The word statistics has many different meanings in our culture. Business statistics also has its own language and definition. the study of statistics is divided into two branches : descriptive statistics and inferential statistics.
In this post I will try to explain some basic differences between these two branches. To understand the difference definitions of population and sample will be useful.
A population can be a group of people("All people working in Microsoft") or set of objects ("All soaps produced on 15th April"). The researcher defines population to be whatever he or she is studying. A sample is portion of the whole, and if properly taken, then representative of the whole.
For many reasons the researchers prefer to work with sample of the population rather than entire population.For e.g., i conducting quality control experiments to determine average life of light bulbs a researcher will base his conclusion on observation on sample of 75 light bulbs rather than total light bulbs. This approach saves time and money.
If a business analyst is using data gathered of whole group to reach conclusions of the same group, the statistics are called descriptive statistics. In short, if population is 75 and all the 75 records are considered to base conclusions then the statistics are descriptive. Most of the data generated by business is descriptive. For e.g., number of employees on vacation during June.
If researcher gathers data from sample to base his conclusion about the whole group then the statistics are inferential. The data generated is used to infer something about the larger set. The use an importance of inferential statistics continue to grow. One of the example of inferential statistics is in pharmaceutical research. When we want to test different medicines then our resources are limited, so we have to consider small sample of patients and then design our experiments to arrive at a conclusion.
Market researchers use inferential statistics to observe the effect of a advertisement on various market segments. If a cold drink company wants to see what effect its advertising of its new bottle has created, then researchers take sample of population from different age groups and based their conclusion on this sample. Advantage of this method is a researcher can perform various experiments without conducting census.
A descriptive measure of population is called parameter and that of sample is called statistic. The former is denoted in Greek letters and the later is denoted in Roman letters.
These were some basics of Descriptive and Inferential statistics. In few of my next blogs, i will explain some more statistical concepts. Moreover, we will start with R : A Statistical and Interpretive programming language.
In this post I will try to explain some basic differences between these two branches. To understand the difference definitions of population and sample will be useful.
A population can be a group of people("All people working in Microsoft") or set of objects ("All soaps produced on 15th April"). The researcher defines population to be whatever he or she is studying. A sample is portion of the whole, and if properly taken, then representative of the whole.
For many reasons the researchers prefer to work with sample of the population rather than entire population.For e.g., i conducting quality control experiments to determine average life of light bulbs a researcher will base his conclusion on observation on sample of 75 light bulbs rather than total light bulbs. This approach saves time and money.
If a business analyst is using data gathered of whole group to reach conclusions of the same group, the statistics are called descriptive statistics. In short, if population is 75 and all the 75 records are considered to base conclusions then the statistics are descriptive. Most of the data generated by business is descriptive. For e.g., number of employees on vacation during June.
If researcher gathers data from sample to base his conclusion about the whole group then the statistics are inferential. The data generated is used to infer something about the larger set. The use an importance of inferential statistics continue to grow. One of the example of inferential statistics is in pharmaceutical research. When we want to test different medicines then our resources are limited, so we have to consider small sample of patients and then design our experiments to arrive at a conclusion.
Market researchers use inferential statistics to observe the effect of a advertisement on various market segments. If a cold drink company wants to see what effect its advertising of its new bottle has created, then researchers take sample of population from different age groups and based their conclusion on this sample. Advantage of this method is a researcher can perform various experiments without conducting census.
A descriptive measure of population is called parameter and that of sample is called statistic. The former is denoted in Greek letters and the later is denoted in Roman letters.
These were some basics of Descriptive and Inferential statistics. In few of my next blogs, i will explain some more statistical concepts. Moreover, we will start with R : A Statistical and Interpretive programming language.
No comments:
Post a Comment