GitHub - mattdwebb/summclust: Stata module for cluster specific information and cluster jackknife (original) (raw)
summclust
Stata module for cluster level measures of leverage, influence, and a cluster jackknife variance estimator.
For a very detailed description see:
MacKinnon, J.G., Nielsen, M.Ø., Webb, M.D., 2022. Leverage, influence, and the Jackknife in Clustered Regression Models: Reliable Inference Using Summclust. Stata Journal (accepted).
nlswork example - using regress
webuse nlswork, clear keep if inrange(age,20,40) reg ln_wage i.grade i.age i.birth_yr union race msp, cluster(ind) Linear regression Number of obs = 17,395 F(11, 11) = . Prob > F = . R-squared = 0.2489 Root MSE = .39938
(Std. err. adjusted for 12 clusters in ind_code) | Robust
ln_wage | Coefficient std. err. t P>|t| [95% conf. interval]-------------+---------------------------------------------------------------- grade | 1 | .0067144 .1567428 0.04 0.967 -.3382742 .3517031 2 | .0693857 .1486907 0.47 0.650 -.2578802 .3966517 3 | -.0917736 .1542778 -0.59 0.564 -.4313367 .2477895 4 | -.0425058 .2090656 -0.20 0.843 -.502656 .4176445 5 | -.0857796 .17182 -0.50 0.627 -.4639529 .2923936 6 | -.1327277 .1845942 -0.72 0.487 -.5390168 .2735614 7 | -.1149881 .205336 -0.56 0.587 -.5669297 .3369535 8 | -.0132159 .1724339 -0.08 0.940 -.3927403 .3663085 9 | .1032753 .1837659 0.56 0.585 -.3011907 .5077413 10 | .1111109 .1781801 0.62 0.546 -.2810609 .5032826 11 | .1728348 .1719334 1.01 0.336 -.2055882 .5512577 12 | .3009656 .1648168 1.83 0.095 -.0617938 .6637249 13 | .3743186 .1644968 2.28 0.044 .0122636 .7363736 14 | .4968325 .1498871 3.31 0.007 .1669333 .8267318 15 | .5968269 .1729627 3.45 0.005 .2161386 .9775151 16 | .6213717 .1736808 3.58 0.004 .2391027 1.003641 17 | .7082245 .1616095 4.38 0.001 .3525243 1.063925 18 | .7528997 .1580522 4.76 0.001 .4050291 1.10077 | age | 21 | .0467232 .0282197 1.66 0.126 -.0153878 .1088343 22 | .0716267 .0207421 3.45 0.005 .0259736 .1172799 23 | .0894485 .0220914 4.05 0.002 .0408256 .1380714 24 | .0889048 .0140717 6.32 0.000 .0579332 .1198765 25 | .0995865 .0166336 5.99 0.000 .0629763 .1361968 26 | .1407115 .0274954 5.12 0.000 .0801945 .2012284 27 | .1249942 .0263429 4.74 0.001 .0670139 .1829745 28 | .1142114 .0200124 5.71 0.000 .0701643 .1582585 29 | .1236353 .0168797 7.32 0.000 .0864834 .1607872 30 | .120622 .0274711 4.39 0.001 .0601585 .1810856 31 | .1764482 .030089 5.86 0.000 .1102227 .2426737 32 | .1648261 .0217204 7.59 0.000 .1170197 .2126325 33 | .1753608 .0259648 6.75 0.000 .1182126 .2325091 34 | .1695028 .0291718 5.81 0.000 .1052962 .2337094 35 | .1945492 .0384418 5.06 0.000 .1099394 .279159 36 | .1870979 .0225457 8.30 0.000 .1374752 .2367206 37 | .1969468 .0330288 5.96 0.000 .1242509 .2696427 38 | .2005178 .0385103 5.21 0.000 .1157573 .2852783 39 | .2137323 .0298338 7.16 0.000 .1480686 .279396 40 | .2314017 .0324123 7.14 0.000 .1600626 .3027408 | birth_yr | 42 | -.4738657 .1899469 -2.49 0.030 -.891936 -.0557954 43 | -.5640077 .1825887 -3.09 0.010 -.9658828 -.1621326 