Any statistical investigation needs information, that information is collected in the form of figures, numbers or words. This collection is known as data. A single piece of information is known as data point and the collection of data points is known as data set or simply data. A much formal definition of data can be given as, “Aggregation of facts is known as data”.
The definition itself clarifies that the factual information aggregated from sample or population is known as data. The underlying assumption here is that the resource of information provides a factual information.
As mentioned earlier the data can be collected in figures, words or numbers. The data collected in numbers can be used readily for statistical investigation while the data collected in other formats may not be used directly for statistical information.
Following are the examples of different forms of data;
1. How satisfy you are with the service of our bank please mark the correct figure
2. How satisfy you are with the service of our bank please mark the correct option
Extremely Satisfied | Satisfied | Neutral | Not Satisfied | Not Satisfied at all |
3. How satisfy you are with the service of our bank, 5 means highest satisfaction
5 | 4 | 3 | 2 | 1 |
Most of the times the data is collected for some specific purpose of research or understanding. Hence it is very important to rely on collected data. A researcher may check the reliability of the data source, may look for other evidences in support of data, may check the adequacy of the data before relying on data completely.
Data can be of various type, following chart presents the types of data
Types of Data
figure - 1
The data collected from internal sources and for internal administrative purposes becomes and internal data and a data collected from outside sources or for external usage becomes an external data. Internal data also reflects the data produced by the day to day operations of the firm such has number of units produced each day, or number of customer taken service in one day. These data can be used for effective management in all functional areas. However, there are data that are produced about the firm by external sources such as opinion of customers' about the firm's performance. These data are termed as External data.
Further the data collected right from the source of information is known as Primary Data and the data collected from as source other than primary becomes a Secondary Data. For instance; a firm may have data about the number of employees working in a shift for internal administrative purposes, this form of data is internal in nature. The balance sheet of the same firm is available on their website produced by external auditors that could be used by investors to access the financial health of the company, this form of data is external in nature. However, the investors can have access to the same balance sheet of the particular firm from their website or from some third party website. Getting the data from the official website of the firm is primary way of collecting data as it is collected from the source of the information, while getting the balance sheet from third party website is a secondary way of collecting the data.
The way of collecting the data is very subjective in nature. The choice between primary and secondary way of collecting the data depends on;
Requirement of project
Availability of resources
Availability of funds
Geographical area to be covered
A researcher shall consider the selection of data collection technique i.e. primary or secondary by keeping above points in mind. However the utility of primary data is very high in cases of creation of new definition and developing new measuring instruments.
Further there are certain merits associated with the primary data. Such as;
The data is original and more reliable in nature. This gives the researcher or investigator a higher amount of confidence before using the data.
The primary data is generally free from biasness as it is a first-hand information.
Since the data is collected particularly for the particular project hence it exactly matches the need of the project. Investigator can always ensure the sufficiency of collected data before moving in to analysis in case of primary data collection.
Some additional data can always be collected in process of primary data collection to cover incomplete, doubtful and false data cases.
Demerits of primary data collection are;
It is a time consuming process in comparison to secondary data collection as it involves a lot of filed work at times.
The higher consumption of time makes the process tedious and costly in comparison to secondary data collection.
Non-availability or difficult availability of the source of information is yet another challenge in primary data collection.
It requires trained manpower to collect and compile the primary data as the data comes in raw form.
As discussed earlier alternative to primary data is secondary data collection. Yet again secondary data comes with certain merits and demerits. These merits and Demerits are described below;
Merits of Secondary Data
The secondary data is available readily complied
It is less expensive and less time consuming comparatively
The interpretation of data and conclusions drawn from the data are also available at times.
Demerits of Secondary Data
The secondary data is not in the format researcher wanted
It may not be collected by the correct procedure
It may not be authentic and has personal biasness
It may not be adequate for the study
The primary data can be collected by five methods. These methods are;
Direct personal interview method
Indirect personal interview method
Mail questionnaire method
Schedule method
Collection of data through correspondents
Hence a careful selection of method of data collection shall be made as it is a onetime exercise in any project and may not be repeated during the commencement of the project. At times the selection of the data collection method is beyond the control of researcher. Further the methods of primary data collection are as follows;
Methods of primary data collection
Direct personal Interview
This method of Primary data collection, the data is collected through personal interviews. The data points (respondents) are contacted one by one by the interviewer and the data is collected in the form of personal interview.
The direct interview can be structured or non-structured. A structured interview can be conducted by multiple interviewers as the format and type of questions remain same. An individual interviewer may follow and unstructured pattern with higher confidence and less error.
The direct personal interview method is suitable where the field of enquiry is small geographically and faction. If the field of enquiry is very large and extensive the method consumes a lot of time and resources hence unadvisable.
The merits of direct personal interview are;
The data collected is original in nature
There is uniformity in collected data.
