Elementary Statistics (1+1)

2.1.14 Precautions in the use of secondary data

Since secondary data have already been obtained it is highly desirable that a proper scrutiny of such data is made before they are used by the investigator. In fact, the user has to be extra-cautious while using secondary data. In this context, Prof. Bowely rightly points out that “secondary data should not be accepted at their face value”. The reason is that such data may be erroneous in many respects due to bias, inadequate size of the sample, substitution, errors of definition, arithmetical errors, etc. Even if there is no error such data may not be suitable and adequate for the purpose of the enquiry. Hence before using such data, the investigator should consider the following aspects:

1.suitability

Whether the data are suitable for the purpose of investigation in view. Before using secondary data the investigator must ensure that the data are suitable for the purpose of the enquiry. The suitability of data can be judged in the light of the nature and scope of investigation. For example, if the object of enquiry is to study the wage levels including allowances of workers and the data relate to basic wages alone, such data would not be suitable for the immediate purpose. It may be difficult to find data which exactly fit to the needs of the present project.

Quit often secondary data do not satisfy immediate needs because they have been compiled for other purposes. Even when directly pertinent to the subject under study, secondary data may be just enough off the point to make them of little or no use. The value of secondary data is frequently impaired by:

(i) Variation in the units of measurement: consumer income, for example, may be measured by individual, family household, spending units or tax return.

(ii) Definition of classes may be different: for example, definition of literate, educated, poor may vary from researcher to researcher.

(iii)Variation in the period to which the data is related to: the data available may relate to a different time period and not serve the purpose of researcher. Data published to promote the interests of a particular group whether it is political, social or commercial are suspicious.

2. Adequacy

Whether the data are adequate for the investigation. If it is found that the data are suitable for the purpose of investigation, they should be tested for adequacy. Adequacy of the data is to be judged in the light of the requirements of the survey and the geographical area covered by the available data. For example, in the illustration given above, if our objective is to study the wage rates of the workers in fish processing industry in India and if the available data cover only the State of Tamil Nadu., it would not serve the purpose. The question of adequacy may also be considered in the light of the time period for which the data are available. For example, for studying trend of prices we may use data for the last 8-10 years but from the source known to us data may be available for the last 2-3 years only which would not serve the purpose.

3. Reliability

Whether the data are reliable. It is very difficult to find out whether the secondary data are reliable or not. The following tests, if applied, may be helpful to determine how far the given data are reliable:

(i) Which specific method of data collection was used? If a source fails to give a detailed description of its method of data collection, researchers should be hesitant about using the information provided. When the methodology is described, researchers should subject it to a painstaking examination.

Data published to promote the interests of a particular group whether it is political, commercial or social are suspect.

(ii) Was the collecting agency unbiased or did it “have an axe to grind”?

(iii) If the enumeration was based on a sample, was the sample representative?

(iv) Were the enumerators capable and properly trained? Incompetent or poorly trained enumerators cannot be depended upon to produce useful result.

(v) Was there a proper check on the accuracy of field work?

(vi) Was the editing, tabulating and analysis carefully and conscientiously done? Carelessness in either one or more of these functions can render of little value the findings of an otherwise valuable study.

(vii) What degree of accuracy was desired by the compiler? How far was it achieved?