44 | -.5379325 .1628801 -3.30 0.007 -.8964293 -.1794358 45 | -.5151845 .1724917 -2.99 0.012 -.8948363 -.1355328 46 | -.5419291 .1782975 -3.04 0.011 -.9343592 -.1494989 47 | -.5288973 .1720382 -3.07 0.011 -.9075507 -.1502438 48 | -.5159896 .1769569 -2.92 0.014 -.9054691 -.1265101 49 | -.5078528 .1765028 -2.88 0.015 -.8963329 -.1193727 50 | -.5150216 .1665272 -3.09 0.010 -.8815455 -.1484977 51 | -.5197465 .1691962 -3.07 0.011 -.8921447 -.1473482 52 | -.5352975 .1765147 -3.03 0.011 -.9238037 -.1467913 53 | -.5109173 .1786392 -2.86 0.016 -.9040996 -.117735 54 | -.5547693 .1934734 -2.87 0.015 -.9806015 -.1289372 | union | .1989258 .0643866 3.09 0.010 .0572118 .3406399 race | -.0863069 .0152056 -5.68 0.000 -.1197742 -.0528396 msp | -.0269398 .0082478 -3.27 0.008 -.0450932 -.0087865 _cons | 1.848848 .2508612 7.37 0.000 1.296707 2.40099
nlswork - using summclust
summclust ln_wage msp union race, fevar(grade age birth_yr) cluster(ind)
SUMMCLUST - MacKinnon, Nielsen, and Webb
Cluster summary statistics for msp when clustered by ind_code. There are 17395 observations within 12 ind_code clusters.
WARNING - Elements of beta undefined when certain cluster(s) are omitted
Two standard errors are calculated: The first standard error uses a generalized inverse. The second standard error drops the singularities.
There are 2 problem clusters, out of 12 clusters. The problematic ind_code cluster(s) are: 4 11 As only 16.67 % of subsamples are singular, dropping them is preferred.
Regression Output
s.e. | Coeff Sd. Err. t-stat P value CI-lower CI-upper -------+---------------------------------------------------------------- CV1 | -0.026940 0.008248 -3.2663 0.0075 -0.045093 -0.008787 CV3 | -0.026940 0.011150 -2.4161 0.0342 -0.051481 -0.002399
Regression Output -- Dropping Singular Omit-One-Cluster Subsamples
s.e. | Coeff Sd. Err. t-stat P value CI-lower CI-upper CV3 | -0.026940 0.006701 -4.0200 0.0030 -0.042099 -0.011780
Cluster Variability
Statistic | Ng Leverage Partial L. all betg kept beg
-----------+-----------------------------------------------------------
min | 35.00 0.085945 0.000700 -0.032772 -0.032772
q1 | 144.50 0.633594 0.004399 -0.027655 -0.027917
median | 905.00 2.794231 0.038554 -0.026891 -0.027082
mean | 1449.58 4.583333 0.083333 -0.026398 -0.027571
q3 | 2112.50 6.190322 0.105043 -0.025268 -0.026587
max | 5736.00 17.008305 0.353148 -0.019198 -0.024202
-----------+-----------------------------------------------------------
coefvar | 1.19 1.166238 1.320154 0.131277 0.074100
adding industry fixed effects using absorb
summclust ln_wage msp union race, fevar(grade age birth_yr) absorb(ind) cluster(ind) nog
SUMMCLUST - MacKinnon, Nielsen, and Webb
Cluster summary statistics for msp when clustered by ind_code. There are 17395 observations within 12 ind_code clusters.
WARNING - Elements of beta undefined when certain cluster(s) are omitted
Two standard errors are calculated: The first standard error uses a generalized inverse. The second standard error drops the singularities.
