Population in Research

Meaning of Population

In research, population refers to the entire group of individuals, objects, organizations, or units that possess certain common characteristics and about which the researcher wants to draw conclusions. In simple words, population is the complete set of units relevant to a particular research study.

A population may include people, households, students, employees, customers, companies, banks, schools, or any other units of analysis.

For example, if a researcher wants to study the job satisfaction of teachers in Simara, all teachers working in Simara are considered the population of the study. The researcher may not collect information from every teacher; instead, a sample can be selected from the population.

Example

Suppose a college has 500 BBS students, and a researcher wants to study their satisfaction with online learning.

Population: All 500 BBS students
Sample: 100 students selected from those 500
Research topic: Students’ Satisfaction with Online Learning

Thus, population is the complete group from which the sample is selected and about which the researcher intends to make a conclusion.

Conclusion

Population is an important concept in research because it defines the scope and boundaries of the study. Proper identification of the population helps the researcher select an appropriate sample and make valid conclusions.

Sampling (नमुना छनोट) को अर्थ

Sampling भन्नाले अनुसन्धानमा अध्ययन गर्नुपर्ने सम्पूर्ण Population बाट निश्चित उद्देश्य र विधिअनुसार केही प्रतिनिधिमूलक एकाइहरू छनोट गर्ने प्रक्रियालाई भनिन्छ।

सरल भाषामा, ठूलो समूह (Population) बाट अनुसन्धानका लागि केही सदस्य छान्ने प्रक्रिया नै Sampling हो।

उदाहरण:
कुनै कलेजमा BBS का ५०० विद्यार्थी छन्। सबै ५०० जनाबाट तथ्याङ्क संकलन गर्न कठिन भएकाले अनुसन्धानकर्ताले तीमध्ये १०० जना विद्यार्थी छनोट गरी अध्ययन गर्छ भने १०० जना छान्ने प्रक्रिया Sampling हो।

परिभाषा:

“Sampling is the process of selecting a representative portion of the population for the purpose of research.”

मुख्य कुरा

Population → Sampling → Sample → Data Collection → Analysis → Conclusion

अर्थात्, Population बाट Sample छनोट गर्ने प्रक्रिया = Sampling।

Meaning of Sampling

Sampling is the process of selecting a small and representative group of individuals, objects, or units from the entire population for the purpose of conducting research.

In research, it is often difficult to collect information from every member of the population because of limitations of time, cost, resources, and manpower. Therefore, the researcher selects a certain number of units from the population using an appropriate sampling method. The selected units are called the sample, and the process of selecting them is called sampling.

Example

Suppose a university has 10,000 BBS students and a researcher wants to study their satisfaction with online learning. It may be difficult to collect data from all 10,000 students. Therefore, the researcher selects 500 students using an appropriate sampling method.

Population: 10,000 BBS students
Sample: 500 selected students
Sampling: The process of selecting 500 students from the 10,000 students

Importance of Sampling

Saves time and cost.
Requires fewer resources and manpower.
Makes research easier and more manageable.
Helps the researcher collect data efficiently.
A properly selected sample can provide a basis for making conclusions about the population.

In short:

Sampling is the systematic process of selecting a representative sample from a population for the purpose of research.

Sampling को विस्तृत अर्थ

Sampling (नमुना छनोट) भन्नाले अनुसन्धानमा अध्ययन गर्नुपर्ने सम्पूर्ण Population बाट अनुसन्धानको उद्देश्यअनुसार निश्चित संख्या वा केही प्रतिनिधिमूलक एकाइहरू छनोट गर्ने व्यवस्थित प्रक्रियालाई Sampling भनिन्छ।

हरेक अनुसन्धानमा सम्पूर्ण Population का सबै सदस्यबाट तथ्याङ्क संकलन गर्न सम्भव नहुन सक्छ। समय, खर्च, जनशक्ति र अन्य स्रोतको सीमितताका कारण Population बाट केही प्रतिनिधिमूलक सदस्यहरू छनोट गरिन्छ। यसरी छनोट गरिएका सदस्यहरूको समूहलाई Sample (नमुना) भनिन्छ र Sample छनोट गर्ने प्रक्रियालाई Sampling भनिन्छ।

उदाहरण

मानौँ, कुनै विश्वविद्यालयअन्तर्गत १०,००० जना BBS विद्यार्थी छन्। अनुसन्धानकर्ताले सबै विद्यार्थीको अध्ययन गर्न नसक्ने भएकाले ५०० जना विद्यार्थीलाई वैज्ञानिक विधिबाट छनोट गर्छ।

Population = १०,००० जना BBS विद्यार्थी
Sample = ५०० जना BBS विद्यार्थी
Sampling = १०,००० बाट ५०० जना छनोट गर्ने प्रक्रिया

Sampling किन गरिन्छ?

