This preview shows pages 1–3. Sign up to view the full content.
This preview has intentionally blurred sections. Sign up to view the full version.
View Full Document
Unformatted text preview: STAT503 — Fall 2009 Lecture Notes: Chapters 1 & 2 1 Chapter 1: Introduction August 24, 2009 The Course This is not just a math course. It is about half math, half science. If you are weak at math but good at science you should try to compensate by 1. doing really well at the science part 2. buying a really nifty calculator and learning how to use it 3. working hard and getting help when you need it If you are good at math but weak at science you should try to compensate by 1. reading the text and examples really carefully 2. following instructions very carefully 3. working hard and getting help when you need it These notes are meant to help organize the subject. Occasionally I leave blank spaces to fill in/calculate answers/practice during the class. You are most welcome to email me comments and corrections on the notes. 1.1 – 1.2 Read Statistics This course is about data: • making sense of data • understanding variability in data • assessing the evidence data provides • using data to answer scientific questions • distinguishing signal from noise Examples: 1. Fruit flies of different genotypes measured for a phenotypic trait such as bristle number, wingspan, viability, mating success, pesticide resistance etc. Are their phenotypes different for different genotypes? Some sources of variability: Chapter12.tex; Last Modified: August 24, 2009 (W. Sharabati) STAT503 — Fall 2009 Lecture Notes: Chapters 1 & 2 2 I individual flies do vary for these traits I traits may be strongly affected by environmental variables I concepts like ”success” or ”resistance” may be difficult to quantify 2. Study to assess the effect of exercise on cholesterol levels. One group exercises and another does not. Is cholesterol reduced in exercise group? Considerations: I people have naturally different levels I they respond differently to the same amount of exercise I may vary in adherence to exercise regimen I diet may have an effect I exercise may affect other factors (e.g. appetite, energy, schedule) Given that there is some variability in data, how can we still make sense of the data? How much is ”noise” and how much is ”signal”? Randomness • data have inherent variability • we model variability mathematically using probability • probability is a mathematical way to express uncertainty, chance, and randomness • we need to learn this language in order to communicate Examples: • probability of snow is 90% • probability of tossing ”heads” is 1/2 • probability of experiencing side effect of a drug is less than 2% • probability of living to 115 is one in a million • probability of winning the lottery is one in 14 billion • probability of heterozygote Aa is 2 p (1 p ); homozygote AA is p 2 , homozygote aa is (1 p ) 2 where p and (1 p ) are frequencies of A and a alleles The Scientific/Statistical Process • Formulate scientific question....
View
Full
Document
This note was uploaded on 04/23/2011 for the course STAT 503 taught by Professor Staff during the Spring '08 term at Purdue.
 Spring '08
 Staff

Click to edit the document details