There are 2 problem clusters, out of 12 clusters. The problematic ind_code cluster(s) are: 4 11 As only 16.67 % of subsamples are singular, dropping them is preferred.
Regression Output
s.e. | Coeff Sd. Err. t-stat P value CI-lower CI-upper -------+---------------------------------------------------------------- CV1 | -0.018955 0.007014 -2.7025 0.0206 -0.034392 -0.003517 CV3 | -0.018955 0.007586 -2.4987 0.0296 -0.035651 -0.002258
Regression Output -- Dropping Singular Omit-One-Cluster Subsamples
s.e. | Coeff Sd. Err. t-stat P value CI-lower CI-upper CV3 | -0.018955 0.004173 -4.5418 0.0014 -0.028396 -0.009514
Cluster Variability
Statistic | Ng Leverage Partial L. all betg kept beg
-----------+-----------------------------------------------------------
min | 35.00 0.079703 0.000700 -0.021394 -0.021394
q1 | 144.50 0.617131 0.004399 -0.020316 -0.020601
median | 905.00 2.752372 0.038554 -0.019050 -0.019281
mean | 1449.58 4.500000 0.083333 -0.018880 -0.019538
q3 | 2112.50 6.066207 0.105044 -0.018852 -0.019028
max | 5736.00 16.728424 0.353143 -0.012367 -0.016767
-----------+-----------------------------------------------------------
coefvar | 1.19 1.170068 1.320148 0.126464 0.061639
Graph option suppressed.
Effective Number of Clusters using gstar or rho.
summclust ln_wage msp union race, fevar(grade age birth_yr) cluster(ind) nog gstar
summclust ln_wage msp union race, fevar(grade age birth_yr) cluster(ind) nog rho(0.5)
SUMMCLUST - MacKinnon, Nielsen, and Webb
Cluster summary statistics for msp when clustered by ind_code. There are 17395 observations within 12 ind_code clusters.
WARNING - Elements of beta undefined when certain cluster(s) are omitted
Two standard errors are calculated: The first standard error uses a generalized inverse. The second standard error drops the singularities.
There are 2 problem clusters, out of 12 clusters. The problematic ind_code cluster(s) are: 4 11 As only 16.67 % of subsamples are singular, dropping them is preferred.
Regression Output
s.e. | Coeff Sd. Err. t-stat P value CI-lower CI-upper -------+---------------------------------------------------------------- CV1 | -0.026940 0.008248 -3.2663 0.0075 -0.045093 -0.008787 CV3 | -0.026940 0.011150 -2.4161 0.0342 -0.051481 -0.002399
Regression Output -- Dropping Singular Omit-One-Cluster Subsamples
s.e. | Coeff Sd. Err. t-stat P value CI-lower CI-upper CV3 | -0.026940 0.006701 -4.0200 0.0030 -0.042099 -0.011780
Cluster Variability
Statistic | Ng Leverage Partial L. all betg kept beg
-----------+-----------------------------------------------------------
min | 35.00 0.085945 0.000700 -0.032772 -0.032772
q1 | 144.50 0.633594 0.004399 -0.027655 -0.027917
median | 905.00 2.794231 0.038554 -0.026891 -0.027082
mean | 1449.58 4.583333 0.083333 -0.026398 -0.027571
q3 | 2112.50 6.190322 0.105043 -0.025268 -0.026587
max | 5736.00 17.008305 0.353148 -0.019198 -0.024202
-----------+-----------------------------------------------------------
coefvar | 1.19 1.166238 1.320154 0.131277 0.074100
Effective Number of Clusters
G*(0) = 5.495 G*(1) = 1.376
Graph option suppressed.
SUMMCLUST - MacKinnon, Nielsen, and Webb
Cluster summary statistics for msp when clustered by ind_code. There are 17395 observations within 12 ind_code clusters.
