Economics 6 Marks Question

1. Sampling error: The Sampling Errors can be minimised by increasing the size of a small sample, so that the difference between the actual and the estimated value is reduced. But the Non-sampling Errors are difficult to rectify as it would require selection of a new sample and conducting a fresh survey. Thus, Non-sampling Errors are more serious than the Sampling Errors.
2. Non-Sampling error: Non-sampling Errors are more serious than the Sampling Errors because the latter can be minimised by taking a larger sample. Non-sampling Errors emerge due to the use of faulty means of collection of data, whereas, the Sampling Errors emerge due to the divergence between the estimated and the actual value of a parameter of a small sized sample population. For example, errors due to personal biasness, misinterpretation of results, miscalculations, etc.

Primary data refers to the data collected by investigator himself.
Methods of Collection of Primary Data:
The primary data are collected by the following methods.

1. Direct personal investigation.
2. Indirect personal investigation.
3. Information through correspondents.
4. Telephonic Interviews.
5. Mailed Questionnaire Method.
6. Questionnaire filled by Enumerators.

Information from Correspondents: According to this method the collection of data is neither through the questionnaire nor through the enumerators but through the local correspondents. This method of collecting the data is not reliable and it should be used only at those places where the purpose the investigation is served by rough estimates.
Advantages:

1. It is very cheap and quick method of collecting data.
2. This method provides information on regular basis from distant places.
3. This method involves less labor and time.

Disadvantages:

1. In this method, correspondent may use any method of collecting data which investigator is relying on.
2. This method is not so reliable and accurate.
3. Data may be biased.
4. It lacks uniformity.

Suitability: This method is suitable when scope of enquiry is large and information is required on regular basis.

1. Census: Census method refer to inclusion of all items in the field of statistical enquiry and sample methods refer to selection of few items as representatives of all the items.
2. Sample: Sample method gives better results than census method because of following reasons:

• Economical method: Census method requires huge expenditure. As a large number of enumerators have to be employed. They have to be trained. Their work has to be coordinated and supervised. There will be expenditure on traveling, food etc in case of census method. The cost of the survey is much smaller if we a sample method because of less efforts involved in it.
• Less time and efficiency consumption: The collection of data, the tabulation, and analysis take much less time in case of sampling method compared to census method. In fact the population census of India takes so much time that it takes place only once in ten years.
• Accuracy: In sampling method it is possible to check the extent or errors and take corrective actions. While in census method, it is almost impossible to detect errors, owing to its large magnitude.
• Less non-sampling errors: The magnitude of non- sampling errors is also much smaller in case of sampling method because of smaller size of data.
• More reliable: In sampling method scientific methods and trained investigators are employed for the collection of data, which make it more reliable than census method.

Secondary data should be used with great care and caution. While using secondary data, the investigator should specifically consider the following factors

1. Reliability of Data: The first and foremost concern of the investigator should be that whether the secondary data is reliable or not. In order to check the reliability of data, the investigator should enquire about

1. The reliability, integrity and experience of the #collecting organisation.
2. The reliability of the source of information.
3. The methods used for the collection and analysis of the data.

2. Suitability of Data: After satisfying himself as regards to the reliability of data, the investigator should check whether the data is suitable or not.

1. For this, it is important that the investigator
2. Observes and compares the objectives, nature and scope of the given enquiry with the original enquiry.
3. Confirms that the various terms and units were clearly defined and were also uniform throughout the earlier investigation and these are relevant for the present enquiry also.
4. Takes into account the difference in time periods for the original enquiry and the investigation in hand.

3. Adequacy of Data: After satisfying himself about the reliability and suitability of data, the investigator should check whether data is adequate or not. For this, he should check the area of study to which the data relates, and also check the time period which the data covers.

Yes, lottery method always gives a random sample. In random sampling, the items which get selected are beyond the control of the investigator, it depends entirely on chance. Each and every unit in the population has an equal chance of being selected. Similarly in lottery method, each individual unit is selected at random from the population and has equal opportunity of being selected.
For example: if there are 50 students, out of which we have to select 5, we will put 50 slips containing the names of all the students in a bowl and mix them well. Then five slips are selected from the bowl one by one without replacement. The students corresponding to these 5 slips will constitute our sample. Here each student has an equal opportunity of being selected same as in case of random selection. Hence, lottery method always gives a random sample.

