Replication Data for: Forecasting Partisan Collective Accountability During the 2024 U.S. Presidential & Congressional Elections

This article considers both presidential approval and party brand differentials, as measured by the generic ballot, to forecast the 2024 U.S. presidential and congressional elections. While both variables are leveraged to forecast collective partisan election outcomes, we consider the variables together as distinct determinants of partisan fortunes at both the executive and legislative levels. First, using a novel time-series of mass national opinion since 1937, we show that presidential approval and generic brands are distinct conceptual and empirical measures of mass public assessments of collective institutions. Second, in a series of fully specified models validated with out-of-sample predictions, we show that presidential approval is the main predictor of presidential elections while, perhaps surprisingly, the vast bulk of the incumbent party's performance in congressional elections is explained by partisan brands. Lastly, we forecast the 2024 U.S. national elections and find that Republicans are well positioned to both win back the White House this November. By contrast, our model forecasts control of both chambers of the U.S. Congress to be essentially a tied contest.本文同时纳入总统支持率与以通用选票（generic ballot）衡量的政党品牌差异两项指标，用于预测2024年美国总统选举与国会选举。尽管两项变量均可用于预测党派整体选举结果，但本文将二者视为行政与立法层面党派选举运势的差异化决定因素，展开联合分析。其一，基于1937年以来的全新全国大众舆论时间序列数据集，本文证实总统支持率与通用政党品牌指标，是大众对集体公共机构评价的两类差异化概念与实证测度维度。其二，在一系列经样本外预测（out-of-sample predictions）验证的完全设定模型（fully specified models）中，本文发现总统支持率是总统选举的核心预测因子；而令人意外的是，国会选举中执政党选举表现的绝大多数波动，均可由党派品牌差异所解释。最后，本文对2024年美国全国性选举开展预测，结果显示共和党有望在今年11月夺回白宫；相较之下，本模型预测美国国会参众两院的控制权争夺将基本呈现势均力敌的局面。