Univrsity Of Tehran Press Accounting and Auditing Review 2645-8020 24 1 2017 05 22 Discussing Aggregation Bias in Estimates of Conditional Conservatism using Ball, Kothari and Nikolayev Model Discussing Aggregation Bias in Estimates of Conditional Conservatism using Ball, Kothari and Nikolayev Model 1 18 61840 10.22059/acctgrev.2017.61840 FA Mohammad Ramezan Ahmadi Assistant Prof. in Accounting, Faculty of Economic and Social Sciences, Shahid Chamran University of Ahvaz, Ahvaz, Iran. Seyed Aziz Arman Prof. in Economic, Faculty of Economic and Social Sciences, Shahid Chamran University of Ahvaz, Ahvaz, Iran. Esmaeel Mazaheri Ph.D. Candidate in Accounting, Faculty of Economic and Social Sciences, Shahid Chamran University of Ahvaz, Ahvaz, Iran. Journal Article 2016 10 01 This study investigates the influence of the aggregation biases in the estimates of the Ball, Kothari and Nikolaev model (2013). In this regard we investigate the effects of two Aggregation biases: omitted-variable bias and truncated-sample bias. This study is done among firms that are listed in Tehran stock exchange between 1379 and 1394. The results of the panel data regression analysis for 1898 firm – year show the estimates of conditional conservatism based on Ball, Kothari and Nikolaev model are contaminated by aggregation bias and The aggregation effect causes these models to underestimate good-news timeliness and overestimate bad-news timeliness, thereby overestimating differential good-news and bad-news timeliness This study investigates the influence of the aggregation biases in the estimates of the Ball, Kothari and Nikolaev model (2013). In this regard we investigate the effects of two Aggregation biases: omitted-variable bias and truncated-sample bias. This study is done among firms that are listed in Tehran stock exchange between 1379 and 1394. The results of the panel data regression analysis for 1898 firm – year show the estimates of conditional conservatism based on Ball, Kothari and Nikolaev model are contaminated by aggregation bias and The aggregation effect causes these models to underestimate good-news timeliness and overestimate bad-news timeliness, thereby overestimating differential good-news and bad-news timeliness https://acctgrev.ut.ac.ir/article_61840_34926730ec171316a9da9ba789af79dd.pdf