Primary data are those which are collected for a specific purpose directly from the field of enquiry, and thus original in nature. The procedure adopted for collection of data may either be complete enumeration or sampling.(i.e. sample survey). Primary data provides a statistician with detailed information. Such data are published by the authorities themselves as Government, Civil bodies, Trade Associations etc. Individuals such as Economists, and institutions like Banks and other allied bodies can collect primary data for a specific purpose, by engaging trained investigators. The collection of primary data is a laborious and time consuming process. It is also expensive. Secondary data are such numerical information which has been already collected by some agency for a specific purpose and are subsequently compiled from that source for application in a different connection. For example the Census figures published will be primary data, whereas the same data reproduced in another publication will come under the category of secondary data. The chief sources of secondary data are: Publications of State Governments, of Foreign governments, and international bodies like ILO, UNO, UNESCO, WHO, etc.
In short, when time and funds are less and accuracy is not so important then secondary method in better, otherwise Primary method in better.

S. No.	Primary data	Secondary data
1.	Primary data are those data which are collected from the primary sources.	Secondary data are those data which are collected from the secondary sources.
2.	Primary data are known as basic data.	Secondary data are known as subsidiary data.
3.	The collection of primary data is more expensive.	The collection of secondary data is comparatively less expensive.
4.	It takes more time to collect the data.	It takes less time to collect the data.
5.	Primary data are more accurate.	Secondary data are less accurate than the primary data.
6.	Primary data are known as first hand data.	Secondary data are known as second hand data.
7.	Primary data are not readily available.	Subsidiary data are readily available.
8.	It is required to take much care at the time of collecting data.	It is not required to take much care at the time of collecting data.

Under telephonic interview method, the investigator asks questions to the informants over the telephone and collects data pertaining to the field of investigation. The merits of telephonic interview are:

1. Less expensive: It is relatively less expensive as the telephone costs are much lower than the cost of personal interviews.
2. High response rate: The response rate is relatively high under this method.
3. Better method: This method is better in cases where the respondents are reluctant to answer certain questions in personal interviews.
4. Less personal influence: Under this method, there is relatively less influence of the investigators on the respondents.

The demerits of telephonic interview are:

1. The limited access to people, as many people may not prefer to give information on telephones.
2. Telephone interviewers can not see visual reactions of the informants towards sensitive questions, due to lack of face to face contact.

Under mailing questionnaire method, a list of question (called questionnaire) pertaining to the investigation is prepared and sent to each informant by mail with a request to complete and return it within a given time schedule. The informants write the answers against the questions and return the duly completed questionnaire to the investigator. Merits of mailing questionnaire method are:

1. Less expensive: It is relatively less expensive than other methods.
2. Wider area: It is the only method where the field of investigation is very vast and the informants are spread over a wide geographical area.
3. No possibility of personal bias: There is no room for personal bias or prejudice on the part of the investigators.
4. Originality: This method is original and fairly reliable, because the information is supplied by the concerned person.

Demerits of mailing questionnaire method are:

1. Limited use: This method cannot be used when the informants are illiterate.
2. Low response rate: It involves some uncertainty about the response. In many cases, the respondents do not return the questionnaire.
3. Lack of flexibility: This method lacks flexibility because, when questions are not properly replied, these cannot be changed to obtain the required information.
4. Inaccurate data: The information supplied by the informants may not be correct and it may be very difficult to verify the accuracy.

Differences between census survey and sample survey are:

S. No.	Basis	Census Survey	Sample Survey
1.	Coverage	The whole universe is taken for collection of data in census survey.	Only representative sample is taken for collection of data in sample survey.
2.	Suitability	This method is suitable when the area under investigation is relatively small.	This method is suitable when the area under investigation is large.
3.	Accuracy	Since, all items are studied under census survey, highest degree of accuracy is possible.	Since only representative samples are studied under sample survey, it is less accurate.
4.	Time	Census survey is very time consuming as all items are studied.	Sample survey is less time consuming as only samples are studied.
5.	Nature of Items	Census survey is suitable when items in the universe have diverse characteristics.	Sample survey is suitable when items in the universe are homogeneous.

