liveBook · Manning

Time scale

A time scale is the interval or duration over which measurements are obtained, observations are grouped, or relevant outcomes are assessed.

How 2 Manning books explain it

Experimentation for Engineers

The duration required to obtain an individual measurement of a metric or to observe a relevant outcome.

How it is used
Guides business-metric design, experiment duration, and the choice of predictors and risk models for trading systems.
How deep it goes
Explains measurement duration, noise, precision, and sample-size effects, but stops short of prescribing experiment stopping rules.
Examples
Compares server latency, page loads, click-through rate, daily active users, FPGA processing, and trading holding periods.
What you can do after
Evaluate experiment feasibility by estimating observation counts, noise effects, precision costs, and metric-driven iteration speed.

Read how Experimentation for Engineers explains time scale →

Outlier Detection in Python

A temporal resolution or interval over which observations are grouped and analyzed.

How it is used
Guides collective-outlier detection by choosing temporal groupings that expose anomalies hidden at other granularities.
How deep it goes
Explains multiscale aggregation, sample-size limitations, multiple-testing risks, and daily feature construction without deriving detection algorithms.
Examples
Uses purchase records grouped by hour, day, month, calendar day, and seconds, including an unusually high 28th day.
What you can do after
Apply aggregation to construct daily comparison tables and interpret flagged periods with attention to evidence strength.

Read how Outlier Detection in Python explains time scale →

Related concepts

These guides are generated from the text of Manning books by Manning's knowledge graph and link to the sections they draw on. The full books are available on liveBook and at manning.com.