WARNING - Elements of beta undefined when certain cluster(s) are omitted
Two standard errors are calculated: The first standard error uses a generalized inverse. The second standard error drops the singularities.
There are 2 problem clusters, out of 12 clusters. The problematic ind_code cluster(s) are: 4 11 As only 16.67 % of subsamples are singular, dropping them is preferred.
Regression Output
s.e. | Coeff Sd. Err. t-stat P value CI-lower CI-upper -------+---------------------------------------------------------------- CV1 | -0.026940 0.008248 -3.2663 0.0075 -0.045093 -0.008787 CV3 | -0.026940 0.011150 -2.4161 0.0342 -0.051481 -0.002399
Regression Output -- Dropping Singular Omit-One-Cluster Subsamples
s.e. | Coeff Sd. Err. t-stat P value CI-lower CI-upper CV3 | -0.026940 0.006701 -4.0200 0.0030 -0.042099 -0.011780
Cluster Variability
Statistic | Ng Leverage Partial L. all betg kept beg
-----------+-----------------------------------------------------------
min | 35.00 0.085945 0.000700 -0.032772 -0.032772
q1 | 144.50 0.633594 0.004399 -0.027655 -0.027917
median | 905.00 2.794231 0.038554 -0.026891 -0.027082
mean | 1449.58 4.583333 0.083333 -0.026398 -0.027571
q3 | 2112.50 6.190322 0.105043 -0.025268 -0.026587
max | 5736.00 17.008305 0.353148 -0.019198 -0.024202
-----------+-----------------------------------------------------------
coefvar | 1.19 1.166238 1.320154 0.131277 0.074100
Effective Number of Clusters
G*(0) = 5.495 G*(.5) = 1.433 G*(1) = 1.376
Graph option suppressed.
All Output
summclust ln_wage msp union race, fevar(grade age birth_yr) cluster(ind) regtable rho(0.5) addmeans table
SUMMCLUST - MacKinnon, Nielsen, and Webb
Cluster summary statistics for msp when clustered by ind_code. There are 17395 observations within 12 ind_code clusters.
WARNING - Elements of beta undefined when certain cluster(s) are omitted
Two standard errors are calculated: The first standard error uses a generalized inverse. The second standard error drops the singularities.
There are 2 problem clusters, out of 12 clusters. The problematic ind_code cluster(s) are: 4 11 As only 16.67 % of subsamples are singular, dropping them is preferred.
Regression Output
s.e. | Coeff Sd. Err. t-stat P value CI-lower CI-upper -------+---------------------------------------------------------------- CV1 | -0.026940 0.008248 -3.2663 0.0075 -0.045093 -0.008787 CV3 | -0.026940 0.011150 -2.4161 0.0342 -0.051481 -0.002399
Regression Output -- Dropping Singular Omit-One-Cluster Subsamples
s.e. | Coeff Sd. Err. t-stat P value CI-lower CI-upper CV3 | -0.026940 0.006701 -4.0200 0.0030 -0.042099 -0.011780
Cluster Variability
Statistic | Ng Leverage Partial L. all betg kept beg
-----------+-----------------------------------------------------------
min | 35.00 0.085945 0.000700 -0.032772 -0.032772
q1 | 144.50 0.633594 0.004399 -0.027655 -0.027917
median | 905.00 2.794231 0.038554 -0.026891 -0.027082
mean | 1449.58 4.583333 0.083333 -0.026398 -0.027571
q3 | 2112.50 6.190322 0.105043 -0.025268 -0.026587
max | 5736.00 17.008305 0.353148 -0.019198 -0.024202
-----------+-----------------------------------------------------------
coefvar | 1.19 1.166238 1.320154 0.131277 0.074100
Effective Number of Clusters
G*(0) = 5.495 G*(.5) = 1.433 G*(1) = 1.376
Alternative Sample Means and Ratios to Arithmetic Mean
| Ng Leverage Partial L. all bet~g kept be~g ----------------+--------------------------------------------------------------
Harmonic Mean | 206.576 0.608440 0.004988 . .
