on human beings. So maybe if the G-force is greater, human beings can tolerate it for a shorter time or something like that.

Limitation is like things that limit the values of G-force and time maybe. Maybe they can't be zero? Can't be a negative value? Or maybe they must be integers? Can they be complex numbers? And so on and so forth..

[iber2011]

Hi I am currently working on this portfolio and need a little help, any kind of pointers will be appreciated. Specifically i need help finding a function. i graphed the points and want to use the general equation for a power function, what do i plug in though? for a, x, or b?

BTW is the function exponential?

Actually, I personally suggest a logarithmic function.

You first need to say that you are going to model a logarithmic function. Mention the general function, y=a+b*ln(x)

Then do some calculations to find the values of a and b.

After you get the function, plot it and comment on how well it fits the data, then use a graphing software to find a power function. Briefly describe what to do in the graphing software and put a screenshot of that software showing the power equation.

However if you still want to model a power function, the general formula would be y=a^bx+c+d

Then substitute 4 sets of values of x and y (which actually are t and G respectively) and solve for a, b, c and d

Further questions are welcomed

hey thanks but what do you substitute in a and b?

[dessskris]

Actually, I personally suggest a logarithmic function.

You first need to say that you are going to model a logarithmic function. Mention the general function, y=a+b*ln(x)

Then do some calculations to find the values of a and b.

hey thanks but what do you substitute in a and b?

No you substitute x and y and then you will get 2 equations in terms of a and b and then you solve for a and b

[iber2011]

simultaneously ??

[dessskris]

simultaneously ??

Yes

[Diana!]

How much discussion do you think I should include for each graph? I haven't written very much but I feel like I have already covered everything. This portfolio seems a lot shorter than the Type 1 we did a few months ago so I'm not sure as to what a reasonable word count should be... Does anyone have any ideas?

[chocolatepear]

The power function should be the best model - check using excel, it fits better.

How would you find the linear regression of a power or exponential function manually?

[theloserwins]

I'd say...

go for power regression for your first part

then on a new set of axis, use log/ln to compare them.

[dessskris]

How much discussion do you think I should include for each graph? I haven't written very much but I feel like I have already covered everything. This portfolio seems a lot shorter than the Type 1 we did a few months ago so I'm not sure as to what a reasonable word count should be... Does anyone have any ideas?

It's not so important how many words/pages you have. The thing is whether you have put enough explanation or not. Explain anything you could explain and show all working and calculations.

---

The power function should be the best model - check using excel, it fits better.

How would you find the linear regression of a power or exponential function manually?

Get the general function first, for example y=a+b^cx then to solve for a, b and c, you need to substitute 3 sets of values of x and y and then solve the system using substitution and elimination.

[`Aii]

I've read through alot of the posts here, but i'm still confused.

First to clarify, what are constraints? I understand what parameters and variables are. ( :

And I saw in a post, that the general equation for the power is : y=a+b*ln(x)

? So it's y = A + B multiplied by x? ?

I'm a bit confused.. I'm the worst at math, totally clueless, sigh.

So just wondering, the first step i would do , is to graph the given information on Excel, but then what? I understand its a scatter graph, but what am i 'looking' for? And is exponential regression still part of the power equation ?I'm very confused, please give me insight. ) : Thank you very much.

edit: also, i dont understand this 'R'value? what is its importance in determining the equation, etc? Is there any specific trend rather than it continues to approach zero?

Edited January 28, 2011 by `Aii

[coollog]

Yeah, right after I typed that I was like "OH WAIT.." and figured it out; however, I was approached today by a few people and was a bit puzzled -- should g-force be the dependent or independent variable? I was trying to think of it logically, because instinctively I made time my independent variable. However, after thinking it over, I began to rationalize "Time is calculated FROM g-force," meaning, to obtain the time, you must see how long the person can undergo g-force value 40 (for argument's sake). Using that logic, g-force would be the independent variable, and that would make sense.

Let me know, maybe I'm thinking too deep into it =)

I see the logic of that, and have considered it...however my Physics teacher last year beat into our heads "TIME GOES ON THE X AXIS, NO MATTER WHAT" so that's what I based my selection on. I don't know if there are applications where this is not so...but I sure do remember the 50% on the lab my group failed because we thought time could be the dependent variable.....there's an argument for either side, I don't know the "official" verdict on whether it is permissible....do what you've been taught and go with your instinct....

No offense to your Physics teacher or anything, but he clearly does not know what he's talking about. The variables that go on the x and y axes correspondingly only correlate with the nature of the variable, whether it is independent or dependent, respectively. Time never HAS to be the independent variable. And for this IA, time isn't, because you are changing the +Gx and +Gz in order to find the time of tolerance in order to model a effect of different G-forces on the time of tolerance.

And to alleviate all the confusion, at least for the +Gx vs. Time data set, the relationship is a power regression. Why? If you plot out the points, you clearly create a relationship that looks like an inverse function. That's y = k / x, which is simply, in other words, or rather notation, y = kx^-1. What is a power regression? It's simply y = ax^b, or y = kx^b. The inverse function is simply a type of power regression, with the exponent being negative. Therefore, the power regression that fits this set of data should look like y = kx^-b. Find a power regression for the data set and your coefficient of determination should be about 99%.

[prashant]

I used a power function to fit the data because the relationship is stronger and is a better representation of the data. (r-value closest to -1)

Does anyone know how to do a good analysis of a graph? we do it in class sometimes and my teacher always marks mine as "Weak"

Does anyone know how to derive the equation for the horizontal G-force? I was absent while learning this last year, and i have no idea how to play around with base functions and change them to fit the graph :|

can't you just take a few random points from the data and plug them into the equation?