समय बचत गर्न
अनुसन्धानको खर्च घटाउन
सीमित जनशक्तिमा अध्ययन गर्न
ठूलो Population लाई सजिलोसँग अध्ययन गर्न
अनुसन्धानलाई व्यवस्थित र प्रभावकारी बनाउन

छोटोमा:

Population बाट अनुसन्धानका लागि उपयुक्त र प्रतिनिधिमूलक Sample छनोट गर्ने व्यवस्थित प्रक्रियालाई Sampling भनिन्छ।

Sampling Process

The diagram shows the seven major steps involved in the sampling process. Sampling is not simply selecting some people from a population; it is a systematic process that begins with defining the population and ends with selecting the sample.

1. Define the Population

The first step is to clearly define the population to be studied.

Population means the entire group of individuals, objects, institutions, or units about which the researcher wants to draw conclusions.

The researcher should clearly specify:

Who will be included?
Where are they located?
What characteristics should they possess?
What is the time period of the study?

Example:
Suppose the researcher wants to study job satisfaction among BBS teachers in Bara district. The population may be defined as all BBS teachers working in colleges of Bara district during the study period.

2. Specify the Sampling Frame

A sampling frame is the actual list or source from which the sample is selected.

It should contain or identify the members of the defined population.

Examples of sampling frames:

Student registration list
Employee list
Voter list
List of registered businesses
Membership records

Example:
If the population is all BBS students of a college, the official student enrollment list can serve as the sampling frame.

Important: A good sampling frame should be as complete and accurate as possible.

3. Specify the Sampling Unit

A sampling unit is the basic unit or element that can be selected during sampling.

It may be:

An individual
A household
A school
A company
A bank
A group or organization

Example:
If the study is about BBS students, each BBS student may be the sampling unit.

If the study is about banks, each bank may be the sampling unit.

4. Selection of Sampling Method

At this stage, the researcher decides how the sample will be selected.

Sampling methods are broadly divided into two categories:

A. Probability Sampling

Every unit has a known chance of being selected.

Examples:

Simple random sampling
Systematic sampling
Stratified sampling
Cluster sampling

B. Non-probability Sampling

The chance of selection is not necessarily known.

Examples:

Convenience sampling
Purposive sampling
Quota sampling
Snowball sampling

Example:
If 500 students are available and the researcher randomly selects 100 students, simple random sampling may be used.

5. Determination of Sample Size

The researcher then determines how many units should be included in the sample.

The sample should be sufficiently large to provide reliable results, but it should also be manageable in terms of time and cost.

Sample size can depend on:

Total population size
Nature of the research
Required level of accuracy
Available time
Research budget
Sampling method
Expected response rate

Example:
If a college has 2,000 students, the researcher may decide to select 200 students as the sample.

So:

Population = 2,000 students
Sample size = 200 students

6. Preparation of Plan for Sampling

Now the researcher prepares a complete sampling plan describing how the sampling will actually be carried out.

The plan may specify:

Target population
Sampling frame
Sampling unit
Sampling method
Sample size
Selection procedure
Time and place of data collection
How non-response will be handled

Example:
A researcher may prepare a plan stating:

“From the list of 2,000 BBS students, 200 students will be selected using simple random sampling, and questionnaires will be distributed during the second week of the study.”

This makes the sampling process clear and systematic.

7. Select the Sample

This is the final step of the sampling process.

After deciding the population, frame, unit, method, sample size, and plan, the researcher actually selects the required units from the population.

Example:
If the researcher has:

Population = 2,000 BBS students
Sampling frame = official student list
Sampling unit = individual student
Sampling method = simple random sampling
Sample size = 200

The researcher finally selects 200 students from the list according to the chosen method.

These 200 students become the sample for the study.

Complete Sampling Process at a Glance

1. Define the Population
↓
2. Specify the Sampling Frame
↓
3. Specify the Sampling Unit
↓
4. Select the Sampling Method
↓
5. Determine the Sample Size
↓
6. Prepare the Sampling Plan
↓
7. Select the Sample

Simple Example

Suppose a researcher wants to study satisfaction with online learning among BBS students.