Harmonic Ratio | 0.143 0.132751 0.059853 . .
Geometric Mean | 623.091 2.042731 0.025557 . .
Geometric Ratio | 0.430 0.445687 0.306684 . .
Quadratic Mean | 2193.268 6.870062 0.134308 0.026605 0.027654
Quadratic Ratio | 1.513 1.498923 1.611699 -1.007868 -1.003015
Linear Regression -- CV3
regresstab[55,6] Coeff Sd. Err. t-stat P value CI-lower CI-upper msp -.02693984 .01115011 -2.4161049 .0342423 -.05148107 -.00239861 union .19892584 .08723856 2.2802515 .04351693 .00691508 .39093661 race -.0863069 .01807802 -4.7741355 .00057683 -.12609634 -.04651745 grade_0 1.5254807 1.4113599 1.0808588 .30288726 -1.5809014 4.6318629 grade_1 1.5321952 1.2308355 1.2448416 .23905821 -1.1768554 4.2412457 grade_2 1.5948664 2.1601628 .73830845 .47578431 -3.1596198 6.3493526 grade_3 1.4337071 1.5396405 .93119603 .37173879 -1.9550188 4.8224331 grade_4 1.482975 1.6146796 .91843298 .37809097 -2.0709108 5.0368607 grade_5 1.4397011 1.600765 .89938316 .38771324 -2.0835589 4.9629611 grade_6 1.392753 1.5747742 .88441443 .39539268 -2.0733016 4.8588077 grade_7 1.4104926 1.6199455 .87070377 .40251817 -2.1549834 4.9759686 grade_8 1.5122648 1.5549938 .97252143 .35169152 -1.9102535 4.9347832 grade_9 1.628756 1.5730991 1.0353804 .32271721 -1.8336118 5.0911239 grade_10 1.6365916 1.5598587 1.0491922 .31659486 -1.7966341 5.0698173 grade_11 1.6983155 1.5473583 1.097558 .29584212 -1.7073972 5.1040282 grade_12 1.8264463 1.5377633 1.1877292 .25995385 -1.5581479 5.2110405 grade_13 1.8997993 1.5361525 1.2367257 .2419428 -1.4812495 5.2808482 grade_14 2.0223132 1.5213371 1.3292999 .21065999 -1.3261272 5.3707537 grade_15 2.1223076 1.5402117 1.3779324 .19560835 -1.2676755 5.5122906 grade_16 2.1468524 1.5511295 1.3840575 .19377784 -1.2671606 5.5608653 grade_17 2.2337052 1.5375016 1.4528149 .1741987 -1.1503131 5.6177235 age_20 2.2783805 1.5311463 1.4880228 .16484144 -1.0916497 5.6484107 age_21 -.23140168 .03610623 -6.4089133 .00005018 -.31087095 -.15193241 age_22 -.18467846 .05457368 -3.3840209 .00609903 -.30479431 -.06456261 age_23 -.15977494 .04435802 -3.6019407 .00415578 -.25740628 -.06214361 age_24 -.1419532 .04719393 -3.0078697 .01191113 -.24582634 -.03808005 age_25 -.14249686 .03533057 -4.0332457 .00197105 -.22025891 -.0647348 age_26 -.13181513 .02522067 -5.2264723 .00028267 -.18732545 -.07630481 age_27 -.09069022 .03964916 -2.2873177 .04297987 -.17795743 -.00342301 age_28 -.1064075 .03126711 -3.4031768 .00589591 -.17522594 -.03758906 age_29 -.11719028 .02928761 -4.00136 .00208135 -.18165188 -.05272868 age_30 -.10776638 .03024707 -3.5628706 .00445038 -.17433972 -.04119304 age_31 -.11077967 .03491967 -3.1724148 .00888033 -.18763734 -.033922 age_32 -.05495346 .03204163 -1.7150646 .11432974 -.12547661 .01556969 age_33 -.06657559 .02410911 -2.7614292 .01850851 -.11963937 -.0135118 age_34 -.05604086 .03011573 -1.8608502 .08968571 -.12232514 .01024341 age_35 -.06189889 .03218787 -1.9230504 .08073372 -.1327439 .00894613 age_36 -.03685251 .0296858 -1.2414191 .24027128 -.10219051 .02848548 age_37 -.0443038 .02986348 -1.4835446 .16600718 -.11003288 .02142527 age_38 -.0344549 .02255514 -1.5275849 .15484494 -.08409843 .01518864 age_39 -.03088389 .03271294 -.94408793 .36539952 -.10288457 .0411168 birth_yr_41 -.01766936 .0205526 -.85971408 .40829262 -.06290534 .02756661 birth_yr_42 .55476933 1.6908593 .32809905 .74899723 -3.1667869 4.2763256 birth_yr_43 .08090363 1.5299037 .05288152 .95877446 -3.2863918 3.448199 birth_yr_44 -.00923838 1.5051971 -.00613766 .99521279 -3.322155 3.3036782 birth_yr_45 .01683678 1.5256865 .01103555 .99139269 -3.3411767 3.3748502 birth_yr_46 .0395848 1.5202128 .02603898 .97969263 -3.3063809 3.3855505 birth_yr_47 .01284025 1.5079881 .00851482 .9933587 -3.3062191 3.3318996 birth_yr_48 .02587206 1.5139837 .01708873 .98667185 -3.3063837 3.3581278 birth_yr_49 .0387797 1.5192548 .02552547 .98009301 -3.3050775 3.3826369 birth_yr_50 .04691649 1.5155191 .03095737 .97585809 -3.2887186 3.3825516 birth_yr_51 .03974773 1.5237534 .02608541 .97965644 -3.314011 3.3935064 birth_yr_52 .03502286 1.5237008 .02298539 .98207359 -3.31862 3.3886657 birth_yr_53 .01947182 1.5179336 .01282784 .98999484 -3.3214775 3.3604212 birth_yr_53 .04385202 1.5126495 .0289902 .97739169 -3.2854672 3.3731712 Linear Regression -- CV3 -- Omitting Singular Omit-One-Cluster Subsamples
regresstabdrop[55,6] Coeff Sd. Err. t-stat P value CI-lower CI-upper msp -.02693984 .00670139 -4.0200395 .00301788 -.04209943 -.01178025 union .19892584 .0492246 4.0411872 .00292338 .08757205 .31027964 race -.0863069 .01412187 -6.1115766 .00017675 -.11825279 -.05436101 grade_0 1.5254807 .24290961 6.2800346 .00014437 .97598102 2.0749804 grade_1 1.5321952 .11879173 12.898164 4.154e-07 1.2634696 1.8009207 grade_2 1.5948664 .05461917 29.199758 3.161e-10 1.4713093 1.7184236 grade_3 1.4337071 .03036961 47.208615 4.301e-12 1.3650063 1.502408 grade_4 1.482975 .17405945 8.5199338 .00001334 1.0892251 1.8767248 grade_5 1.4397011 .0530426 27.142354 6.060e-10 1.3197104 1.5596918 grade_6 1.392753 .09893212 14.077865 1.955e-07 1.168953 1.616553 grade_7 1.4104926 .0305955 46.101316 5.320e-12 1.3412808 1.4797045 grade_8 1.5122648 .04407332 34.312481 7.486e-11 1.4125641 1.6119656 grade_9 1.628756 .03309808 49.209987 2.963e-12 1.553883 1.7036291 grade_10 1.6365916 .03027105 54.064589 1.274e-12 1.5681137 1.7050695 grade_11 1.6983155 .04484924 37.867212 3.100e-11 1.5968595 1.7997715 grade_12 1.8264463 .04818676 37.903489 3.074e-11 1.7174403 1.9354523 grade_13 1.8997993 .05370427 