|2. Study Guide|
|1. Melissinos (2003) Chapter 10|
|2. Poisson Statistics|
|3. Graphing Data|
|4. Bevington Problems|
|5. Error Propagation|
|6. Chi-Sq dos and don'ts|
|1. Error Analysis video|
|2. Lecture on Systematic Errors|
|3. Applied Statistics|
A Pre-Lab is due at the beginning of class. For purposes of data analysis, there will be a presentation on Python. The goal of any scientific experiment is to make quantitative statements about the the physical world. A common question is, are your measurements consistent with a particular theory or not? This question can only be answered by careful analysis, including both systematic uncertainties and random "statistical" error. Experimentalists and theorists both need to understand how experiments work, how they don't exactly work perfectly, and methods of measurement, data analysis and error estimation.
You need to master these techniques before undertaking any of your experiments, and you will use them for the rest of your career in science. We start with statistical errors: measurement, error propagation, and curve fitting. Later we explore methods of detecting, controlling, and estimating systematic errors.
Experience with error analysis and curve fitting is a prerequisite for each experiment, including your first one on nuclear decay! Read the Study Guide, review Chapter 10 in Melissinos, and look at the useful links on error analysis. You will need to have a working knowledge of this material in your first week of class. See the Reports tab for info on getting started with Python for data analysis.