Sampling Process	Example
Population	All 2,000 BBS students
Sampling Frame	Official student enrollment list
Sampling Unit	Individual BBS student
Sampling Method	Simple random sampling
Sample Size	200 students
Sampling Plan	Randomly select 200 students and collect data
Sample Selection	Final 200 students selected

Conclusion

Thus, sampling is a systematic and sequential process. A researcher first identifies who should be studied, determines where the population can be identified, decides what unit will be selected, chooses an appropriate sampling method, determines the sample size, prepares a sampling plan, and finally selects the sample. A properly designed sampling process increases the reliability and validity of research findings.

Sampling Process (नमुना छनोट प्रक्रिया)

Sampling Process भन्नाले अनुसन्धानका लागि सम्पूर्ण Population (समष्टि) बाट उपयुक्त र प्रतिनिधिमूलक Sample (नमुना) छनोट गर्न अपनाइने क्रमबद्ध तथा व्यवस्थित प्रक्रियालाई जनाउँछ।

तपाईंले पठाउनुभएको चित्रअनुसार Sampling Process का ७ वटा मुख्य चरणहरू छन्।

१. Define the Population — समष्टि निर्धारण

सबैभन्दा पहिले अनुसन्धानकर्ताले कुन समूहलाई अध्ययन गर्ने हो भन्ने स्पष्ट रूपमा निर्धारण गर्नुपर्छ।

Population भन्नाले अनुसन्धानसँग सम्बन्धित सम्पूर्ण व्यक्ति, वस्तु, संस्था वा एकाइहरूको समूह हो।

यस क्रममा अनुसन्धानकर्ताले निम्न कुरा स्पष्ट गर्नुपर्छ:

कसलाई अध्ययन गर्ने?
कुन स्थानमा अध्ययन गर्ने?
Population मा कसलाई समावेश गर्ने?
कुन समयावधिलाई अध्ययन गर्ने?

उदाहरण:
“बारा जिल्लाका BBS विद्यार्थीहरूको Online Learning सम्बन्धी सन्तुष्टि” अध्ययन गर्ने हो भने बारा जिल्लाका सम्बन्धित सबै BBS विद्यार्थी Population हुन्।

२. Specify the Sampling Frame — नमुना ढाँचा निर्धारण

Sampling Frame भन्नाले Population मा रहेका सबै सम्भावित एकाइहरूको सूची वा अभिलेख, जसबाट Sample छनोट गरिन्छ, त्यसलाई जनाउँछ।

उदाहरण:

विद्यार्थीहरूको नामावली
कर्मचारीको सूची
मतदाता नामावली
बैंक तथा कम्पनीहरूको सूची
विद्यालयको दर्ता सूची

उदाहरण:
कलेजका BBS विद्यार्थीहरूको अध्ययन गर्दा कलेजको आधिकारिक विद्यार्थी नामावली Sampling Frame हुन सक्छ।

३. Specify Sampling Unit — नमुना एकाइ निर्धारण

Sampling Unit भन्नाले Population बाट Sample छनोट गर्दा छनोट गरिने मूलभूत एकाइलाई भनिन्छ।

Sampling Unit हुन सक्छ:

व्यक्ति
परिवार
विद्यार्थी
शिक्षक
विद्यालय
कम्पनी
बैंक आदि।

उदाहरण:
BBS विद्यार्थीको अध्ययनमा एक जना विद्यार्थी Sampling Unit हो।

४. Selection of Sampling Method — नमुना छनोट विधि निर्धारण

अब अनुसन्धानकर्ताले Population बाट Sample कसरी छनोट गर्ने? भन्ने निर्णय गर्नुपर्छ।

Sampling methods मुख्यतः दुई प्रकारका हुन्छन्:

क. Probability Sampling

Simple Random Sampling
Systematic Sampling
Stratified Sampling
Cluster Sampling

ख. Non-probability Sampling

Convenience Sampling
Purposive Sampling
Quota Sampling
Snowball Sampling

उदाहरण:
२,००० विद्यार्थीमध्ये २०० विद्यार्थीलाई चिठ्ठा वा Computer-generated random numbers बाट छनोट गरियो भने Simple Random Sampling प्रयोग भएको हुन्छ।

५. Determination of Sample Size — नमुना आकार निर्धारण

यस चरणमा अनुसन्धानकर्ताले कति वटा एकाइलाई Sample मा समावेश गर्ने? भनेर निर्धारण गर्छ।

Sample Size निर्धारण गर्दा:

Population को आकार
अनुसन्धानको प्रकृति
आवश्यक शुद्धता
समय
लागत
उपलब्ध जनशक्ति
Sampling Method

जस्ता कुरालाई ध्यान दिइन्छ।

उदाहरण:
यदि Population मा २,००० BBS विद्यार्थी छन् र अनुसन्धानकर्ताले २०० जना विद्यार्थीलाई अध्ययन गर्ने निर्णय गर्छ भने:

