ETW1001 EXAM -SECTION D: TIME SERIES

Q1 — What is a time series?

A time series is data collected over time at regular intervals (e.g. daily, monthly, yearly).

Why do we analyse time series data?

To understand patterns over time, such as trends, seasonality, and fluctuations.

What makes time series data different from cross-sectional data?

Time series data is ordered in time, meaning observations are not independent.

What is a trend in a time series?

A long-term upward or downward movement in the data over time.

How do you interpret an upward trend?

The variable is increasing consistently over time.

How do you interpret a downward trend?

The variable is decreasing consistently over time.

What is seasonality?

Regular, repeating patterns that occur at the same time each period (every year, every month).

How do you identify seasonality conceptually?

By observing repeated peaks and troughs at regular intervals.

What are irregular or random components?

Unpredictable fluctuations caused by random or external events.

What is the main purpose of a time series plot?

To visually identify trend, seasonality and volatility over time

How do you interpret volatility in a time series?

High volatility= large fluctuation

Low volatility= stable values over time

What does it mean if the series fluctuates around a constant level?

There is no clear trend, only random variation.

What is time series regression used for?

To describe and explain the relationship between time and a variable.

What does the dependent variable represent in time series regression?

The variable being explained (e.g. sales, demand, temperature).

What does time represent as an independent variable?

The passage of time (e.g. year, month), used to capture trends.

How do you interpret a positive time coefficient?

The dependent variable increases over time.

How do you interpret a negative time coefficient?

The dependent variable decreases over time.

What does the intercept represent in a time series regression?

The estimated value of the variable at time zero (baseline level).

What does a strong time trend suggest?

That time is an important factor influencing the variable.

What does it mean if the regression fits the data poorly?

Time alone does not explain much of the variation.

Why should regression results be interpreted with caution in time series?

Because observations may be correlated over time, violating independence assumptions.

What is forecasting in time series analysis?

Using past data patterns to predict future values.

Why is trend important for forecasting?

Because future values often continue the existing trend.

Why can forecasts be inaccurate?

Due to random shocks, structural changes, or unexpected events.