Predicting the unpredictable: new experimental evidence on forecasting random walks
We investigate how individuals use measures of apparent predictability from price charts to predict future market prices. Subjects in our experiment predict both random walk times series, as in the seminal work by Bloomfield and Hales (2002) (BH), and stock price time series. We successfully replica...
| Main Authors: | , , , , |
|---|---|
| Other Authors: | |
| Format: | Journal Article |
| Language: | English |
| Published: |
2023
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/172196 |
| _version_ | 1826123594391879680 |
|---|---|
| author | Bao, Te Corgnet, Brice Hanaki, Nobuyuki Riyanto, Yohanes E. Zhu, Jiahua |
| author2 | School of Social Sciences |
| author_facet | School of Social Sciences Bao, Te Corgnet, Brice Hanaki, Nobuyuki Riyanto, Yohanes E. Zhu, Jiahua |
| author_sort | Bao, Te |
| collection | NTU |
| description | We investigate how individuals use measures of apparent predictability from price charts to predict future market prices. Subjects in our experiment predict both random walk times series, as in the seminal work by Bloomfield and Hales (2002) (BH), and stock price time series. We successfully replicate the experimental findings in BH that subjects are less trend-chasing when there are more reversals in random walk times series. We do not find evidence that subjects overreact less to the trend when there are more reversals in the stock price prediction task. Our subjects also appear to use other variables such as autocorrelation coefficient, amplitude and volatility as measures of predictability. However, as random walk theory predicts, relying on apparent patterns in past data does not improve their prediction accuracy. |
| first_indexed | 2024-10-01T06:06:52Z |
| format | Journal Article |
| id | ntu-10356/172196 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2024-10-01T06:06:52Z |
| publishDate | 2023 |
| record_format | dspace |
| spelling | ntu-10356/1721962023-11-29T02:11:18Z Predicting the unpredictable: new experimental evidence on forecasting random walks Bao, Te Corgnet, Brice Hanaki, Nobuyuki Riyanto, Yohanes E. Zhu, Jiahua School of Social Sciences Social sciences::Economic theory Asset Prices Price Prediction We investigate how individuals use measures of apparent predictability from price charts to predict future market prices. Subjects in our experiment predict both random walk times series, as in the seminal work by Bloomfield and Hales (2002) (BH), and stock price time series. We successfully replicate the experimental findings in BH that subjects are less trend-chasing when there are more reversals in random walk times series. We do not find evidence that subjects overreact less to the trend when there are more reversals in the stock price prediction task. Our subjects also appear to use other variables such as autocorrelation coefficient, amplitude and volatility as measures of predictability. However, as random walk theory predicts, relying on apparent patterns in past data does not improve their prediction accuracy. Ministry of Education (MOE) Nanyang Technological University Financial supports from the ANR-ORA project “Behavioral and Experimental analyses on Macro-Finance (BEAM)” (ANR-15-ORAR-0004), NTU SSHR 2025 Seed Grant, Tier 1 Grant from MOE of Singapore (RG 69/19), NTU-WeBank JRC on FinTech research grant (NWJ-2020-009), and Joint Usage/Research Center at ISER, Osaka University, Japan Society for the Promotion of Science (18K19954, 20H05631) are gratefully acknowledged. 2023-11-29T02:11:18Z 2023-11-29T02:11:18Z 2023 Journal Article Bao, T., Corgnet, B., Hanaki, N., Riyanto, Y. E. & Zhu, J. (2023). Predicting the unpredictable: new experimental evidence on forecasting random walks. Journal of Economic Dynamics and Control, 146, 104571-. https://dx.doi.org/10.1016/j.jedc.2022.104571 0165-1889 https://hdl.handle.net/10356/172196 10.1016/j.jedc.2022.104571 2-s2.0-85144321338 146 104571 en RG 69/19 NWJ-2020-009 Journal of Economic Dynamics and Control © 2022 Elsevier B.V. All rights reserved. |
| spellingShingle | Social sciences::Economic theory Asset Prices Price Prediction Bao, Te Corgnet, Brice Hanaki, Nobuyuki Riyanto, Yohanes E. Zhu, Jiahua Predicting the unpredictable: new experimental evidence on forecasting random walks |
| title | Predicting the unpredictable: new experimental evidence on forecasting random walks |
| title_full | Predicting the unpredictable: new experimental evidence on forecasting random walks |
| title_fullStr | Predicting the unpredictable: new experimental evidence on forecasting random walks |
| title_full_unstemmed | Predicting the unpredictable: new experimental evidence on forecasting random walks |
| title_short | Predicting the unpredictable: new experimental evidence on forecasting random walks |
| title_sort | predicting the unpredictable new experimental evidence on forecasting random walks |
| topic | Social sciences::Economic theory Asset Prices Price Prediction |
| url | https://hdl.handle.net/10356/172196 |
| work_keys_str_mv | AT baote predictingtheunpredictablenewexperimentalevidenceonforecastingrandomwalks AT corgnetbrice predictingtheunpredictablenewexperimentalevidenceonforecastingrandomwalks AT hanakinobuyuki predictingtheunpredictablenewexperimentalevidenceonforecastingrandomwalks AT riyantoyohanese predictingtheunpredictablenewexperimentalevidenceonforecastingrandomwalks AT zhujiahua predictingtheunpredictablenewexperimentalevidenceonforecastingrandomwalks |