ANNEXES
. biprobit IQS IQI PAUVRE M_EFFORT NETUDE2 NETUDE3 NETUDE4
LOC3 MPROM STATUT2 STATUT3 GENRE2 GENRE3 GENRE4 TYPEH4 TYPEH5 TYPEH6
Bivariate probit regression Number of obs
= 802
Wald chi2(30)
= 229.19
Log likelihood = -719.18279 Prob > chi2
= 0.0000
------------------------------------------------------------------------------
| Coef. Std. Err. z P>|z| [95%
Conf. Interval]
-------------+----------------------------------------------------------------
IQS |
PAUVRE | -.352008 .1325887 -2.65 0.008
-.611877 -.092139
M_EFFORT | 4.46e-06 8.08e-07 5.51 0.000
2.87e-06 6.04e-06
NETUDE2 | .0913988 .1539762 0.59 0.553
-.2103889 .3931865
NETUDE3 | -.1069213 .3659873 -0.29 0.770
-.8242433 .6104007
NETUDE4 | .1628033 .2093816 0.78 0.437
-.2475772 .5731837
LOC3 | -.3321874 .1703905 -1.95 0.051
-.6661467 .0017719
MPROM | .003398 .027552 0.12 0.902
-.0506029 .057399
STATUT2 | .1162616 .2588931 0.45 0.653
-.3911596 .6236828
STATUT3 | .393065 .2460161 1.60 0.110
-.0891176 .8752477
GENRE2 | .4277027 .3148316 1.36 0.174
-.189356 1.044761
GENRE3 | .1784031 .2324278 0.77 0.443
-.2771471 .6339533
GENRE4 | .0671506 .3078579 0.22 0.827
-.5362399 .6705411
TYPEH4 | -.2734055 .3098836 -0.88 0.378
-.8807661 .3339552
TYPEH5 | .2132881 .5531629 0.39 0.700
-.8708912 1.297467
TYPEH6 | -.6389286 .3427922 -1.86 0.062
-1.310789 .0329318
_cons | 1.521197 .4330525 3.51 0.000
.6724301 2.369965
-------------+----------------------------------------------------------------
IQI |
PAUVRE | -.312502 .1243213 -2.51 0.012
-.5561673 -.0688366
M_EFFORT | 9.40e-07 2.48e-07 3.80 0.000
4.55e-07 1.43e-06
NETUDE2 | .4888503 .1716514 2.85 0.004
.1524198 .8252808
NETUDE3 | .8892736 .304487 2.92 0.003
.2924901 1.486057
NETUDE4 | .7430802 .1918359 3.87 0.000
.3670886 1.119072
LOC3 | -.5812157 .116692 -4.98 0.000
-.8099278 -.3525035
MPROM | -.0345196 .0259731 -1.33 0.184
-.085426 .0163868
STATUT2 | .232002 .2416376 0.96 0.337
-.241599 .705603
STATUT3 | .3609945 .2365828 1.53 0.127
-.1026994 .8246884
GENRE2 | -.023685 .2787394 -0.08 0.932
-.5700042 .5226342
GENRE3 | .1352361 .2266918 0.60 0.551
-.3090717 .5795438
GENRE4 | .1899455 .2888327 0.66 0.511
-.3761561 .7560471
TYPEH4 | -.1779087 .2054848 -0.87 0.387
-.5806516 .2248341
TYPEH5 | .4853476 .2923156 1.66 0.097
-.0875805 1.058276
TYPEH6 | -.5059752 .2641893 -1.92 0.055
-1.023777 .0118263
_cons | -.6801188 .3623371 -1.88 0.061
-1.390286 .0300489
-------------+----------------------------------------------------------------
/athrho | .2837643 .0923895 3.07 0.002
.1026842 .4648444
-------------+----------------------------------------------------------------
rho | .2763854 .085332
.1023248 .4340243
------------------------------------------------------------------------------
Likelihood-ratio test of rho=0: chi2(1) = 9.75604 Prob
> chi2 = 0.0018
. test NETUDE2 NETUDE3 NETUDE4
( 1) [IQS]NETUDE2 = 0
( 2) [IQI]NETUDE2 = 0
( 3) [IQS]NETUDE3 = 0
( 4) [IQI]NETUDE3 = 0
( 5) [IQS]NETUDE4 = 0
( 6) [IQI]NETUDE4 = 0
