Chapter 16 - 1. Chapter 16 a. No one can prove that a model...

Info iconThis preview shows pages 1–3. Sign up to view the full content.

View Full Document Right Arrow Icon
1. Chapter 16 a. No one can prove that a model is correct but we want to use good models b. There are different degrees of accepting/rejecting a model i. Types of evaluations 1. Refute=the data are not compatible with a model and force us to reject it a. Absolute classification-there is no returning to reconsider a refuted model 2. Support: the data are not only compatible with a model but a. Is a reversible designation—additional data may ultimately refute it 3. refute many of the alternatives and lead us to think that it is possibly useful c. A model cannot be supported unless the data would (had they turned out different in certain ways) have refuted the model i. Support means that the model could have failed the test but didn’t d. A lesser degree of compatibility between data and a model is i. Consistent : the data don’t refute the model ii. Data that support a model are consistent with it, but data may also be consistent without giving much confidence to it e. At the furthest extreme, data may be consistent with a model but be i. Irrelevant: the data do not address the model in any way that could have caused us to reject it. 2. Which models to start with a. Notion of progress in the scientific process involves rejecting models and replacing them with new models. b. Different philosophies about what kinds of models to choose initially i. Null model approach 1. Default model 2. One we think is commonly true or a model that we don’t think is true but we use anyway tio demonstrate we can reject something 3. No data can reject all alternative models (you can’t prove negative)
Background image of page 1

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
a. No limit to how many models are relevant toward a particular goal
Background image of page 2
Image of page 3
This is the end of the preview. Sign up to access the rest of the document.

This note was uploaded on 06/09/2011 for the course ADVERTISIN 9390103 taught by Professor Murphey during the Spring '11 term at University of Texas at Austin.

Page1 / 5

Chapter 16 - 1. Chapter 16 a. No one can prove that a model...

This preview shows document pages 1 - 3. Sign up to view the full document.

View Full Document Right Arrow Icon
Ask a homework question - tutors are online