1 / 29

Topic 32: Two-Way Mixed Effects Model

Topic 32: Two-Way Mixed Effects Model. Outline. Two-way mixed models Three-way mixed models. Data for two-way design. Y is the response variable Factor A with levels i = 1 to a Factor B with levels j = 1 to b Y ijk is the k th observation in cell (i, j) k = 1 to n ij

june
Download Presentation

Topic 32: Two-Way Mixed Effects Model

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript

  1. Topic 32: Two-Way Mixed Effects Model

  2. Outline • Two-way mixed models • Three-way mixed models

  3. Data for two-way design • Y is the response variable • Factor A with levels i = 1 to a • Factor B with levels j = 1 to b • Yijk is the kth observation in cell (i, j) k = 1 to nij • Have balanced designs with n = nij

  4. Two-way mixed model • Two-way mixed model has • One fixed effect • One random effect • Tests: • Again use EMS as guide • Two possible models • Unrestricted mixed model (SAS) • Restricted mixed model (Text)

  5. KNNL Example • KNNL Problem 25.15, p 1080 • Y is fuel efficiency in miles per gallon • Factor A represents four different drivers, a=4 levels • Factor B represents five different cars of the same model , b=5 • Each driver drove each car twice over the same 40-mile test course

  6. Read and check the data data a1; infile 'c:\...\CH25PR15.TXT'; input mpg driver car; proc print data=a1; run;

  7. The data Obs mpg driver car 1 25.3 1 1 2 25.2 1 1 3 28.9 1 2 4 30.0 1 2 5 24.8 1 3 6 25.1 1 3 7 28.4 1 4 8 27.9 1 4 9 27.1 1 5 10 26.6 1 5

  8. Prepare the data for a plot data a1; set a1; if (driver eq 1)*(car eq 1) then dc='01_1A'; if (driver eq 1)*(car eq 2) then dc='02_1B'; ⋮ if (driver eq 4)*(car eq 5) then dc='20_4E';

  9. Plot the data title1 'Plot of the data'; symbol1 v=circle i=none c=black; proc gplot data=a1; plot mpg*dc/frame; run;

  10. Find the means proc means data=a1; output out=a2 mean=avmpg; var mpg; by driver car;

  11. Plot the means title1 'Plot of the means'; symbol1 v='A' i=join c=black; symbol2 v='B' i=join c=black; symbol3 v='C' i=join c=black; symbol4 v='D' i=join c=black; symbol5 v='E' i=join c=black; proc gplot data=a2; plot avmpg*driver=car/frame; run;

  12. Example Revisited • Suppose that the four drivers were not randomly selected and there is interest in comparing the four drivers in the study • Driver (A) is now a fixed effect • Still consider Car (B) to be a random effect

  13. Mixed effects model(unrestricted) • Yijk = μ + i + j + ()ij + εijk • Σi =0 (unknown constants) • j ~ N(0, σ2) • ()ij ~ N(0, σ2) • εij ~ N(0, σ2) • σY2 = σ2 + σ2 + σ2

  14. Mixed effects model(restricted) • Yijk = μ + i + j + ()ij + εijk • Σi =0 (unknown constants) • Σ(b)ij =0 for all j • εij ~ N(0, σ2) • σY2 = σ2 + ((a-1)/a)σ2 + σ2

  15. Parameters • There are a+3 parameters in this model • a fixed effects means • σ2 • σ2 • σ2

  16. ANOVA table • The terms and layout of the ANOVA table are the same as what we used for the fixed effects model • The expected mean squares (EMS) are different and vary based on the choice of unrestricted or restricted mixed model

  17. EMS (unrestricted) • E(MSA) = σ2 + bnΣi2 /(a-1)+ nσ2 • E(MSB) = σ2 + anσ2 + nσ2 • E(MSAB) = σ2 + nσ2 • E(MSE) = σ2 • Estimates of the variance components can be obtained from these equations, replacing E(MS) with table value, or other methods such as ML

  18. EMS (restricted) • E(MSA) = σ2 + bnΣi2 /(a-1)+ nσ2 • E(MSB) = σ2 + anσ2 • E(MSAB) = σ2 + nσ2 • E(MSE) = σ2 • Estimates of the variance components can be obtained from these equations, replacing E(MS) with table value, or other methods such as ML Diff here

  19. Hypotheses (unrestricted) • H0A: σ2 = 0; H1A: σ2 ≠ 0 • H0A is tested by F = MSA/MSAB with df a-1 and (a-1)(b-1) • H0B: σ2 = 0; H1B : σ2 ≠ 0 • H0B is tested by F = MSB/MSAB with df b-1 and (a-1)(b-1) • H0AB : σ2 = 0; H1AB : σ2 ≠0 • H0AB is tested by F = MSAB/MSE with df (a-1)(b-1) and ab(n-1)

  20. Hypotheses (restricted) • H0A: σ2 = 0; H1A: σ2 ≠ 0 • H0A is tested by F = MSA/MSAB with df a-1 and (a-1)(b-1) • H0B: σ2 = 0; H1B : σ2 ≠ 0 • H0B is tested by F = MSB/MSE with df b-1 and ab(n-1) • H0AB : σ2 = 0; H1AB : σ2 ≠0 • H0AB is tested by F = MSAB/MSE with df (a-1)(b-1) and ab(n-1)

  21. Comparison of Means • To compare fixed levels of A, std error is • Degrees of freedom for t tests and CIs are then (a-1)(b-1) • This is true for both unrestricted and restricted mixed models

  22. Using Proc Mixed proc mixed data=a1; class car driver; model mpg=driver; random car car*driver / vcorr; lsmeans driver / adjust=tukey; run; SAS considers unrestricted model only…results in slightly different variance estimates

  23. SAS Output

  24. SAS Output

  25. SAS Output

  26. Three-way models • We can have zero, one, two, or three random effects • EMS indicate how to do tests • In some cases the situation is complicated and we need approximations of an F test, e.g. when all are random, use MS(AB)+MS(AC)-MS(ABC) to test A

  27. Last slide • Finish reading KNNL Chapter 25 • We used program topic32.sas to generate the output for today

More Related