Lecture 1312014.pdf

2 Pages
Unlock Document

University of Minnesota Twin Cities
CHEM 2121
Nicholas Frost

Lecture 1312014Friday January 31 20141221 PMComparing Data SetsFirst find mean and standard deviations of both data setsThen do F testThen do corresponding t test to see if data is actually significantGrubbs Testreplaces q test did in AP chemdeciding if need to remove outlier a point that really doesnt describe data setex xbar01046M s00010M43G 01029 M 01046M00010M1692 01029 Mreally is an outliercalc43Grubbs test is good for 1 point onlydont keep doing it again and again but if have large data set and have 2 that seem like outliers can we do grubbs test twice for both based on original avg and standard deviation and then remove both if outliernot reallyBut if you know for sure you did an experimental mistake just cross off that point dont need to statistically prove itUsing Gaussian Distribution to Make Predictions section 41 zabisca and normal error curvelearn on your ownMethod of Least SquaresWe do it on lines but can work for nonlinear curves as well3 Key assumptions 1 all data points have the same error magnitude of error in measuring those points is the same 2 the error is random and Gaussian 3 The error in y is larger than the error in x bc x is independent we control the measurements of x dataResiduals difference between your data pt and predicted data pt2yy1pre
More Less

Related notes for CHEM 2121

Log In


Don't have an account?

Join OneClass

Access over 10 million pages of study
documents for 1.3 million courses.

Sign up

Join to view


By registering, I agree to the Terms and Privacy Policies
Already have an account?
Just a few more details

So we can recommend you notes for your school.

Reset Password

Please enter below the email address you registered with and we will send you a link to reset your password.

Add your courses

Get notes from the top students in your class.