Estimate cor—max MASH

One example: p = 3

\[ \hat{\beta}|\beta \sim N_{3}(\hat{\beta}; \beta, \left(\begin{matrix} 1 & 0.7 & 0.2 \\ 0.7 & 1 & 0.4 \\ 0.2 & 0.4 & 1 \end{matrix}\right)) \]

\[ \beta \sim \frac{1}{4}\delta_{0} + \frac{1}{4}N_{3}(0, \left(\begin{matrix} 1 & 0 &0\\ 0 & 0 & 0 \\ 0 & 0 & 0 \end{matrix}\right)) + \frac{1}{4}N_{3}(0, \left(\begin{matrix} 1 & 0 & 0 \\ 0 & 1 & 0 \\ 0 & 0 & 0 \end{matrix}\right)) + \frac{1}{4}N_{3}(0, \left(\begin{matrix} 1 & 1 & 1 \\ 1 & 1 & 1 \\ 1 & 1 & 1 \end{matrix}\right)) \]

set.seed(1)
Sigma = cbind(c(1,0.7,0.2), c(0.7,1,0.4), c(0.2,0.4,1))
U0 = matrix(0,3,3)
U1 = matrix(0,3,3); U1[1,1] = 1
U2 = diag(3); U2[3,3] = 0
U3 = matrix(1,3,3)
data = generate_data(n=4000, p=3, V=Sigma, Utrue = list(U0=U0, U1=U1,U2=U2,U3=U3))

We find the estimate of V with canonical covariances and the PCA covariances.

m.data = mash_set_data(data$Bhat, data$Shat)
m.1by1 = mash_1by1(m.data)
strong = get_significant_results(m.1by1)

U.pca = cov_pca(m.data, 3, subset = strong)
U.ed = cov_ed(m.data, U.pca, subset = strong)
U.c = cov_canonical(m.data)

The PCA correlation matrices are:

1. We run the algorithm in estimate cor mle with 3 different initial points for \(\rho\), (-0.5,0,0.5). The \(\rho\) in each iteration is estimated using optim function. The estimated correlation is

Vhat.mle = estimateV(m.data, c(U.c, U.ed), init_rho = c(-0.5,0,0.5), tol=1e-4, optmethod = 'mle')
Vhat.mle$V

          [,1]      [,2]      [,3]
[1,] 1.0000000 0.7009268 0.1588733
[2,] 0.7009268 1.0000000 0.4001842
[3,] 0.1588733 0.4001842 1.0000000

2. The result uses algorithm in estimate cor em. \(\rho\) in each iteration is the root of a third degree polynomial.

Vhat.em = estimateV(m.data, c(U.c, U.ed), init_rho = c(-0.5,0,0.5), tol = 1e-4, optmethod = 'em2')
Vhat.em$V

          [,1]      [,2]      [,3]
[1,] 1.0000000 0.7086927 0.1706391
[2,] 0.7086927 1.0000000 0.4187296
[3,] 0.1706391 0.4187296 1.0000000

The running time (in sec.) for each pairwise correlation is

table = data.frame(rbind(Vhat.mle$ttime, Vhat.em$ttime), row.names = c('mle', 'em'))
colnames(table) = c('12','13','23')
table %>% kable() %>% kable_styling()

The time is the total running time with different initial point.

3. The result uses algorithm in estimate cor em V.

Vhat.emV = estimateV(m.data, c(U.c, U.ed), init_V = list(diag(ncol(m.data$Bhat)), clusterGeneration::rcorrmatrix(3), clusterGeneration::rcorrmatrix(3)), tol = 1e-4, optmethod = 'emV')
Vhat.emV$V

          [,1]      [,2]      [,3]
[1,] 1.0000000 0.5487183 0.2669639
[2,] 0.5487183 1.0000000 0.4654711
[3,] 0.2669639 0.4654711 1.0000000

4. Using the original truncated correlation:

Vhat.tru = estimate_null_correlation(m.data)
Vhat.tru

          [,1]      [,2]      [,3]
[1,] 1.0000000 0.4296283 0.1222433
[2,] 0.4296283 1.0000000 0.3324459
[3,] 0.1222433 0.3324459 1.0000000

The truncated correlation underestimates the correlations.

