version 1.4

DESCRIPTION

@@ -1,14 +1,16 @@
 Package: BayesGOF
 Type: Package
 Title: Bayesian Modeling via Goodness of Fit
-Version: 1.3
-Date: 2017-11-14
+Version: 1.4
+Date: 2018-01-02
 Author: Subhadeep Mukhopadhyay, Douglas Fletcher
 Maintainer: Doug Fletcher <tug25070@temple.edu>
 Description: Non-parametric method for learning prior distribution starting with parametric (subjective) prior.  It performs four interconnected tasks: (i) characterizes the uncertainty of the elicited prior; (ii) exploratory diagnostic for checking prior-data conflict; (iii) computes the final statistical prior density estimate; and (iv) performs macro- and micro-inference. Primary reference is Mukhopadhyay, S. and Fletcher, D. (2017, Technical Report). 
 Depends: orthopolynom, VGAM
+Suggests: knitr, rmarkdown
+VignetteBuilder: knitr
 License: GPL-2
 NeedsCompilation: no
-Packaged: 2017-11-16 02:29:46 UTC; Doug
+Packaged: 2018-01-03 14:43:19 UTC; Doug
 Repository: CRAN
-Date/Publication: 2017-11-16 10:20:32 UTC
+Date/Publication: 2018-01-05 19:00:44 UTC

