Regresiones Ellipticity v6

library(readxl)
library(ggplot2)
library(CGPfunctions)
library(plotly)
library(lmtest)

#Definir directorio
setwd("G:/TRABAJO/CONSULTORIAS/TRABAJOS VARIOS/JORGE CHAVARRIA/analisis4")

data1 = read_excel("Bicuspid4.xlsx")
head(data1,5)

Modelo 1

mod1=lm(Ellipticity ~ 
        Predilatation + Postdilation +
        Raphaecalcification +
        SVDmax +
        ICD4mm + 
        CCV
        , 
        data = data1)
summary(mod1)

Call:
lm(formula = Ellipticity ~ Predilatation + Postdilation + Raphaecalcification + 
    SVDmax + ICD4mm + CCV, data = data1)

Residuals:
     Min       1Q   Median       3Q      Max 
-0.07665 -0.02952 -0.00092  0.02322  0.11700 

Coefficients:
                      Estimate Std. Error t value Pr(>|t|)    
(Intercept)          1.119e+00  4.281e-02  26.136   <2e-16 ***
Predilatation        7.993e-04  8.773e-03   0.091   0.9276    
Postdilation        -9.231e-03  9.642e-03  -0.957   0.3409    
Raphaecalcification  1.648e-02  8.671e-03   1.901   0.0605 .  
SVDmax              -2.460e-03  1.293e-03  -1.902   0.0602 .  
ICD4mm               1.915e-03  2.116e-03   0.905   0.3678    
CCV                  6.266e-06  7.988e-06   0.784   0.4349    
---
Signif. codes:  0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1

Residual standard error: 0.0393 on 92 degrees of freedom
Multiple R-squared:  0.09752,   Adjusted R-squared:  0.03866 
F-statistic: 1.657 on 6 and 92 DF,  p-value: 0.1406

Calculos Intervalo de confianza Regresion Lineal Modelo 1

# Obtener el resumen del modelo
summary_mod1 <- summary(mod1)

# Extraer los coeficientes
coefficients <- coef(summary_mod1)[, 1]

# Extraer los intervalos de confianza
conf_intervals <- confint(mod1)

# Extraer los p-values
p_values <- summary_mod1$coefficients[, 4]

# Crear el data frame consolidado
consolidado1 <- data.frame(Coefficient = coefficients,
                          Lower_CI = conf_intervals[, 1],
                          Upper_CI = conf_intervals[, 2],
                          p_value = p_values)

# Mostrar el data frame consolidado Modelo 1
print(consolidado1)

NA

Modelo 2

mod2=lm(Ellipticity ~ 
        Predilatation + Postdilation +
        Raphaecalcification +
        SVDmax +
        ICD4mm_calc +  #indexado 
        CCV
        , 
        data = data1)
summary(mod2)

Call:
lm(formula = Ellipticity ~ Predilatation + Postdilation + Raphaecalcification + 
    SVDmax + ICD4mm_calc + CCV, data = data1)

Residuals:
      Min        1Q    Median        3Q       Max 
-0.092449 -0.024742 -0.002218  0.021768  0.113101 

Coefficients:
                      Estimate Std. Error t value Pr(>|t|)    
(Intercept)          9.457e-01  7.407e-02  12.769  < 2e-16 ***
Predilatation        4.246e-03  8.505e-03   0.499  0.61884    
Postdilation        -8.412e-03  9.167e-03  -0.918  0.36124    
Raphaecalcification  1.813e-02  8.316e-03   2.180  0.03182 *  
SVDmax              -1.992e-03  9.369e-04  -2.126  0.03617 *  
ICD4mm_calc          1.883e-01  6.365e-02   2.959  0.00393 ** 
CCV                  7.524e-06  7.290e-06   1.032  0.30478    
---
Signif. codes:  0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1

Residual standard error: 0.03772 on 92 degrees of freedom
Multiple R-squared:  0.1686,    Adjusted R-squared:  0.1144 
F-statistic: 3.109 on 6 and 92 DF,  p-value: 0.008085

