Times Series Data

What is a time series?

a collection of observations of well-defined data items obtained through repeated measurements over time. It is drawn as a scatterplot with time as the explanatory variable.

What are the three components of a time series?

• the trend (long term direction)

• the seasonal (systematic, calendar related movements)

• the irregular (unsystematic, short term flucutuations)

What is a seasonal pattern?

A repeating pattern in data that occurs at regular intervals due to seasonal or periodic influences.

What is a cyclic pattern?

A general pattern of rises and falls in data that occurs over time, but without a fixed or regular interval.

What is the main difference between cyclic and seasonal patterns?

the unpredictability of when peaks and troughs occur in cyclic patterns

What is a random pattern?

A pattern in data where fluctuations occur unpredictably around a stable average, with no clear trend or repeating pattern.

What types of trends can occur?

• increasing/upward

• decreasing/downward

• constant

What is seasonality?

Regular and predictable changes in data that occur at fixed intervals, caused by calendar-related factors, and showing consistent timing and similar magnitude each period.

How do you calculate a cycle mean?

The average value of the data for each time period, found by adding all values in the period and dividing by the number of intervals.

Example - 2016 (4 quarters):
Cycle mean=A+B+C+D/4

How do you calculate the individual seasonal index?

Taking a value in a period and dividing it by its cycle mean.

Example - 2016 Quater 1:
Seasonal index=Q1/cycle mean

How do you calcu