Rによる統計解析ハンドブック 第1章演習問題解答

This post is solutions of chapter 1 of `A Handbook of Statistical Analyses Using R, Second Edition'. As far as I know, there's no solutions on Web, so I decided to post my answers and hope to sophiscate them through discussing if needed.

このポストはRによる統計解析ハンドブック(第2版)の第1章の解答になります。私の知る限り、解法はWeb上にありませんので、私の解答を掲載することを決心しました。必要があれば議論して解答をより良くしたいと思っています。

Because almost no contents in the text book is written in this post, so please get one previously.

テキストに書かれている内容はほぼこのポストにありませんので、本は予め入手しておいてください。

1

library(HSAUR2)
prof.meds <- tapply(Forbes2000$profits, Forbes2000$country, median, na.rm=T)
print(prof.meds[c("United States", "United Kingdom", "France", "Germany")])

In the following answers, assume that `library(HSAUR2)' is already executed.

以後library(HSAUR2)は既に実行されていることを仮定せよ。

2

ger.deficit <- Forbes2000$country == "Germany" & Forbes2000$profits < 0
print(Forbes2000[ger.deficit, ])

3

Insurance Company is majority of this data (bermuda).

bermuda <- Forbes2000$country == "Bermuda"
print(table(Forbes2000[bermuda, "category"]))

4

big.profit <- Forbes2000[Forbes2000$profits >= sort(Forbes2000$profits, dec=T)[50],]
big.profit <- big.profit[!is.na(big.profit$profits),]
plot(big.profit$assets, big.profit$sales, log="xy", type="n")
text(big.profit$assets, big.profit$sales, abbreviate(big.profit$country))

5

print(tapply(Forbes2000$profits, Forbes2000$country, mean, na.rm=T))
larger <- function(x, th){
  return(length(which(x > th)))
}
print(tapply(Forbes2000$profits, Forbes2000$country, larger, 5))