Session 9 - How to Test for Trends Part II.docx

2 Pages
114 Views
Unlock Document

Department
Cell and Systems Biology
Course
CSB345H1
Professor
William Navarre
Semester
Fall

Description
HMB325H © Lis| Page 1013 S E S S I O N 9 : H O W TO T E S T F O R T R E N D S ( PA R T I I ) CONFIDENCE INTERVAL FOR A LINE 1. the regression line will run w/in those boundaries (of the 95% CI) 95% of the time 2. the standard error of the line varies, so the CI for the line must be done on a point-by- point basis: 1 x−X ́)2 s ̂y y∗x + 2 √n (n−1)s x sy: standard of error for y (at that x) sy*xvariability about the line x: x-value we’re interested in calculating the CI 3. ex. what is 95% CI of the regression line when x = 40? 1. calculate y 2. use the equation of the line to calculate the y-value when x = 40 3. determine the ‘multiplier’ from table.058, t , df = n – 2 4. CI = (y-value) ± multiplier y s CONFIDENCE INTERVAL FOR AN OBSERVATION 4. (prediction interval) 5. confidence interval around an indiv observation 6. also done on a point-by-point basis, but must also take into consideration the variable of indiv data values for the x-value: 2 1 (x−X)́ s ynews y∗x1+ n 2 √ (n−1)s x 7. (same as CI for a line) STUDY POWER 1. to calculate the power of a correlation study, we need to specify (or have specified) 1. r to be detected 2. sample size needed 2. calculate: Z = ln 1+r ρ 2 (1−r s = 1 Z √ n−3 sz: SD of the z distribution (z is normally distributed w this SD) 3. distribution of the study results will be cpnZred at Z /s 4. subtract this new centred value from the cut-off value of 1.96 (for α = .05) 5. Table 6-2 to find study power HMB325H © Lis| Page 2013 SAMPLE SIZE 1. to calc
More Less

Related notes for CSB345H1

Log In


OR

Join OneClass

Access over 10 million pages of study
documents for 1.3 million courses.

Sign up

Join to view


OR

By registering, I agree to the Terms and Privacy Policies
Already have an account?
Just a few more details

So we can recommend you notes for your school.

Reset Password

Please enter below the email address you registered with and we will send you a link to reset your password.

Add your courses

Get notes from the top students in your class.


Submit