When applying analytic functions to a subset of multiple time series (MTS) in a signal, what is the resulting data structure?

Question

Options

• AA single time series with aggregated values
• BIndividual time series with separate calculations
• CA combined time series with separate timestamps
• DA scatter plot showing the relationships between MTS

• B
  95% (21)
• C
  5% (1)

Explanation

Applying analytic functions to a subset of MTS preserves the individual identity of each time series - each one receives its own independent calculation, producing separate output series rather than collapsing them together. Option B is correct because analytic functions (like rolling averages, percentiles, or transforms) operate per series, maintaining the granularity of the original data.

Why the distractors fail:

• A describes aggregation (e.g., sum() across all series into one), not analytic functions applied to a subset - aggregation collapses, analytics preserve.
• C is incoherent as a data structure: combining series while keeping timestamps separate contradicts how time series data works.
• D describes a visualization type, not a data structure - scatter plots show relationships but aren't the output of applying analytic functions.

Memory tip: Remember "analytic = individual analysis." Just as an analyst reviews each case separately, analytic functions evaluate each time series on its own terms, leaving you with as many output series as you started with in the subset.

No community discussion yet for this question.