Differences between census survey and sample survey are:

S. No.	Basis	Census Survey	Sample Survey
1.	Coverage	The whole universe is taken for collection of data in census survey.	Only representative sample is taken for collection of data in sample survey.
2.	Suitability	This method is suitable when the area under investigation is relatively small.	This method is suitable when the area under investigation is large.
3.	Accuracy	Since, all items are studied under census survey, highest degree of accuracy is possible.	Since only representative samples are studied under sample survey, it is less accurate.
4.	Time	Census survey is very time consuming as all items are studied.	Sample survey is less time consuming as only samples are studied.
5.	Nature of Items	Census survey is suitable when items in the universe have diverse characteristics.	Sample survey is suitable when items in the universe are homogeneous.

The differences between direct personal investigation and indirect oral investigation are:

S. No.	Basis	Direct Personal Investigation	Indirect Oral Investigation
1.	Source of Information	In direct personal investigation, information is collected directly from the concerned persons.	In indirect oral investigation, information is collected from persons other than the concerned persons.
2.	Area of Investigation	This method of data collection is suitable if the area of investigation is limited.	This method of data collection is suitable when the area of investigation is large.
3.	Cost	This method of data collection is costly.	This method of data collection is comparatively cheaper.
4.	Knowledge about Informants	In this method, the investigator should know the language and the culture of the informants.	This method does not require the investigator to be well-versed with the language and culture of the informants.

Mailing questionnaire is suitable for the cases enumerated below:

1. Where the informants are educated.
2. Where the information is required to be regularly supplied.
3. Where the area of inquiry is wide.

Schedule filled by enumerators is suitable for the cases enumerated below:

1. When the field of study is large.
2. When the organisation has adequate resources at its disposal.
3. Where the informants are illiterate.

The procedure of selecting random sample of 3 students out of 10 in a class is as follows:

1. Assign a particular number between 1 to 10 to all the 10 students like, 01, 02, 03, 04, 05, 06, 07, 08, 09, 10.
2. Select a number randomly. Let us assume that the number selected is 05.
3. Consult the Two-Digit Random Number Table, two numbers successive to the selected random number (i.e. 05) either horizontally or vertically are the remaining two students (i.e. 06 and 07).

The NSSO was established in the year 1950 under the Ministry of Finance to conduct surveys and collect data on estimates of literacy, school enrolment, utilisation of educational services, employment, unemployment, manufacturing and service sector enterprises, morbidity, maternity, child care, utilisation of public distribution system, etc and to publish the results of the surveys through reports and its quarterly journal “Sarvekshana'. The NSSO conducts continuous surveys on various problems in successive rounds quinquennially (every five years).NSSO was formed with the following objectives in view:

1. To provide statistical information which helps the government to formulate various plans and policies.
2. To evolve suitable statistical techniques which help in the analysis of statistical data so that the solutions to various economic and administrative problems can be figured out and the future trends can be estimated.

To collect and publish data which can be used by various individuals and organisations to understand and resolve various economic problems. To publish data which proves to be useful for those research workers who are engaged in research work in various socio-economic fields.

Example 1: A study was conducted to know the average income of people in a village. The total number of person was 750. Out of these, 70 villagers selected and their average income was recorded. So, in this example:

• Population is the number of total villagers which is equal to 750.
• Sample is the 70 villagers whose average income was recorded.
• Variable under study is the income of the villagers.

Example 2: In order to study the to record the level of sugar in the blood, blood sample of 1000 people was taken from 10,000 people. So, in this example

• Population is the total number of people i.e., 10,000.
• Sample is the 1000 people.
• Variable is the sugar level.

There are some agencies which operate at the national and state level to collect, process and tabulate data for larger benefit. At the national level, the agencies operating are Census of India, National Sample Survey Organisation (NSSO), Central Statistical Organisation (CSO), Registrar General of India (RGI), Labour Bureau, etc.

• Census of India gives the most complete and on going demographic record of population.
• The census is conducted regularly since 1951. It gives information on the size, density, sex-ratio, migration, literacy, etc. Census data is used to understand many economic and social issues in India.
• NSSO, another government organisation, conducts nation-wide continuous survey on socio-economic issues. The data collected by it is released through its quarterly journal “Sarvekshana”. NSSO also collects details of industrial activities and retail prices for various goods, which are used for planning purposes by the Government of India.