The data obtained is flexible and as per the necessity of the project.
The data collected is highly reliable in this case.
The communication is very effective in this method.
Additional information and cross checking of doubtful information is also possible in this method.
Demerits of Direct Personal Interview
The method requires experts to collect the data.
The method is highly time and money consuming.
The issues of personal biasness can affect the results substantially.
Direct personal interviews are also conducted telephonically but this method of conducting direct personal interviews is avoided due to following reasons;
Serious communication errors
Authenticity of respondent
Adjustment of language of communication
Tech errors
There are cases when the direct source of information cannot be trusted such as in case a new method of primary data collection can be adopted with greater confidence as per following details.
Indirect personal interview
In this method the information (data) is collected from an indirect Primary source called witness, primary witness or eye witness. The witness shall be a person that is not motivated to give the color to the facts and information. The witness shall have an ability to observe and describe the situation properly. However a single witness shall not be trusted. The interviewer collects the data through interviewing each witness.
The method is most suitable when direct primary source of information cannot be trusted. For instance in case of a road accident none of the involved parties may give the correct information, hence the witnesses of the incident can provide a better data (information) about the incident.
The method is primarily used in investigations and audits.
Merits of indirect personal interview method
This method is more or less free from biasness
It can provide much accurate information where otherwise the right information was not available
Using this method some untold and additional information can also be gathered
Demerits of indirect personal interview method
One of the biggest demerits of this method is the biasness of witness
Single witness cannot be trusted
Experts are needed to collect the information
Sometimes no witness is available
Information through correspondents
In this method; the data collection agencies appoint their correspondents across the geographical location they want to collect data from. These enumerators or correspondents collect the required data as first-hand information and send it to the head-office.
The method is most suitable when data/information is required regularly, the degree of accuracy of data is not very high, and the field of investigation is very vast. The new channels, newspapers and magazines follow this method of data collection primarily.
Merits of information through correspondents
Regular flow of first-hand information is obtained
Results are easy and prompt
A wide geographical area is covered through this method
A very useful method for extensive geographical researches
Demerits of information through correspondents
The personal biasness of correspondent can play a big role
The results are prompt, easy but raw
The correspondent may or may not provide the requires information exactly
Mail questionnaire method
This is one of the most popular method of primary data collection in practice. This method is adopted by most of the researchers and investigators to collect the data. The method is much used in studies related to social sciences.
The suitability of the method lies in the concept of covering very extensive geographical area in very less time. The method is most suitable when the wide geographical area is to be covered in limited period of time.
In this method an instrument for systematic collection of primary data is developed, known as questionnaire. The questionnaire is an instrument that contains questions and statements related to purpose of study and contains a space for answers and responses respectively. The questionnaire are distributed to population or sample through post-mail or electronic-mail. The respondents are then asked to fill the questionnaires and mail them back to the researcher or investigator.
In modern times the questionnaire can be developed through various online platforms such as google forms and one drive forms for free of cost. These forms can be easily accessed and operated through smart digital electronic devices such as laptops, tablets and smartphones. Hence, digital divide is also considered before adopting this method.
The responses of the participants are recorded by these digital platforms in MS Excel and are ready for further analysis by a little formatting and coding.
Merits of mail questionnaire method
This method can cover a wide geographical area at a considerably low cost.
This method collects very systematic data
The scope of personal biasness is very less
Answer to sensitive questions can be recorded much effectively
The responses are ready to operate for analysis
Demerits of mail questionnaire method
The method is not suitable in illiterate areas
The questionnaire development is a challenging job
The method often results in poor response
The method generates a lot of half filled questionnaires
The doubtful answers and responses cannot be cross verified.
In case of high digital divide it is difficult to administer.
Information through schedule method
To overcome the de-merits of the mail questionnaire method the new method of data collection has been developed and named as information through schedule. In this method the questionnaire is carried by an enumerator and he gets the response and answers filled by the respondent. The questionnaire carried by an enumerator is called a schedule that is to be completed by the enumerator with the response of the enumerator.
There could be more than one enumerators doing the job simultaneously.
Merits of Information through Schedule Method
The method covers a wide geographical area
The data is more or less free from personal biasness
No incomplete questions remain in the collected data
The answers that are doubtful can be crosschecked
The response of the people remains high
De-merits of information through Schedule Method
This method is comparatively expensive as the enumerators are paid
This method is time consuming
This method requires trained professionals
A tedious administration is needed for the same
Methods of Secondary Data Collection
Secondary data can be collected two ways;
Published sources: Published sources of secondary data are; government publications, research journals, research reports, private publications, blogs, e-sources
Unpublished sources: The unpublished sources of secondary data are; thesis, project reports, private journals and certain self-written materials.
***
Thank you sir for sharing this with us.
Shalni gaud
924107