5. mash 1by1: Run ash for each condition, and estimate correlation matrix based on the non-significant samples.

V.mash = cor((data$Bhat/data$Shat)[-strong,])
V.mash

          [,1]      [,2]      [,3]
[1,] 1.0000000 0.5313446 0.2445663
[2,] 0.5313446 1.0000000 0.4490049
[3,] 0.2445663 0.4490049 1.0000000

All the estimated correlation matrices above are positive definite.

FError = c(norm(Vhat.mle$V - Sigma, 'F'),
           norm(Vhat.em$V - Sigma, 'F'),
           norm(Vhat.emV$V - Sigma, 'F'),
           norm(Vhat.tru - Sigma, 'F'),
           norm(V.mash - Sigma, 'F'))
OpError = c(norm(Vhat.mle$V - Sigma, '2'),
           norm(Vhat.em$V - Sigma, '2'),
           norm(Vhat.emV$V - Sigma, '2'),
           norm(Vhat.tru - Sigma, '2'),
           norm(V.mash - Sigma, '2'))
table = data.frame(FrobeniusError = FError, SpectralError = OpError, row.names = c('mle','em','emV','trunc','m.1by1'))
table %>% kable() %>% kable_styling()

m.data.mle = mash_set_data(data$Bhat, data$Shat, V=Vhat.mle$V)
m.model.mle = mash(m.data.mle, c(U.c,U.ed), verbose = FALSE)

m.data.em = mash_set_data(data$Bhat, data$Shat, V=Vhat.em$V)
m.model.em = mash(m.data.em, c(U.c,U.ed), verbose = FALSE)

m.data.emV = mash_set_data(data$Bhat, data$Shat, V=Vhat.emV$V)
m.model.emV = mash(m.data.emV, c(U.c,U.ed), verbose = FALSE)

m.data.trunc = mash_set_data(data$Bhat, data$Shat, V=Vhat.tru)
m.model.trunc = mash(m.data.trunc, c(U.c,U.ed), verbose = FALSE)

m.data.1by1 = mash_set_data(data$Bhat, data$Shat, V=V.mash)
m.model.1by1 = mash(m.data.1by1, c(U.c,U.ed), verbose = FALSE)

m.data.correct = mash_set_data(data$Bhat, data$Shat, V=Sigma)
m.model.correct = mash(m.data.correct, c(U.c,U.ed), verbose = FALSE)

null.ind = which(apply(data$B,1,sum) == 0)
V.trun = c(get_loglik(m.model.trunc), length(get_significant_results(m.model.trunc)), sum(get_significant_results(m.model.trunc) %in% null.ind))
V.mle = c(get_loglik(m.model.mle), length(get_significant_results(m.model.mle)), sum(get_significant_results(m.model.mle) %in% null.ind))
V.em = c(get_loglik(m.model.em), length(get_significant_results(m.model.em)), sum(get_significant_results(m.model.em) %in% null.ind))
V.emV = c(get_loglik(m.model.emV), length(get_significant_results(m.model.emV)), sum(get_significant_results(m.model.emV) %in% null.ind))
V.1by1 = c(get_loglik(m.model.1by1), length(get_significant_results(m.model.1by1)), sum(get_significant_results(m.model.1by1) %in% null.ind))
V.correct = c(get_loglik(m.model.correct), length(get_significant_results(m.model.correct)), sum(get_significant_results(m.model.correct) %in% null.ind))
temp = cbind(V.mle, V.em, V.emV, V.trun, V.1by1, V.correct)
colnames(temp) = c('MLE','EM','EMV', 'Truncate', 'm.1by1', 'True')
row.names(temp) = c('log likelihood', '# significance', '# False positive')
temp %>% kable() %>% kable_styling()