Questionnaire must be examined and edited if necessary.Statistical enquiry refers to an investigation on a topic by any agency or an individual which involves quantitative facts. In other words, statistical enquiry implies search of truth by using statistical tools. All statistical enquiries involve collection of data, their organization, presentation, analysis and interpretation. Collection of data is the foundation of all other exercises involved in undertaking a statistical enquiry. Organization, presentation and analysis all will become futile if there is any defect in data collected. Therefore it is of utmost importance in a statistical enquiry. An investigator whether it be an individual or an agency has to plan all stages of data collection much in advance. He has to move step by step. Given below are some of the major steps in collection of data.
Develop a complete plan for survey: It is important to draw a complete plan for a statistical survey before we start collecting data actually. The statistician 25 has to plan three things.

1. What data to be obtained;
2. From whom data are to be obtained
3. By what methods the data are to be obtained-primary or secondary.

He also has to decide the expenditure to be incurred and time availability. The expenditure and the time period will determine most of the subsequent steps he has to take.

1. Decide whether to adopt census method or sample method: For conducting survey on any issue, the investigator has two options: sample and census. Which method will depend on budget, availability of time and accuracy requirement?
2. Preparing Questionnaire: Designing the questionnaire is influenced by many considerations like number of questions to be included, language of questions, types of questions, ordering of the questions etc. we shall discuss it in detail later in this chapter under the heading "construction of a questionnaire".
3. Mode of Distribution of Questionnaire: There are different ways in which questionnaire can be sent. It can be personal or by post or by e mail. In personal it can be filled either by respondent or enumerator. These methods have also been discussed in detail later in the chapter.
4. Check the filled in forms for completeness and consistency: It is the last stage in collection of data. This stage comes when duly filled forms are returned by the respondents. Each

Ans. "Indirect Interview" method is a method of primary data collection used when it is not possible to gather the required information from the other sources. This may be due to the respondents being reluctant to open up on touchy or personal issues. So, the investigator approaches third party' who knows about the issue/ problem being studied. A list of questions relating to the investigation is prepared and asked from the third party and the answers are duly recorded.
For example, to conduct a study of the eating habits (say junk food consumption of the students of a particular school) direct interview will not help us but an Indirect Interview through a third party' shall be suitably conducted. Third party in this case may be a bakery shop selling pizzas, burgers, noodles etc. near the school.

• The difference between the Indirect Interview and Personal Interview lies w.r.t. the area of investigation. Through Indirect Interview a large area of investigation can be covered, whereas through a personal interview very limited area is covered up. In terms of reliability factor, the third party may not be a authentic source whereas in case of personal interview the reliability and accuracy of the study is more.
• In terms of cost involved, Indirect Interview is relatively less expensive than the Personal Interview method.

1. Originality: Primary data is collected by the investigator himself. It is original and first hand information. On the other hand, secondary data is already available in published or unpublished form. It is not original in character.
2. Accuracy: The information obtained through primary data is more reliable and accurate whereas the information obtained through secondary data is not perfectly accurate and reliable.
3. Suitability of objective. Primary data is always collected according to specific objective. It does not require any adjustment or modification. On the other hand, secondary data is the data which has already been collected for some other objective. So, it needs to be modified to suit the objective of the study.

Ans. The most common methods of collecting primary data are:

1. Personal Interview method.
2. Indirect Interview method.
3. Mailing Questionnaire method.
4. Telephone Interview method.

In Mailing Questionnaire method, the data in a survey is collected by mail and the questionnaire is sent to all individuals by mail, alongwith a request letter to complete and return it by the given date assigned.The merits of mailing questionnaire method are:

1. It is relatively a less expensive method, as the mailing costs are much less than the personal interview method.
2. It allows the researcher to have access to people in remote and far-off areas, which may be either difficult to reach by a person or by a telephone.

The demerits of mailing questionnaire method are:

1. On account of lack of personal touch in the mailing questionnaire method, there is a possibility of ‘misunderstanding of certain questions' asked. As a result, the questions may be misunderstood and thereby wrongly attempted.
2. Response rate to the mail questionnaire may also below, due to the lack of personal touch. Many questionnaires may not be returned and rest of them may be returned incomplete, with many questions not attempted and the questionnaire may even get lost in the mail itself.