I heard that there are two points where it's easier to do so. Anyone figure out what those points are?

Edit: Found it. It helps if you keep Time as x and +Gx as y. Then use the point 1,11 for simultaneous equations.

hey there, i m doing the same IA but can you explain the simultaneous method in detail from the beginning. it would be very helpful. =)

Edited January 29, 2011 by Austin Glau
no text speak

[dessskris]

I've read through alot of the posts here, but i'm still confused.

First to clarify, what are constraints? I understand what parameters and variables are. ( :

And I saw in a post, that the general equation for the power is : y=a+b*ln(x)

? So it's y = A + B multiplied by x? ?

I'm a bit confused.. I'm the worst at math, totally clueless, sigh.

So just wondering, the first step i would do , is to graph the given information on Excel, but then what? I understand its a scatter graph, but what am i 'looking' for? And is exponential regression still part of the power equation ?I'm very confused, please give me insight. ) : Thank you very much.

edit: also, i dont understand this 'R'value? what is its importance in determining the equation, etc? Is there any specific trend rather than it continues to approach zero?

First to clarify, what are constraints?

TBH idk what constraints are. Google it.

And I saw in a post, that the general equation for the power is : y=a+b*ln(x)

? So it's y = A + B multiplied by x? ?

What?? A power equation is y= a + b*c^dx or something along those lines.

But y = a + b*ln(x) is a logarithmic function and it means a plus (b times ln(x))

the first step i would do , is to graph the given information on Excel, but then what? I understand its a scatter graph, but what am i 'looking' for?

I suggest using a program other than Excel. Use TI-Nspire if you have one. You first put a table of the data given from the task. Then plot it in a graphing software but don't show any best fit function yet. Model your own function analytically and then plot it together with the data series. Compare them.

And is exponential regression still part of the power equation ?

No they are completely different.

i dont understand this 'R'value? what is its importance in determining the equation, etc?

R-squared value suggests how accurate your data points are. The more accurate they are, the closer its value is to 1. If you have for example 7 data points and 1 of them is a bit off, you R-squared value might be even lower than 0.9 but if your data points fit the curve well, it should be somewhere between 0.9700-1 because it's quite accurate.

Is there any specific trend rather than it continues to approach zero?

Other than that? I am not so sure but can your variables be positive? can they be negative? etc

---

Yeah, right after I typed that I was like "OH WAIT.." and figured it out; however, I was approached today by a few people and was a bit puzzled -- should g-force be the dependent or independent variable? I was trying to think of it logically, because instinctively I made time my independent variable. However, after thinking it over, I began to rationalize "Time is calculated FROM g-force," meaning, to obtain the time, you must see how long the person can undergo g-force value 40 (for argument's sake). Using that logic, g-force would be the independent variable, and that would make sense.

Let me know, maybe I'm thinking too deep into it =)

I see the logic of that, and have considered it...however my Physics teacher last year beat into our heads "TIME GOES ON THE X AXIS, NO MATTER WHAT" so that's what I based my selection on. I don't know if there are applications where this is not so...but I sure do remember the 50% on the lab my group failed because we thought time could be the dependent variable.....there's an argument for either side, I don't know the "official" verdict on whether it is permissible....do what you've been taught and go with your instinct....

No offense to your Physics teacher or anything, but he clearly does not know what he's talking about. The variables that go on the x and y axes correspondingly only correlate with the nature of the variable, whether it is independent or dependent, respectively. Time never HAS to be the independent variable. And for this IA, time isn't, because you are changing the +Gx and +Gz in order to find the time of tolerance in order to model a effect of different G-forces on the time of tolerance.

And to alleviate all the confusion, at least for the +Gx vs. Time data set, the relationship is a power regression. Why? If you plot out the points, you clearly create a relationship that looks like an inverse function. That's y = k / x, which is simply, in other words, or rather notation, y = kx^-1. What is a power regression? It's simply y = ax^b, or y = kx^b. The inverse function is simply a type of power regression, with the exponent being negative. Therefore, the power regression that fits this set of data should look like y = kx^-b. Find a power regression for the data set and your coefficient of determination should be about 99%.

Sorry but I still think that time can possibly go in the x-axis. I would say both cases are possible, but if I were to do this task I'd still put time on the x-axis and G on the y-axis.

And I don't understand your other explanation.. A power regression is y=a+b*c^dx or something like that. The thing is that it's a constant to the power of x something, not x something to the power of a constant. Your kx^b is actually polynomial of b^th degree but the coefficients of the other terms are zero.

---

hey there, i m doing the same IA but can u explain the simultaneous method in detail from the beginning. it would be very helpful. =)

I might not be understanding your question correctly but I suppose simultaneous method in this context should be solving equations simultaneously using elimination or substitution or matrices.

[coollog]

Sorry but I still think that time can possibly go in the x-axis. I would say both cases are possible, but if I were to do this task I'd still put time on the x-axis and G on the y-axis.

And I don't understand your other explanation.. A power regression is y=a+b*c^dx or something like that. The thing is that it's a constant to the power of x something, not x something to the power of a constant. Your kx^b is actually polynomial of b^th degree but the coefficients of the other terms are zero.

It is possible to put time on the x-axis if you truly want to, although it makes it more confusing, which is exactly the opposite of a graph's purpose.

A power regression is in the form of y = x^b + c, but you don't really need the c here. The equation you gave, y=a+b*c^dx, is an exponential regression, not a power regression.

[icdiik]

hey did anyone find any constraints and limitations to the model and the implications of it in terms of G-force acting on a human being... basically it is the last question of the portfolio....... i m almost done with eveything else bt stuck with this one...

pls help