chi2( 6) = 17.98
Prob > chi2 = 0.0063
. test STATUT2 STATUT3
( 1) [IQS]STATUT2 = 0
( 2) [IQI]STATUT2 = 0
( 3) [IQS]STATUT3 = 0
( 4) [IQI]STATUT3 = 0
chi2( 4) = 7.81
Prob > chi2 = 0.0986
. test GENRE2 GENRE3 GENRE4
( 1) [IQS]GENRE2 = 0
( 2) [IQI]GENRE2 = 0
( 3) [IQS]GENRE3 = 0
( 4) [IQI]GENRE3 = 0
( 5) [IQS]GENRE4 = 0
( 6) [IQI]GENRE4 = 0
chi2( 6) = 3.60
Prob > chi2 = 0.7307
. test TYPEH4 TYPEH5 TYPEH6
( 1) [IQS]TYPEH4 = 0
( 2) [IQI]TYPEH4 = 0
( 3) [IQS]TYPEH5 = 0
( 4) [IQI]TYPEH5 = 0
( 5) [IQS]TYPEH6 = 0
( 6) [IQI]TYPEH6 = 0
chi2( 6) = 18.00
Prob > chi2 = 0.0062
. estat ic
------------------------------------------------------------------------------
Model | Obs ll(null) ll(model) df AIC
BIC
-------------+----------------------------------------------------------------
. | 802 . -719.1828 33 1504.366
1659.04
------------------------------------------------------------------------------
. estat summarize
Estimation sample biprobit Number of obs =
802
-------------------------------------------------------------
Variable | Mean Std. Dev. Min
Max
-------------+-----------------------------------------------
IQS | .8229426 .3819554 0
1
IQI | .3503741 .4773848 0
1
PAUVRE | .3067332 .4614254 0
1
M_EFFORT | 3623.385 441724.5 -231860
7.8e+06
NETUDE2 | .5710723 .4952318 0
1
NETUDE3 | .032419 .1772206 0
1
NETUDE4 | .2468828 .431467 0
1
LOC3 | .6845387 .4649893 0
1
MPROM | .0002813 2.258075 -3.63093
11.2024
STATUT2 | .3840399 .4866709 0
1
STATUT3 | .5448878 .4982918 0
1
GENRE2 | .0935162 .2913362 0
1
GENRE3 | .7793017 .4149762 0
1
GENRE4 | .0723192 .2591773 0
1
TYPEH4 | .7605985 .4269845 0
1
TYPEH5 | .0573566 .2326678 0
1
TYPEH6 | .0947631 .2930702 0
1
-------------------------------------------------------------
. mfx compute, dydx at(mean)
Marginal effects after biprobit
y = Pr(IQS=1,IQI=1) (predict)
= .3218205
------------------------------------------------------------------------------
variable | dy/dx Std. Err. z P>|z| [ 95%
C.I. ] X
---------+--------------------------------------------------------------------
PAUVRE*| -.1134412 .04007 -2.83 0.005 -.191977
-.034905 .306733
M_EFFORT | 4.39e-07 .00000 4.70 0.000 2.6e-07
6.2e-07 3623.39
NETUDE2*| .1674786 .05632 2.97 0.003 .057096
.277861 .571072
NETUDE3*| .3142797 .10794 2.91 0.004 .102721
.525839 .032419
NETUDE4*| .2727488 .06995 3.90 0.000 .135651
.409847 .246883
LOC3*| -.2161857 .04274 -5.06 0.000 -.299959
-.132412 .684539
MPROM | -.0118528 .00909 -1.30 0.192 -.029668
.005962 .000281
STATUT2*| .084071 .08592 0.98 0.328 -.084334
.252476 .38404
STATUT3*| .1333087 .08011 1.66 0.096 -.023711
.290329 .544888
GENRE2*| -.000431 .09881 -0.00 0.997 -.194105
.193243 .093516
GENRE3*| .0504816 .07591 0.67 0.506 -.098302
.199265 .779302
GENRE4*| .0696082 .10722 0.65 0.516 -.140539
.279756 .072319
TYPEH4*| -.0695398 .07518 -0.93 0.355 -.216883
.077803 .760599
TYPEH5*| .1851111 .11394 1.62 0.104 -.038201
.408423 .057357
TYPEH6*| -.1702348 .06727 -2.53 0.011 -.302082
-.038388 .094763
