5.2. ARITHMETIC MEAN

Arithmetic mean is the most commonly used measure of central tendency. It is defined as the sum of the values of all observations divided by the number of observations and is usually denoted by X̄. In general, if there are N observations as X₁, X₂, X₃, ..., Xₙ, then the Arithmetic Mean is given by X̄ = (X₁ + X₂ + ... + Xₙ) / N.

The arithmetic mean, often called the average, is calculated by adding up all the observations and dividing the total by the number of observations. For instance, if you have five numbers: 2, 4, 6, 8, and 10, you would first add them together to get 30. Then, you divide that sum by 5 (the total number of observations), resulting in an arithmetic mean of 6.

Imagine you are tracking the daily high temperatures in your city for a week: 70°F, 75°F, 80°F, 68°F, 72°F, 78°F, and 74°F. To find the average temperature for that week, you add all these numbers to get a total of 519°F, then divide by 7 (since there are 7 days). The average temperature gives you a quick understanding of the week's weather pattern.

The calculation of arithmetic mean can be studied under two broad categories: (1) Arithmetic Mean for Ungrouped Data and (2) Arithmetic Mean for Grouped Data.

To calculate the arithmetic mean for ungrouped data, you simply sum all the values and divide by the number of values. For grouped data, where values are combined into intervals, you find the mid-point of each interval, multiply it by the frequency of the interval, and then apply the mean formula. This helps to summarize large data sets more efficiently.

If you're managing a class, and you want to calculate the average score of 30 students on a test. You gather their scores (ungrouped data) and add them all together, then divide by 30. However, if you had a larger class, like 150 students, it may be easier to group their scores into ranges (like 0-50, 51-100) and calculate the average using the mid-points of these ranges, making the calculation simpler.

If the number of observations in the data is large, calculating the arithmetic mean may become tedious. Hence, the assumed mean method helps simplify the calculation.

In the assumed mean method, you pick an arbitrary 'assumed mean' based on logic or previous experience. You then calculate deviations for all observations from this assumed mean. By averaging these deviations, you can accurately estimate the arithmetic mean without computing sums for all raw data. This method saves time and effort, especially when processing large datasets.

Consider a scenario where a company has to evaluate average sales from multiple retail outlets. If each outlet has a different number of transactions and purchase sizes, rather than sorting through every single transaction, the manager can assume a typical value (say average sales of past months), calculate how far each outlet's current sales deviate from this typical value, and use these deviations to ascertain whether sales are up or down overall.

The calculations can be further simplified by dividing all the deviations taken from assumed mean by a common factor ‘c’. The objective is to avoid large numerical figures.

In the step deviation method, rather than working with large numbers, you choose a 'common factor' to make your calculations simpler. Each deviation from the assumed mean is divided by this common factor, thus, reducing the size of the numbers you work with. This leads to less cumbersome calculations while still giving an accurate estimate of the mean.

If you are calculating the average income of families in a neighborhood, and the incomes are very large, such as in the hundreds of thousands, managing these figures directly can be overwhelming. By using a smaller common factor (like thousands), you can convert these large figures into more manageable numbers to work with, allowing you to focus on the overall trends instead of getting bogged down by each detail.

In case of discrete series, frequency against each observation is multiplied by the value of observation. The values obtained are summed up and divided by total number of frequencies.

When dealing with grouped data, you calculate the mean by first determining the midpoint of each class interval. Multiply this midpoint by the frequency of that interval to get a weighted sum. Then sum all of these products together and divide by the total number of observations (frequencies) to find the mean for the grouped data.

Think about it like finding the average height of students in different age groups. You first note down how many students fall in each height range (say 4.5 - 5.0 feet, 5.1 - 5.5 feet, and so forth). Instead of counting their height directly, you’ll use the average height - say 5.0 feet for the first group. By doing this for all groups and using the number of students in each group (frequency), you find a more efficient average height for all students together.

--