mattbaggott

# minor changes from script by dsparks
# Letting plyr do the work for us.
# 

# Install and load needed packages
doInstall <- TRUE  # Change to FALSE if you don't want packages installed.
toInstall <- c("foreign", "plyr", "Hmisc", "ggplot2")
toInstall <- toInstall[!toInstall%in%library()$results[,1]] #check if present
if(doInstall&length(toInstall)!=0)
     {install.packages(toInstall, repos = "http://cran.r-project.org")}

mattbaggott

gastwirth <- function(x,...){
  # gastwirth's location estimator
  # discussed in Ronald Pearson's Exploring Data in Engineering, the Sciences, and Medicine
  # and at http://exploringdatablog.blogspot.com/2012/03/gastwirths-location-estimator.html
  ordstats = quantile(x, probs=c(1/3,1/2,2/3),...)
  weights = c(0.3,0.4,0.3)
  sum(weights*ordstats)
  #
}

mattbaggott

# Copyright 2012 Felix Schönbrodt
# All rights reserved.
#
# FreeBSD License
#
# Redistribution and use in source and binary forms, with or without
# modification, are permitted provided that the following conditions are
# met:
#
# 1. Redistributions of source code must retain the above copyright

mattbaggott

cria.tau <- function(data){

# Giolo, Suely Ruiz. "Turnbull's nonparametric estimator for interval-censored data'."
# Department of Statistics, Federal University of Paraná (2004): 1-10.

l <- data$left
r <- data$right
tau <- sort(unique(c(l,r[is.finite(r)])))
return(tau)
}

mattbaggott

###############################################################################################
## Function washer.AV in R-language
## Original Author : Andrea Venturini (andrea.venturini@bancaditalia.it)
## Venturini, A. (2011). Time Series Outlier Detection: A New Non Parametric Methodology 
## (Washer). Statistica 71: 329-344.
################################################################################################
washer.AV = function( dati ) #   p      t     i     y
{          # dati structure:  phenom./date/series/values/... other
           # example:    Phenomenon     Time    Zone    Value    ...
           #             -----------  --------   --     -----  --------  

mattbaggott

arch_test <- function (x, order=10){
    # AutoRegressive Conditional Heteroskedasticity (ARCH) estimator 
    xsq <- x^2 
    nobs <- length(x) 
    inds <- outer(0:(nobs - order - 1), order:1, "+") 
    xmat <- xsq[inds] 
    dim(xmat) <- dim(inds) 
    xreg <- lm(xsq[-1:-order] ~ xmat) 
    summary(xreg)$r.squared * (nobs - order) 
} 

mattbaggott

# improved list of objects
.ls.objects <- function (pos = 1, pattern, order.by,
                        decreasing=FALSE, head=FALSE, n=5) {
    napply <- function(names, fn) sapply(names, function(x)
                                         fn(get(x, pos = pos)))
    names <- ls(pos = pos, pattern = pattern)
    obj.class <- napply(names, function(x) as.character(class(x))[1])
    obj.mode <- napply(names, mode)
    obj.type <- ifelse(is.na(obj.class), obj.mode, obj.class)
    obj.size <- napply(names, object.size)

mattbaggott

#######################
#
# short investigation of id'ing breakpoints in data
#
# matt@baggott.net

library("bcp")
library("ggplot2")
library("changepoint")
library("reshape")

mattbaggott

##
## demonstration of distributions overlapping on lineplots
## matt@baggott.net
## Dec 11, 2012
##
## in response to: http://stats.stackexchange.com/questions/45591/r-plot-time-indexed-densities/45614#45614

library(ggplot2)   # for plotting
library(lubridate) # for getting year from dates in dataset
library(plyr)      # for getting annual mean easily

mattbaggott

##
## Sample code to teach about timezones in R
## matt@baggott.net
## Dec 13, 2012

## Time zones are important to understand when working with dates
## because the most common date class for R, POSIX, is actually a date/time
## class. (POSIX = "Portable Operating System Interface,
## an IEEE standard)
##