Scribd
Upload
38 views3 pages

Least Square Exponential Fit

The document describes an experiment where an object was dropped from varying heights and its distance over time was recorded. It then uses this data to calculate the gravitational constant g through two different curve fitting methods: 1) A power fit analysis that models distance as a function of time squared and calculates g as 9.8146 m/s2. 2) An exponential fit analysis that first linearizes the data by taking the natural log before determining the best fit line and calculating constants A, B, and C that characterize the exponential relationship between distance and time.

Uploaded by

Professor Saad
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
38 views3 pages

Least Square Exponential Fit

The document describes an experiment where an object was dropped from varying heights and its distance over time was recorded. It then uses this data to calculate the gravitational constant g through two different curve fitting methods: 1) A power fit analysis that models distance as a function of time squared and calculates g as 9.8146 m/s2. 2) An exponential fit analysis that first linearizes the data by taking the natural log before determining the best fit line and calculating constants A, B, and C that characterize the exponential relationship between distance and time.

Uploaded by

Professor Saad
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 3

Example:

During an experiment of dropping an object vertically downwards, if 𝑑 is the


distance covered in meters in 𝑡 seconds, the data {(𝑡 , 𝑑 )} is obtained as

(0.2,0.1960), (0.4,0.7850), (0.6,1.7665), (0.8, 3.1405) and (1, 4.9075)

Ignoring the air friction and the gravitational constant 𝑔 in the relation

1
𝑑 = 𝑔𝑡
2

can be calculated by approximating the given data by Power Fit

𝑑 = 𝐴𝑡 .

Following is the table used to find the sums for calculating 𝐴 of the Power Fit.

𝑡 𝑑 𝑑 𝑡 𝑡

0.2 0.1960 0.00784 0.0016

0.4 0.7850 0.12560 0.0256

0.6 1.7665 0.63594 0.1296

0.8 3.1405 2.00992 0.4096

1 4.9075 4.90750 1.0000

Sum=7.68680 Sum=1.5664

It may be noted that 𝑀 = 2 for the Power Fit 𝑑 = 𝐴𝑡 .


Putting the values of summations in the following relation for calculating A:
∑ 𝑡 𝑑
𝐴= = 4.9073
(∑ 𝑡 )

Comparing the Power Fit 𝑑 = 𝐴𝑡 with 𝑑 = 𝑔𝑡 , we get 𝑔 = 9.8146𝑚/𝑠𝑒𝑐 .

Exponential Fit (𝒚 = 𝑪𝒆𝑨𝒙 ):

Consider the data {(𝑥 , 𝑦 )} which is to be approximated by the following


exponential fit

𝑦 = 𝐶𝑒 (1)
To determine the best exponential fit, instead of minimizing the root-mean-
squares error, data linearization method is developed.

Data Linearization Method:


Since the exponential fit is required when the nature of data seems to be
exponentially shooting. Firstly, the data is transformed to be linearized as under.
The exponential fit (1) can be rewritten as:
ln(𝑦) = ln( 𝐶𝑒 )
or
ln(𝑦) = 𝐴𝑥 + ln (𝐶)
Comparing this equation with
𝑌 = 𝐴𝑋 + 𝐵 (2)
So, the linearization of data can be defined as
𝑌 = ln(𝑦) , 𝑋 = 𝑥, where 𝐵 = ln (𝐶)
The process of transforming the given data (𝑥 , 𝑦 ) to (𝑋 , 𝑌 ) is called the data
linearization.
To determine the best linear fit (2) for the transformed data (𝑋 , 𝑌 ), the
corresponding normal equations can be written as
𝑋 𝐴+ 𝑋 𝐵= 𝑋 𝑌

𝑋 𝐴 + 𝑁𝐵 = 𝑌

The above equation obviously provides the values of 𝐴 & 𝐵. Consequently 𝐶


can be evaluated as
𝐶=𝑒

You might also like