| Title | Programmer/Email | R Code | Sample Run | Macro Parameters |
|---|---|---|---|---|
| ScatterW Interaction | SallyThurston thurston@bst.rochester.edu | ### ARGUMENTS: ### tdat is database ### yname is name of y variable in tdat ### xname is name of x variable in tdat, for which we want partial plot ### dummyvar is name of dummy variable for which we want interaction ### x0name is name of x*I(dummy variable==0) (THIS MUST BE PART OF THE DATASET) ### x1name is name of x*I(dummy variable==1) (THIS MUST BE PART OF THE DATASET) ### covnames is vector of names of remaining variables ### txlab is name to go on x-axis of plot (default is xname) ### tylab is name to go on y-axis of plot (default is yname) ### cex.xylab is size of x and y axes ### ttitle is title of plot (default is none) ### cex.title is size of title ### print.results=TRUE if want to print regression results on screen ### ### show.legend=TRUE means include legend ### legend.x0name is what to go in the legend to indicate slope for x0 ### legend.x1name is what to go in the legend to indicate slope for x1 ### legend.loc is location of legend. Possible values are: ### "topleft","topright","bottomleft","bottomright","top","bottom","left","right","center" ### cex.legend is size of legend ### ### confidence.bands=TRUE if want confidence bands on the plot ### lty.lev0 is line type for plotting the line for dummy=0 ### lty.lev1 is line type for plotting the line for dummy=1 ### lty.confidence is line type for the confidence interval ### col.lev0 is color for points and line for dummy=0 ### col.lev1 is color for points and line for dummy=1 ### pch.lev0 is plotting character for dummy=0 ### pch.lev1 is plotting character for dummy=1 ### cex.points is size of points ### ### lwd.slope is lwd for slopes ### lwd.confidence is lwd for confidence bands ### ### The user has the option to either view the plots on the screen ### (save.plots=FALSE, which is the default), or to save the plots ### (save.plots=TRUE) ### If save.plots=TRUE, save either to pdf files (type.plots="pdf", the default) ### or as eps files (type.plots="eps"). The user controls the base name ### of the plots with the basename= argument, so if basename=silly and ### type.plots="pdf" then the plots will be silly1.pdf, silly2.pdf, etc. ### ### ndigits is number of digits to show when printing regression model |
||
| ScatterW Slope | SallyThurston | Thurston_R-Code_File Scatter W Slope | ### ARGUMENTS: ### tdat is database ### yname is name of y variable in tdat ### xname is name of x variable in tdat ### covnames is vector of names of remaining variables ### txlab is name to go on x-axis of plot ### tylab is name to go on y-axis of plot ### adjusted=TRUE if want adjusted line ### unadjusted=TRUE if want unadjusted line (note: can show both adjusted and unadjusted) ### col.adj=color to show adjusted regression line (and associated legend) ### col.unadj=color to show unadjusted regression line (and associated legend) ### conf.bands.adj=TRUE if want confidence band for adjusted regression lines ### conf.bands.unadj=TRUE if want confidence band for unadjusted regression lines ### cex.xylab=size of x and y axis labels ### pch.points=plotting character for the points (pch.points=1 is circles) ### cex.points=size of points ### ### (Next arguments apply to optional checks) ### print.results=TRUE means the program will output the sample size and regression summary ### check.line=TRUE means to also show (overlay) the regression line using the abline command ### (in addition to line using predict command: normally this should be FALSE) ### (For the adjusted line, will not be the same unless covnames are centered.) ### ### (Next arguments apply to the case when user wants to save the file) ### save.plots=TRUE means the user wants to create a file of the plot ### type.plots="eps" or "pdf" are the two options if save.plots=TRUE ### basename.plot=base name of the file, e.g. basename.plot=silly and type.plots="pdf" will create silly.pdf ### ### (Next arguments apply to legend showing slope and p-value) ### show.legend=TRUE means put slope and p-value on plot ### legend.loc=location of legend ### cex.legend=size of legend ### round.slope=n means to round slope in legend to n digits (default=2) |
|
| Kappa R | Yan Ma | Rochester_Kappa Statistics_R Function | The required parameters (n, g, t, x, y, weight): 1. n=Number of subjects 2. g=Number of categories 3. t= Number of time points 4. x Matrix for the first rater\x92s ratings, where element x(i,j) represents the rater\x92s rating on the ith subject at time j 2 for Cicchetti-Allison weighted kappa; weight=3 for Fleiss-Cohen weighted kappa. |
|
| Mann Whitney Wilcoxon R | Rui Chen | Rochester_MMW Longitudinal_R Function | dataset | |
| Multivariate Partial Least Squares (R) | Danh Nguyen | Davis_Partial Least Squares_R Function | Input argument(s) X_s Matrix of predictors (genes)--standardized to mean 0 variance 1 variance 1 ("training X" of size n x p). Y_s Matrix (or vector) of responses Y_s--also standardized ("training Y" of size nxL). X_ps Matrix of predictor values (test/validation X) to construct test components, X_ps (of size mxp). lv The number of PLS components (lv). Return(s): T1 n x lv matrix of PLS training components based on training information. T2 m x lv matrix of PLS test components contructed from training information. PVEX 1 x lv vector of cummulative percent of X-variation explained. PVEY 1 x lv vector of cummulative percent of Y-variation explained. W p x lv matrix of X-weights. B p x 1 vector of "regression coefficients". V p x 1 vector of linear combination of sum of squares of X-weights This is the so called 'VIP' (variable influence on projection) (Wold 1994; SAS Institue Inc., 1999). |
|
| Summarize R Macro | SallyThurston | Rochester_Summarize R_Function | For (1) lookup: colname (column name of a dataframe), longnames (vector of longer variable names, where the name of longnames should include colname) For (2) summarize: ### REQUIRED arguments are: ### tmat = dataframe containing variable for which we want a summary ### OPTIONAL arguments are: ### digits = number of digits to show in the summary ### quants = quantiles to be included. Default is c(0,.25,.5,.75,1) ### If don't want quantiles, make quants=NULL ### latex = TRUE if want output in LaTeX ### full.latex = TRUE if want latex output to be a stand-alone ### LaTeX file. If latex=TRUE and full.latex=FALSE, the ### output can be included with an \include{filename} command. ### (may be useful if output from this function will be ### included as one part of a larger set of function calls.) ### SD = TRUE if want to show SD ### nmis = TRUE if want to show number missing observations ### uniq = TRUE if want to show number of categories ### lookup.names = vector of longer variable names, where column names ### should match variable names in tmat ### filename = name of file where output should be saved ### (default is NULL, not to save it to a file) ### screen = TRUE if want to view results on the screen ### caption = caption for LaTeX format |
|
| U_ICC.R | Dr. Naiji Lu | (n,t,y) n=number of subjects t=number of time points y is the data |
||
| Variance Smoothing of Fully Moderated t-statistic | Lianbo Yu | fmt.R | Amean: vector of residual variances of all genes. df: degrees of freedom for sigmasq. span1: span parameter in LOESS smoothing function. span2: span parameter in LOESS smoothing function. iter1: iteration number in LOESS smoothing function. iter2: iteration number in LOESS smoothing function. b: number of genes on either side of moving average window when calculating variance of log residual variances. |
|
| Zero Inflated Poisson R | Naji Lu | Rochester_ZIP_R Function | The required parameters (n, noc): 1. n=Number of subjects 2. noc=Number of covariates |