MD5

@@ -1,50 +1,55 @@
-cfd4bef72baae3a4552280fa451fc676 *DESCRIPTION
+ff715b03553ac6270dbb83c08e7f16df *DESCRIPTION
 a4f3d575676f1b80e1058c92810fd2b7 *NAMESPACE
 e8cdb771de69edc672a7aac8d9440bb9 *R/BetaBinoMLE.R
-41c4e27fc84725947452cf8a4c781290 *R/DS.PostMean.R
-b26eb9d329b41e2370371b06b92f2048 *R/DS.PostMean.reduce.R
+fe43131dc70d9bfb435a4e0dcd3ae58d *R/ConMean.prt.2.R
+f534a2cee775d2300a120951ff633f4a *R/DS.PostMean.R
+6f77a33e7e6f0fa1184b966f73dae483 *R/DS.PostMean.reduce.R
 df69695935b3e562e17b49c8223033a9 *R/DS.macro.inf.R
-468477eb09a9719982eac417a2c94b62 *R/DS.micro.inf.R
-f6bd71b34fe492a6b41c5767eb31772a *R/DS.mode.map.R
+d7e1d4d09924ca058faacdad2455fa6d *R/DS.micro.inf.R
+60be8417bea981f785e722ec25c278b9 *R/DS.mode.map.R
 03be355b3798c6a69b97548e5eee3926 *R/DS.mode.reduce.R
-176d6138242fd09744d1d85328a1a37f *R/DS.prior.R
+8f5455dc47b5866c8c6423ee6b5f83ab *R/DS.prior.R
 e5354a65b65d2c5b81582559ee7a1030 *R/EXP.denom.R
 5ded1e76591fbd05471de371c5261042 *R/EXP.num.1.R
 cd2cdbd50f105ec57eb2fd32efc9630d *R/EXP.num.2.R
-074ac6883254aa2c0c110ef810250a9e *R/EXP.score.R
+399a1ec91a0e02f8186b74648054c169 *R/EXP.score.R
 e04999cc772d27e577942b140b77ef24 *R/LP.basis.beta.R
 0488b1290b901beda5de0d54c6000679 *R/LP.smooth.R
 6b2a90b2028ddec70ff0a68fa1a519e0 *R/Local.Mode.R
-2809c3ee1ee7446e7a65b25a9705376a *R/PP.prt.2.R
 cc0c13114ef93fab90e4634341fa76ce *R/Reduce.LP.coef.R
 7fa03fde303c925b5de4e3fa82bfe8a4 *R/mom.est.R
-a704236500da903d6e489b72cf9a7a59 *R/plot.DS_GF.R
-4a066dcb7cf21ec5cae398acb93e70a2 *R/plot.DS_GF_macro_mean.R
-72934ff6d9d54321965bd059222208d3 *R/plot.DS_GF_macro_mode.R
-4958fab993b56a933daa39ab4f52c953 *R/plot.DS_GF_micro.R
+71c42d22a062530811bf5774eab9b56f *R/plot.DS_GF.R
+1f8be9e42445840b66f7f2457fa95f15 *R/plot.DS_GF_macro_mean.R
+22ffc8f09ab875efedf86b9f35707f27 *R/plot.DS_GF_macro_mode.R
+ca68dbc678d9f573c109a904b2ac29fb *R/plot.DS_GF_micro.R
 32731dab82fe5d939ab07f068eece6e5 *R/print.DS_GF.R
 847051f9d55ea4d3df293cbe661e8fb7 *R/print.DS_GF_macro_mean.R
 5d2acbda0d40b6b8ea5074459f8916ba *R/print.DS_GF_macro_mode.R
 9a2ea0cbaae526bf289d047e08c484c2 *R/print.DS_GF_micro.R
 c5751d11df67d3e13765bb79a0ed8cdf *R/rDS.R
 904d66c45aae0007a9a9790007834619 *R/rDS.posterior.R
 43346db63edf02693e6dc6cde4561463 *R/weight.fun.beta.R
-e8e8a76b16019e4560c612c15fd0e13d *build/partial.rdb
+52e60785b26ceed34594689813d7cde2 *build/partial.rdb
+32bb6c15cc261cc5a800feaef03df159 *build/vignette.rds
 4eb418b2906c27f4d7c4f1820cdfef39 *data/rat.rda
 86f2e44eba816a17d1c21b98238eb0f9 *data/ship.rda
 2ea567712e420d7dad930065d164f0ea *data/surg.rda
 b2cc985b167635ee9460b40031cb97b1 *data/tacks.rda
 d5e17a0af9b0f694d178a824213f7f04 *data/terb.rda
+b6b93be51774b48490af693f8da7b977 *inst/doc/vignette_BayesGOF.R
+cbd58b4bd918f85fd591770a32884297 *inst/doc/vignette_BayesGOF.Rmd
+e4d0976b6350f76127b0c4229a87fbc2 *inst/doc/vignette_BayesGOF.html
 f602b20ce666636fd4ce1fe3e2e4b14f *man/BayesGOF-package.Rd
 d5fe161c86340df185b1bf8722ed3244 *man/BetaBinoMLE.Rd
-761067228b62ec63a273ba5dbe9034b2 *man/DS.PostMean.Rd
+b14a54fa25faf8496826ef5e2a0938aa *man/DS.PostMean.Rd
 f212f760e4377b14adde601a86a6c06b *man/DS.macro.inf.Rd
 323c51a0c260a624791b4c2a5cd96081 *man/DS.micro.inf.Rd
-cda9fcc073393201bc5ec9e9d1c94817 *man/DS.prior.Rd
+883a6c582feafd1a0c212e75a234c579 *man/DS.prior.Rd
 80f2637e9f992da56001c6e04a910c57 *man/LP.basis.beta.Rd
 c5ae2041c3448673d570d4f62292a08a *man/rDS.Rd
 d0e4b41b002567b8dd89ece7943ad973 *man/rat.Rd
 036e74bea69c9cb18ce9435abda7a77d *man/ship.Rd
 1a4578d3061e06f366a3a81187e2d7bb *man/surg.Rd
 7df318a497e78c94fafa22de2db27802 *man/tacks.Rd
 e260deea72882c143a52313389aa8b6d *man/terb.Rd
+cbd58b4bd918f85fd591770a32884297 *vignettes/vignette_BayesGOF.Rmd

R/PP.prt.2.R → R/ConMean.prt.2.R

@@ -1,4 +1,4 @@
-PP.prt.2 <-
+ConMean.prt.2 <-
 function(c.vec, weight, leg.mat, u, par1, par2){
 	#### theta is G inv u = qnorm(u,muhat,tauhat)
 	inner.part <- qbeta(u, par1, par2)*leg.mat