35.375201 5.700e-11 1.7783118 2.0212868 grade_14 2.0223132 .04536743 44.576326 7.193e-12 1.919685 2.1249415 grade_15 2.1223076 .06443564 32.936859 1.079e-10 1.976544 2.2680711 grade_16 2.1468524 .04766407 45.041319 6.554e-12 2.0390288 2.254676 grade_17 2.2337052 .03926509 56.887815 8.068e-13 2.1448814 2.322529 age_20 2.2783805 .04149541 54.906809 1.109e-12 2.1845113 2.3722496 age_21 -.23140168 .02631308 -8.7941686 .00001031 -.29092601 -.17187735 age_22 -.18467846 .03727956 -4.9538798 .0007871 -.26901068 -.10034624 age_23 -.15977494 .03421122 -4.6702496 .00116818 -.2371661 -.08238378 age_24 -.1419532 .03072991 -4.6193826 .00125545 -.21146907 -.07243732 age_25 -.14249686 .02668939 -5.3390836 .00046904 -.20287244 -.08212128 age_26 -.13181513 .02000524 -6.5890316 .00010054 -.17707012 -.08656015 age_27 -.09069022 .0322717 -2.8102093 .02037009 -.16369387 -.01768657 age_28 -.1064075 .02863872 -3.7155114 .00480385 -.17119279 -.04162221 age_29 -.11719028 .02844676 -4.119635 .00259936 -.18154133 -.05283923 age_30 -.10776638 .02481049 -4.3435811 .00186767 -.16389161 -.05164115 age_31 -.11077967 .0305838 -3.6221682 .00555296 -.17996503 -.04159431 age_32 -.05495346 .031094 -1.7673332 .11097223 -.12529298 .01538606 age_33 -.06657559 .0218068 -3.0529731 .01372673 -.11590601 -.01724517 age_34 -.05604086 .02974556 -1.8840076 .09221451 -.12333 .01124827 age_35 -.06189889 .03158625 -1.9596783 .08168663 -.13335195 .00955417 age_36 -.03685251 .02100713 -1.7542863 .11327696 -.08437394 .01066891 age_37 -.0443038 .02671514 -1.6583783 .1316167 -.10473765 .01613004 age_38 -.0344549 .01834714 -1.877944 .0931113 -.075959 .00704921 age_39 -.03088389 .026119 -1.1824301 .26733098 -.08996916 .02820139 birth_yr_41 -.01766936 .01973859 -.89516857 .39400765 -.06232115 .02698242 birth_yr_42 .55476933 .56058733 .9896216 .34821711 -.71336731 1.822906 birth_yr_43 .08090363 .0490327 1.6499933 .13334235 -.03001604 .1918233 birth_yr_44 -.00923838 .04787192 -.19298125 .85125832 -.1175322 .09905543 birth_yr_45 .01683678 .04521277 .37238997 .71822037 -.08544162 .11911518 birth_yr_46 .0395848 .03613013 1.0956173 .30169724 -.04214724 .12131683 birth_yr_47 .01284025 .03338732 .38458447 .70947513 -.06268712 .08836761 birth_yr_48 .02587206 .04828062 .5358684 .6050377 -.08334628 .1350904 birth_yr_49 .0387797 .04453096 .8708479 .40646599 -.06195634 .13951573 birth_yr_50 .04691649 .04809926 .97540976 .35484392 -.0618916 .15572458 birth_yr_51 .03974773 .04738512 .838823 .42328765 -.06744486 .14694031 birth_yr_52 .03502286 .04339815 .8070127 .440464 -.06315058 .1331963 birth_yr_53 .01947182 .03379989 .57609102 .57867298 -.05698886 .09593249 birth_yr_53 .04385202 .04731431 .92682356 .37820219 -.06318039 .15088442
Cluster by Cluster Statistics