Last updated: 2019-11-18
Checks: 7 0
Knit directory: smash-gen/
This reproducible R Markdown analysis was created with workflowr (version 1.5.0). The Checks tab describes the reproducibility checks that were applied when the results were created. The Past versions tab lists the development history.
Great! Since the R Markdown file has been committed to the Git repository, you know the exact version of the code that produced these results.
Great job! The global environment was empty. Objects defined in the global environment can affect the analysis in your R Markdown file in unknown ways. For reproduciblity it’s best to always run the code in an empty environment.
The command set.seed(20180501) was run prior to running the code in the R Markdown file. Setting a seed ensures that any results that rely on randomness, e.g. subsampling or permutations, are reproducible.
Great job! Recording the operating system, R version, and package versions is critical for reproducibility.
Nice! There were no cached chunks for this analysis, so you can be confident that you successfully produced the results during this run.
Great job! Using relative paths to the files within your workflowr project makes it easier to run your code on other machines.
Great! You are using Git for version control. Tracking code development and connecting the code version to the results is critical for reproducibility. The version displayed above was the version of the Git repository at the time these results were generated.
Note that you need to be careful to ensure that all relevant files for the analysis have been committed to Git prior to generating the results (you can use wflow_publish or wflow_git_commit). workflowr only checks the R Markdown file, but you know if there are other scripts or data files that it depends on. Below is the status of the Git repository when the results were generated:
Ignored files:
Ignored: .DS_Store
Ignored: .Rhistory
Ignored: .Rproj.user/
Ignored: data/.DS_Store
Untracked files:
Untracked: analysis/chipexoeg.Rmd
Untracked: analysis/efsd.Rmd
Untracked: analysis/pre0221.Rmd
Untracked: analysis/smashadditive.Rmd
Untracked: analysis/talk1011.Rmd
Untracked: data/chipexo_examples/
Untracked: data/chipseq_examples/
Untracked: talk.Rmd
Untracked: talk.html
Untracked: talk.pdf
Unstaged changes:
Modified: analysis/binomial.Rmd
Modified: analysis/fda.Rmd
Modified: analysis/protein.Rmd
Modified: analysis/r2.Rmd
Modified: analysis/r2b.Rmd
Modified: analysis/sigma.Rmd
Note that any generated files, e.g. HTML, png, CSS, etc., are not included in this status report because it is ok for generated content to have uncommitted changes.
These are the previous versions of the R Markdown and HTML files. If you’ve configured a remote Git repository (see ?wflow_git_remote), click on the hyperlinks in the table below to view them.
| File | Version | Author | Date | Message |
|---|---|---|---|---|
| Rmd | e3dc37c | Dongyue Xie | 2019-11-19 | wflow_publish(c(“analysis/initialinvest.Rmd”, “analysis/estimatenugget.Rmd”, |
Now we are ready to apply smashgen to Poisson data with unknown nugget effect. It’s very important to note that when the range of mean function is small, the \(SNR=\frac{sd(mu)}{mean[sd(noise)]}\) could be very large. For example, if the mean function is spike and has range [1,3]. Then the stand deviation of mean function is around 0.48 and the average of \(s_t^2=1/e^\mu_t\) is around 0.92. So even without nugget effect, the SNR is already about 0.52. Adding the nugget effect would make it smaller. SNR in this situation matters to smashgen because we are using Gaussian approximation to it so a very low SNR would make it very difficult to recover the true mean. This is the reason why smashgen performs poorly when the range of mean function is small.
From 3, when the scale of mean function is small(smallest around 0.1-0.3), smash outperforms smashgen under all the mean functions. From 4, when we increased the scale of mean function(smallest around 50, largest around 200), smashgen outperforms smash for almost all the functions except Doppler. Smashgen cannot capture the high frequency fluctuation of Doppler at the beginning. For Heavysine, Parabola, Wave and timeshifted mean functions, using symmlet8 basis outperforms using Haar basis.
In 5, we compared smash and smashgen on estimating on estimating \(\mu\) and \(\log\mu\). For step function, smashgen gives better estimate of \(\log\mu\) but worse estimation of \(\mu\). For heavysine, smash and smashgen are similar while smashgen with symmlet8 achieved lower MSE when mean function range is (50,100). For Doppler, smashgen with symmlet8 achieved lower MSE when mean function range is (50,100). For parabola, the two methods are similar. For wave, smashgen with symmlet8 won. It’s very interesting to see that though smashgen gave smaller MSE for estimating \(\log\mu\), the MSE for estimating \(\mu\) became larger, for example in step and bump functions.
sessionInfo()R version 3.6.1 (2019-07-05)
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/3.6/Resources/lib/libRblas.0.dylib
LAPACK: /Library/Frameworks/R.framework/Versions/3.6/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
loaded via a namespace (and not attached):
[1] workflowr_1.5.0 Rcpp_1.0.2 rprojroot_1.3-2 digest_0.6.21
[5] later_1.0.0 R6_2.4.0 backports_1.1.5 git2r_0.26.1
[9] magrittr_1.5 evaluate_0.14 stringi_1.4.3 rlang_0.4.0
[13] fs_1.3.1 promises_1.1.0 whisker_0.4 rmarkdown_1.16
[17] tools_3.6.1 stringr_1.4.0 glue_1.3.1 httpuv_1.5.2
[21] xfun_0.10 yaml_2.2.0 compiler_3.6.1 htmltools_0.4.0
[25] knitr_1.25