R/DS.PostMean.R

@@ -1,26 +1,14 @@
 DS.PostMean <-
-function(y.i, n.i, g.par, u, LP.par, method = c("LP-Score", "Theta")){
-		method = match.arg(method)
+function(y.i, n.i, g.par, u, LP.par){
 		post.par1.i <- y.i + g.par[1]
 		post.par2.i <- n.i - y.i + g.par[2]
-		weight <- weight.fun.beta(u, g.par[1],g.par[2],post.par1.i,post.par2.i)
+		weight <- weight.fun.beta(u, g.par[1], g.par[2], post.par1.i, post.par2.i)
 		leg.mat <- LP.basis.beta(u,c(1,1), length(LP.par))
-		#leg.mat2 <- Leg.poly(u, length(LP.par))
-		switch(method,
-		"LP-Score" = {
-			vec.map <- (EXP.num.1(weight, leg.mat) + 
-						EXP.num.2(LP.par, weight, leg.mat) ) / 
-						EXP.denom(LP.par, weight, leg.mat)
-			return(vec.map)
-			},
-		"Theta" = {
-			if(sum(LP.par^2) == 0){
+		if(sum(LP.par^2) == 0){
 				ConMean.ind <- (post.par1.i)/(post.par1.i + post.par2.i)
 				} else {
 				post.mu <- post.par1.i /(post.par1.i + post.par2.i)
-				ConMean.ind <- ( post.mu + PP.prt.2(LP.par, weight, leg.mat, u, g.par[1], g.par[2]) ) / EXP.denom(LP.par,weight,leg.mat)
+				ConMean.ind <- ( post.mu + ConMean.prt.2(LP.par, weight, leg.mat, u, g.par[1], g.par[2]) ) / EXP.denom(LP.par,weight,leg.mat)
 				}
-			return(ConMean.ind)
-		}
-		)
+		return(ConMean.ind)
 	}

R/DS.PostMean.reduce.R

@@ -13,7 +13,7 @@ function(DS.GF.obj){
 		B <- dim(DS.GF.obj$prior.data)[1]
 		u <- seq(1/B,1-(1/B), length.out = B) ##unit interval, 0 to 1
 		ConMean.vec <- NULL
-		ConMean.vec <- apply(DS.GF.obj$obs.data, 1, function(x) DS.PostMean(x[1], x[2], DS.GF.obj$g.par, u, DS.GF.obj$LP.par, method = "Theta"))
+		ConMean.vec <- apply(DS.GF.obj$obs.data, 1, function(x) DS.PostMean(x[1], x[2], DS.GF.obj$g.par, u, DS.GF.obj$LP.par))
 	}
 	return(ConMean.vec)
 }

R/DS.micro.inf.R

@@ -2,34 +2,31 @@ DS.micro.inf <-
 function(DS.GF.obj, y.i, n.i){
 #####################################################
 # INPUTS
-#  y.0			number of successes in sample
-#  n.0			number of total trials in sample
+#  y.i			number of successes in new study
+#  n.i			number of total trials in new study
 #  DS.GF.obj		AutoBayes-DataCorrect object
 # OUTPUTS
 		out <- list()
-		alpha_0 <- DS.GF.obj$g.par[1]
-		beta_0 <- DS.GF.obj$g.par[2]
-		c.vec <- DS.GF.obj$LP.par
-		post.alph.i <- y.i + alpha_0
-		post.beta.i <- n.i - y.i + beta_0
-		##calculate denominator/standardization constant
+		#find posterior parameters
+		post.alph.i <- y.i + DS.GF.obj$g.par[1]
+		post.beta.i <- n.i - y.i + DS.GF.obj$g.par[2]
+		##determine parametric density
 		B=250
 		u.int <- seq(1/B, 1-(1/B), length.out = B)
-		leg.mat.den <- LP.basis.beta(u.int, c(1,1), length(c.vec))
-		wght.den <- weight.fun.beta(u.int,alpha_0,beta_0,
-					post.alph.i,post.beta.i)
-		##Get non-standard LP adjusted density
 		eb.pos.den <- dbeta(u.int, post.alph.i, post.beta.i)
-		#u.theta <- pbeta(u.int, alpha_0, beta_0)
-		Leg.G <- LP.basis.beta(u.int, c(alpha_0, beta_0), length(c.vec))
-		nstd.dc.pos <- eb.pos.den*(1+Leg.G%*%c.vec)
-		denom <- EXP.denom(c.vec, wght.den, leg.mat.den)
-		ds.pos <- nstd.dc.pos/denom
+		##determine LP density
+		#Leg(u) for weight function
+		leg.mat.den <- LP.basis.beta(u.int, c(1,1), length(DS.GF.obj$LP.par))
+		wght.den <- weight.fun.beta(u.int, DS.GF.obj$g.par[1], DS.GF.obj$g.par[2],
+					post.alph.i,post.beta.i)
+		Leg.G <- LP.basis.beta(u.int, c(DS.GF.obj$g.par[1], DS.GF.obj$g.par[2]), length(DS.GF.obj$LP.par))
+		ds.pos <- eb.pos.den*(1+Leg.G%*%DS.GF.obj$LP.par) / EXP.denom(DS.GF.obj$LP.par, wght.den, leg.mat.den)
+		#Format output
 		out$post.data <- data.frame(theta.vals = u.int,
 									parm.pos = eb.pos.den,
 									ds.pos = ds.pos)				
 		out$post.data[out$post.data<0]<-0
-		out$post.mean <- DS.PostMean(y.i, n.i, DS.GF.obj$g.par, u.int, DS.GF.obj$LP.par, method = "Theta")
+		out$post.mean <- DS.PostMean(y.i, n.i, DS.GF.obj$g.par, u.int, DS.GF.obj$LP.par)
 		out$post.mode <- DS.mode.map(y.i, n.i, DS.GF.obj$g.par, DS.GF.obj$LP.par, B)
 		out$study <- c(y.i, n.i)
 		class(out) <- "DS_GF_micro"