------------------------------------------------------------------------------
(*) dy/dx is for discrete change of dummy variable from 0 to 1
. mfx compute, dyex at(mean)
Elasticities after biprobit
y = Pr(IQS=1,IQI=1) (predict)
= .3218205
------------------------------------------------------------------------------
variable | dy/ex Std. Err. z P>|z| [ 95%
C.I. ] X
---------+--------------------------------------------------------------------
PAUVRE | -.0359179 .01329 -2.70 0.007 -.06197
-.009866 .306733
M_EFFORT | .0015913 .00034 4.70 0.000 .000927
.002255 3623.39
NETUDE2 | .0978961 .03399 2.88 0.004 .031271
.164521 .571072
NETUDE3 | .0098829 .00345 2.86 0.004 .003112
.016653 .032419
NETUDE4 | .0644825 .01644 3.92 0.000 .032254
.096711 .246883
LOC3 | -.1434349 .02804 -5.12 0.000 -.198386
-.088483 .684539
MPROM | -3.33e-06 .00000 -1.30 0.192 -8.3e-06
1.7e-06 .000281
STATUT2 | .0319603 .03241 0.99 0.324 -.031562
.095482 .38404
STATUT3 | .0735173 .04502 1.63 0.102 -.014713
.161747 .544888
GENRE2 | .0002575 .00914 0.03 0.978 -.01766
.018175 .093516
GENRE3 | .0400108 .06184 0.65 0.518 -.081194
.161215 .779302
GENRE4 | .0048756 .00732 0.67 0.505 -.009462
.019213 .072319
TYPEH4 | -.052126 .05489 -0.95 0.342 -.159712
.05546 .760599
TYPEH5 | .0099418 .00593 1.68 0.094 -.001687
.02157 .057357
TYPEH6 | -.0181339 .00876 -2.07 0.038 -.035297
-.000971 .094763
------------------------------------------------------------------------------
. probit IQS PAUVRE M_EFFORT NETUDE2 NETUDE3 NETUDE4 LOC3
MPROM STATUT2 STATUT3 GENRE2 GENRE3 GENRE4 TYPEH4 TYPEH5 TYPEH6
Probit regression Number of obs
= 802
LR chi2(15)
= 141.39
Prob > chi2
= 0.0000
Log likelihood = -303.76093 Pseudo R2
= 0.1888
------------------------------------------------------------------------------
IQS | Coef. Std. Err. z P>|z| [95%
Conf. Interval]
-------------+----------------------------------------------------------------
PAUVRE | -.3361712 .1330708 -2.53 0.012
-.5969852 -.0753572
M_EFFORT | 4.69e-06 8.18e-07 5.74 0.000
3.09e-06 6.29e-06
NETUDE2 | .0968035 .153961 0.63 0.530
-.2049546 .3985615
NETUDE3 | -.045758 .3705613 -0.12 0.902
-.7720448 .6805288
NETUDE4 | .2045312 .2094031 0.98 0.329
-.2058914 .6149538
LOC3 | -.3021582 .1702894 -1.77 0.076
-.6359192 .0316028
MPROM | .0058747 .0276861 0.21 0.832
-.048389 .0601385
STATUT2 | .1089448 .258726 0.42 0.674
-.3981487 .6160384
STATUT3 | .4066412 .2454672 1.66 0.098
-.0744656 .8877481
GENRE2 | .4237278 .315327 1.34 0.179
-.1943017 1.041757
GENRE3 | .1597309 .2332499 0.68 0.493
-.2974305 .6168923
GENRE4 | .083946 .3111837 0.27 0.787
-.5259628 .6938548
TYPEH4 | -.2568133 .312542 -0.82 0.411
-.8693845 .3557578
TYPEH5 | .2565094 .5752346 0.45 0.656
-.8709297 1.383948
TYPEH6 | -.6287403 .3450195 -1.82 0.068
-1.304966 .0474856
_cons | 1.495613 .4376921 3.42 0.001
.6377519 2.353473
------------------------------------------------------------------------------
Note: 0 failures and 20 successes completely determined.
