error.bars: Plot means and confidence intervals

Description

One of the many functions in R to plot means and confidence intervals. Can be done using barplots if desired. Can also be combined with such functions as boxplot to summarize distributions. Means and standard errors are calculated from the raw data using describe. Alternatively, plots of means +/- one standard deviation may be drawn.

Usage

error.bars(x,stats=NULL, ylab = "Dependent Variable",xlab="Independent Variable",
  main=NULL,eyes=TRUE, ylim = NULL, xlim=NULL,alpha=.05,sd=FALSE, labels = NULL, 
   pos = NULL,  arrow.len = 0.05,arrow.col="black", add = FALSE,bars=FALSE,within=FALSE,
    ...)

Arguments

A data frame or matrix of raw data

stats

Alternatively, a data.frame of descriptive stats from (e.g., describe)

ylab

y label

xlab

x label

main

title for figure

ylim

if specified, the limits for the plot, otherwise based upon the data

xlim

if specified, the x limits for the plot, otherwise c(.5,nvar + .5)

eyes

should 'cats eyes' plots be drawn

alpha

alpha level of confidence interval -- defaults to 95% confidence interval

if TRUE, draw one standard deviation instead of standard errors at the alpha level

labels

X axis label

pos

where to place text: below, left, above, right

arrow.len

How long should the top of the error bars be?

arrow.col

What color should the error bars be?

add

add=FALSE, new plot, add=TRUE, just points and error bars

bars

bars=TRUE will draw a bar graph if you really want to do that

within

should the error variance of a variable be corrected by 1-SMC?

...

other parameters to pass to the plot function, e.g., typ="b" to draw lines, lty="dashed" to draw dashed lines

Value

Graphic output showing the means + x These confidence regions are based upon normal theory and do not take into account any skew in the variables. More accurate confidence intervals could be found by resampling.

Details

Drawing the mean +/- a confidence interval is a frequently used function when reporting experimental results. By default, the confidence interval is 1.96 standard errors of the t-distribution.

If within=TRUE, the error bars are corrected for the correlation with the other variables by reducing the variance by a factor of (1-smc). This allows for comparisons between variables.

The error bars are normally calculated from the data using the describe function. If, alternatively, a matrix of statistics is provided with column headings of values, means, and se, then those values will be used for the plot (using the stats option). However, in this case, the error bars will be one s.e. rather than a function of the alpha level.

If sd is TRUE, then the error bars will represent one standard deviation from the mean rather than be a function of alpha and the standard errors.

Examples

Run this code

x <- replicate(20,rnorm(50))
boxplot(x,notch=TRUE,main="Notched boxplot with error bars")
error.bars(x,add=TRUE)
abline(h=0)

error.bars(attitude,alpha=.5,main="50 percent confidence limits") #another example
error.bars(attitude,bar=TRUE)  #show the use of bar graphs


#combine with a strip chart and boxplot
stripchart(attitude,vertical=TRUE,method="jitter",jitter=.1,pch=19,
           main="Stripchart with 95 percent confidence limits")
boxplot(attitude,add=TRUE)
error.bars(attitude,add=TRUE,arrow.len=.2)

#use statistics from somewhere else
my.stats <- data.frame(values=c(1,4,8),mean=c(10,12,18),se=c(2,3,5))
error.bars(stats=my.stats,type="b",main="data with confidence intervals")
#note that in this case, the error bars are 1 s.e.  To modify that, change the s.e.

#Consider the case where we get stats from describe
temp <- describe(attitude)
error.bars(stats=temp)
#these error bars will be just one s.e.

#adjust the s.e. to vary by alpha level
alpha <- .05
temp[,"se"] <- temp[,"se"] * qt(1-alpha/2,temp[,"n"])
error.bars(stats=temp)
#show these do not differ from the other way by overlaying the two
error.bars(attitude,add=TRUE)

Run the code above in your browser using DataLab

Get 50% off unlimited learning