This preview shows pages 1–11. Sign up to view the full content.
This preview has intentionally blurred sections. Sign up to view the full version.
View Full DocumentThis preview has intentionally blurred sections. Sign up to view the full version.
View Full DocumentThis preview has intentionally blurred sections. Sign up to view the full version.
View Full DocumentThis preview has intentionally blurred sections. Sign up to view the full version.
View Full DocumentThis preview has intentionally blurred sections. Sign up to view the full version.
View Full Document
Unformatted text preview: STA 100 Lecture 4 Paul Baines Department of Statistics University of California, Davis January 10th, 2011 Admin for the Day I Homework 1 due Wednesday, Jan 12th in class I Electronic submissions are not valid: we need paper! I If you complete your homework on computer (e.g., doc, pdf) then please also submit it to Smartsite via the Assignments tab I Smartsite submission not required if you handwrite your homework solutions I Forums: Thanks and please use! I Discussion Sections start tomorrow! Admin for the Day I Homework 1 due Wednesday, Jan 12th in class I Electronic submissions are not valid: we need paper! I If you complete your homework on computer (e.g., doc, pdf) then please also submit it to Smartsite via the Assignments tab I Smartsite submission not required if you handwrite your homework solutions I Forums: Thanks and please use! I Discussion Sections start tomorrow! References for Today: Rosner, Ch 6.16.2, 6.4 (7th Ed.) References for Wednesday: Rosner, Ch 3.13.6 (7th Ed.) Recap: Measures of Spread I Sample Variance: Var ( X ) = 1 n 1 n X i =1 ( X i ¯ X ) 2 (1) I Standard Deviation: SD ( X ) = p Var ( X ) = v u u t 1 n 1 n X i =1 ( X i ¯ X ) 2 (2) Why n 1? We will see (next week). Linear Transformations Birthweights of 20 babies born in San Diego (grams): 3265, 3260, 3245, 3484, 4146, 3323, 3649, 3200, 3031, 2069, 2581, 2841, 3609, 2838, 3541, 2759, 3248, 3314, 3101, 2834 I Mean = 3166.9g, Var = 198323.6, SD = 445.323 I Need to convert to kilograms i.e., y = x / 1000. I Need to compute new mean, var and SD. Do we need to convert each data point to kgs, and then recompute? Linear Transformations More generally, if y = ax + b then: 1. Mean( y ) = a * Mean( x ) + b 2. Var( y ) = a 2 * Var( x ) 3. SD( y ) = a * SD( x ) Linear Transformations More generally, if y = ax + b then: 1. Mean( y ) = a * Mean( x ) + b 2. Var( y ) = a 2 * Var( x ) 3. SD( y ) = a * SD( x ) These enable us to easily compute mean, SD and variance after a linear transformation – without converting each data point and recomputing. Example Birthweights of 20 babies born in San Diego (grams): 3265, 3260, 3245, 3484, 4146, 3323, 3649, 3200, 3031, 2069, 2581, 2841, 3609, 2838, 3541, 2759, 3248, 3314, 3101, 2834 I Mean = 3166.9g, Var = 198323.6, SD = 445.323 I Need to convert to kilograms i.e., y = x / 1000. I What are a and b ? I Compute the mean, variance, SD of the new data in kilograms: I Mean = ? Variance = ? SD = ? Producing Useful Graphs Plotting Principles: I Choose axes/scaling so that the data is not overly ‘clumped’ in one part of the graph I Always label axes and the plot itself I Select informative color schemes (more later) I Do not overclutter I Message should be rapidly discernible Tufte’s Principles: web link. Some Perspective Even in cuttingedge of science, plotting the data is the crucial first step....
View
Full
Document
This note was uploaded on 03/09/2011 for the course STAT 100 taught by Professor drake during the Spring '10 term at UC Davis.
 Spring '10
 DRAKE
 Statistics

Click to edit the document details