EAS 102 G/H
Midterm Spring 2008
SOLUTIONS
Problem 1.
a.
Fit 1 is the best because it yields the smallest sum of squared error (0.089491<0.09893).
b.
Concerns:
a.
The y data is to the closest 0.05 units.
Is this resolution of measurement?
b.
A lot of spread in the data, same y for different x, what is the cause of all this
variation.
c.
I have no idea what x and y physically represent.
Advantages/disadvantages:
Although Fit 1 is better from the standpoint of error, it is not
much different than Fit 2.
Fit 1 may be good enough and is a simple equation.
It may be
easier to implement a linear equation in analysis than x as an exponent.
If the equation
for fit 1, has some physical or chemical basis it may be better to use that.
c.
What does the data represent?
How was the data collected: what are the limits of the
measurements?
Could more data be collected since there is so much scatter in the
results?
Could the range of x be expanded to better see the trends of the data?
d.
This preview has intentionally blurred sections. Sign up to view the full version.
View Full Document
This is the end of the preview.
Sign up
to
access the rest of the document.
 Spring '09
 Coffin
 a. b. c., e. f. g., maximum allowable length, G/H Midterm Spring

Click to edit the document details