[1] "Thu Dec 25 21:34:40 2014"
[1] "sensibilidad y especificidad"
[1] "pruebas simples"
[1] "modelos"
[1] "M10 IPMAF   vs Predictores, etapa 0"

Call:
svyglm(formula = IPMAF ~ EdadM + log(EdadM) + Sexo + ZHAZ + ZWHZ + 
    DOW + DOM + Estrato + ESQ + R24 + ESQ:R24 + FEU + FMU, SP, 
    family = quasibinomial)

Survey design:
svydesign(id = ~Cong1, strata = ~Estrato, weights = ~SWtC, fpc = ~SSG, 
    nest = TRUE, data = subset(eP, !is.na(eP$P1R)))

Coefficients:
                  Estimate Std. Error t value Pr(>|t|)  
(Intercept)       -18.5903     6.1570   -3.02    0.029 *
EdadM              -0.9834     0.3842   -2.56    0.051 .
log(EdadM)         10.8456     3.8511    2.82    0.037 *
SexoF               0.9254     0.6997    1.32    0.243  
ZHAZ               -0.0344     0.1889   -0.18    0.863  
ZWHZ                0.0679     0.2197    0.31    0.770  
DOW                -0.0481     0.1303   -0.37    0.727  
DOM                -0.4334     0.8938   -0.48    0.648  
EstratoMedio Alto  -1.6803     0.7862   -2.14    0.086 .
EstratoMedio       -0.5421     0.7859   -0.69    0.521  
EstratoMedio Bajo  -2.2538     1.4158   -1.59    0.172  
EstratoBajo        -0.6798     0.5542   -1.23    0.275  
ESQC3               0.1684     0.8566    0.20    0.852  
R24SR              -0.1604     0.8987   -0.18    0.865  
FEU                 0.9222     0.7545    1.22    0.276  
FMU                 0.1754     0.5241    0.33    0.751  
ESQC3:R24SR         0.8772     1.1997    0.73    0.497  
---
Signif. codes:  0 *** 0.001 ** 0.01 * 0.05 . 0.1   1

(Dispersion parameter for quasibinomial family taken to be 1.1687)

Number of Fisher Scoring iterations: 6

[1] "M01 IPMAF   vs Predictores, etapa I"

Call:
svyglm(formula = IPMAF ~ EdadM + log(EdadM) + ESQ + R24 + ESQ:R24 + 
    FEU + FMU, SP, family = quasibinomial)

Survey design:
svydesign(id = ~Cong1, strata = ~Estrato, weights = ~SWtC, fpc = ~SSG, 
    nest = TRUE, data = subset(eP, !is.na(eP$P1R)))

Coefficients:
            Estimate Std. Error t value Pr(>|t|)   
(Intercept) -17.0864     5.4945   -3.11   0.0077 **
EdadM        -0.8991     0.4378   -2.05   0.0592 . 
log(EdadM)   10.1673     4.9789    2.04   0.0605 . 
ESQC3         0.2272     0.7460    0.30   0.7652   
R24SR        -0.0192     0.6598   -0.03   0.9772   
FEU           0.4190     1.1848    0.35   0.7289   
FMU           0.6754     0.5819    1.16   0.2651   
ESQC3:R24SR   0.4627     1.0511    0.44   0.6665   
---
Signif. codes:  0 *** 0.001 ** 0.01 * 0.05 . 0.1   1

(Dispersion parameter for quasibinomial family taken to be 1.5653)

Number of Fisher Scoring iterations: 5

[1] "M06 IPMAF   vs Predictores, etapa II"

Call:
svyglm(formula = IPMAF ~ EdadM + log(EdadM) + R24, SP, family = quasibinomial)

Survey design:
svydesign(id = ~Cong1, strata = ~Estrato, weights = ~SWtC, fpc = ~SSG, 
    nest = TRUE, data = subset(eP, !is.na(eP$P1R)))

Coefficients:
            Estimate Std. Error t value Pr(>|t|)
(Intercept)   1.3925     0.8232    1.69     0.11
EdadM        -0.0853     0.1045   -0.82     0.43
log(EdadM)   -0.8108     0.6416   -1.26     0.22
R24SR         0.1306     0.5395    0.24     0.81