par(mfrow=c(2,3))
barplot(get_estimated_pi(m.model.mle), las=2, cex.names = 0.7, main='MLE', ylim=c(0,0.8))
barplot(get_estimated_pi(m.model.em), las=2, cex.names = 0.7, main='EM', ylim=c(0,0.8))
barplot(get_estimated_pi(m.model.emV), las=2, cex.names = 0.7, main='EMV', ylim=c(0,0.8))
barplot(get_estimated_pi(m.model.trunc), las=2, cex.names = 0.7, main='Truncate', ylim=c(0,0.8))
barplot(get_estimated_pi(m.model.1by1), las=2, cex.names = 0.7, main='m.1by1', ylim=c(0,0.8))
barplot(get_estimated_pi(m.model.correct), las=2, cex.names = 0.7, main='True', ylim=c(0,0.8))

m.mle.seq = ROC.table(data$B, m.model.mle)
m.em.seq = ROC.table(data$B, m.model.em)
m.emV.seq = ROC.table(data$B, m.model.emV)
m.trun.seq = ROC.table(data$B, m.model.trunc)
m.1by1.seq = ROC.table(data$B, m.model.1by1)
m.correct.seq = ROC.table(data$B, m.model.correct)

rrmse = rbind(RRMSE(data$B, data$Bhat, list(m.model.mle, m.model.em, m.model.emV, m.model.trunc, m.model.1by1, m.model.correct)))
colnames(rrmse) = c('MLE','EM','EMV', 'Truncate','m.1by1','True')
row.names(rrmse) = 'RRMSE'
rrmse %>% kable() %>% kable_styling()

barplot(rrmse, ylim=c(0,(1+max(rrmse))/2), names.arg = c('MLE','EM', 'EMV','Truncate','m.1by1','True'), las=2, cex.names = 0.7, main='RRMSE')

More simulations: p = 5

I randomly generate 10 positive definite correlation matrices, V. The sample size is 4000.

\[ \hat{z}|z \sim N_{5}(z, V) \] \[ z\sim\frac{1}{4}\delta_{0} + \frac{1}{4}N_{5}(0,\left(\begin{matrix} 1 & \mathbf{0}_{1\times 4} \\ \mathbf{0}_{4\times 1} & \mathbf{0}_{4\times 4} \end{matrix}\right)) + \frac{1}{4}N_{5}(0,\left(\begin{matrix} \mathbf{1}_{2\times 2} & \mathbf{0}_{1\times 3} \\ \mathbf{0}_{3\times 1} & \mathbf{0}_{3\times 3} \end{matrix}\right)) + \frac{1}{4}N_{5}(0,\mathbf{1}_{5\times 5}) \]

set.seed(100)
n=4000; p = 5
U0 = matrix(0,p,p)
U1 = U0; U1[1,1] = 1
U2 = U0; U2[c(1:2), c(1:2)] = 1
U3 = matrix(1, p,p)
Utrue = list(U0 = U0, U1 = U1, U2 = U2, U3 = U3)
for(t in 1:10){
  Vtrue = clusterGeneration::rcorrmatrix(p)
  data = generate_data(n, p, Vtrue, Utrue)
  # mash cov
  m.data = mash_set_data(Bhat = data$Bhat, Shat = data$Shat)
  m.1by1 = mash_1by1(m.data)
  strong = get_significant_results(m.1by1)