Calculos Intervalo de confianza Regresion Lineal Modelo 2

# Obtener el resumen del modelo
summary_mod2 <- summary(mod2)

# Extraer los coeficientes
coefficients <- coef(summary_mod2)[, 1]

# Extraer los intervalos de confianza
conf_intervals <- confint(mod2)

# Extraer los p-values
p_values <- summary_mod2$coefficients[, 4]

# Crear el data frame consolidado
consolidado2 <- data.frame(Coefficient = coefficients,
                          Lower_CI = conf_intervals[, 1],
                          Upper_CI = conf_intervals[, 2],
                          p_value = p_values)

# Mostrar el data frame consolidado Modelo 1
print(consolidado2)

Modelo 3

mod3=lm(Ellipticity ~ 
        Predilatation + Postdilation +
        Raphaecalcification +
        SVDmax +
        ICD4mm + 
        CCV_calc        #indexado 
        , 
        data = data1)
summary(mod3)

Call:
lm(formula = Ellipticity ~ Predilatation + Postdilation + Raphaecalcification + 
    SVDmax + ICD4mm + CCV_calc, data = data1)

Residuals:
      Min        1Q    Median        3Q       Max 
-0.069053 -0.026743 -0.001909  0.022573  0.117635 

Coefficients:
                     Estimate Std. Error t value Pr(>|t|)    
(Intercept)          1.114608   0.038779  28.742   <2e-16 ***
Predilatation       -0.001202   0.008654  -0.139   0.8898    
Postdilation        -0.009596   0.009499  -1.010   0.3150    
Raphaecalcification  0.013713   0.008567   1.601   0.1129    
SVDmax              -0.002534   0.001272  -1.992   0.0493 *  
ICD4mm               0.001951   0.001999   0.976   0.3316    
CCV_calc             0.007780   0.004289   1.814   0.0729 .  
---
Signif. codes:  0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1

Residual standard error: 0.03875 on 92 degrees of freedom
Multiple R-squared:  0.1229,    Adjusted R-squared:  0.06566 
F-statistic: 2.148 on 6 and 92 DF,  p-value: 0.05524

Calculos Intervalo de confianza Regresion Lineal Modelo 3

# Obtener el resumen del modelo
summary_mod3 <- summary(mod3)

# Extraer los coeficientes
coefficients <- coef(summary_mod3)[, 1]

# Extraer los intervalos de confianza
conf_intervals <- confint(mod3)

# Extraer los p-values
p_values <- summary_mod3$coefficients[, 4]

# Crear el data frame consolidado
consolidado3 <- data.frame(Coefficient = coefficients,
                          Lower_CI = conf_intervals[, 1],
                          Upper_CI = conf_intervals[, 2],
                          p_value = p_values)

# Mostrar el data frame consolidado Modelo 1
print(consolidado3)

NA

Modelo 4

mod4=lm(Ellipticity ~ 
        Predilatation + Postdilation +
        Raphaecalcification +
        SVDmax +
        ICD4mm_calc +   #indexado
        CCV_calc        #indexado 
        , 
        data = data1)
summary(mod4)

Call:
lm(formula = Ellipticity ~ Predilatation + Postdilation + Raphaecalcification + 
    SVDmax + ICD4mm_calc + CCV_calc, data = data1)

Residuals:
      Min        1Q    Median        3Q       Max 
-0.086384 -0.024556 -0.002889  0.020226  0.113059 

Coefficients:
                     Estimate Std. Error t value Pr(>|t|)    
(Intercept)          0.951193   0.073230  12.989  < 2e-16 ***
Predilatation        0.002877   0.008464   0.340  0.73471    
Postdilation        -0.008853   0.009096  -0.973  0.33297    
Raphaecalcification  0.016276   0.008329   1.954  0.05372 .  
SVDmax              -0.001903   0.000863  -2.205  0.02995 *  
ICD4mm_calc          0.177071   0.063655   2.782  0.00656 ** 
CCV_calc             0.006746   0.004143   1.628  0.10686    
---
Signif. codes:  0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1

