------------------------------------------------------------------------------- name: log: Q:\C-modelling\runmlwin\website\logfiles\2020-03-27\16\18_Modellin > g_Cross-classified_Data.smcl log type: smcl opened on: 27 Mar 2020, 17:43:23 . **************************************************************************** . * MLwiN User Manual . * . * 18 Modelling Cross-classified Data 271 . * . * Rasbash, J., Steele, F., Browne, W. J. and Goldstein, H. (2012). . * A User’s Guide to MLwiN, v2.26. Centre for Multilevel Modelling, . * University of Bristol. . **************************************************************************** . * Stata do-file to replicate all analyses using runmlwin . * . * George Leckie and Chris Charlton, . * Centre for Multilevel Modelling, 2012 . * http://www.bristol.ac.uk/cmm/software/runmlwin/ . **************************************************************************** . . * 18.1 An introduction to cross-classification . . . . . . . . . . . . . 271 . . * 18.2 How cross-classified models are implemented in MLwiN . . . . . . .273 . . * 18.3 Some computational considerations . . . . . . . . . . . . . . . . 273 . . . . * 18.4 Modelling a two-way classification: An example . . . . . . . . . .275 . . use "http://www.bristol.ac.uk/cmm/media/runmlwin/xc.dta", clear . . describe Contains data from http://www.bristol.ac.uk/cmm/media/runmlwin/xc.dta obs: 3,435 vars: 11 21 Oct 2011 12:19 ------------------------------------------------------------------------------- storage display value variable name type format label variable label ------------------------------------------------------------------------------- vrq int %9.0g Verbal reasoning score attain byte %9.0g Age 16 attainment pid int %9.0g Primary school ID sex byte %9.0g Gender sc byte %9.0g Social class sid byte %9.0g Secondary school ID fed byte %9.0g Father's education choice byte %9.0g Number of secondary schools attended med byte %9.0g Mother's education cons byte %9.0g Constant pupil byte %9.0g Pupil ID ------------------------------------------------------------------------------- Sorted by: . . tabulate sid, generate(s) Secondary | school ID | Freq. Percent Cum. ------------+----------------------------------- 1 | 219 6.38 6.38 2 | 199 5.79 12.17 3 | 156 4.54 16.71 4 | 139 4.05 20.76 5 | 175 5.09 25.85 6 | 250 7.28 33.13 7 | 109 3.17 36.30 8 | 107 3.11 39.42 9 | 114 3.32 42.74 10 | 92 2.68 45.41 11 | 234 6.81 52.23 12 | 253 7.37 59.59 13 | 216 6.29 65.88 14 | 290 8.44 74.32 15 | 147 4.28 78.60 16 | 134 3.90 82.50 17 | 233 6.78 89.29 18 | 257 7.48 96.77 19 | 111 3.23 100.00 ------------+----------------------------------- Total | 3,435 100.00 . . local c = 1 . . forvalues s=2/19 { 2. . constraint define `c' [RP3]var(s1) = [RP3]var(s`s') 3. . local c = `c' + 1 4. . } . . runmlwin attain cons, /// > level3(cons: s1-s19, diagonal) /// > level2(pid: cons) level1(pupil: cons) /// > constraints(1/18) nopause ( 1) [RP3]var(s1) - [RP3]var(s2) = 0 ( 2) [RP3]var(s1) - [RP3]var(s3) = 0 ( 3) [RP3]var(s1) - [RP3]var(s4) = 0 ( 4) [RP3]var(s1) - [RP3]var(s5) = 0 ( 5) [RP3]var(s1) - [RP3]var(s6) = 0 ( 6) [RP3]var(s1) - [RP3]var(s7) = 0 ( 7) [RP3]var(s1) - [RP3]var(s8) = 0 ( 8) [RP3]var(s1) - [RP3]var(s9) = 0 ( 9) [RP3]var(s1) - [RP3]var(s10) = 0 (10) [RP3]var(s1) - [RP3]var(s11) = 0 (11) [RP3]var(s1) - [RP3]var(s12) = 0 (12) [RP3]var(s1) - [RP3]var(s13) = 0 (13) [RP3]var(s1) - [RP3]var(s14) = 0 (14) [RP3]var(s1) - [RP3]var(s15) = 0 (15) [RP3]var(s1) - [RP3]var(s16) = 0 (16) [RP3]var(s1) - [RP3]var(s17) = 0 (17) [RP3]var(s1) - [RP3]var(s18) = 0 (18) [RP3]var(s1) - [RP3]var(s19) = 0 MLwiN 3.05 multilevel model Number of obs = 3435 Normal response model (hierarchical) Estimation algorithm: IGLS ----------------------------------------------------------- | No. of