SAS/STAT 922 User's Guide: The MIXED Procedure (Book Excerpt)

More documents

Recommendations

Info

4552 ✦ Chapter 56: The MIXED Procedure Table 56.5 continued Option Description Degrees of Freedom and p-values ADJUST= Determines the method for multiple comparison adjustment of LSmeans differences ALPHA=˛ Determines the confidence level (1 ˛) LOWER Performs one-sided, lower-tailed inference STEPDOWN Adjusts multiple comparison p-values further in a step-down fashion TESTVALUE= Specifies values under the null hypothesis for tests UPPER Performs one-sided, upper-tailed inference Statistical Output CL Constructs confidence limits for means and mean differences CORR Displays the correlation matrix of LS-means COV Displays the covariance matrix of LS-means E Prints the L matrix ELSM Prints the K matrix JOINT Produces a joint F or chi-square test for the LS-means and LSmeans differences SEED= Specifies the seed for computations that depend on random numbers For details about the syntax of the LSMESTIMATE statement, see the section “LSMESTIMATE Statement” on page 496 of Chapter 19, “Shared Concepts and Topics.” MODEL Statement MODEL dependent = < fixed-effects >< / options > ; The MODEL statement names a single dependent variable and the fixed effects, which determine the X matrix of the mixed model (see the section “Parameterization of Mixed Models” on page 4606 for details). The specification of effects is the same as in the GLM procedure; however, unlike PROC GLM, you do not specify random effects in the MODEL statement. The MODEL statement is required. An intercept is included in the fixed-effects model by default. If no fixed effects are specified, only this intercept term is fit. The intercept can be removed by using the NOINT option. Table 56.6 summarizes options in the MODEL statement. These are subsequently discussed in detail in alphabetical order.
Table 56.6 Summary of Important MODEL Statement Options Option Description Model Building NOINT Excludes fixed-effect intercept from model MODEL Statement ✦ 4553 Statistical Computations ALPHA=˛ Determines the confidence level (1 ˛) for fixed effects ALPHAP=˛ Determines the confidence level (1 ˛) for predicted values CHISQ Requests chi-square tests DDF= Specifies denominator degrees of freedom (list) DDFM= Specifies the method for computing denominator degrees of freedom HTYPE= Selects the type of hypothesis test INFLUENCE Requests influence and case-deletion diagnostics NOTEST Suppresses hypothesis tests for the fixed effects OUTP= Specifies output data set for predicted values and related quantities OUTPM= Specifies output data set for predicted values and related quantities RESIDUAL Adds Pearson-type and studentized residuals to output data sets VCIRY Adds scaled marginal residual to output data sets Statistical Output CL Displays confidence limits for fixed-effects parameter estimates CORRB Displays correlation matrix of fixed-effects parameter estimates COVB Displays covariance matrix of fixed-effects parameter estimates COVBI Displays inverse covariance matrix of fixed-effects parameter estimates E, E1, E2, E3 Displays L matrix coefficients INTERCEPT Adds a row for the intercept to test tables SOLUTION Displays fixed-effects parameter estimates (and scale parameter in GLM models) Singularity Tolerances