  U.pca = cov_pca(m.data, 3, subset = strong)
  U.ed = cov_ed(m.data, U.pca, subset = strong)
  U.c = cov_canonical(m.data)
  Vhat.mle <- estimateV(m.data, c(U.c, U.ed), init_rho = c(-0.5,0,0.5), tol=1e-4, optmethod = 'mle')
  Vhat.em <- estimateV(m.data, c(U.c, U.ed), init_rho = c(-0.5,0,0.5), tol=1e-4, optmethod = 'em2')
  Vhat.emV <- estimateV(m.data, c(U.c, U.ed), init_V = list(diag(ncol(m.data$Bhat)), clusterGeneration::rcorrmatrix(p), clusterGeneration::rcorrmatrix(p)),tol=1e-4, optmethod = 'emV')
  saveRDS(list(V.true = Vtrue, V.mle = Vhat.mle, V.em = Vhat.em, V.emV = Vhat.emV, data = data, strong=strong),
          paste0('../output/MASH.result.',t,'.rds'))
}

files = dir("../output/AddEMV/"); files = files[grep("MASH.result",files)]
times = length(files)
result = vector(mode="list",length = times)
for(i in 1:times) {
  result[[i]] = readRDS(paste("../output/AddEMV/", files[[i]], sep=""))
}

mle.pd = numeric(times)
em.pd = numeric(times)
for(i in 1:times){
  m.data = mash_set_data(result[[i]]$data$Bhat, result[[i]]$data$Shat)
  
  result[[i]]$V.trun = estimate_null_correlation(m.data, apply_lower_bound = FALSE)
  m.1by1 = mash_1by1(m.data)
  strong = get_significant_results(m.1by1)
  result[[i]]$V.1by1 = cor(m.data$Bhat[-strong,])
  U.c = cov_canonical(m.data)
  U.pca = cov_pca(m.data, 3, subset = strong)
  U.ed = cov_ed(m.data, U.pca, subset = strong)

  m.data.true = mash_set_data(Bhat = m.data$Bhat, Shat = m.data$Shat, V = result[[i]]$V.true)
  m.model.true = mash(m.data.true, c(U.c,U.ed), verbose = FALSE)
  
  m.data.trunc = mash_set_data(Bhat = m.data$Bhat, Shat = m.data$Shat, V = result[[i]]$V.trun)
  m.model.trunc = mash(m.data.trunc, c(U.c,U.ed), verbose = FALSE)
  
  m.data.1by1 = mash_set_data(Bhat = m.data$Bhat, Shat = m.data$Shat, V = result[[i]]$V.1by1)
  m.model.1by1 = mash(m.data.1by1, c(U.c,U.ed), verbose = FALSE)
  
  m.data.emV = mash_set_data(Bhat = m.data$Bhat, Shat = m.data$Shat, V = result[[i]]$V.emV$V)
  m.model.emV = mash(m.data.emV, c(U.c,U.ed), verbose = FALSE)
  
  # MLE
  
  m.model.mle = m.model.mle.F = m.model.mle.2 = list()
  R <- tryCatch(chol(result[[i]]$V.mle$V),error = function (e) FALSE)
  if(is.matrix(R)){
    mle.pd[i] = 1
    m.data.mle = mash_set_data(Bhat = m.data$Bhat, Shat = m.data$Shat, V = result[[i]]$V.mle$V)
    m.model.mle = mash(m.data.mle, c(U.c,U.ed), verbose = FALSE)
  }else{
    V.mle.near.F = as.matrix(Matrix::nearPD(result[[i]]$V.mle$V, conv.norm.type = 'F', keepDiag = TRUE)$mat)
    V.mle.near.2 = as.matrix(Matrix::nearPD(result[[i]]$V.mle$V, conv.norm.type = '2', keepDiag = TRUE)$mat)
    
    result[[i]]$V.mle.F = V.mle.near.F
    result[[i]]$V.mle.2 = V.mle.near.2
    
    # mashmodel
    m.data.mle.F = mash_set_data(Bhat = m.data$Bhat, Shat = m.data$Shat, V = V.mle.near.F)
    m.model.mle.F = mash(m.data.mle.F, c(U.c,U.ed), verbose = FALSE)
    
    m.data.mle.2 = mash_set_data(Bhat = m.data$Bhat, Shat = m.data$Shat, V = V.mle.near.2)
    m.model.mle.2 = mash(m.data.mle.2, c(U.c,U.ed), verbose = FALSE)
  }
  
