250 likes | 332 Views
Chapter Four Day One. Transforming Data. Homework. P. 265 2,4 P. 276 5,7,9. First Steps to Achieving Linearity. Make a scatterplot of data Note non-linear form Think of a “common-sense” relationship. Example. Average length and weight of Atlantic Ocean rockfish. Achieving Linearity.
E N D
Chapter FourDay One Transforming Data
Homework • P. 265 2,4 • P. 276 5,7,9
First Steps to Achieving Linearity • Make a scatterplot of data • Note non-linear form • Think of a “common-sense” relationship
Example • Average length and weight of Atlantic Ocean rockfish
Achieving Linearity • Now lets graph length3 vs. weight • L1 = length • L2 = weight • L3 = length3 • Plot L3 vs. L2 • Perform linreg on L3 vs. L2
Model • weight = 4.066 + 0.0147(length)3 • Now report r and r2 • Make residual plot
Types of Nonlinear Models • Exponential Models y = bx Use an exponential model if there is a linear relationship between x and log y. • Power Models y = xb • Use a power Model if there is a linear relationship between log x and log y.
Review of Logartithms • Y = logb x if and only if by = x • Evaluate • Log10100 = • Log 2 8 = • Log 3 1/9 =
Solve each equation • logx 125 = 3 • Log 4 x = 4
Laws of Logarthims • Logb (MN) = logb M + logb N • Logb (M/N) = logb M – logb N • Logb Mp = p logb M
Exponential Models • Show that if y = abx, then there is a linear relationship between x and log y
Review of Exponential Models • Make scatterplot and note very strong non-linear form. • Take the log of the y-values and put the results in L3. • Do a linreg on L1 vs. L3 (x versus log y) • Write log(y) = bx + a • Untransform to get final exponential model
Untransform • Log y = a + bx