. test NETUDE2 NETUDE3 NETUDE4
( 1) NETUDE2 = 0
( 2) NETUDE3 = 0
( 3) NETUDE4 = 0
chi2( 3) = 1.12
Prob > chi2 = 0.7715
. test STATUT2 STATUT3
( 1) STATUT2 = 0
( 2) STATUT3 = 0
chi2( 2) = 6.25
Prob > chi2 = 0.0440
. test GENRE2 GENRE3 GENRE4
( 1) GENRE2 = 0
( 2) GENRE3 = 0
( 3) GENRE4 = 0
chi2( 3) = 2.05
Prob > chi2 = 0.5624
. test TYPEH4 TYPEH5 TYPEH6
( 1) TYPEH4 = 0
( 2) TYPEH5 = 0
( 3) TYPEH6 = 0
chi2( 3) = 6.54
Prob > chi2 = 0.0880
. estat ic
------------------------------------------------------------------------------
Model | Obs ll(null) ll(model) df AIC
BIC
-------------+----------------------------------------------------------------
. | 802 -374.4554 -303.7609 16 639.5219
714.5156
------------------------------------------------------------------------------
. mfx compute, dydx at(mean)
Marginal effects after probit
y = Pr(IQS) (predict)
= .93323711
------------------------------------------------------------------------------
variable | dy/dx Std. Err. z P>|z| [ 95%
C.I. ] X
---------+--------------------------------------------------------------------
PAUVRE*| -.0481097 .02299 -2.09 0.036 -.093164
-.003055 .306733
M_EFFORT | 6.07e-07 .00000 9.12 0.000 4.8e-07
7.4e-07 3623.39
NETUDE2*| .0126671 .02045 0.62 0.536 -.027405
.052739 .571072
NETUDE3*| -.0061159 .05111 -0.12 0.905 -.106292
.09406 .032419
NETUDE4*| .0245252 .02345 1.05 0.296 -.021437
.070488 .246883
LOC3*| -.036113 .02014 -1.79 0.073 -.075594
.003368 .684539
MPROM | .0007605 .00359 0.21 0.832 -.006268
.007789 .000281
STATUT2*| .0138459 .03269 0.42 0.672 -.050227
.077919 .38404
STATUT3*| .0545345 .03565 1.53 0.126 -.015329
.124398 .544888
GENRE2*| .0422942 .02425 1.74 0.081 -.005234
.089822 .093516
GENRE3*| .022113 .03468 0.64 0.524 -.045856
.090082 .779302
GENRE4*| .0102945 .03613 0.28 0.776 -.060526
.081115 .072319
TYPEH4*| -.0301212 .03311 -0.91 0.363 -.095013
.03477 .760599
TYPEH5*| .0279465 .05164 0.54 0.588 -.073261
.129154 .057357
TYPEH6*| -.1164904 .08565 -1.36 0.174 -.284361
.05138 .094763
------------------------------------------------------------------------------
(*) dy/dx is for discrete change of dummy variable from 0 to 1
. mfx compute, dyex at(mean)
Elasticities after probit
y = Pr(IQS) (predict)
= .93323711
------------------------------------------------------------------------------
variable | dy/ex Std. Err. z P>|z| [ 95%
C.I. ] X
---------+--------------------------------------------------------------------
PAUVRE | -.0133483 .00593 -2.25 0.024 -.024964
-.001733 .306733
M_EFFORT | .0022008 .00024 9.12 0.000 .001728
.002674 3623.39
NETUDE2 | .0071563 .01142 0.63 0.531 -.015234
.029547 .571072
NETUDE3 | -.000192 .00156 -0.12 0.902 -.00324
.002856 .032419
NETUDE4 | .0065367 .00674 0.97 0.332 -.006676
.019749 .246883
LOC3 | -.0267755 .01597 -1.68 0.094 -.058086
.004534 .684539
MPROM | 2.14e-07 .00000 0.21 0.832 -1.8e-06
2.2e-06 .000281
STATUT2 | .0054161 .01302 0.42 0.677 -.020093
.030925 .38404
STATUT3 | .028683 .01807 1.59 0.112 -.006732
.064098 .544888
GENRE2 | .0051296 .00387 1.33 0.185 -.002452
.012711 .093516
GENRE3 | .0161139 .02371 0.68 0.497 -.030357
.062584 .779302
GENRE4 | .0007859 .00292 0.27 0.788 -.00493
.006502 .072319