  # EM
  m.model.em = m.model.em.F = m.model.em.2 = list()
  R <- tryCatch(chol(result[[i]]$V.em$V),error = function (e) FALSE)
  if(is.matrix(R)){
    em.pd[i] = 1
    m.data.em = mash_set_data(Bhat = m.data$Bhat, Shat = m.data$Shat, V = result[[i]]$V.em$V)
    m.model.em = mash(m.data.em, c(U.c,U.ed), verbose = FALSE)
  }else{
    V.em.near.F = as.matrix(Matrix::nearPD(result[[i]]$V.em$V, conv.norm.type = 'F', keepDiag = TRUE)$mat)
    V.em.near.2 = as.matrix(Matrix::nearPD(result[[i]]$V.em$V, conv.norm.type = '2', keepDiag = TRUE)$mat)
    
    result[[i]]$V.em.F = V.em.near.F
    result[[i]]$V.em.2 = V.em.near.2
    
    # mashmodel
    m.data.em.F = mash_set_data(Bhat = m.data$Bhat, Shat = m.data$Shat, V = V.em.near.F)
    m.model.em.F = mash(m.data.em.F, c(U.c,U.ed), verbose = FALSE)
      
    m.data.em.2 = mash_set_data(Bhat = m.data$Bhat, Shat = m.data$Shat, V = V.em.near.2)
    m.model.em.2 = mash(m.data.em.2, c(U.c,U.ed), verbose = FALSE)
  }
  
  result[[i]]$m.model = list(m.model.true = m.model.true, m.model.trunc = m.model.trunc, 
                             m.model.1by1 = m.model.1by1, m.model.emV = m.model.emV,
                             m.model.mle = m.model.mle,
                             m.model.mle.F = m.model.mle.F, m.model.mle.2 = m.model.mle.2, 
                             m.model.em = m.model.em,
                             m.model.em.F = m.model.em.F, m.model.em.2 = m.model.em.2)
}

temp = matrix(0,nrow = times, ncol = 7)
for(i in 1:times){
  temp[i, ] = error.cor(result[[i]], norm.type='F', mle.pd = mle.pd[i], em.pd = em.pd[i])
}
colnames(temp) = c('Trunc','m.1by1', 'MLE','MLE.F', 'EM', 'EM.F', 'EMV')
temp[temp==0] = NA
temp %>% kable() %>% kable_styling()

temp = matrix(0,nrow = times, ncol = 7)
for(i in 1:times){
  temp[i, ] = error.cor(result[[i]], norm.type='2', mle.pd = mle.pd[i], em.pd = em.pd[i])
}
colnames(temp) = c('Trunc','m.1by1', 'MLE','MLE.2', 'EM', 'EM.2', 'EMV')
temp[temp==0] = NA
temp %>% kable() %>% kable_styling()

mle.time = em.time = numeric(times)
for(i in 1:times){
  mle.time[i] = sum(result[[i]]$V.mle$ttime)
  em.time[i] = sum(result[[i]]$V.em$ttime)
}
temp = cbind(mle.time, em.time)
colnames(temp) = c('MLE', 'EM')
row.names(temp) = 1:10
temp %>% kable() %>% kable_styling()

temp = matrix(0,nrow = times, ncol = 10)
for(i in 1:times){
  temp[i, ] = loglik.cor(result[[i]]$m.model, mle.pd = mle.pd[i], em.pd = em.pd[i])
}
colnames(temp) = c('True', 'Trunc','m.1by1', 'MLE','MLE.F', 'MLE.2', 'EM', 'EM.F', 'EM.2','EMV')
temp[temp == 0] = NA
temp[,-c(6,9)] %>% kable() %>% kable_styling()

par(mfrow=c(1,2))
for(i in 1:times){
  plotROC(result[[i]]$data$B, result[[i]]$m.model, mle.pd = mle.pd[i], em.pd = em.pd[i], title=paste0('Data', i, ' '))
}

