regplot.confbands.fun_function(x,y,confidencelevel,CImean,PI,CIregline){
	#### For a simple linear regression line, this function
	#### will plot the line, CI for mean response, prediction intervals, 
	#### and a CI for the regression line.
	lm1_lm(y~x)	
	plot(x,y,ylim=c(min(y),(max(y)+.2*max(y))))
	abline(lm1$coefficients)
	#### calculation of components of intervals ####
	n_length(y)
	sx2_(var(x))
	shat_summary(lm1)$sigma
	s2hat_shat^2
	SEmuhat_shat*sqrt(1/n+ ((x-mean(x))^2)/((n-1)*sx2))
	SEpred_sqrt(s2hat+SEmuhat^2)
	t.quantile_qt(confidencelevel,lm1$df.residual)
	####
	if (CImean==T){
		mean.up_lm1$fitted+t.quantile*SEmuhat
		mean.down_lm1$fitted-t.quantile*SEmuhat
		lines(x,mean.up,lty=2)
		lines(x,mean.down,lty=2)
	}
	if (PI==T){
		PI.up_lm1$fitted+t.quantile*SEpred
		PI.down_lm1$fitted-t.quantile*SEpred
		lines(x,PI.up,lty=3)
		lines(x,PI.down,lty=3)
	}
	if (CIregline==T){
		HW_sqrt(2*qf(confidencelevel,n-lm1$df.residual,lm1$df.residual))*SEmuhat	
		CIreg.up_lm1$fitted+HW
		CIreg.down_lm1$fitted-HW
		lines(x,CIreg.up,lty=4)
		lines(x,CIreg.down,lty=4)
	}	
	choices_c(CImean,PI,CIregline)
	line.type_c(2,3,4)
	names.line_c("CI for mean resp.","Prediction Int.","CI for reg. line")
	legend(max(x)-.2*max(x),max(y)+.2*max(y),legend=names.line[choices],lty=line.type[choices])
	
}