Population = 2,000
Sample Size = 200

६. Preparation of Plan for Sampling — Sampling Plan तयार गर्ने

यस चरणमा अनुसन्धानकर्ताले Sampling कसरी सञ्चालन गर्ने भन्ने सम्पूर्ण योजना तयार गर्छ।

यस योजनामा निम्न कुरा समावेश हुन सक्छन्:

Population
Sampling Frame
Sampling Unit
Sampling Method
Sample Size
Sample छनोट गर्ने प्रक्रिया
Data collection को समय र स्थान
Non-response भएमा अपनाउने उपाय

उदाहरण:
“२,००० BBS विद्यार्थीको नामावलीबाट Simple Random Sampling प्रयोग गरी २०० जना विद्यार्थी छनोट गर्ने र उनीहरूबाट Questionnaire मार्फत तथ्याङ्क संकलन गर्ने।”

७. Select the Sample — नमुना छनोट गर्ने

यो Sampling Process को अन्तिम चरण हो।

अघिल्ला सबै निर्णय गरिसकेपछि अनुसन्धानकर्ताले तोकिएको विधि प्रयोग गरी Population बाट वास्तविक Sample छनोट गर्छ।

उदाहरण:

Population = २,००० BBS विद्यार्थी
Sampling Frame = विद्यार्थीको आधिकारिक नामावली
Sampling Unit = एक जना विद्यार्थी
Sampling Method = Simple Random Sampling
Sample Size = २००

अब नामावलीबाट Random Method प्रयोग गरेर २०० विद्यार्थी छनोट गरिन्छ। यी २०० विद्यार्थी नै अध्ययनको Sample हुन्छन्।

Sampling Process को सरल क्रम

Population निर्धारण
↓
Sampling Frame निर्धारण
↓
Sampling Unit निर्धारण
↓
Sampling Method छनोट
↓
Sample Size निर्धारण
↓
Sampling Plan तयार
↓
Sample छनोट

छोटो उदाहरण

कुनै कलेजमा २,००० BBS विद्यार्थी छन् र उनीहरूको Online Learning सम्बन्धी सन्तुष्टि अध्ययन गर्नुपर्यो भने:

Population: २,००० विद्यार्थी
Sampling Frame: विद्यार्थीको नामावली
Sampling Unit: एक विद्यार्थी
Sampling Method: Simple Random Sampling
Sample Size: २०० विद्यार्थी
Sampling Plan: Random रूपमा २०० विद्यार्थी छनोट गरी Questionnaire दिने
Sample: छनोट भएका २०० विद्यार्थी

निष्कर्ष

यसरी Population पहिचान गर्नेदेखि Sample छनोट गर्नेसम्मका क्रमबद्ध चरणहरूलाई Sampling Process भनिन्छ। राम्रो Sampling Process ले अनुसन्धानका लागि प्रतिनिधिमूलक Sample छनोट गर्न, समय तथा लागत बचत गर्न र अनुसन्धानको निष्कर्षलाई बढी विश्वसनीय बनाउन सहयोग गर्छ।

Types of Sampling

Sampling is the process of selecting a certain number of units from a larger population for the purpose of research. Based on the method used to select the sample, sampling is broadly divided into two major types:

Probability Sampling
Non-Probability Sampling

The figure shows four methods under probability sampling and five methods under non-probability sampling.

1. Probability Sampling

Probability sampling is a sampling method in which every member of the population has a known and usually non-zero chance of being selected.

Selection is based on randomness, rather than the researcher's personal judgment.

Main types:

A. Simple Random Sampling

Simple random sampling is a method in which every member of the population has an equal chance of being selected.

The researcher may use:

Lottery method
Random number table
Computer-generated random numbers

Example:
A college has 1,000 students and the researcher wants to select 100 students. If the researcher assigns numbers from 1 to 1,000 and randomly selects 100 numbers, it is simple random sampling.

Advantage: Easy to understand and reduces personal bias.

B. Systematic Sampling

In systematic sampling, the researcher selects members from a population at a fixed interval after choosing a starting point randomly.

The interval can be calculated as:

Sampling Interval (k) = Population Size (N) ÷ Sample Size (n)

Example:
Population = 1,000 students
Required sample = 100 students

\[ k = \frac{1000}{100}=10 \]

The researcher may randomly select the first student and then select every 10th student from the list.

For example:

7, 17, 27, 37, 47, 57...

Advantage: Simple, quick and convenient when an ordered population list is available.

