Detritus Wiki

User Tools

Site Tools

Trace:
neuroimagen:adni_cusp

Differences

This shows you the differences between two versions of the page.

Link to this comparison view

Both sides previous revision Previous revision
Next revision 		Previous revision
neuroimagen:adni_cusp [2015/12/21 16:37]
osotolongo [Notas para Composite Scores] 		neuroimagen:adni_cusp [2020/08/04 10:58] (current)
Line 1: Line 1:
 ====== Using ADNI data for Cusp model fitting ====== ====== Using ADNI data for Cusp model fitting ======
  
 +[[neuroimagen:alt_cusp_method|Or you can use this alternative method]]
 ===== Simple way ===== ===== Simple way =====
  
Line 563: Line 563:
 ++++ ++++
  
 +++++ Malo para el FDG |
 +<code>
 +> summary(fit)
 +
 +Call:
 +cusp(formula = y ~ drcs, alpha = alpha ~ zwb + zAge + m.PTGENDER + 
 +    zEduc, beta = beta ~ zwb + zAge + m.PTGENDER + zEduc, data = datac)
 +
 +Deviance Residuals: 
 +     Min        1Q    Median        3Q       Max  
 +-3.02185  -0.35020   0.05687   0.63803   3.60924  
 +
 +Coefficients:
 +                     Estimate Std. Error z value Pr(>|z|)    
 +a[(Intercept)]      -0.508309   0.023910 -21.259  < 2e-16 ***
 +a[zwb]               0.524366   0.014518  36.119  < 2e-16 ***
 +a[zAge]             -0.077225   0.020089  -3.844 0.000121 ***
 +a[m.PTGENDERFemale]  0.266786   0.007268  36.705  < 2e-16 ***
 +a[zEduc]             0.210118   0.021580   9.737  < 2e-16 ***
 +b[(Intercept)]       0.842972   0.015688  53.734  < 2e-16 ***
 +b[zwb]              -0.589807         NA      NA       NA    
 +b[zAge]             -0.124395   0.033468  -3.717 0.000202 ***
 +b[m.PTGENDERFemale]  0.600601   0.040893  14.687  < 2e-16 ***
 +b[zEduc]             0.122145   0.034828   3.507 0.000453 ***
 +w[(Intercept)]      -0.426748   0.014152 -30.154  < 2e-16 ***
 +w[drcs]              1.169788   0.008142 143.666  < 2e-16 ***
 +---
 +Signif. codes:  0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1
 +
 +
 +  Null deviance: 3895.6  on 3317  degrees of freedom
 +Linear deviance: 2026.9  on 3312  degrees of freedom
 +Logist deviance:     NA  on   NA  degrees of freedom
 + Delay deviance: 2475.7  on 3306  degrees of freedom
 +
 +             R.Squared    logLik npar      AIC     AICc      BIC
 +Linear model 0.2880251 -3890.378    6 7792.755 7792.781 7829.398
 +Cusp model   0.3869597 -3622.986   12 7269.971 7270.066 7343.257
 +---
 +Note: R.Squared for cusp model is Cobb's pseudo-R^2. This value
 +      can become negative.
 +
 + Chi-square test of linear vs. cusp model
 +
 +X-squared = 534.8, df = 6, p-value = 0
 +
 +Number of optimization iterations: 43
 +</code>
 +++++
 +
 +++++ Pesimo para el AV45 |
 +<code>
 +> summary(fit)
 +
 +Call:
 +cusp(formula = y ~ drcs, alpha = alpha ~ zwb + zAge + m.PTGENDER + 
 +    zEduc, beta = beta ~ zwb + zAge + m.PTGENDER + zEduc, data = datac)
 +
 +Deviance Residuals: 
 +     Min        1Q    Median        3Q       Max  
 +-2.77918  -0.53934  -0.09885   0.52564   2.93425  
 +
 +Coefficients:
 +                     Estimate Std. Error z value Pr(>|z|)    
 +a[(Intercept)]      -0.329897         NA      NA       NA    
 +a[zwb]              -0.509019   0.029985 -16.976  < 2e-16 ***
 +a[zAge]             -0.175968   0.022751  -7.735 1.04e-14 ***
 +a[m.PTGENDERFemale]  0.492413   0.050822   9.689  < 2e-16 ***
 +a[zEduc]             0.185683   0.026500   7.007 2.44e-12 ***
 +b[(Intercept)]       0.149342         NA      NA       NA    