Residual standard error: 0.03741 on 92 degrees of freedom
Multiple R-squared:  0.1825,    Adjusted R-squared:  0.1292 
F-statistic: 3.424 on 6 and 92 DF,  p-value: 0.004273

Calculos Intervalo de confianza Regresion Lineal Modelo 4

# Obtener el resumen del modelo
summary_mod4 <- summary(mod4)

# Extraer los coeficientes
coefficients <- coef(summary_mod4)[, 1]

# Extraer los intervalos de confianza
conf_intervals <- confint(mod4)

# Extraer los p-values
p_values <- summary_mod4$coefficients[, 4]

# Crear el data frame consolidado
consolidado4 <- data.frame(Coefficient = coefficients,
                          Lower_CI = conf_intervals[, 1],
                          Upper_CI = conf_intervals[, 2],
                          p_value = p_values)

# Mostrar el data frame consolidado Modelo 1
print(consolidado4)

Modelo 5

mod5=lm(Ellipticity ~ 
        Predilatation + Postdilation +
        Raphaecalcification +
        MaxSinAnnDcalc + #indexado
        ICD4mm_calc +    #indexado
        CCV_calc         #indexado 
        , 
        data = data1)
summary(mod5)

Call:
lm(formula = Ellipticity ~ Predilatation + Postdilation + Raphaecalcification + 
    MaxSinAnnDcalc + ICD4mm_calc + CCV_calc, data = data1)

Residuals:
      Min        1Q    Median        3Q       Max 
-0.087251 -0.023916 -0.003034  0.023495  0.114802 

Coefficients:
                      Estimate Std. Error t value Pr(>|t|)    
(Intercept)          9.255e-01  7.386e-02  12.530  < 2e-16 ***
Predilatation       -8.898e-05  8.545e-03  -0.010  0.99171    
Postdilation        -7.319e-03  9.285e-03  -0.788  0.43261    
Raphaecalcification  1.599e-02  8.482e-03   1.885  0.06263 .  
MaxSinAnnDcalc      -3.850e-02  3.248e-02  -1.185  0.23890    
ICD4mm_calc          1.897e-01  6.853e-02   2.768  0.00683 ** 
CCV_calc             5.273e-03  4.140e-03   1.274  0.20596    
---
Signif. codes:  0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1

Residual standard error: 0.03809 on 92 degrees of freedom
Multiple R-squared:  0.1523,    Adjusted R-squared:  0.097 
F-statistic: 2.755 on 6 and 92 DF,  p-value: 0.01656

Calculos Intervalo de confianza Regresion Lineal Modelo 5

# Obtener el resumen del modelo
summary_mod5 <- summary(mod5)

# Extraer los coeficientes
coefficients <- coef(summary_mod5)[, 1]

# Extraer los intervalos de confianza
conf_intervals <- confint(mod5)

# Extraer los p-values
p_values <- summary_mod5$coefficients[, 4]

# Crear el data frame consolidado
consolidado5 <- data.frame(Coefficient = coefficients,
                          Lower_CI = conf_intervals[, 1],
                          Upper_CI = conf_intervals[, 2],
                          p_value = p_values)

# Mostrar el data frame consolidado Modelo 1
print(consolidado5)

Modelo 6

mod6=lm(Ellipticity ~ 
        Predilatation + Postdilation +
        Raphaecalcification +
        MaxSinAnnDcalc + #indexado
        ICD4mm_calc +    #indexado
        CCV
        , 
        data = data1)
summary(mod6)

Call:
lm(formula = Ellipticity ~ Predilatation + Postdilation + Raphaecalcification + 
    MaxSinAnnDcalc + ICD4mm_calc + CCV, data = data1)

Residuals:
      Min        1Q    Median        3Q       Max 
-0.096452 -0.027094 -0.003153  0.024810  0.113320 