TYPEH4 | -.0252859 .03072 -0.82 0.410 -.085486
.034914 .760599
TYPEH5 | .0019046 .00426 0.45 0.655 -.00644
.010249 .057357
TYPEH6 | -.0077129 .00439 -1.76 0.079 -.016326
.000901 .094763
------------------------------------------------------------------------------
. probit IQI PAUVRE M_EFFORT NETUDE2 NETUDE3 NETUDE4 LOC3
MPROM STATUT2 STATUT3 GENRE2 GENRE3 GENRE4 TYPEH4 TYPEH5 TYPEH6
Probit regression Number of obs
= 802
LR chi2(15)
= 198.28
Prob > chi2
= 0.0000
Log likelihood = -420.29988 Pseudo R2
= 0.1909
------------------------------------------------------------------------------
IQI | Coef. Std. Err. z P>|z| [95%
Conf. Interval]
-------------+----------------------------------------------------------------
PAUVRE | -.309579 .1243907 -2.49 0.013
-.5533803 -.0657778
M_EFFORT | 9.40e-07 2.48e-07 3.79 0.000
4.54e-07 1.43e-06
NETUDE2 | .4952073 .1720466 2.88 0.004
.1580022 .8324123
NETUDE3 | .8976417 .3052243 2.94 0.003
.299413 1.49587
NETUDE4 | .7463351 .1919883 3.89 0.000
.3700449 1.122625
LOC3 | -.5817448 .1167157 -4.98 0.000
-.8105033 -.3529863
MPROM | -.0342869 .0260656 -1.32 0.188
-.0853746 .0168008
STATUT2 | .2161808 .2410807 0.90 0.370
-.2563287 .6886902
STATUT3 | .3544155 .2359466 1.50 0.133
-.1080312 .8168623
GENRE2 | .0047049 .2798087 0.02 0.987
-.5437102 .55312
GENRE3 | .1574288 .2287225 0.69 0.491
-.2908591 .6057167
GENRE4 | .2123179 .2914418 0.73 0.466
-.3588976 .7835334
TYPEH4 | -.1852043 .2046241 -0.91 0.365
-.5862601 .2158516
TYPEH5 | .4806323 .2923771 1.64 0.100
-.0924163 1.053681
TYPEH6 | -.4964143 .2625991 -1.89 0.059
-1.011099 .0182706
_cons | -.692406 .3645227 -1.90 0.058
-1.406857 .0220454
------------------------------------------------------------------------------
Note: 0 failures and 1 success completely determined.
. test NETUDE2 NETUDE3 NETUDE4
( 1) NETUDE2 = 0
( 2) NETUDE3 = 0
( 3) NETUDE4 = 0
chi2( 3) = 17.35
Prob > chi2 = 0.0006
. test STATUT2 STATUT3
( 1) STATUT2 = 0
( 2) STATUT3 = 0
chi2( 2) = 3.05
Prob > chi2 = 0.2172
. test GENRE2 GENRE3 GENRE4
( 1) GENRE2 = 0
( 2) GENRE3 = 0
( 3) GENRE4 = 0
chi2( 3) = 1.31
Prob > chi2 = 0.7264
. test TYPEH4 TYPEH5 TYPEH6
( 1) TYPEH4 = 0
( 2) TYPEH5 = 0
( 3) TYPEH6 = 0
chi2( 3) = 12.64
Prob > chi2 = 0.0055
. predict probiqi
(option p assumed; Pr(IQI))
(1279 missing values generated)
. estat ic
------------------------------------------------------------------------------
Model | Obs ll(null) ll(model) df AIC
BIC
-------------+----------------------------------------------------------------
. | 802 -519.4377 -420.2999 16 872.5998
947.5935
------------------------------------------------------------------------------
. estat summarize
Estimation sample probit Number of obs =
802
-------------------------------------------------------------
Variable | Mean Std. Dev. Min
Max
-------------+-----------------------------------------------
IQI | .3503741 .4773848 0
1
PAUVRE | .3067332 .4614254 0
1
M_EFFORT | 3623.385 441724.5 -231860
7.8e+06
NETUDE2 | .5710723 .4952318 0
1
NETUDE3 | .032419 .1772206 0
1
NETUDE4 | .2468828 .431467 0
1
LOC3 | .6845387 .4649893 0
1
MPROM | .0002813 2.258075 -3.63093
11.2024
STATUT2 | .3840399 .4866709 0
1
STATUT3 | .5448878 .4982918 0
1
GENRE2 | .0935162 .2913362 0
