Out-of-sample stock return predictability in Australia

This article demonstrates how a spurious regression problem caused by dividend persistence is compounded by a spurious correlation problem when the dependent and independent variables in dividend behaviour regressions are ratios composed of common component variables. This article utilises a simulation procedure to take account of these problems, with the findings implying that extreme care should be taken when using ratios as predictor or explanatory variables in time series regression. This article introduces a reformulated Lintner first difference dividend behaviour model that is not subject to spurious regression in which past prices predict subsequent changes in dividends.

“…The results indicate that the regression

\bar{R}^{2}

equals 1.80 percent for the CRSP value‐weighted index and 2.23 percent for the S&P 500 index; these

{\overset{R}{true}}^{2}

values are also typically reported in prior dividend yield return predictability studies, including those conducted in international settings (Goyal and Welch, , ; Dou et al ., )…”

Section: Dividend Predictability and Spurious Regressionmentioning

confidence: 99%

Dividend persistence and dividend behaviour

Chan

Powell²,

Shi

et al. 2016

“…The most recent study by Dou et al . () examines the out‐of‐sample stock returns predictability in Australia using GICS when predicting sector returns.…”

mentioning

confidence: 99%

Industry concentration, excess returns and innovation in Australia

Gallagher

Ignatieva

McCulloch

2014

Self Cite

This paper examines market concentration and stock returns on the Australian Securities Exchange. We find that dominant companies operating in concentrated industries in Australia are able to generate significant risk-adjusted excess stock returns. Our results for Australian data are opposite to that found by Hou and Robinson (2006) for United States market data. Hou and Robinson reason that United States firms which operate in concentrated industries are insulated from competitive pressures, have lower levels of innovation (Arrow, 1962) and therefore experience lower profitability and stock returns. By contrast, the Australian data show a significant and positive relationship between concentration and innovation expenditure. Therefore, the excess stock returns of dominant companies in Australia are consistent with previous research linking innovation expenditure with excess stock returns. We hypothesize that the apparent contradiction of our results compared with Hou and Robinson (2006) for the United States market is resolved by an examination of the differences in size and competition in United States and Australian industries and the consequent differential ability of dominant companies in the two countries to generate monopoly rents and invest in 'Schumpeterian' (Schumpeter, 1942) innovation.

“…This estimation uncertainty has a substantial impact on t h e equity premium both theoretically (Yan, 2009) and empirically in various equity markets (e.g., Dou et al, 2012;Welch and Goyal, 2008).…”

Section: Model Set-upmentioning

confidence: 99%

Improving equity premium forecasts by incorporating structural break uncertainty

Tian

Zhou

2016

This paper compares five alternative methods for directly dealing with structural break uncertainty in forecasting the U.S. equity premium using 30 widely used bivariate and multivariate predictive regressions. We find that two recently developed methods -Robust Optimal Weights on Observations and Forecast Combination across Estimation Windows -outperform the conventional rolling window and post-break estimation methods. This result indicates that very early historical information is beneficial for U.S. equity premium forecasting but should be discounted to incorporate structural break uncertainty.