SINGCHOL= Tunes sensitivity in computing Cholesky roots SINGRES= Tunes singularity criterion for residual variance SINGULAR= Tunes the sensitivity in sweeping ZETA= Tunes the sensitivity in forming Type 3 functions You can specify the following options in the MODEL statement after a slash (/). ALPHA=number requests that a t-type confidence interval be constructed for each of the fixed-effects parameters with confidence level 1 number. The value of number must be between 0 and 1; the default is 0.05. ALPHAP=number requests that a t-type confidence interval be constructed for the predicted values with confidence level 1 number. The value of number must be between 0 and 1; the default is 0.05.
Page 1 and 2: SAS/STAT ® 9.22 User’s Guide The
Page 3 and 4: Chapter 56 The MIXED Procedure Cont
Page 5 and 6: Basic Features ✦ 4515 Repeated me
Page 7 and 8: PROC MIXED Contrasted with Other SA
Page 9 and 10: proc mixed data=heights; class Fami
Page 11 and 12: Figure 56.6 Fit Statistics Fit Stat
Page 13 and 14: Figure 56.10 Dimensions and Number
Page 15 and 16: Syntax: MIXED Procedure The followi
Page 17 and 18: Table 56.1 continued Statement Desc
Page 19 and 20: PROC MIXED Statement ✦ 4529 CL< =
Page 21 and 22: INFO PROC MIXED Statement ✦ 4531
Page 23 and 24: ORD PROC MIXED Statement ✦ 4533 d
Page 25 and 26: PROC MIXED Statement ✦ 4535 RESID
Page 27 and 28: PROC MIXED Statement ✦ 4537 RANDO
Page 29 and 30: CLASS Statement ✦ 4539 Because so
Page 31 and 32: contrast 'A narrow' A 1 -1 0 A*B .5
Page 33 and 34: ESTIMATE Statement ESTIMATE ’labe
Page 35 and 36: ID Statement ID variables ; ID Stat
Page 37 and 38: ADJUST=BON proc mixed; class A; mod
Page 39 and 40: LSMEANS Statement ✦ 4549 BYLEVEL
Page 41: SLICE= fixed-effect LSMESTIMATE Sta
Page 45 and 46: MODEL Statement ✦ 4555 DDFM=KENWA
Page 47 and 48: E E1 E2 E3 MODEL Statement ✦ 4557
Page 49 and 50: Table 56.8 continued Description Su
Page 51 and 52: SIZE=n MODEL Statement ✦ 4561 If
Page 53 and 54: MODEL Statement ✦ 4563 Table 56.1
Page 55 and 56: The estimated prediction variance i
Page 57 and 58: PARMS Statement PARMS (value-list)
Page 59 and 60: OLS PRIOR Statement ✦ 4569 By def
Page 61 and 62: PRIOR Statement ✦ 4571 JEFFREYS s
Page 63 and 64: RANDOM Statement ✦ 4573 TDATA= en
Page 65 and 66: RANDOM Statement ✦ 4575 GCORR dis
Page 67 and 68: RANDOM Statement ✦ 4577 component
Page 69 and 70: Table 56.12 continued Option Descri
Page 71 and 72: proc mixed; class a; model y = a x;
Page 73 and 74: REPEATED Statement ✦ 4583 assumed
Page 75 and 76: REPEATED Statement ✦ 4585 functio
Page 77 and 78: REPEATED Statement ✦ 4587 The fol
Page 79 and 80: TYPE=SP(EXPGA)(c1 c2) TYPE=SP(GAUGA
Page 81 and 82: TYPE=UN@AR(1) TYPE=UN@CS REPEATED S
Page 83 and 84: WEIGHT Statement WEIGHT variable ;
Page 85 and 86: Example: Growth Curve with Compound
Page 87 and 88: Mixed Models Theory ✦ 4597 Such a
Page 89 and 90: 2 6 Z D 6 4 2 6 G D 6 4 1 1 1 1 1 1
Page 91 and 92: Estimating Fixed and Random Effects
Page 93 and 94:
Inference and Test Statistics Mixed
Page 95 and 96:
Mixed Models Theory ✦ 4605 (2002,
Page 97 and 98:
Intercept Parameterization of Mixed
Page 99 and 100:
Table 56.18 continued Data I A B(A)
Page 101 and 102:
Residuals and Influence Diagnostics
Page 103 and 104:
Scaled Residuals Residuals and Infl
Page 105 and 106:
