Collection of Data:- Data is a tool that provides information and helps us understand the problem. is helpful. Therefore, the purpose of data collection is to gather evidence for a clear and concrete solution to a problem. Therefore, collection of data is the first and foremost task for statistical research.
Sources of Data :-
- Primary sources
- Secondary source
Primary Data :-
1. Primary data are those which are first collected by the researcher himself for his purpose.
2 . Primary data are original as the researcher himself collects them from the original source.
3. Collecting primary data requires a lot of money, time and effort.
4. If the researcher makes a mark list of economics subject by asking the students of class XI, then the data obtained in this way will be considered as primary data.
Methods of collecting primary data:-
1) Direct Personal Research
2) Indirect oral research
3) Receiving information from reporters
4) by telephone, post or by enumerators.
Secondary Data :-
1. Secondary data are those that have already been collected. They are stored by some other organization for some other purpose.
2 . Secondary data are not original as the researcher obtains them from the records of other persons or institutions.
3. Relatively less money, time and effort is required to collect secondary data.
4. If the researcher, through the class teacher, makes a mark sheet of economics of class XI by obtaining information from school records such as mark sheet or result register, then it will be considered as secondary data.
Sources for collecting secondary Data :-
1) Published sources,
2 ) Unpublished sources ,
3) Other sources – Website etc.
Qualities of a good questionnaire :-
1) Introduction of the investigator and a description of the investigator’s purpose.
2) The questionnaire should not be too long.
3) The questionnaire should start from general questions and move towards specific questions.
4) Questions should be simple and clear.
5) The questions should not be double negative.
6) Should not be indicative questions.
7) The question should not indicate the choice of answer.
Methods of Sampling :-
Divine sample or. Random Sampling :-
a) Simple random sample
b) Committed sample
c) level sample
d) systematic sample
D) Multilevel sampling
Random sampling or random sampling :-
a) Thought sample
b) Absent sample
c) Sample as per convenience
Census survey:- In this method of investigation, every unit of the whole is included.
Sample Survey:- In this method of investigation, some representative units of the whole are studied.
Sampling Errors – Sampling Errors reveal the difference between the sample estimation and the actual value of a particular population.
Non-sampling errors:- These errors are found in the data compiled by census method or sampling method.
Types of Errors :-
Sampling errors
1. biased errors
2 . partial errors
Non-sampling errors
1. Errors in data acquisition
2 . unanswerable errors
3. measurement errors
Census of India and National Sample Survey Organization
The Census of India provides complete information related to the demographic situation of the country. Such as population size, growth rate, distribution, projection, density, sex ratio and literacy.
The National Sample Survey Organization has been set up by the Government of India to conduct national level surveys on socio-economic issues (such as employment, education, maternity-child care, use of public distribution departments, etc.).
The data collected by NSSO is published from time to time in various reports and in its quarterly magazine “Survey”.
Points to remember:-
Presentation of raw data in a simple, concise and systematic manner is called systematization of data so as to make them easily capable of further statistical analysis.
To divide the collected data into different classes and groups on the basis of their similarities and dissimilarities is called classification.
Features of Classification :-
1. Clarity
2 . Broadness
3. Homogeneity
4. Compatibility
5. Elastic
6. Stability
Basis of Classification :-
1. Chronological classification: – When the data can be classified in ascending or descending order in terms of time such as year, quarter, monthly or weekly etc.
2 . Spatial classification: – When the data is divided into geographic locations such as countries. It is classified into state, city, district, town, etc. ,
3. Qualitative classification:- The classification of data based on characteristics is called qualitative classification. Such as nationality, literacy, gender, marital status, etc.
4. Quantitative classification: – When the nature of the characteristics is quantitative. So the classification done on this basis is called quantitative classification. Like height, weight, income, income, marks of students etc. Example: Height. load etc.
Variables :-
Variable refers to an attribute or quality that can be measured. And which changes from time to time.
Variable Types :-
1. Discrete Variables – These variables can only have a fixed value. Its values change only with a finite ‘bounce’. These jumps occur from one value to another, but no value comes in between. Example number of students, number of employees.
2 . Continuous Variables – Variables that can take all possible values (integers or fractions) within a given range are called continuous variables. For example, height, weight etc.
Frequency distribution
This is a general way of classifying raw data into a quantitative variable. Indicates that a variable. How are the different values of k distributed among the different classes with the frequencies in their corresponding classes.
Class – A certain set of values is called a class such as 0 – 10 , 10 – 20 , 20 – 30 etc. ,
Class limits – Every class has two limits – lower limit and upper limit. For example, in a class of 10 – 20, 10 is the lower limit (L) and 20 is the upper limit (L2 ).
Class difference – The difference between the upper limit of the class and the lower limit is called class difference. For example, the square difference of 10 – 20 is 10.
Class Frequency – The number of items included in a class is called frequency or frequency of that class. It is represented by f.
Middle value – The mid point of the class interval of a class is called the middle value. It can be obtained by dividing the sum of the upper limit and the lower limit of the square by 2. It is also called the class symbol.
Exclusive Series – By this the classes are formed in this way. That the upper limit of one class is equal to the lower limit of the next class eg – 0 – 10 , 10 – 201
Inclusive series – This is the series in which all the frequencies of a class are included in the same class, that is, the value of the upper limit of a class is also included in that class. Like 0 – 9 , 10 – 19 .
Loss of information – An inherent flaw is found in the classification of data in the form of frequency distribution. It summarizes the refined statistics. Presenting them makes them concise and understandable, but it does not reveal the detailed details which are found in raw data. Therefore, there would have been loss of information in classifying the raw data.