C. Stratified Sampling

In stratified sampling, the population is divided into different homogeneous groups or strata based on particular characteristics, and samples are selected from each stratum.

Strata may be based on:

Gender
Age
Income
Education
Occupation
Geographic area

Example:
Suppose a college has:

600 male students
400 female students

Total = 1,000 students.

If the researcher wants a sample of 100 students and wants both groups properly represented, students can be selected from both male and female strata proportionately.

Main purpose: To ensure that important groups of the population are properly represented.

D. Cluster Sampling

In cluster sampling, the population is divided into groups or clusters, usually based on geographical or organizational units. Instead of selecting individuals from the whole population, the researcher selects some clusters and studies the units within them.

Example:
Suppose a researcher wants to study school students throughout Bara district.

Instead of selecting students from every school, the researcher may:

Divide schools into clusters.
Randomly select some schools.
Collect data from students in the selected schools.

Here, schools are clusters.

Advantage: Useful when the population is geographically scattered and can reduce travel and research costs.

2. Non-Probability Sampling

In non-probability sampling, every member of the population does not have a known or equal chance of being selected.

The researcher may select participants based on:

Convenience
Judgment
Availability
Specific characteristics
Voluntary participation
Recommendations from other participants

It is generally easier, faster and cheaper than probability sampling, but it may have greater risk of sampling bias.

Main types:

A. Purposive or Judgmental Sampling

In purposive sampling, the researcher deliberately selects participants who are considered appropriate or knowledgeable for the research.

The selection is based on the researcher's purpose or judgment.

Example:
A researcher wants to study the challenges faced by experienced research supervisors. Instead of selecting teachers randomly, the researcher specifically selects teachers who have experience supervising research.

Useful when: The researcher needs information from people with particular knowledge, experience or characteristics.

B. Quota Sampling

In quota sampling, the researcher divides the population into different categories and decides a fixed number (quota) of respondents from each category.

Unlike stratified sampling, the participants within each category are generally not selected randomly.

Example:
A researcher needs 100 respondents:

50 males
50 females

The researcher continues selecting available respondents until each quota is fulfilled.

Main feature: A fixed number of respondents is required from each group.

C. Convenience Sampling

Convenience sampling means selecting participants who are easily available and accessible to the researcher.

Example:
A researcher wants to study customer satisfaction and collects information from customers who happen to be available at a nearby shopping center.

Similarly, a teacher conducting a study may collect data from students who are readily available in their class.

Advantages:

Easy
Quick
Low cost

Limitation: It may not properly represent the entire population.

D. Self-Selecting Sampling

Self-selecting sampling, also called voluntary response sampling, occurs when individuals voluntarily choose themselves to participate in the research.

The researcher invites people to participate, and those who are interested respond.

Example:
A researcher posts an online survey:

“Students interested in participating in this research may complete this questionnaire.”

Students who voluntarily respond become the sample.

Limitation: People who volunteer may have different opinions or characteristics from those who do not participate, creating self-selection bias.

E. Snowball Sampling

Snowball sampling is used when it is difficult to identify or access members of a particular population.

The researcher first finds a few suitable participants. These participants then identify or refer other suitable participants, and the process continues like a snowball growing larger.

Example:
Suppose a researcher wants to study a group of people who are difficult to identify through ordinary lists. The researcher finds 5 suitable participants. Those 5 participants refer other people, who then refer additional participants.

Thus:

Initial participants → Referrals → More participants → Larger sample

Useful for: Hard-to-reach or hidden populations.

Probability vs. Non-Probability Sampling

Basis	Probability Sampling	Non-Probability Sampling
Selection	Based on random selection	Not necessarily random
Chance of selection	Known	Usually unknown
Researcher judgment	Limited	Often important
Bias	Generally lower	Generally higher
Representativeness	Usually better	May be limited
Cost	Usually higher	Usually lower
Time	May require more time	Usually faster
Examples	Random, systematic, stratified, cluster	Purposive, quota, convenience, self-selecting, snowball

Easy Way to Remember

Probability Sampling

Randomness is important.

Simple Random → Systematic → Stratified → Cluster

Non-Probability Sampling

Randomness is not essential.

Purposive → Quota → Convenience → Self-selecting → Snowball

Conclusion

The choice of sampling technique depends on the nature and objectives of the research, population characteristics, availability of a sampling frame, time, cost, and available resources. Probability sampling is generally preferred when the researcher wants a more representative sample and wishes to generalize findings to the population, while non-probability sampling is useful when accessibility, specific expertise, limited resources, or hard-to-reach populations are involved.