Coefficients:
                      Estimate Std. Error t value Pr(>|t|)    
(Intercept)          9.147e-01  7.404e-02  12.354   <2e-16 ***
Predilatation        2.540e-03  8.636e-03   0.294   0.7694    
Postdilation        -7.052e-03  9.362e-03  -0.753   0.4532    
Raphaecalcification  1.901e-02  8.459e-03   2.247   0.0270 *  
MaxSinAnnDcalc      -3.371e-02  3.259e-02  -1.034   0.3036    
ICD4mm_calc          1.985e-01  6.884e-02   2.884   0.0049 ** 
CCV                  1.458e-06  6.733e-06   0.216   0.8291    
---
Signif. codes:  0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1

Residual standard error: 0.03842 on 92 degrees of freedom
Multiple R-squared:  0.1378,    Adjusted R-squared:  0.08154 
F-statistic:  2.45 on 6 and 92 DF,  p-value: 0.03044

Calculos Intervalo de confianza Regresion Lineal Modelo 6

# Obtener el resumen del modelo
summary_mod6 <- summary(mod6)

# Extraer los coeficientes
coefficients <- coef(summary_mod6)[, 1]

# Extraer los intervalos de confianza
conf_intervals <- confint(mod6)

# Extraer los p-values
p_values <- summary_mod6$coefficients[, 4]

# Crear el data frame consolidado
consolidado6 <- data.frame(Coefficient = coefficients,
                          Lower_CI = conf_intervals[, 1],
                          Upper_CI = conf_intervals[, 2],
                          p_value = p_values)

# Mostrar el data frame consolidado Modelo 1
print(consolidado6)

Regresion Logistica

mod7 <- glm(formula = Ellipticitycalc ~ 
              Predilatation + Postdilation +
        Raphaecalcification +
        MaxSinAnnDcalc + #indexado
        ICD4mm_calc +    #indexado
        CCV_calc         #indexado 
        , 
        family = "binomial", data = data1)
summary(mod7)

Call:
glm(formula = Ellipticitycalc ~ Predilatation + Postdilation + 
    Raphaecalcification + MaxSinAnnDcalc + ICD4mm_calc + CCV_calc, 
    family = "binomial", data = data1)

Deviance Residuals: 
    Min       1Q   Median       3Q      Max  
-1.8991  -1.0168  -0.5704   1.0444   1.9476  

Coefficients:
                    Estimate Std. Error z value Pr(>|z|)   
(Intercept)          -8.8395     4.5793  -1.930  0.05357 . 
Predilatation        -0.2636     0.4963  -0.531  0.59539   
Postdilation         -0.3861     0.5369  -0.719  0.47206   
Raphaecalcification   0.6055     0.4877   1.242  0.21440   
MaxSinAnnDcalc       -3.9400     1.8941  -2.080  0.03751 * 
ICD4mm_calc          12.5321     4.4240   2.833  0.00462 **
CCV_calc              0.2779     0.2403   1.156  0.24763   
---
Signif. codes:  0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1

(Dispersion parameter for binomial family taken to be 1)

    Null deviance: 136.75  on 98  degrees of freedom
Residual deviance: 121.22  on 92  degrees of freedom
AIC: 135.22

Number of Fisher Scoring iterations: 4

Calculos de Odd Ratio modelo 7

#Resumen modelo logistico
summary_mod7 <- summary(mod7)

# Extraer los odds ratios
odds_ratios <- exp(summary_mod7$coefficients[, 1])

# Extraer los intervalos de confianza
conf_intervals <- exp(confint(mod7))

Waiting for profiling to be done...

# Extraer los p-values
p_values <- summary_mod7$coefficients[, 4]

# Crear el data frame consolidado
consolidado7 <- data.frame(Odds_Ratio = odds_ratios,
                          Lower_CI = conf_intervals[, 1],
                          Upper_CI = conf_intervals[, 2],
                          p_value = p_values)

# Mostrar el data frame consolidado
print(consolidado7)

NA