The published sources of secondary data can be classified as:

1. Official Publications of Central Government The various dapartments, ministries and organisations of Central Government collect, compile and publish statistical data on a number of topics such as prices, population, production, consumption, employment, poverty, etc.
2. For example, National Sample Survey Organisation (NSSO), Census of India, etc. The information supplied by these organisation is more authentic and reliable than that obtained from other sources on the same subject.
3. Publications of Semi-Government Statistical Organisations: The publications of semi-government statistical organisations provide very useful information.
4. For example, the data published by the Municipal and District Boards, Corporations, Block and Panchayat Samitis on vital statistics (births and deaths), health, sanitation and other related subjects provide reliable and useful information.
5. Publications of Research Institutions: Individual research scholars and various research institutes, such as the Indian Statistical Institute (ISI), Indian Council of Agricultural Research (ICAR), etc. publish the findings of their research work in the form of research papers or journals. These papers and journals are also an important source of secondary data.
6. Publications of Commercial and Financial Institutions: Commercial and financial institutions such as the Federation of Indian Chamber of Commerce and Industries (FICCI), Trade Unions, Stock Exchanges, etc. publish reports on various economic and business phenomena. These reports also provide useful secondary data.
7. Reports of Various Committees and Commissions Appointed by the Government: The Central or the State Governments appoint various committees or commissions to conduct a detailed study on a specific problem or issue. The reports of these committees and commissions are an important source of secondary data. For example, Kothari Commission's report on Educational Reforms, Wanchoo Commission's report on taxation, etc.
8. Private Publications: These are published by private organisations or individuals. Examples of private publications are journals, newspapers, annual reports, articles, market reviews, etc.
9. International Publications: The publications of foreign governments and international organisations are also a source of valuable secondary data. For example, IMF, ILO, World Bank, UNO, etc publish many reports and books which contain secondary data.

Not representative of entire population: The accuracy of the samples drawn depe. In statistics population has a different meaning than what it is in general usage. Generally speaking, population refers to the number of people living in a geographical area but in statistics, it refers to the collection of all possible observations of specified characteristic of interest. It is also called universe. For example, if we wish to know likelihood of olay effects amongst women then women in age group of 30 and above who belong to upper middle class families will constitute our population. Sample refers to a part of population selected for analysis and drawing inferences about the population. The process of drawing samples is called sampling. If we selected 1000 women by using any method of sampling, it will be sample. When population consists of definite number of items, it is called definite population. On the other hand, when it consists of infinite number of items, it is called infinite population. For example, number of students in a class is a definite population but number of pollution creating vehicles is practically indefinite. Census Method: It is also called complete enumeration method. In this method data are collected of reach and every item of population. Advantages:

1. It provides information about each and every item of the population.
2. Element of bias is eliminated as results are based on each and every item.
3. It is an exhaustive survey which can be used for other purposes later as secondary data.
4. It helps to study diversity in the universe. It is especially useful in case of diverse population.
5. When items in a universe are of complex nature then it is necessary to use census method.

Disadvantages:

1. Census method requires a lot of expenditure in terms of time, effort and money.
2. It is possible only for definite population.
3. It is very time consuming.
4. It is not possible in some cases like we, can't use census method to find infection in blood of a person. A lady can't taste entire food to judge if it is cooked or not.

Suitability:Census method is useful when:

• Population size is limited.
• Population consists of diverse items.
• High degree of accuracy and reliability is required.
• Enough time and funds are available.

Sampling Method: In this method, a group of items are selected from population either o randomly or otherwise and these items are studies to draw inferences about the entire population. Samples are a subset of population.Advantages of Sample Method:

• Less Costly: Sample method is more economical than census method. It needs to collect data from a part of population and hence costs less.
• Less Time consuming: It is far less time consuming as compared to census method. Due to smaller volume of data, it takes lesser time.
• Greater Accuracy: Accuracy of sampling data is more because it involves lesser calculations and lesser handling of data.
• Scientific Approach: It is a scientific method of data collection because it does not take all items but scientifically selects such a part of population which is representative of entire population.
• Greater Scope: When we want to collect data in greater details, this method is more useful. It is also more useful when enumerators are required to collect data and help of experts is required.
• Mathematical Convenience: Sample data is mathematically easier to handle as it is small in volume.
• Exceptional Applicability: In many cases, we have only one option which is sampling method. When we want to test blood, we can take only a sample and not entire blood. Similarly, for testing your knowledge, teacher can't give the complete chapter in test but takes some questions at random which are sample for her.