(Dispersion parameter for quasibinomial family taken to be 1.0143)

Number of Fisher Scoring iterations: 4

[1] "M08 IPMAF   vs Esquema y Nivel, magnitud"

Call:
svyglm(formula = IPMAF ~ R24, SP, family = quasibinomial)

Survey design:
svydesign(id = ~Cong1, strata = ~Estrato, weights = ~SWtC, fpc = ~SSG, 
    nest = TRUE, data = subset(eP, !is.na(eP$P1R)))

Coefficients:
            Estimate Std. Error t value Pr(>|t|)  
(Intercept)   -1.307      0.505   -2.59    0.018 *
R24SR          0.382      0.517    0.74    0.469  
---
Signif. codes:  0 *** 0.001 ** 0.01 * 0.05 . 0.1   1

(Dispersion parameter for quasibinomial family taken to be 0.99928)

Number of Fisher Scoring iterations: 4

[1] "M11 GFREM01 vs Predictores, etapa 0"

Call:
svyglm(formula = GFREM01 ~ EdadM + log(EdadM) + Sexo + ZHAZ + 
    ZWHZ + DOW + DOM + Estrato + ESQ + R24 + ESQ:R24 + FEU + 
    FMU, SP, family = quasibinomial)

Survey design:
svydesign(id = ~Cong1, strata = ~Estrato, weights = ~SWtC, fpc = ~SSG, 
    nest = TRUE, data = subset(eP, !is.na(eP$P1R)))

Coefficients:
                  Estimate Std. Error t value Pr(>|t|)    
(Intercept)          9.322     17.657    0.53   0.6201    
EdadM                0.270      0.460    0.59   0.5824    
log(EdadM)          -4.926      6.114   -0.81   0.4570    
SexoF                1.305      0.472    2.77   0.0396 *  
ZHAZ                 0.304      0.382    0.79   0.4630    
ZWHZ                 0.109      0.245    0.45   0.6746    
DOW                 -0.008      0.160   -0.05   0.9620    
DOM                 -3.615      1.377   -2.63   0.0468 *  
EstratoMedio Alto    0.118      1.961    0.06   0.9542    
EstratoMedio        17.890      1.378   12.99  4.8e-05 ***
EstratoMedio Bajo    1.002      1.140    0.88   0.4197    
EstratoBajo          0.910      1.124    0.81   0.4550    
ESQC3               -1.682      1.611   -1.04   0.3444    
R24SR               17.247      1.160   14.87  2.5e-05 ***
FEU                  1.471      2.321    0.63   0.5541    
FMU                 -0.342      0.820   -0.42   0.6937    
ESQC3:R24SR        -15.181      1.708   -8.89   0.0003 ***
---
Signif. codes:  0 *** 0.001 ** 0.01 * 0.05 . 0.1   1

(Dispersion parameter for quasibinomial family taken to be 0.45665)

Number of Fisher Scoring iterations: 19

[1] "M02 GFREM01 vs Predictores, etapa I"

Call:
svyglm(formula = GFREM01 ~ EdadM + log(EdadM) + ESQ + R24 + ESQ:R24 + 
    FEU + FMU, SP, family = quasibinomial)

Survey design:
svydesign(id = ~Cong1, strata = ~Estrato, weights = ~SWtC, fpc = ~SSG, 
    nest = TRUE, data = subset(eP, !is.na(eP$P1R)))

Coefficients:
            Estimate Std. Error t value Pr(>|t|)    
(Intercept)   6.3403     9.7019    0.65     0.52    
EdadM         0.0284     0.2912    0.10     0.92    
log(EdadM)   -1.6014     4.0819   -0.39     0.70    
ESQC3        -1.3964     1.1837   -1.18     0.26    
R24SR        16.4396     0.9121   18.02  4.4e-11 ***
FEU           0.2874     1.7871    0.16     0.87    
FMU           0.1466     0.8163    0.18     0.86    
ESQC3:R24SR -14.6548     1.6335   -8.97  3.5e-07 ***
---
Signif. codes:  0 *** 0.001 ** 0.01 * 0.05 . 0.1   1

(Dispersion parameter for quasibinomial family taken to be 0.77044)