R/DS.mode.map.R

@@ -12,8 +12,7 @@ function(y.i, n.i, g.par, LP.par, B){
 	post.par2.i <- n.i - y.i + g.par[2]
 	theta.rng <- seq(1/B,1-(1/B), length.out = B)
 	base.den <- dbeta(theta.rng, post.par1.i, post.par2.i)
-	u <- pbeta(theta.rng ,g.par[1], g.par[2]) 
-	Leg.G <- LP.basis.beta(u,c(1,1),length(LP.par))
+	Leg.G <- LP.basis.beta(theta.rng, g.par, length(LP.par))
 	adj <-1+ (Leg.G %*% (LP.par))
 	ds.den <- base.den * adj
 	ds.mode <- theta.rng[which.max(ds.den)]

R/DS.prior.R

@@ -3,8 +3,8 @@ function(yn.df, max.m = 8, start.par, iter.c = 200,
 						B = 1000, smooth.crit = "BIC"){
 ####iterates through given conditions to find c-vector
 #### INPUTS		
-#### y.i 	   		predictions for X from each of k servers
-#### n.i	   		Bi-beta: number observations per y.i
+#### yn.df 			dataframe with 1st column as predictions for X from each of k servers
+#### 		   		and second column as number observations per y.i
 #### start.par   	user-desired parameters for designated prior for beta-bin: c(alpha, beta)
 #### max.m			maximum order of legendre polynomials desired
 #### iter.c			number of iterations desired for calculating LP coefficents
@@ -40,9 +40,11 @@ function(yn.df, max.m = 8, start.par, iter.c = 200,
 		dev.m <- NULL
 		B.loop <- 150
 		u.loop <- seq(1/B.loop,1-(1/B.loop), length.out = B.loop) ##unit interval, 0 to 1
+		## Generate Posterior Values for Weight Function
 		post.alpha.i <- start.par[1] + yn.df[,1]
 		post.beta.i <- yn.df[,2] - yn.df[,1] + start.par[2]
 		post.mat <- data.frame(al = post.alpha.i, be = post.beta.i)
+		## Generate Weight Function Matrix for Conditional Expectation
 		wght.loop <- apply(post.mat, 1, function(x) weight.fun.beta(u.loop, start.par[1], start.par[2], x[1], x[2]))
 		###Determine LP coefficients
 		if(smooth.crit == "BIC"){
@@ -114,4 +116,4 @@ function(yn.df, max.m = 8, start.par, iter.c = 200,
 				 class(out) <- "DS_GF"
 				 return(out)
 				 }
-}	
+}

R/EXP.score.R

@@ -5,4 +5,4 @@ function(u, LP.par, weight.vec, leg.mat){
 						EXP.num.2(LP.par, weight.vec, leg.mat) ) / 
 						EXP.denom(LP.par, weight.vec, leg.mat)
 			return(vec.map)
-}	
+}

