Skip to contents

Financial time series used in examples in chapter 5.

Usage

data(ibm)
data(ibm9912.tp)
data(ibmdurad)
data(ibm1to5.dur)
data(ibm91.ads)
data(ibm91.adsx)
data(day15.ori)
data(day15)

Format

  • ibm IBM transactions data (11/1/1990 - 1/31/1991) data.frame of date.time, volume, bid, ask, and price of IBM stock transactions. date.time is of class 'chron', while volume, bid, ask, and price are all numeric. Some tranactions have the same date.time values, which is why this is a data.frame and not a zoo object.

  • ibm9912.tp IBM transactions data of December 1999: data.frame of date.time and price.

  • ibmdurad Adjusted time durations between trades of IBM stock (11/01/1990-1/31/1991). Format: data.frame with columns date.time and adjusted.duration

  • ibm1to5.dur subset of 'ibmdurad' limited to positive durations in the first 5 trading days.

  • ibm91.ads a data.frame on the changes in the price of IBM stock transactions between November 1, 1990 and January 31, 1991. This period includes 63 trading days, during which 59,838 transactions were recorded during normal trading hours. The first transaction for each day was dropped leaving the 59,775 transactions in this data.frame.

    • A.priceChange 1 if a price change from the previous trade, 0 otherwise

    • DirectionOfChg 1 if positive, -1 if negative, 0 if no change

    • SizeInTicks Size of the price change in number of ticks of 1/8 of a US dollar. NOTE: In this data.frame there are 10 anomalous records for which A.priceChange !=0 but SizeInTicks == 0. These correspond to price changes of half a tick, which got rounded down to 0.

  • ibm91.adsx a data.frame with 6 variables the same transactions as in 'ibm91.ads':

    • volume.thousandsthousands of shares traded

    • time.betw.tradesseconds between the previous two trades

    • bid.ask.spread the bid-ask spread in USD of the current transaction.

    • A.priceChange 1 if the previous trade involved a price change from its predacessor, and 0 otherwise

    • DirectionOfChg 1 if the previous change was positive, -1 if negative, 0 if no change

    • SizeInTicks Size of the price change in the previous trade in number of ticks of 1/8 of a US dollar. NOTE: The last three columns are ibm91.ads lagged one transaction, so ibm91.adsx[-1, 4:5] == ibm91.ads[-59775, ], with 24 exceptions.

  • day15.ori data.frame with the transaction time and the stock price for the 728 IBM stock transactions that occurred during normal trading hours on November 21, 1990.

  • day15 a zoo object with the following columns supposedly summarizing only the price changes in day15.ori:

    • timeBetwPriceChg time in seconds since the last price change

    • DirectionOfChange 1 if the price increased, -1 if it decreased

    • priceChgTicks price change in number of ticks of USD 1/8.

    • nTradesWoChg number of trades without a price change since the previous price change ... supposedly. These numbers do not match a manual extraction of these data from 'day15.ori'.

    • multTrans 1 if there were multiple transactions within the same one second interval, 0 if not.

    • dailyCumChg cumulative price change in USD since the start of normal trading on November 21, 1990.

References

Ruey Tsay (2005) Analysis of Financial Time Series, 2nd ed. (Wiley, ch. 5)

See also