अनुसन्धानमा Sampling का प्रकारहरू

Sampling (नमुना छनोट) भन्नाले अनुसन्धानका लागि सम्पूर्ण Population (समष्टि) बाट निश्चित र उपयुक्त एकाइहरू छनोट गर्ने प्रक्रियालाई भनिन्छ। Sampling लाई मुख्यतः दुई प्रकारमा विभाजन गरिन्छ:

Probability Sampling (सम्भाव्यतामूलक नमुना छनोट)
Non-Probability Sampling (असम्भाव्यतामूलक नमुना छनोट)

१. Probability Sampling (सम्भाव्यतामूलक Sampling)

यस विधिमा Population को प्रत्येक सदस्यलाई Sample मा छनोट हुने निश्चित तथा ज्ञात सम्भावना हुन्छ। सामान्यतः छनोट गर्दा Random/यादृच्छिक विधि प्रयोग गरिन्छ।

यसका मुख्य प्रकारहरू:

A. Simple Random Sampling (सरल यादृच्छिक नमुना छनोट)

यसमा Population का हरेक सदस्यलाई Sample मा पर्ने समान अवसर हुन्छ।

छनोट गर्न:

Lottery/चिठ्ठा विधि
Random number table
Computer-generated random numbers

प्रयोग गर्न सकिन्छ।

उदाहरण:
कुनै कलेजमा १,००० विद्यार्थी छन् र अनुसन्धानका लागि १०० जना छनोट गर्नुपर्छ। प्रत्येक विद्यार्थीलाई १ देखि १,००० सम्म नम्बर दिएर Random रूपमा १०० नम्बर छनोट गरियो भने यो Simple Random Sampling हो।

फाइदा: व्यक्तिगत पक्षपात कम हुन्छ।

B. Systematic Sampling (क्रमबद्ध नमुना छनोट)

यसमा Population को सूचीबाट निश्चित अन्तराल (fixed interval) मा Sample छनोट गरिन्छ।

Sampling interval:

\[ k = \frac{N}{n} \]

जहाँ,
N = Population Size
n = Sample Size

उदाहरण:
Population = १,००० विद्यार्थी
Sample = १०० विद्यार्थी

\[ k=\frac{1000}{100}=10 \]

पहिलो विद्यार्थी Random रूपमा छनोट गरेपछि प्रत्येक १०औँ विद्यार्थी छनोट गरिन्छ।

जस्तै:

7, 17, 27, 37, 47, 57...

यसलाई Systematic Sampling भनिन्छ।

C. Stratified Sampling (स्तरीकृत नमुना छनोट)

यस विधिमा सम्पूर्ण Population लाई कुनै विशेष विशेषताका आधारमा विभिन्न समूह वा Strata मा विभाजन गरिन्छ र प्रत्येक समूहबाट Sample छनोट गरिन्छ।

Strata बनाउन सकिने आधार:

लिङ्ग
उमेर
आय
शिक्षा
पेशा
भौगोलिक क्षेत्र

उदाहरण:
कुनै कलेजमा:

पुरुष विद्यार्थी = ६००
महिला विद्यार्थी = ४००

जम्मा = १,०००

अनुसन्धानकर्ताले दुवै समूहको उचित प्रतिनिधित्व हुने गरी Sample छनोट गर्छ भने त्यो Stratified Sampling हो।

मुख्य उद्देश्य: Population का महत्वपूर्ण समूहहरू Sample मा उचित रूपमा प्रतिनिधित्व गराउनु।

D. Cluster Sampling (समूहगत नमुना छनोट)

यस विधिमा Population लाई विभिन्न समूह वा Cluster मा विभाजन गरिन्छ र ती Clusters मध्ये केहीलाई Random रूपमा छनोट गरिन्छ।

उदाहरण:
बारा जिल्लाका विद्यालयका विद्यार्थीहरूको अध्ययन गर्नुपर्यो भने जिल्लाका सबै विद्यालयबाट विद्यार्थी छनोट गर्नुको सट्टा केही विद्यालयलाई Random रूपमा छनोट गरेर ती विद्यालयका विद्यार्थीबाट तथ्याङ्क संकलन गर्न सकिन्छ।

यहाँ विद्यालय = Cluster हो।

फाइदा: Population ठूलो भौगोलिक क्षेत्रमा फैलिएको अवस्थामा समय र खर्च बचाउन उपयोगी हुन्छ।

२. Non-Probability Sampling (असम्भाव्यतामूलक Sampling)

यस विधिमा Population का सबै सदस्यलाई Sample मा पर्ने समान वा ज्ञात सम्भावना हुँदैन। Sample छनोट गर्दा अनुसन्धानकर्ताको निर्णय, सुविधा, उपलब्धता वा उद्देश्य महत्वपूर्ण हुन सक्छ।