R/plot.DS_GF.R

@@ -1,15 +1,16 @@
 plot.DS_GF <-
-function(x, plot.type = c("Ufunc","mDev","DS_G"), ...) {
+function(x, plot.type = c("Ufunc","mDev","DSg"), ...) {
 	method = match.arg(plot.type)
 	switch(method,
 		"Ufunc" = {
 			plot(x$UF.dat$UF.x, x$UF.dat$UF.y, 
-				xlim = c(0,1),ylim = c(0,2.5), 
+				xlim = c(0,1),
+				#ylim = c(0,2.5), 
 				main = "",
 				type = "l",
 				lwd = 2,
 				xlab = "", ylab = "", font.main = 1,
-				cex.lab=1.25, cex.axis=1.25, cex.main=1.25, cex.sub=1.25)
+				cex.lab=1.25, cex.axis=1.25, cex.main=1.25, cex.sub=1.25,...)
 			abline(h = 1, col = "red", lwd = 2, cex = 3, lty = "dashed")
 			title(ylab = expression(paste(hat(d))), line = 2.3, cex.lab=1.25)
 			},
@@ -19,24 +20,23 @@ function(x, plot.type = c("Ufunc","mDev","DS_G"), ...) {
 				main = "", 
 				type = "l", lwd = 2, col = "darkorchid",
 				xlab = "m", ylab = "Deviance: AIC", font.main = 1,
-				cex.lab=1.5, cex.axis=2, cex.main=2, cex.sub=1.5)
+				cex.lab=1.5, cex.axis=2, cex.main=2, cex.sub=1.5,...)
 				} else {
 			plot(x$dev.df$m, x$dev.df$dev, 
 				main = "",
 				type = "l", lwd = 2, col = "darkorchid",
 				xlab = "m", ylab = "Deviance: BIC", font.main = 1,
-				cex.lab=1.5, cex.axis=2, cex.main=2, cex.sub=1.5)
+				cex.lab=1.5, cex.axis=2, cex.main=2, cex.sub=1.5,...)
 				}
 			},
-		"DS_G" = {
+		"DSg" = {
 			if(sum(x$LP.par^2)==0){
 				plot(x$prior.data$theta.vals, x$prior.data$parm.prior, 
-					xlim = c(0,1), 
 					main = "",
 					type = "l", lwd = 2, col = "blue", lty = "dashed",
 					xlab = "", #expression(theta) 
 					ylab = "", font.main = 1,
-					cex.lab=1.25, cex.axis=1.5, cex.main=1.5, cex.sub=1.5)
+					cex.lab=1.25, cex.axis=1.5, cex.main=1.5, cex.sub=1.5, ...)
 				title(ylab = expression(paste(hat(pi)(theta))), line = 2.3, cex.lab=1.25)
 				legend("bottom", legend = "g",
 					xpd = TRUE, horiz = TRUE, inset = c(0, -.18),
@@ -45,12 +45,10 @@ function(x, plot.type = c("Ufunc","mDev","DS_G"), ...) {
 			} else {
 				x.name <- deparse(substitute(x))
 				plot(x$prior.data$theta.vals, x$prior.data$ds.prior, 
-					xlim = c(0,1), 
 					main = "",
-					#main = bquote(.(x.name)~"Prior Densities: G and"~Pi), 
 					type = "l", lwd = 2, col = "red3",
 					xlab = "", ylab = "", font.main = 1,
-					cex.lab=1.25, cex.axis=1.25, cex.main=1.25, cex.sub=1.25)
+					cex.lab=1.25, cex.axis=1.25, cex.main=1.25, cex.sub=1.25,...)
 				title(ylab = expression(paste(hat(pi)(theta))), line = 2.3, cex.lab=1.25)
 				lines(x$prior.data$theta.vals, x$prior.data$parm.prior, 
 					  col = "blue", lwd = 2, cex = 3, lty = "dashed")

R/plot.DS_GF_macro_mean.R

@@ -2,11 +2,11 @@ plot.DS_GF_macro_mean <-
 function(x, ...){
 	par(mar=c(5,5,4,2)+0.3) #changes left margin to make large labels fit
 	plot(x$prior.data$theta.vals, x$prior.data$parm.prior, 
-		xlim = c(0,1), 
+		#xlim = c(0,1), 
 		main = "MacroInference: Mean", 
 		type = "l", yaxs = "i", lwd = 2, col = "red3", 
 		xlab = expression(theta), ylab = "", font.main = 1,
-		cex.lab=1.45, cex.axis=1.5, cex.main=2, cex.sub=1.5)
+		cex.lab=1.45, cex.axis=1.5, cex.main=2, cex.sub=1.5, ...)
 	title(ylab = expression(paste(hat(pi)(theta))), line = 2.3, cex.lab=1.45)
 	points(x$model.mean, 0, col = "green", pch = 17, cex = 1.5)
 	axis(1, at=seq(x$model.mean - x$mean.sd,

