It is better to be roughly right than precisely wrong.

—John Maynard Keynes

The information from a good statistical analysis is always concise and often precise. Statistics is the science which helps us to summarise, analyse and make inference from data to support fact based decisions in the field of Business, Economics, Healthcare, Education etc. The result of such analytical initiatives will be incredible growth and performance in respective fields. The information (Data) may quantitative or qualitative.

Qualitative data describe items in terms of some quality or categorization.

Eg; If we ask someone’s weight, the answers may be overweight, underweight or obese. The answers are categorical. If we made any query regarding the support from a retail outlet, the result will be good, bad, no so good, and average etc. These types of responses are the marks for quality.

Quantitative data is a numerical measurement expressed not by means of a natural language description, but in terms of numbers for which arithmetic operations such as averaging make sense.

Eg; As it is mentioned in the previous example some can answer his weight as 50kg, or 65kg.  

Statistical inference will deliver insights for strategic decision making. We draws insights from gathered data.  Data generates due to measurement and the measurement should be precise to get dependable results. Accuracy in data collection, careful data entry and cleaning and the use of most suitable analytical tool with clever interpretation will result into best business decisions. So measurement mechanisms should be calibrated continuously and rigorously to get a competitive edge on your decisions.

The four generally used scales of measurement are listed here from weakest to strongest. They are nominal scale, ordinal scale, interval scale and ratio scale.

“Nominal” stands for name of a “category”. The nominal scale of measurement is used for qualitative rather than quantitative data. Here the numbers are used simply for groups or classes.

Eg; Male: Female: 1:2, Good: Bad: Average: : 1: 2: 3

In ordinal scale of measurement, data elements may be “ordered” according to their relative size or quality.

Eg; A product can be ranked by a customer in 5 point scale such that 1 for worst and 5 for best and 2, 3, 4 stands for the opinions between best and worst. Here we do not know how much better one product is than others, only that it is better.

In the interval scale of measurement the value of zero is assigned arbitrarily and therefore we cannot take ratios of two measurements. But we can take ratios of intervals. 

A good example is how we measure time of day, which is in an interval scale. We cannot say 10:00 A.M. is twice as long as 5:00 A.M. But we can say that the interval between 0:00 A.M. (midnight) and 10:00 A.M., which is duration of 10 hours, is twice as long as the interval between 0:00 A.M. and 5:00 A.M., which is duration of 5 hours. This is because 0:00 A.M. does not mean absence of any time.

If two measurements are in ratio scale, then we can take ratios of those measurements. The zero in this scale is an absolute zero. Money, for example, is measured in a ratio scale. A sum of `100 is twice as large as ` 50. A sum of `0 means absence of any money and is thus an absolute zero. We have already seen that measurement of duration (but not time of day) is in a ratio scale. In general, the interval between two interval scale measurements will be in ratio scale. Other examples of the ratio scale are measurements of weight, volume, area, or length. 

will continue...

It's a humble beginning.