यसका मुख्य प्रकारहरू:

A. Purposive or Judgmental Sampling

(उद्देश्यपूर्ण वा निर्णयात्मक नमुना छनोट)

यसमा अनुसन्धानकर्ताले अनुसन्धानको उद्देश्यअनुसार विशेष ज्ञान, अनुभव वा योग्यता भएका व्यक्तिहरूलाई जानाजानी छनोट गर्छ।

उदाहरण:
अनुसन्धान Supervisors ले सामना गर्ने समस्याको अध्ययन गर्नुपर्यो भने अनुभवी Research Supervisors लाई मात्र छनोट गर्नु।

उपयोग: विशेष ज्ञान वा अनुभव भएका व्यक्तिबाट सूचना लिनुपर्ने अवस्थामा।

B. Quota Sampling (कोटा नमुना छनोट)

यसमा Population लाई विभिन्न समूहमा विभाजन गरी प्रत्येक समूहबाट निश्चित संख्या (Quota) मा Respondents छनोट गरिन्छ।

उदाहरण:
१०० जना Respondents चाहिएको छ भने:

पुरुष = ५०
महिला = ५०

यसरी प्रत्येक समूहको निश्चित संख्या पूरा हुने गरी Respondents छनोट गरिन्छ।

मुख्य विशेषता: प्रत्येक समूहका लागि निश्चित संख्या/Quota तोकिन्छ।

C. Convenience Sampling (सुविधाजनक नमुना छनोट)

यसमा अनुसन्धानकर्तालाई सजिलै उपलब्ध र पहुँचमा रहेका व्यक्तिहरूलाई Sample मा समावेश गरिन्छ।

उदाहरण:
ग्राहक सन्तुष्टिको अध्ययन गर्दा बजारमा भेटिएका र सजिलै उपलब्ध भएका ग्राहकहरूबाट Questionnaire भर्न लगाउनु।

फाइदा:

सजिलो
कम खर्चिलो
समय बचत

सीमा: Sample ले सम्पूर्ण Population लाई राम्रोसँग प्रतिनिधित्व नगर्न सक्छ।

D. Self-Selecting Sampling (स्व-छनोट नमुना)

यसमा अनुसन्धानमा सहभागी हुने व्यक्तिहरूले आफैँ इच्छापूर्वक सहभागिता जनाउँछन्।

उदाहरण:
अनुसन्धानकर्ताले Online Survey राख्छ:

“यस अनुसन्धानमा इच्छुक विद्यार्थीहरूले Questionnaire भर्न सक्नुहुन्छ।”

आफ्नो इच्छाले Questionnaire भर्ने विद्यार्थीहरू Sample बन्छन्।

सीमा: सहभागी हुने र नहुने व्यक्तिहरूको विचार फरक हुन सक्ने भएकाले Selection Bias आउन सक्छ।

E. Snowball Sampling (स्नोबल नमुना छनोट)

यस विधिमा सुरुमा केही उपयुक्त Respondents छनोट गरिन्छ। त्यसपछि उनीहरूले उस्तै विशेषता भएका अन्य व्यक्तिहरूलाई सिफारिस/सम्पर्क गराउँछन्। यसरी Sample क्रमशः बढ्दै जान्छ।

यसको स्वरूप:

पहिलो Respondents → अन्य Respondents को सिफारिस → थप Respondents → ठूलो Sample

उदाहरण:
सजिलै पहिचान गर्न वा सम्पर्क गर्न नसकिने विशेष समूहको अध्ययन गर्दा सुरुमा केही व्यक्तिलाई खोजिन्छ र उनीहरूबाट थप सम्भावित Respondents को सम्पर्क प्राप्त गरिन्छ।

Probability र Non-Probability Sampling बीचको फरक

आधार	Probability Sampling	Non-Probability Sampling
छनोट	Random आधारमा	Random हुनैपर्छ भन्ने छैन
छनोट हुने सम्भावना	ज्ञात हुन्छ	सामान्यतः अज्ञात हुन्छ
Researcher को Judgment	कम	बढी हुन सक्छ
Bias	तुलनात्मक रूपमा कम	तुलनात्मक रूपमा बढी हुन सक्छ
Representativeness	सामान्यतः राम्रो	सीमित हुन सक्छ
खर्च	तुलनात्मक रूपमा बढी	तुलनात्मक रूपमा कम
समय	बढी लाग्न सक्छ	कम लाग्न सक्छ