R/plot.DS_GF_macro_mode.R

@@ -7,10 +7,10 @@ function(x, ...){
 		}
 	if(dim(x$prior.data)[2] == 3){
 		par(mar=c(5,5,4,2)+0.3) #changes left margin to make large labels fit
-		plot(x$prior.data$theta.vals, x$prior.data$ds.prior, xlim = c(0,1), 
+		plot(x$prior.data$theta.vals, x$prior.data$ds.prior, 
 			main = "MacroInference: Modes", type = "l", yaxs = "i", lwd = 2, col = "red3",
 			xlab = expression(theta), ylab = "", font.main = 1,
-			cex.lab=1.45, cex.axis=1.5, cex.main=2, cex.sub=1.5)
+			cex.lab=1.45, cex.axis=1.5, cex.main=2, cex.sub=1.5, ...)
 		title(ylab = expression(paste(hat(pi)(theta))), line = 2.3, cex.lab=1.45)
 		points(x$model.modes, rep(0, length(x$model.modes)), col = "green", pch = 17, cex = 1.5)
 		for(i in 1:length(x$model.modes)){
@@ -19,15 +19,15 @@ function(x, ...){
 			}
 		} else {
 		par(mar=c(5,5,4,2)+0.3) #changes left margin to make large labels fit
-		plot(x$prior.data$theta.vals, x$prior.data$parm.prior, xlim = c(0,1), 
+		plot(x$prior.data$theta.vals, x$prior.data$parm.prior, 
 			main = "MacroInference: Modes", type = "l", yaxs = "i", lwd = 2, col = "red3",
 			xlab = expression(theta), ylab = "", font.main = 1,
-			cex.lab=1.45, cex.axis=1.5, cex.main=2, cex.sub=1.5)
+			cex.lab=1.45, cex.axis=1.5, cex.main=2, cex.sub=1.5, ...)
 		title(ylab = expression(paste(hat(pi)(theta))), line = 2.3, cex.lab=1.45)
 		points(x$model.modes, rep(0, length(x$model.modes)), col = "green", pch = 17, cex = 1.5)
 		for(i in 1:length(x$model.modes)){
 			axis(1, at=seq(mode.mat[i,1],mode.mat[i,2],length=20),tick=TRUE,
 						col="goldenrod4",labels = F,tck=-0.015)
 		}
 	}
-}
+}

R/plot.DS_GF_micro.R

@@ -1,11 +1,10 @@
 plot.DS_GF_micro <-
-function(x, x.lim = c(0,1), ...){
-	plot(x$post.data$theta.vals, x$post.data$ds.pos, xlim = x.lim, 
+function(x, ...){
+	plot(x$post.data$theta.vals, x$post.data$ds.pos,  
 		main = "Posterior Density Estimate", type = "l", lwd = 2, col = "red3",
 		xlab = expression(theta), ylab = "", font.main = 1,
-		cex.lab=1.45, cex.axis=1.5, cex.main=1.5, cex.sub=1.5)
+		cex.lab=1.45, cex.axis=1.5, cex.main=1.5, cex.sub=1.5, ...)
 	title(ylab = expression(paste(hat(pi)(theta[i]~"|"~y[i]))), line = 2.3, cex.lab=1.45)
 	lines(x$post.data$theta.vals, x$post.data$parm.pos,
 		col = "blue", lty = "dashed", lwd = 2)
 	}
-

inst/doc/vignette_BayesGOF.R

@@ -0,0 +1,36 @@
+## ---- message  = FALSE---------------------------------------------------
+library(BayesGOF)
+set.seed(8697)
+data(rat)
+###Use MLE to determine starting values
+rat.start <- BetaBinoMLE(rat$y, rat$n)$estimate
+
+## ------------------------------------------------------------------------
+rat.ds <- DS.prior(rat, max.m = 6, rat.start)
+
+## ---- fig.height = 5.5, fig.width = 5.5, fig.align = 'center'------------
+plot(rat.ds, plot.type = "Ufunc")
+
+## ------------------------------------------------------------------------
+rat.ds
+
+## ----fig.height = 5.5, fig.width = 5.5,fig.align = 'center'--------------
+plot(rat.ds, plot.type = "DSg")
+
+## ---- warning = FALSE----------------------------------------------------
+rat.macro.md <- DS.macro.inf(rat.ds, num.modes = 2 , iters = 25, method = "mode") 
+
+## ------------------------------------------------------------------------
+rat.macro.md
+
+## ---- fig.height = 5.5, fig.width = 5.5,fig.align = 'center'-------------
+
+plot(rat.macro.md)
+
+## ---- fig.align = 'center'-----------------------------------------------
+rat.y71.micro <- DS.micro.inf(rat.ds, y.i = 4, n.i = 14)
+rat.y71.micro
+
+## ----fig.height = 5.5, fig.width = 5.5,fig.align = 'center'--------------
+plot(rat.y71.micro)
+