Disadvantages of Sample Method:

• Difficult to achieve complete accuracy: It is almost impossible that there are no difference between results of census method and results of sampling methods. There always exist some difference which is called sampling errors.
• Bias in Sample Selection: Many a times, sample is selected in a biased way. He might have some interest in a particular interest and may modify the data accordingly. For example, if principal ask teacher to give five copies of her class, teachers used biased selection of sampling.
• Samples are ends on whether the sample is representative of the characteristics of population. Practically, no sample is proper represents entire population.
• Not possible in case of Heterogeneous Population: Sampling method cannot be used in case of heterogeneous population.
• Lack of expertise: For drawing a sample scientifically, specialized knowledge and expertise is required which is not so easily available.

Suitability:

• Sample method is useful when:
• Population is homogeneous.
• Experts are available to withdraw sample scientifically.
• Less time and money is available.
• Accuracy is not so important.

There are two methods of random sampling.

1. Unrestricted Random Sampling.
2. Restricted random sampling.

Unrestricted Random Sampling: It is also called simple random sample. A simple random sample is one in which each and every item of the universe has V an equal chance of selection. Selection of all items is purely on chance. So each and every item of the universe has an equal chance of being selected or rejected.
There are two most popular methods of taking sample from this method
Lottery Method: It is the simplest method of selecting a random sample. Under this method, all items of the population are numbered or nailed and these numbers or names are written on small slips. These slips are put in a bowl and requisite numbers of slips are withdrawn at random. It is to be noted that all slips must be of same size and colour. It is also recommended that a non party should be asked to pick the slips. This method is widely used in quiz contests for selecting a question for the team, government departments make use of this method for allotment of benefits under schemes etc.
Use of Random Number Tables: When the population size is very large, it becomes a cumbersome task to make so many slips and using lottery method. To save time and energy, random number tables are used. A random number table is a simply a table which is created by scrambling the digits 0-9. The most popular random table is Tippet's Random Number Table which consists of 10,400 four digited random numbers, giving in all 41,600 digits (10,400 × 4). For example, if we have to select 100 persons from a group of 800 then we can select first 100 from Triplett's table which are below 800. There are some other random number tables also. These are:

1. Fisher and Yates Table: It is a table of 15,000 random digits written in the form of 1, 500 groups.
2. Rand Corporation: It consists of one million random digits consisting of 2, 00,000 random numbers of 5 digits each.
3. M.G. Kendall and B.B. Smith Table: this table consists of 1,00,000 digits grouped into 25,000 set of 4-digit random number. Stratified Sampling/Mixed Sampling: In this form of sampling, the population is first divided into two or more mutually exclusive segments based on some categories of variables of interest in the research. It is designed to organize the population into homogenous subsets before sampling, then drawing a random sample within each subset. With stratified random sampling the population of N units is divided into subpopulations of units respectively. These subpopulations, called strata, are non-overlapping and together they comprise the whole of the population. When these have been determined, a sample is drawn from each, with a separate draw for each of the different strata. The sample sizes within the strata are denoted by respectively. If a SRS is taken within each stratum, then the whole sampling procedure is described as stratified random sampling. The primary benefit of this method is to ensure that cases from smaller strata of the population are included in sufficient numbers to allow comparison.

Cluster Sampling: In some instances the sampling unit consists of a group or cluster of smaller units that we call elements or subunits. There are two main reasons for the widespread application of cluster sampling. Although the first intention may be to use the elements as sampling units, it is found in many surveys that no reliable list of elements in the population is available and that it would be prohibitively expensive to construct such a list. In many countries there are no complete and updated lists of the people, the houses or the farms in any large geographical region.
Systematic Sampling: This method of sampling is at first glance very different from SRS. In practice, it is a variant of simple random sampling that involves some listing of elements - every nth element of list is then drawn for inclusion in the sample. Say you have a list of 10,000 people and you want a sample of 1,000.
Creating such a sample includes three steps:

• Divide number of cases in the population by the desired sample size. In this example, dividing 10,000 by 1,000 gives a value of 10.
• Select a random number between one and the value attained in Step 1. In this example, we choose a number between 1 and 10 - say we pick 7.
• Starting with case number chosen in Step 2, take every tenth record (7, 17, 27, etc.).