Number of Fisher Scoring iterations: 18

[1] "M07 GFREM01 vs Predictores, etapa II"

Call:
svyglm(formula = GFREM01 ~ EdadM + log(EdadM) + R24, SP, family = quasibinomial)

Survey design:
svydesign(id = ~Cong1, strata = ~Estrato, weights = ~SWtC, fpc = ~SSG, 
    nest = TRUE, data = subset(eP, !is.na(eP$P1R)))

Coefficients:
            Estimate Std. Error t value Pr(>|t|)    
(Intercept)  -16.091      3.875   -4.15  0.00060 ***
EdadM         -0.883      0.201   -4.40  0.00035 ***
log(EdadM)    12.148      2.696    4.51  0.00027 ***
R24SR          1.052      0.519    2.03  0.05769 .  
---
Signif. codes:  0 *** 0.001 ** 0.01 * 0.05 . 0.1   1

(Dispersion parameter for quasibinomial family taken to be 0.88916)

Number of Fisher Scoring iterations: 8

[1] "M09 GFREM01 vs Esquema y Nivel, magnitud"

Call:
svyglm(formula = GFREM01 ~ R24, SP, family = quasibinomial)

Survey design:
svydesign(id = ~Cong1, strata = ~Estrato, weights = ~SWtC, fpc = ~SSG, 
    nest = TRUE, data = subset(eP, !is.na(eP$P1R)))

Coefficients:
            Estimate Std. Error t value Pr(>|t|)   
(Intercept)    1.278      0.350    3.65   0.0016 **
R24SR         -0.236      0.392   -0.60   0.5537   
---
Signif. codes:  0 *** 0.001 ** 0.01 * 0.05 . 0.1   1

(Dispersion parameter for quasibinomial family taken to be 1.0146)

Number of Fisher Scoring iterations: 4

[1] "M03 Macronutrientes vs. AMA"

Call:
svyglm(formula = DEUP ~ IPMAF, SP, family = gaussian)

Survey design:
svydesign(id = ~Cong1, strata = ~Estrato, weights = ~SWtC, fpc = ~SSG, 
    nest = TRUE, data = subset(eP, !is.na(eP$P1R)))

Coefficients:
             Estimate Std. Error t value Pr(>|t|)  
(Intercept)  6.35e-09   3.18e-09    2.00    0.059 .
IPMAF       -6.33e-09   3.18e-09   -1.99    0.060 .
---
Signif. codes:  0 *** 0.001 ** 0.01 * 0.05 . 0.1   1

(Dispersion parameter for gaussian family taken to be 1.1669e-13)

Number of Fisher Scoring iterations: 1

[1] "M04 Micronutrientes vs. AMA"

Call:
svyglm(formula = DMUP ~ IPMAF, SP, family = gaussian)

Survey design:
svydesign(id = ~Cong1, strata = ~Estrato, weights = ~SWtC, fpc = ~SSG, 
    nest = TRUE, data = subset(eP, !is.na(eP$P1R)))

Coefficients:
            Estimate Std. Error t value Pr(>|t|)   
(Intercept) -0.03921    0.01068   -3.67   0.0015 **
IPMAF       -0.00886    0.03694   -0.24   0.8128   
---
Signif. codes:  0 *** 0.001 ** 0.01 * 0.05 . 0.1   1

(Dispersion parameter for gaussian family taken to be 0.013329)

Number of Fisher Scoring iterations: 2

[1] "M05 Vitamina A Usual vs GDVA"

Call:
svyglm(formula = VFU ~ GFREM01, SP, family = gaussian)

Survey design:
svydesign(id = ~Cong1, strata = ~Estrato, weights = ~SWtC, fpc = ~SSG, 
    nest = TRUE, data = subset(eP, !is.na(eP$P1R)))

Coefficients:
            Estimate Std. Error t value Pr(>|t|)  
(Intercept)  -0.1626     0.0728   -2.23    0.037 *
GFREM01      -0.0823     0.0813   -1.01    0.323  
---
Signif. codes:  0 *** 0.001 ** 0.01 * 0.05 . 0.1   1

(Dispersion parameter for gaussian family taken to be 0.18447)

Number of Fisher Scoring iterations: 2