1
GENRE3 | .7793017 .4149762 0
1
GENRE4 | .0723192 .2591773 0
1
TYPEH4 | .7605985 .4269845 0
1
TYPEH5 | .0573566 .2326678 0
1
TYPEH6 | .0947631 .2930702 0
1
-------------------------------------------------------------
. mfx compute, dydx at(mean)
Marginal effects after probit
y = Pr(IQI) (predict)
= .33295741
------------------------------------------------------------------------------
variable | dy/dx Std. Err. z P>|z| [ 95%
C.I. ] X
---------+--------------------------------------------------------------------
PAUVRE*| -.1091167 .04211 -2.59 0.010 -.191652
-.026582 .306733
M_EFFORT | 3.41e-07 .00000 3.73 0.000 1.6e-07
5.2e-07 3623.39
NETUDE2*| .1757471 .05868 2.99 0.003 .060729
.290765 .571072
NETUDE3*| .3464156 .11063 3.13 0.002 .129586
.563245 .032419
NETUDE4*| .2829009 .07244 3.91 0.000 .140931
.424871 .246883
LOC3*| -.217439 .04386 -4.96 0.000 -.303402
-.131476 .684539
MPROM | -.0124612 .00947 -1.32 0.188 -.031023
.006101 .000281
STATUT2*| .0792694 .08892 0.89 0.373 -.095012
.253551 .38404
STATUT3*| .1273767 .08339 1.53 0.127 -.03607
.290824 .544888
GENRE2*| .0017113 .10186 0.02 0.987 -.197931
.201354 .093516
GENRE3*| .0560406 .07957 0.70 0.481 -.099918
.211999 .779302
GENRE4*| .0797871 .11253 0.71 0.478 -.140764
.300338 .072319
TYPEH4*| -.068564 .07696 -0.89 0.373 -.219403
.082275 .760599
TYPEH5*| .1854992 .11602 1.60 0.110 -.041904
.412902 .057357
TYPEH6*| -.1610999 .07343 -2.19 0.028 -.305011
-.017189 .094763
------------------------------------------------------------------------------
(*) dy/dx is for discrete change of dummy variable from 0 to 1
. mfx compute, dyex at(mean)
Elasticities after probit
y = Pr(IQI) (predict)
= .33295741
------------------------------------------------------------------------------
variable | dy/ex Std. Err. z P>|z| [ 95%
C.I. ] X
---------+--------------------------------------------------------------------
PAUVRE | -.0345114 .01381 -2.50 0.012 -.061579
-.007444 .306733
M_EFFORT | .0012374 .00033 3.73 0.000 .000588
.001887 3623.39
NETUDE2 | .1027799 .03547 2.90 0.004 .033263
.172297 .571072
NETUDE3 | .0105763 .00358 2.95 0.003 .003558
.017595 .032419
NETUDE4 | .066966 .01708 3.92 0.000 .033491
.100441 .246883
LOC3 | -.1447306 .02895 -5.00 0.000 -.201467
-.087994 .684539
MPROM | -3.51e-06 .00000 -1.32 0.188 -8.7e-06
1.7e-06 .000281
STATUT2 | .0301733 .03361 0.90 0.369 -.035707
.096053 .38404
STATUT3 | .0701859 .04667 1.50 0.133 -.021285
.161657 .544888
GENRE2 | .0001599 .00951 0.02 0.987 -.018479
.018799 .093516
GENRE3 | .0445882 .06477 0.69 0.491 -.082353
.171529 .779302
GENRE4 | .0055805 .00766 0.73 0.466 -.009432
.020593 .072319
TYPEH4 | -.051196 .05656 -0.91 0.365 -.162052
.05966 .760599
TYPEH5 | .010019 .00611 1.64 0.101 -.001947
.021985 .057357
TYPEH6 | -.0170967 .00903 -1.89 0.058 -.034795
.000602 .094763
------------------------------------------------------------------------------
1: AFC entre les types de matériau des murs et le
type de quartiers
2: AFC entre le type de matériau de la toiture
des logements et le type de quartiers
3: AFC entre le type de matériau du pavement des
logements et le type de quartiers
4: AFC entre le type de toilettes utilisées et
le type de quartiers
| 