Stratified Sampling: In this form of sampling, the population is first divided into two or more mutually exclusive segments based on some categories of variables of interest in the research. It is designed to organize the population into homogenous subsets before sampling, then drawing a random sample within each subset. With stratified random sampling the population of N units is divided into subpopulations of units respectively. These subpopulations, called strata, are non-overlapping and together they comprise the whole of the population. When these have been determined, a sample is drawn from each, with a separate draw for each of the different strata. The sample sizes within the strata are denoted by respectively. If a SRS is taken within each stratum, then the whole sampling procedure is described as stratified random sampling. The primary benefit of this method is to ensure that cases from smaller strata of the population are included in sufficient numbers to allow comparison.Its Merits include:

• Administrative convenience may dictate the use of stratification, for example, if an agency administering a survey may have regional offices, which can supervise the survey for a part of the population.
• Stratification may improve the estimates of characteristics of the whole population. It may be possible to divide a heterogeneous population into sub-populations, each of which is internally homogenous. If these strata are homogenous, i.e., the measurements vary little from one unit to another; a precise estimate of any stratum mean can be obtained from a small sample in that stratum. The estimate can then be combined into a precise estimate for the whole population.
• There is also a statistical advantage in the method, as a stratified random sample nearly always results in a smaller variance for the estimated mean or other population parameters of interest.

Demerits:Sampling problems may be inherent with certain sub populations, such as people living in institutions (e.g. hotels, hospitals, prisons). Systematic Sampling: This method of sampling is at first glance very different from SRS. In practice, it is a variant of simple random sampling that involves some listing of elements - every nth element of list is then drawn for inclusion in the sample. Say you have a list of 10,000 people and you want a sample of 1,000. Creating such a sample includes three steps:

• Divide number of cases in the population by the desired sample size. In this example, dividing 10,000 by 1,000 gives a value of 10.
• Select a random number between one and the value attained in Step 1. In this example, we choose a number between 1 and 10 - say we pick 7.
• Starting with case number chosen in Step 2, take every tenth record (7, 17, 27, etc.). More generally, suppose that the N units in the population are ranked 1 to N in some order (e.g., alphabetic). To select a sample of n units, we take a unit at random, from the 1st k units and take every k-th unit thereafter.

The advantages of systematic sampling method over simple random sampling include:

• It is easier to draw a sample and often easier to execute without mistakes. This is a particular advantage when the drawing is done in the field.
• It stratifies the population into n strata, consisting of the 1st k units, the 2nd k units, and so on. Thus, we might expect the systematic sample to be as precise as a stratified random sample with one unit per stratum. The difference is that with the systematic one the units occur at the same relative position in the stratum Do whereas with the stratified, the position Sit in the stratum is determined separately a by randomization within each stratum.

1. Difference between Sampling and non sampling errors:

1. Sampling Errors: When sample method is used, we cannot expect to get the same result as we would have got if we would have used census method. There is always a difference in conclusions drawn from sample and conclusions of the universe. This is called sampling error. These errors are minimum when random sampling techniques are used and size of sample is fairly large. As we increase size of sample, sampling error keeps falling and become zero at 100% i.e. census method. Therefore, these errors exist only in sample method.
2. Non Sampling Errors: These errors are committed due to human mistake or clerical reasons. These are also called measurement errors. These errors are found in sampling as well as census method rather their occurrence is more expected in census method due to large volume of data. These errors can be minimized with care and caution.

2. Difference between Random and Non random Sampling:

S. No.	Basis	Random Sampling	Non Random Sampling
1.	Meaning	It is a sampling method in which each and every item of the population has an equal chance of being selected.	In this method, all items of the population do not have an equal chance of selection. It depends on the judgment and convenience of investigator.
2.	Scientific	This is a scientific method of sample selection.	This is an unscientific method of sample selection.
3.	Bias	It is free from bias.	It involves personal bias.
4.	Other Name	It is also called probability sampling.	It is also called non probabitity samplhg.
5.	Recommended	It is recommended by experts.	It is not recommended by experts.