Predicted Values, PRESS Residual, a
Page 107 and 108:
When ITER=0 and 2 is profiled, then
Page 109 and 110:
Using results in Cook and Weisberg
Page 111 and 112:
Default Output ✦ 4621 The Evaluat
Page 113 and 114:
Null Model Likelihood Ratio Test De
Page 115 and 116:
Table 56.22 continued ODS Table Nam
Page 117 and 118:
ODS Table Names ✦ 4627 CAUTION: T
Page 119 and 120:
ODS Graphics ✦ 4629 Some of the v
Page 121 and 122:
Figure 56.16 Panel of the Condition
Page 123 and 124:
Figure 56.18 Deletion Estimates ODS
Page 125 and 126:
Computational Issues Computational
Page 127 and 128:
Memory Computational Issues ✦ 463
Page 129 and 130:
Examples: MIXED Procedure Examples:
Page 131 and 132:
Example 56.1: Split-Plot Design ✦
Page 133 and 134:
Example 56.1: Split-Plot Design ✦
Page 135 and 136:
4 F 23.5 24.5 25.0 26.5 5 F 21.5 23
Page 137 and 138:
Output 56.2.4 Repeated Measures Ana
Page 139 and 140:
Output 56.2.7 Repeated Measures Ana
Page 141 and 142:
Example 56.2: Repeated Measures ✦
Page 143 and 144:
Output 56.2.14 Analysis with Compou
Page 145 and 146:
Example 56.2: Repeated Measures ✦
Page 147 and 148:
Example 56.3: Plotting the Likeliho
Page 149 and 150:
Output 56.3.3 continued Number of O
Page 151 and 152:
Output 56.3.8 Fit Statistics and Li
Page 153 and 154:
Output 56.3.12 Least Squares Means
Page 155 and 156:
Both G and R are known. 2 2 1 1 2 1
Page 157 and 158:
Output 56.4.2 Model Dimensions and
Page 159 and 160:
Example 56.4: Known G and R ✦ 466
Page 161 and 162:
Example 56.5: Random Coefficients
Page 163 and 164:
Example 56.5: Random Coefficients
Page 165 and 166:
Output 56.5.7 Random Coefficients A
Page 167 and 168:
Output 56.5.10 continued Covariance
Page 169 and 170:
Example 56.6: Line-Source Sprinkler
Page 171 and 172:
Output 56.6.3 Model Dimensions and
Page 173 and 174:
Example 56.6: Line-Source Sprinkler
Page 175 and 176:
Example 56.7: Influence in Heteroge
Page 177 and 178:
Example 56.7: Influence in Heteroge
Page 179 and 180:
Output 56.7.5 Covariance Parameter
Page 181 and 182:
Output 56.7.7 Restricted Likelihood
Page 183 and 184:
Output 56.7.9 Covariance Parameter
Page 185 and 186:
Example 56.8: Influence Analysis fo
Page 187 and 188:
Output 56.8.2 Restricted Likelihood
Page 189 and 190:
Page 191 and 192:
Page 193 and 194:
Output 56.8.8 Distribution of Condi
Page 195 and 196:
Output 56.9.2 Type 3 Tests in Split
Page 197 and 198:
Output 56.9.5 Parameter Estimates i
Page 199 and 200:
Output 56.10.1 Analysis of LS-Means
Page 201 and 202:
References ✦ 4711 Cook, R. D. (19
Page 203 and 204:
References ✦ 4713 Harville, D. A.
Page 205 and 206:
References ✦ 4715 Matérn, B. (19
Page 207 and 208:
Bulletin No. 343, Louisiana Agricul
Page 209 and 210:
Subject Index 2D geometric anisotro
Page 211 and 212:
graphics, influence diagnostics, 46
Page 213 and 214:
matrix notation, theory (MIXED), 45
Page 215 and 216:
parameter constraints, 4568, 4636 p
Page 217:
subject effect MIXED procedure, 454
Page 220 and 221:
INFLUENCE option, MODEL statement (
Page 222 and 223:
NSAMPLE= option, 4572 NSEARCH= opti
Page 224 and 225:
ESTIMATE statement (MIXED), 4544 LS
Page 227:
SAS® Publishing Delivers! Whether
show all

SAS/STAT 922 User's Guide: The MIXED Procedure (Book Excerpt)

You also want an ePaper? Increase the reach of your titles

Delete template?

Save as template?