Observations per Group Level Variable | Groups Minimum Average Maximum ----------------+------------------------------------------ cons | 1 3435 3435.0 3435 pid | 148 1 23.2 72 ----------------------------------------------------------- Run time (seconds) = 1.18 Number of iterations = 4 Log likelihood = -8574.5656 Deviance = 17149.131 ------------------------------------------------------------------------------ attain | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- cons | 5.504051 .1748762 31.47 0.000 5.161299 5.846802 ------------------------------------------------------------------------------ ------------------------------------------------------------------------------ Random-effects Parameters | Estimate Std. Err. [95% Conf. Interval] -----------------------------+------------------------------------------------ Level 3: cons | var(s1) | .347889 .1622717 .0298423 .6659356 var(s2) | .347889 .1622717 .0298423 .6659356 var(s3) | .347889 .1622717 .0298423 .6659356 var(s4) | .347889 .1622717 .0298423 .6659356 var(s5) | .347889 .1622717 .0298423 .6659356 var(s6) | .347889 .1622717 .0298423 .6659356 var(s7) | .347889 .1622717 .0298423 .6659356 var(s8) | .347889 .1622717 .0298423 .6659356 var(s9) | .347889 .1622717 .0298423 .6659356 var(s10) | .347889 .1622717 .0298423 .6659356 var(s11) | .347889 .1622717 .0298423 .6659356 var(s12) | .347889 .1622717 .0298423 .6659356 var(s13) | .347889 .1622717 .0298423 .6659356 var(s14) | .347889 .1622717 .0298423 .6659356 var(s15) | .347889 .1622717 .0298423 .6659356 var(s16) | .347889 .1622717 .0298423 .6659356 var(s17) | .347889 .1622717 .0298423 .6659356 var(s18) | .347889 .1622717 .0298423 .6659356 var(s19) | .347889 .1622717 .0298423 .6659356 -----------------------------+------------------------------------------------ Level 2: pid | var(cons) | 1.123741 .1979374 .7357908 1.511691 -----------------------------+------------------------------------------------ Level 1: pupil | var(cons) | 8.111626 .1999722 7.719688 8.503565 ------------------------------------------------------------------------------ . . . . . * 18.5 Other aspects of the SETX command . . . . . . . . . . . . . . . . 277 . . forvalues s=1/19 { 2. . generate s`s'Xvrq = s`s'*vrq 3. . } . . local c = 19 . . forvalues s=2/19 { 2. . constraint define `c' [RP3]var(s1Xvrq) = [RP3]var(s`s'Xvrq) 3. . local c = `c' + 1 4. . } . . runmlwin attain cons, /// > level3(cons: s1-s19 s1Xvrq-s19Xvrq, diagonal) /// > level2(pid: cons) level1(pupil: cons) /// > constraints(1/36) nopause ( 1) [RP3]var(s1) - [RP3]var(s2) = 0 ( 2) [RP3]var(s1) - [RP3]var(s3) = 0 ( 3) [RP3]var(s1) - [RP3]var(s4) = 0 ( 4) [RP3]var(s1) - [RP3]var(s5) = 0 ( 5) [RP3]var(s1) - [RP3]var(s6) = 0 ( 6) [RP3]var(s1) - [RP3]var(s7) = 0 ( 7) [RP3]var(s1) - [RP3]var(s8) = 0 ( 8) [RP3]var(s1) - [RP3]var(s9) = 0 ( 9) [RP3]var(s1) - [RP3]var(s10) = 0 (10) [RP3]var(s1) - [RP3]var(s11) = 0 (11) [RP3]var(s1) - [RP3]var(s12) = 0 (12) [RP3]var(s1) - [RP3]var(s13) = 0 (13) [RP3]var(s1) - [RP3]var(s14) = 0 (14) [RP3]var(s1) - [RP3]var(s15) = 0 (15) [RP3]var(s1) - [RP3]var(s16) = 0 (16) [RP3]var(s1) - [RP3]var(s17) = 0 (17) [RP3]var(s1) - [RP3]var(s18) = 0 (18) [RP3]var(s1) - [RP3]var(s19) = 0 (19) [RP3]var(s1Xvrq) - [RP3]var(s2Xvrq) = 0 (20) [RP3]var(s1Xvrq) - [RP3]var(s3Xvrq) = 0 (21) [RP3]var(s1Xvrq) - [RP3]var(s4Xvrq) = 0 (22) [RP3]var(s1Xvrq) - [RP3]var(s5Xvrq) = 0 (23) [RP3]var(s1Xvrq) - [RP3]var(s6Xvrq) = 0 (24) [RP3]var(s1Xvrq) - [RP3]var(s7Xvrq) = 0 (25) [RP3]var(s1Xvrq) - [RP3]var(s8Xvrq) = 0 (26) [RP3]var(s1Xvrq) - [RP3]var(s9Xvrq) = 0 (27) [RP3]var(s1Xvrq) - [RP3]var(s10Xvrq) = 0 (28) [RP3]var(s1Xvrq) - [RP3]var(s11Xvrq) = 0 (29) [RP3]var(s1Xvrq) - [RP3]var(s12Xvrq) = 0 (30) [RP3]var(s1Xvrq) - [RP3]var(s13Xvrq) = 