 +b[zwb]               0.169838   0.006714  25.295  < 2e-16 ***
 +b[zAge]             -0.183744         NA      NA       NA    
 +b[m.PTGENDERFemale]  0.701522         NA      NA       NA    
 +b[zEduc]             0.127566         NA      NA       NA    
 +w[(Intercept)]      -0.049160   0.016707  -2.943  0.00326 ** 
 +w[drcs]              1.088235   0.010977  99.138  < 2e-16 ***
 +---
 +Signif. codes:  0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1
 +
 +
 +  Null deviance: 1649.6  on 1691  degrees of freedom
 +Linear deviance: 1051.9  on 1686  degrees of freedom
 +Logist deviance:     NA  on   NA  degrees of freedom
 + Delay deviance: 1403.4  on 1680  degrees of freedom
 +
 +             R.Squared    logLik npar      AIC     AICc      BIC
 +Linear model 0.2448373 -1998.714    6 4009.428 4009.478 4042.030
 +Cusp model   0.1503419 -2015.754   12 4055.508 4055.693 4120.712
 +---
 +Note: R.Squared for cusp model is Cobb's pseudo-R^2. This value
 +      can become negative.
 +
 + Chi-square test of linear vs. cusp model
 +
 +X-squared = 34.08, df = 6, p-value = 6.494e-06
 +
 +Number of optimization iterations: 68
 +</code>
 +++++
 +
 +++++  Pero bastante bueno para el PiB |
 +<code>
 +> summary(fit)
 +
 +Call:
 +cusp(formula = y ~ drcs, alpha = alpha ~ zwb + zAge + m.PTGENDER + 
 +    zEduc, beta = beta ~ zwb + zAge + m.PTGENDER + zEduc, data = datac)
 +
 +Deviance Residuals: 
 +     Min        1Q    Median        3Q       Max  
 +-1.39747  -0.34765   0.02365   0.61995   2.80434  
 +
 +Coefficients:
 +                    Estimate Std. Error z value Pr(>|z|)    
 +a[(Intercept)]      -0.41926    0.10606  -3.953 7.71e-05 ***
 +a[zwb]              -0.41509    0.08006  -5.185 2.16e-07 ***
 +a[zAge]             -0.01542    0.06966  -0.221  0.82483    
 +a[m.PTGENDERFemale]  0.01350    0.14087   0.096  0.92365    
 +a[zEduc]             0.15078    0.07280   2.071  0.03835 *  
 +b[(Intercept)]       1.38998    0.24548   5.662 1.49e-08 ***
 +b[zwb]               0.09861    0.13536   0.729  0.46629    
 +b[zAge]             -0.33692    0.11845  -2.844  0.00445 ** 
 +b[m.PTGENDERFemale]  0.61578    0.24049   2.561  0.01045 *  
 +b[zEduc]             0.04128    0.12358   0.334  0.73837    
 +w[(Intercept)]      -0.49934    0.05477  -9.116  < 2e-16 ***
 +w[drcs]              1.23598    0.04958  24.928  < 2e-16 ***
 +---
 +Signif. codes:  0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1
 +
 +
 +  Null deviance: 297.20  on 217  degrees of freedom
 +Linear deviance: 154.46  on 212  degrees of freedom
 +Logist deviance:     NA  on  NA  degrees of freedom
 + Delay deviance: 152.70  on 206  degrees of freedom
 +
 +             R.Squared    logLik npar      AIC     AICc      BIC
 +Linear model 0.2060384 -271.7741    6 555.5482 555.9463 575.8552
 +Cusp model   0.5180603 -235.4183   12 494.8367 496.3586 535.4506
 +---
 +Note: R.Squared for cusp model is Cobb's pseudo-R^2. This value
 +      can become negative.
 +
 + Chi-square test of linear vs. cusp model
 +
 +X-squared = 72.71, df = 6, p-value = 1.135e-13
 +
 +Number of optimization iterations: 34
 +</code>
 +++++
  
neuroimagen/adni_cusp.1450715822.txt.gz · Last modified: 2020/08/04 10:47 (external edit)

Page Tools

Except where otherwise noted, content on this wiki is licensed under the following license: CC Attribution-Share Alike 4.0 International
CC Attribution-Share Alike 4.0 International Donate Powered by PHP Valid HTML5 Valid CSS Driven by DokuWiki