3. Difference between census and sample method:

S. No.	Basis	Sample Method	Census Method
1.	Items of study	Only few units of the population studied.	Each and every unit of the population is studied.
2.	Cost	Relatively less amount of finance, till labour is required.	Requires large amount of finance, time and labour.
3.	Reliability	Results are less reliable.
		Results are quite reliable.
4.	Suitability	It is more suitable if population homogeneous in nature.	It is more suitable if population is heterogeneous in nature.
5.	Possibility	It can be used, if part of the population is missing.	It cannot be used when part of the population is missing.
6.	Nature of Error	It may have sampling as well as non sampling errors.	It may have only non sampling errors.
7.	Organisation	It is easy to be organised.	It is difficult to be organised.

4. Difference between Biased and Unbiased errors:

1. Biased Errors: Biased errors are those errors which arise because conclusions have been drawn from a biased sample. These errors can be eliminated by choosing unbiased sample.
2. Unbiased errors: These errors occur due to usage of sample method. If on the basis of height of five students in a class of 15 we are calculating average height, obviously results will vary from actual. These errors cannot be eliminated.

When investigator uses the data which is used by someone else, it is called secondary data. Sources of secondary data are as follows: Published Printed Sources: There are a variety of published printed sources. Their credibility depends on many factors. For example, on the writer, publishing company and time and date when published. New sources are preferred and old sources should be avoided as new technology and researches bring new facts into light. Books: Books are available today on any topic that you want to research. The use of books start before even you have selected the topic. After selection of topics books provide insight on how much work has already been done on the same topic and you can prepare your literature review. Books are secondary source but most authentic one in secondary sources.

• Journals/ periodicals: Journals and periodicals are becoming more important as far as data collection is concerned. The reason is that journals provide up-to-date information which at times books cannot and secondly, journals can give information on the very specific topic on which you are researching rather talking about more general topics.
• Magazines/ Newspapers: Magazines are also effective but not very reliable. Newspaper on the other hand are more reliable and in some cases the information can only be obtained from newspapers as in the case of some political studies.

Published Electronic Sources: As internet is becoming more advance, fast and reachable to the masses; it has been seen that much information that is not available in printed form is available on internet. In the past the credibility of internet was questionable but today it is not. The reason is that in the past journals and books were seldom published on internet but today almost every journal and book is available online. Some are free and for others you have to pay the price. E-journals: E-journals are more commonly available than printed journals. Latest journals are difficult to retrieve without subscription but if your university has an e-library you can view any journal, print it and those that are not available you can make an order for them. General Websites: Generally websites do not contain very reliable information so their content should be checked for the reliability before quoting from them. Weblogs: Weblogs are also becoming common. They are actually diaries written by different people. These diaries are as reliable to use as personal written diaries. Unpublished Personal Records: Some unpublished data may also be useful in some cases. Diaries: Diaries are personal records and are rarely available but if you are conducting a descriptive research then they might be very useful. The Anne Franks diary is the most famous example of this. That diary contained the most accurate records of Nazi wars. Letters: Letters like diaries are also a rich source but should be checked for their reliability before using them. Government Records: There are two major government agencies which provide data. These are CSO and NSSO. Central Statistical Office (CSO) It is responsible for coordination of statistical activities in the country and for evolving and maintaining statistical standards. Its activities include compilation of National Accounts; conduct of Annual Survey of Industries and Economic Censuses, compilation of Index of Industrial Production, as well as Consumer Price Indices. It also deals with various social statistics, training, international cooperation, Industrial Classification etc. The CSO is headed by a Director-General who is assisted by 5 Additional Director-Generals looking after the National Accounts Division, Social Statistics Division, Economic Statistics Division, Training Division and the Coordination and Publication Division. CSO is located in the Sardar Patel Bhawan, Parliament Street, New Delhi. The Industrial Statistics Wing of CSO is located in Kolkata. The Computer Centre also under the CSO is located in RK Puram, New Delhi. National Sample Survey Office (NSSO)It has four divisions:

• Survey Design and Research Division
• (SDRD)–Kolkata
• Field Operations Division (FOD)-New Delhi
• Data Processing Division (DPD)–Kolkata
• Co-ordination and Publication Division (CPD)-New Delhi
• The surveys on Consumer Expenditure, Employment-Unemployment, Social Consumption (Health, Education etc.), Manufacturing Enterprises, Service Sector Enterprises are carried out once in 5years. And survey of Land and Livestock Holding and Debt and Investment are carried out once in 10 years.