Poverty and Income Inequality Dataset (Imputed Series Using CAGR and Linear Interpolation), 1977-2024

This dataset compiles poverty and income inequality indicators extracted from the World Development Indicators (WDI, World Bank), specifically the Poverty headcount ratio at $3.00 a day (2021 PPP) and the Gini Index. Because WDI provides incomplete time series for many countries, a systematic imputation procedure has been applied to fill missing values in a consistent and transparent way. Missing values were treated according to the following rules: when both bounding values (previous and next available observations) were strictly positive (>0), missing observations were filled using the Compound Annual Growth Rate (CAGR) method, ensuring a smooth exponential trend (Vt = Vi × (Vf/Vi)^(t/n)); when at least one of the bounding values was zero, a simple linear interpolation was applied to preserve continuity without introducing artificial exponential behavior (Vt = Vi + (t/n)(Vf − Vi)). The dataset is organized with rows representing years and columns representing countries, a structure intentionally chosen to simplify time-series cross-sectional analysis and to facilitate the coding of a panel dataset constructed by the researcher. Separate files are provided for low-income, lower-middle-income, and upper-middle-income countries, each containing both poverty and Gini index series imputed according to the methodology described above. This dataset is suitable for cross-country econometric analysis, longitudinal poverty and income inequality studies, panel-data analysis, policy evaluation, and broader research in development economics. Researchers are encouraged to cite the original WDI source in addition to this processed dataset.