Time Series

What is the Time Series? 

When the values of a variable are recorded concerning the time of its occurrence, then the arrangement is known as a Time Series. Time Series helps in understanding the trend, periodicity, etc. in long-term time-series data. The period may be a year, quarter, month, week, days, hours, and so on. Time series graph is also known as ‘Histogram’ or ‘Line Graph’. When the actual time series data is graphed, the histogram is called ‘Absolute Histogram’. When the index number of the given data is graphed, the histogram is called ‘Index Histogram’. 

Variables in Time Series

In time series in statistics, there are two variables: (i) Time (i) Variable under study (like figures of national income, sale, production, employment, etc.) 

Types: Time Series graph may be of two types: 

(i) One Variable Graph; 

(i) Two or more than two Variables Graph 

Steps for Making Time Series Graph 

Step 1: Plot ‘Time’ along the X-axis as it is an independent variable. The other variable is a the dependent variable, so it is measured along the Y-axis. The scale along the Y-axis must begin at zero as an origin to facilitate a correct understanding of the graph. 

Step 2: Plot each pair of values on the graph by a point that corresponds to the value of the independent variable on the X-axis and the value of the dependent variable on the Y-axis. 

Step 3: The various points so obtained are joined by straight lines (not by freehand) to get the time-series graph. 

Important Points for Constructing Time Series Graphs 

1. Equal distances on the Y-axis should mean equal absolute amounts. Similarly, equal distances on the X-axis should mean equal time duration. 
2. The graph must have a suitable title, which must be self-explanatory about the nature of the information in the graph. 
3. If more than one variable is plotted on the same graph paper, then a different type of line should be used for each curve (Simple line, dotted line, broken line, etc.). An index should be given to show the scales and meaning of different lines. 
4. Indication of years, units, etc., should be done horizontally and not vertically so that turning of the graph from one side to another is avoided. 

One Variable Graph 

If only one variable is to be shown, then time is measured along the X-axis and the value of the variable on the Y-axis. The various time points are plotted against the corresponding values and are joined by a straight line. 

The fluctuation of the said line depicts the variations in the variable and the distance of the points from the baseline of the graph indicates the magnitude. 

Two or more than two Variables Graph 

Whenever two or more values are shown on the same graph, then it is preferred to use different types of lines, e.g., a dotted line, a broken line, or a thick line. 

• Such a graph is generally used for data relating to exports-imports, maximum-minimum temperatures, birth rate-death rate, revenues-costs, etc. 
• when two or more variables are to be plotted on the same graph, then the variables can be given either in the same units or in different units. Let us discuss the two cases separately. 

Graphs of Two Variables measured in “Same Units” 

If the unit of measurement is the same, we can represent two or more variables on the same graph. The method of preparing this graph is the same as in the case of one variable, but there will be two or more curves instead of one curve. 

Graphs of Two Variables measured in “Different Units” 

If two variables are given in two different units, then we should have two scales, i.e., one on the left hand and the other on the right-hand side. For example, exports (quantity in million tons) and exports (values in 7 crores) about the same period can be displayed on the same graph. 

However, to facilitate the comparison of various curves, the average values of all the variables are taken on a common line, often drawn in the middle of the graph. This line is known as Common Average Line. 

Time Series Data 

A set of observations gathered through repeated measurements over time is known as time-series data. If you plot the points on a graph, you’ll notice that one of the axes is always time. Because time is a component of everything. observable, time-series data may be found everywhere. Sensors and systems are always releasing a continuous stream of time series data as our world becomes increasingly instrumented. Such information can be used in a variety of sectors. Let’s look at some examples to put this in context. 

Time series data can be used for a variety of purposes, including: 

• Weather data can be tracked on a daily, hourly, or weekly basis. 
• Changes in application performance are being tracked. 
• Medical equipment that allows you to see your vitals in real-time 
• Monitoring network logs

Conclusion 

A time series is a set of well-defined data items observed over time through repeated measurements. A time series might be created by monitoring the value of retail sales each month of the year. This is due to the fact that sales income is well defined and recorded at regular periods. Data that is collected seldom or only once is not considered a time series