Time-series forecasting relies on what type of data analysis?

Time-series forecasting is fundamentally about analyzing data points collected or recorded at specific time intervals. The primary goal of this approach is to identify patterns or trends from historical data to make informed predictions about future values. By examining how data has changed over time—considering seasonality, cyclical trends, and overall movements—analysts can create models that estimate future outcomes based on these observable behaviors.

In contrast, options focusing on estimating population parameters, finding correlations, or employing random sampling methods do not capture the essence of time-series analysis. While useful in various statistical analyses, those methodologies are not tailored specifically for predicting future observations based on historical data sequences, which is the core of time-series forecasting. Thus, the correct answer embodies the foundational principle of this forecasting technique.