RRMSE

par(mfrow=c(1,2))
for(i in 1:times){
  rrmse = rbind(RRMSE(result[[i]]$data$B, result[[i]]$data$Bhat, result[[i]]$m.model))
  barplot(rrmse, ylim=c(0,(1+max(rrmse))/2), las=2, cex.names = 0.7, main='RRMSE')
}

Expand here to see past versions of unnamed-chunk-31-1.png:

Version	Author	Date
802266a	zouyuxin	2018-08-15

Expand here to see past versions of unnamed-chunk-31-2.png:

Version	Author	Date
802266a	zouyuxin	2018-08-15

Expand here to see past versions of unnamed-chunk-31-3.png:

Version	Author	Date
802266a	zouyuxin	2018-08-15

Expand here to see past versions of unnamed-chunk-31-4.png:

Version	Author	Date
802266a	zouyuxin	2018-08-15

Expand here to see past versions of unnamed-chunk-31-5.png:

Version	Author	Date
802266a	zouyuxin	2018-08-15

Session information

sessionInfo()

R version 3.5.1 (2018-07-02)
Platform: x86_64-apple-darwin15.6.0 (64-bit)
Running under: macOS High Sierra 10.13.6

Matrix products: default
BLAS: /Library/Frameworks/R.framework/Versions/3.5/Resources/lib/libRblas.0.dylib
LAPACK: /Library/Frameworks/R.framework/Versions/3.5/Resources/lib/libRlapack.dylib

locale:
[1] en_US.UTF-8/en_US.UTF-8/en_US.UTF-8/C/en_US.UTF-8/en_US.UTF-8

attached base packages:
[1] stats     graphics  grDevices utils     datasets  methods   base     

other attached packages:
[1] kableExtra_0.9.0 knitr_1.20       mashr_0.2-11     ashr_2.2-10     

loaded via a namespace (and not attached):
 [1] corrplot_0.84            lattice_0.20-35         
 [3] Rmosek_8.0.69            colorspace_1.3-2        
 [5] htmltools_0.3.6          viridisLite_0.3.0       
 [7] yaml_2.2.0               rlang_0.2.1             
 [9] R.oo_1.22.0              pillar_1.3.0            
[11] R.utils_2.6.0            ExtremeDeconvolution_1.3
[13] REBayes_1.3              foreach_1.4.4           
[15] plyr_1.8.4               stringr_1.3.1           
[17] munsell_0.5.0            workflowr_1.1.1         
[19] rvest_0.3.2              R.methodsS3_1.7.1       
[21] mvtnorm_1.0-8            codetools_0.2-15        
[23] evaluate_0.11            pscl_1.5.2              
[25] doParallel_1.0.11        parallel_3.5.1          
[27] highr_0.7                Rcpp_0.12.18            
[29] readr_1.1.1              backports_1.1.2         
[31] scales_0.5.0             rmeta_3.0               
[33] clusterGeneration_1.3.4  truncnorm_1.0-8         
[35] hms_0.4.2                digest_0.6.15           
[37] stringi_1.2.4            grid_3.5.1              
[39] rprojroot_1.3-2          tools_3.5.1             
[41] magrittr_1.5             tibble_1.4.2            
[43] crayon_1.3.4             whisker_0.3-2           
[45] pkgconfig_2.0.1          MASS_7.3-50             
[47] Matrix_1.2-14            SQUAREM_2017.10-1       
[49] xml2_1.2.0               assertthat_0.2.0        
[51] rmarkdown_1.10           httr_1.3.1              
[53] rstudioapi_0.7           iterators_1.0.10        
[55] R6_2.2.2                 git2r_0.23.0            
[57] compiler_3.5.1