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.

#1 2012-04-29 19:18:54

tina123
Member
Registered: 2012-04-29
Posts: 83

Regression line problem

Hello guys,

    A regression is a statistical analysis assessing the association between two variables. It is used to find the relationship between two variables.

This is given data set

X Values    Y Values
60              3.1
61              3.6
62              3.8
63              4
65              4.1

This is regression eq of x = 64

            Regression Equation(y) = a + bx
            = -8.098 + 0.19(64).
            = -8.098 + 12.16
            = 4.06

y = 4.06 for x = 64 . What does it meant ?
How is it saying that data is strongly related or different ?
Can some one please explain this .
Thanks

Offline

#2 2012-04-29 20:39:42

Bob
Administrator
Registered: 2010-06-20
Posts: 10,058

Re: Regression line problem

hi tina123

When you have x and y data, the regression line calculation tells you how you can estimate y given x.

It does not tell you how reliable that estimate might be.

To say that, you need to calculate the correlation coefficient from the x and y pairs.

the calculation is similar to the line calculation and will give a number between -1 and + 1.


coefficient = r = 0 would mean there is no relationship whatsoever.

In this case you would still be able to calculate the regression line, but it would be meaningless.

If r = 1, the correlation is perfect and the line would tell you a new y exactly from an x.

More if you want to post back.

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

#3 2012-04-29 21:02:27

Bob
Administrator
Registered: 2010-06-20
Posts: 10,058

Re: Regression line problem

hi again,

I have used Excel to calculate the line and I get

y =  -7.96351  + 0.18783x

This makes y = 4.0581

The correlation coefficient is r = 0.91187 which is very high, so you may safely conclude that the y estimate is good.

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

Board footer

Powered by FluxBB