Analysts forecast error: A robust prediction model and its short term trading

Kris Boudt, Peter de Goeij, James Thewissen, Geert Van Campenhout

Research output: Contribution to journalArticleScientificpeer-review

Abstract

We examine the profitability of implementing a short term trading strategy based on predicting the error in analysts' earnings per share forecasts using publicly available information. Since large earnings surprises may lead to extreme values in the forecast error series that disrupt their smooth autoregressive dynamics, we propose to use robust fixed effect panel estimation methods as an alternative to panel least squares or the pooled least absolute deviations estimator. For the I/B/E/S data from 1998 to 2010, we show that the strategy of taking a long (short) position in stocks with the most pessimistic (optimistic) consensus forecast and closing the position on the first post announcement day has an annual gross abnormal return of 16.56%, after correcting for market risk, size, book-to-market and price momentum effects. A key insight is that the profitability of the trading strategy stems from using robust forecasting methods.
Original languageEnglish
Pages (from-to)683-715
JournalAccounting and Finance
Volume55
Issue number3
DOIs
Publication statusPublished - Sep 2015

Fingerprint

Trading strategies
Profitability
Forecast error
Prediction model
Analysts' forecasts
Announcement
Deviation
Earnings per share
Earnings surprises
Analysts
Market risk
Panel estimation
Forecasting method
Extreme values
Price momentum
Book-to-market
Abnormal returns
Estimator
Fixed effects
Momentum effect

Keywords

  • financial analysts
  • forecast error
  • short term prediction
  • trading strategy

Cite this

Boudt, Kris ; de Goeij, Peter ; Thewissen, James ; Van Campenhout, Geert. / Analysts forecast error : A robust prediction model and its short term trading. In: Accounting and Finance. 2015 ; Vol. 55, No. 3. pp. 683-715.
@article{5fe49a5f2b984d099c354fce787228bb,
title = "Analysts forecast error: A robust prediction model and its short term trading",
abstract = "We examine the profitability of implementing a short term trading strategy based on predicting the error in analysts' earnings per share forecasts using publicly available information. Since large earnings surprises may lead to extreme values in the forecast error series that disrupt their smooth autoregressive dynamics, we propose to use robust fixed effect panel estimation methods as an alternative to panel least squares or the pooled least absolute deviations estimator. For the I/B/E/S data from 1998 to 2010, we show that the strategy of taking a long (short) position in stocks with the most pessimistic (optimistic) consensus forecast and closing the position on the first post announcement day has an annual gross abnormal return of 16.56{\%}, after correcting for market risk, size, book-to-market and price momentum effects. A key insight is that the profitability of the trading strategy stems from using robust forecasting methods.",
keywords = "financial analysts, forecast error, short term prediction, trading strategy",
author = "Kris Boudt and {de Goeij}, Peter and James Thewissen and {Van Campenhout}, Geert",
year = "2015",
month = "9",
doi = "10.1111/acfi.12076",
language = "English",
volume = "55",
pages = "683--715",
journal = "Accounting and Finance",
issn = "0810-5391",
publisher = "Wiley-Blackwell",
number = "3",

}

Analysts forecast error : A robust prediction model and its short term trading. / Boudt, Kris; de Goeij, Peter; Thewissen, James; Van Campenhout, Geert.

In: Accounting and Finance, Vol. 55, No. 3, 09.2015, p. 683-715.

Research output: Contribution to journalArticleScientificpeer-review

TY - JOUR

T1 - Analysts forecast error

T2 - A robust prediction model and its short term trading

AU - Boudt, Kris

AU - de Goeij, Peter

AU - Thewissen, James

AU - Van Campenhout, Geert

PY - 2015/9

Y1 - 2015/9

N2 - We examine the profitability of implementing a short term trading strategy based on predicting the error in analysts' earnings per share forecasts using publicly available information. Since large earnings surprises may lead to extreme values in the forecast error series that disrupt their smooth autoregressive dynamics, we propose to use robust fixed effect panel estimation methods as an alternative to panel least squares or the pooled least absolute deviations estimator. For the I/B/E/S data from 1998 to 2010, we show that the strategy of taking a long (short) position in stocks with the most pessimistic (optimistic) consensus forecast and closing the position on the first post announcement day has an annual gross abnormal return of 16.56%, after correcting for market risk, size, book-to-market and price momentum effects. A key insight is that the profitability of the trading strategy stems from using robust forecasting methods.

AB - We examine the profitability of implementing a short term trading strategy based on predicting the error in analysts' earnings per share forecasts using publicly available information. Since large earnings surprises may lead to extreme values in the forecast error series that disrupt their smooth autoregressive dynamics, we propose to use robust fixed effect panel estimation methods as an alternative to panel least squares or the pooled least absolute deviations estimator. For the I/B/E/S data from 1998 to 2010, we show that the strategy of taking a long (short) position in stocks with the most pessimistic (optimistic) consensus forecast and closing the position on the first post announcement day has an annual gross abnormal return of 16.56%, after correcting for market risk, size, book-to-market and price momentum effects. A key insight is that the profitability of the trading strategy stems from using robust forecasting methods.

KW - financial analysts

KW - forecast error

KW - short term prediction

KW - trading strategy

U2 - 10.1111/acfi.12076

DO - 10.1111/acfi.12076

M3 - Article

VL - 55

SP - 683

EP - 715

JO - Accounting and Finance

JF - Accounting and Finance

SN - 0810-5391

IS - 3

ER -