Shiny Apps by Bingshu Chen

Shiny Apps are web-based aplication frameworks for Statistic software R . Below are shiny apps developed by Bingshu Chen.

Shiny App for treatment-biomarker interaction . Reference: Chen, B. E., Jiang, W. and Tu, D. (2014). See publication number 20.

Biomarker is very useful in predicting a subject's response to a new intervention. Identification of such a biomarker is important in enhancing positive outcome and avoiding negative outcome. A threshold of the biomarker is often needed to define a sensitive subset for making easy clinical or health related decisions. Recently, a shiny app to explore the interaction between treatment-biomarker was developed by Bingshu Chen from the Department of Public Health Sciences, Queen's University. The app can analyze data uploaded by users and estimate the optimal threshold parameter using the profile likelihood method by Chen, Jiang and Tu (2014). Users can also specific their threshold parameter of interest and explore how the biomarker interacts with the intervention variable.
Shiny App for pick winner design sample size.

Sample size for randomize phase II pick the winner design based Richard Simon's method.
Shiny App for INB and ICER sample size.

Sample size calculation for health ecominics in randomized clinical trials(INB and ICER). (References: See publication 1 and 3).
Shiny App for genetics association study sample size.
PGA: power calculator for case-control genetic association analysis. Referece: See publication number 13.
Shiny App for quantile regression sample size.

To learn more about Shiny Apps, go to http://shiny.rstudio.com/

URL of this web page: http://statapps.tk

Multivariate recurrent event with dependent censoring (Chen and Cook, Biostatistics , 2004): R source codes .
Resampling-based multiple hypothesis testing procedures (Chen et al, Genetics Epidemiology , 2006): Windows Binary code . Reqire installation of Matlab runtime library (119.8Mb).
Gene region-level testing procedure for SNP data, using the min P test resampling approach: minPtest, http://cran.r-project.org/web/packages/minPtest.(This R package for minPtest was developed by Stefanie Hieke ).
Analysis of clustered competing risks data (Chen et al, Biometrics, 2008): Matlab source codes . Reference: See publication number 12.
Power and sample size for genetics association study. Referece: See publication number 13.
deepAFT: A non-linear accelerated failure time model with artificial neural network: https://cran.r-project.org/package=dnn. Referece: See publication number 37.