0 (31) [RP3]var(s1Xvrq) - [RP3]var(s14Xvrq) = 0 (32) [RP3]var(s1Xvrq) - [RP3]var(s15Xvrq) = 0 (33) [RP3]var(s1Xvrq) - [RP3]var(s16Xvrq) = 0 (34) [RP3]var(s1Xvrq) - [RP3]var(s17Xvrq) = 0 (35) [RP3]var(s1Xvrq) - [RP3]var(s18Xvrq) = 0 (36) [RP3]var(s1Xvrq) - [RP3]var(s19Xvrq) = 0 MLwiN 3.05 multilevel model Number of obs = 3435 Normal response model (hierarchical) Estimation algorithm: IGLS ----------------------------------------------------------- | No. of Observations per Group Level Variable | Groups Minimum Average Maximum ----------------+------------------------------------------ cons | 1 3435 3435.0 3435 pid | 148 1 23.2 72 ----------------------------------------------------------- Run time (seconds) = 3.53 Number of iterations = 7 Log likelihood = -7498.3883 Deviance = 14996.777 ------------------------------------------------------------------------------ attain | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- cons | -9.806004 .314339 -31.20 0.000 -10.4221 -9.18991 ------------------------------------------------------------------------------ ------------------------------------------------------------------------------ Random-effects Parameters | Estimate Std. Err. [95% Conf. Interval] -----------------------------+------------------------------------------------ Level 3: cons | var(s1) | .3761075 .5852487 -.7709589 1.523174 var(s2) | .3761075 .5852487 -.7709589 1.523174 var(s3) | .3761075 .5852487 -.7709589 1.523174 var(s4) | .3761075 .5852487 -.7709589 1.523174 var(s5) | .3761075 .5852487 -.7709589 1.523174 var(s6) | .3761075 .5852487 -.7709589 1.523174 var(s7) | .3761075 .5852487 -.7709589 1.523174 var(s8) | .3761075 .5852487 -.7709589 1.523174 var(s9) | .3761075 .5852487 -.7709589 1.523174 var(s10) | .3761075 .5852487 -.7709589 1.523174 var(s11) | .3761075 .5852487 -.7709589 1.523174 var(s12) | .3761075 .5852487 -.7709589 1.523174 var(s13) | .3761075 .5852487 -.7709589 1.523174 var(s14) | .3761075 .5852487 -.7709589 1.523174 var(s15) | .3761075 .5852487 -.7709589 1.523174 var(s16) | .3761075 .5852487 -.7709589 1.523174 var(s17) | .3761075 .5852487 -.7709589 1.523174 var(s18) | .3761075 .5852487 -.7709589 1.523174 var(s19) | .3761075 .5852487 -.7709589 1.523174 var(s1Xvrq) | .0248308 .008066 .0090217 .0406399 var(s2Xvrq) | .0248308 .008066 .0090217 .0406399 var(s3Xvrq) | .0248308 .008066 .0090217 .0406399 var(s4Xvrq) | .0248308 .008066 .0090217 .0406399 var(s5Xvrq) | .0248308 .008066 .0090217 .0406399 var(s6Xvrq) | .0248308 .008066 .0090217 .0406399 var(s7Xvrq) | .0248308 .008066 .0090217 .0406399 var(s8Xvrq) | .0248308 .008066 .0090217 .0406399 var(s9Xvrq) | .0248308 .008066 .0090217 .0406399 var(s10Xvrq) | .0248308 .008066 .0090217 .0406399 var(s11Xvrq) | .0248308 .008066 .0090217 .0406399 var(s12Xvrq) | .0248308 .008066 .0090217 .0406399 var(s13Xvrq) | .0248308 .008066 .0090217 .0406399 var(s14Xvrq) | .0248308 .008066 .0090217 .0406399 var(s15Xvrq) | .0248308 .008066 .0090217 .0406399 var(s16Xvrq) | .0248308 .008066 .0090217 .0406399 var(s17Xvrq) | .0248308 .008066 .0090217 .0406399 var(s18Xvrq) | .0248308 .008066 .0090217 .0406399 var(s19Xvrq) | .0248308 .008066 .0090217 .0406399 -----------------------------+------------------------------------------------ Level 2: pid | var(cons) | .2941492 .0650318 .1666891 .4216092 -----------------------------+------------------------------------------------ Level 1: pupil | var(cons) | 4.236561 .1045988 4.031551 4.441571 ------------------------------------------------------------------------------ . . // Note: The final models in this section of the manual are for demonstration > only. . // The models presented in the manual do not converge with the current data. . // We have therefore not given the runmlwin commands for these models. . . . . * 18.6 Reducing storage overhead by grouping . . . . . . . . . . . . . . 