4/16/2020
CURVE FITTING
Muhammad Atique ur Rehman
Assistant Professor
YIPS
Biostatistics
Fitting of Parabola
What is Parabola?
It a set of all points in a plane that are equidistant from a
fixed line (Directrix) and a fixed point (Focus) in the plane.
1
4/16/2020
Fitting of Parabola
Problem: We will be provided with data table of two
variables and we have to find a relation of degree 2 that best
fits the given data.
We will perform the following steps in order to obtain the
required relation.
Step-I: Let the equation of
Parabola.
Fitting of Parabola…
Step-II: Write the normal equations:-
2
4/16/2020
Fitting of Parabola…
Where : n = Number of data values
Step-III: Find the values of all above sums in the same way as in
the previous section.
Step-IV: Substitute all the above calculated values in normal
equations.
Step-V:We will have now two equations in two unknowns ‘a’ and
‘b’. We will solve these equations to find the values of ‘a’ and ‘b’.
Step-VI: Substitute the values of ‘a’ and ‘b’ in equation in step-I
to have the required equation of straight line that fits the curve
best and can also predict about the unknown values.
For Higher Degree Curve
One can use the following relation for finding the normal
equations for higher order curves.
Where : A is the constant arising with respect to the term
and degree of the curve to be fitted.
nd
For 2 degree we have seen that we require three normal
equations and in the same way we will remember that the
number of normal equations will be one more than the
degree of the curve.
3
4/16/2020
For Higher Degree Curve…
The rest of the required equation in a short way can also be
found by simply replacing ‘n’ and multiplying the both sides
by .
Assignment
Q.1. Find a second degree curve that best fits the following data.
x 1 2 3 4
y 6 11 18 27
Q.2. Fit the a second degree parabola to the following data taking x
as the independent variable.
x 1 2 3 4 5 6 7 8 9
y 2 6 7 8 10 11 11 10 9
Q.3. Fit the second degree parabola to the following data.
x 1929 1930 1931 1932 1933 1934 1935 1936 1937
y 352 356 357 358 360 361 361 360 359