279 . . use "http://www.bristol.ac.uk/cmm/media/runmlwin/xc.dta", clear . . ssc install supclust checking supclust consistency and verifying not already installed... all files already exist and are up to date. . . supclust sid pid, generate(region) 1 clusters in 3435 observations . . drop region . . bysort sid pid: generate numchildren = _N . . drop if numchildren<3 (168 observations deleted) . . supclust sid pid, generate(region) 6 clusters in 3267 observations . . bysort region sid: generate rsid = 1 if _n==1 (3,248 missing values generated) . . bysort region (sid): replace rsid = sum(rsid) (3261 real changes made) . . tabulate rsid, generate(rs) rsid | Freq. Percent Cum. ------------+----------------------------------- 1 | 1,020 31.22 31.22 2 | 769 23.54 54.76 3 | 267 8.17 62.93 4 | 292 8.94 71.87 5 | 467 14.29 86.16 6 | 99 3.03 89.19 7 | 249 7.62 96.82 8 | 104 3.18 100.00 ------------+----------------------------------- Total | 3,267 100.00 . . local c = 1 . . forvalues s=2/8 { 2. . constraint define `c' [RP3]var(rs1) = [RP3]var(rs`s') 3. . local c = `c' + 1 4. . } . . sort region pid pupil . . runmlwin attain cons, /// > level3(region: rs1-rs8, diagonal) /// > level2(pid: cons) level1(pupil: cons) /// > constraints(1/7) nopause ( 1) [RP3]var(rs1) - [RP3]var(rs2) = 0 ( 2) [RP3]var(rs1) - [RP3]var(rs3) = 0 ( 3) [RP3]var(rs1) - [RP3]var(rs4) = 0 ( 4) [RP3]var(rs1) - [RP3]var(rs5) = 0 ( 5) [RP3]var(rs1) - [RP3]var(rs6) = 0 ( 6) [RP3]var(rs1) - [RP3]var(rs7) = 0 ( 7) [RP3]var(rs1) - [RP3]var(rs8) = 0 MLwiN 3.05 multilevel model Number of obs = 3267 Normal response model (hierarchical) Estimation algorithm: IGLS ----------------------------------------------------------- | No. of Observations per Group Level Variable | Groups Minimum Average Maximum ----------------+------------------------------------------ region | 6 78 544.5 1330 pid | 135 3 24.2 72 ----------------------------------------------------------- Run time (seconds) = 0.71 Number of iterations = 5 Log likelihood = -8153.6587 Deviance = 16307.317 ------------------------------------------------------------------------------ attain | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- cons | 5.581951 .1812115 30.80 0.000 5.226783 5.937119 ------------------------------------------------------------------------------ ------------------------------------------------------------------------------ Random-effects Parameters | Estimate Std. Err. [95% Conf. Interval] -----------------------------+------------------------------------------------ Level 3: region | var(rs1) | .3838316 .188726 .0139355 .7537278 var(rs2) | .3838316 .188726 .0139355 .7537278 var(rs3) | .3838316 .188726 .0139355 .7537278 var(rs4) | .3838316 .188726 .0139355 .7537278 var(rs5) | .3838316 .188726 .0139355 .7537278 var(rs6) | .3838316 .188726 .0139355 .7537278 var(rs7) | .3838316 .188726 .0139355 .7537278 var(rs8) | .3838316 .188726 .0139355 .7537278 -----------------------------+------------------------------------------------ Level 2: pid | var(cons) | 1.10259 .2014954 .7076658 1.497513 -----------------------------+------------------------------------------------ Level 1: pupil | var(cons) | 8.104429 .2047401 7.703145 8.505712 ------------------------------------------------------------------------------ . . . . * 18.7 Modelling a multi-way cross-classification . . . . . . . . . . . .280 . . * 18.8 MLwiN commands for cross-classifications . . . . . . . . . . . . .281 . . * Chapter learning outcomes . . . . . . . . . . . . . . . . . . . . . . .282 . . . . **************************************************************************** . exit end of do-file