सजिलै सम्झने तरिका

Probability Sampling:
Simple Random → Systematic → Stratified → Cluster

Non-Probability Sampling:
Purposive → Quota → Convenience → Self-Selecting → Snowball

निष्कर्ष

Sampling को उपयुक्त विधि छनोट गर्दा अनुसन्धानको उद्देश्य, Population को प्रकृति, Sampling Frame को उपलब्धता, समय, लागत र स्रोतसाधनलाई ध्यान दिनुपर्छ। Probability Sampling प्रतिनिधिमूलक Sample प्राप्त गर्न उपयोगी हुन्छ भने Non-Probability Sampling विशेष उद्देश्य, सीमित स्रोत वा पहुँच गर्न कठिन Population को अध्ययनमा बढी उपयोगी हुन सक्छ।

Sampling Error

Meaning of Sampling Error

Sampling Error refers to the difference between the characteristics or results obtained from a sample and the actual characteristics of the entire population, which occurs because only a portion of the population is studied.

In simple words, when the selected sample does not perfectly represent the population, the difference that occurs is called Sampling Error.

Example

Suppose a college has 2,000 students. The actual average monthly expenditure of all students is Rs. 5,000. A researcher selects 200 students and finds that their average monthly expenditure is Rs. 5,500.

Population Mean = Rs. 5,000
Sample Mean = Rs. 5,500
Difference = Rs. 500

This difference may occur due to sampling error.

Sources of Sampling Error

The figure shows the following major sources:

1. Faulty Selection of Sample

This occurs when the researcher selects an inappropriate or unrepresentative sample from the population.

Example:
A researcher wants to study the satisfaction of all students in a college but selects only high-performing students.

The selected sample may not represent the opinions of all students.

2. Selection of Convenient Unit

This occurs when the researcher selects units simply because they are easily available or convenient to reach, instead of selecting them through an appropriate sampling procedure.

Example:
A researcher wants to study 1,000 students but collects information only from 50 students who happen to be available nearby.

This can create sampling bias.

3. Faulty Determination of Sampling Units

A sampling unit is the basic unit selected from the population.

If the researcher incorrectly defines the sampling unit, the sample may not properly represent the research population.

Example:
If the research is about individual BBS students, each student should normally be the sampling unit. If the researcher incorrectly treats an entire class as the sampling unit, the study may not match its intended design.

4. Improper Choice of Statistics

Sampling error can also be associated with using inappropriate statistical measures or techniques for analyzing sample data.

For example:

Using an unsuitable statistical test
Applying a statistical measure that does not fit the nature of the data
Drawing conclusions using inappropriate statistical procedures

This may lead to inaccurate conclusions about the population.

5. Improper Sample Design

Sample design is the overall plan for selecting a sample from the population.

If the sample design is inappropriate, the resulting sample may not adequately represent the population.

Example:
A researcher wants to study students from all faculties of a university but selects respondents only from the Management Faculty.

The sample does not adequately represent the entire student population.

6. Improper Sample Size

An inadequate sample size can increase the possibility that the sample will not represent the population properly.

Example:
A researcher wants to study 50,000 students but selects only 10 students.

Ten students are unlikely to adequately represent such a large population.

Therefore, sample size should be determined considering factors such as:

Population size
Nature of the study
Variability in the population
Required level of accuracy
Available time and resources

Summary

Source	Meaning
Faulty selection of sample	Selecting an inappropriate or unrepresentative sample
Selection of convenient unit	Selecting units simply because they are easily accessible
Faulty determination of sampling units	Incorrectly defining the basic unit of selection
Improper choice of statistics	Using unsuitable statistical measures or techniques
Improper sample design	Using an inappropriate plan for selecting the sample
Improper sample size	Selecting a sample that is too small or otherwise inadequate

Conclusion

Sampling Error is the difference between a sample result and the corresponding population value caused by studying only a sample rather than the entire population. It can be reduced by using an appropriate sampling method, clearly defining the sampling unit, developing a proper sample design, selecting a representative sample, and determining an adequate sample size.

Sampling Error

Sampling Error (नमुना त्रुटि) भन्नाले Population बाट Sample छनोट गर्दा Sample ले सम्पूर्ण Population लाई सही रूपमा प्रतिनिधित्व गर्न नसक्दा उत्पन्न हुने त्रुटिलाई भनिन्छ।

सरल भाषामा, Population को सट्टा केही Sample मात्र अध्ययन गरिने भएकाले Sample र Population को वास्तविक विशेषताबीच देखिने फरकलाई Sampling Error भनिन्छ।

उदाहरण

मानौँ, एउटा कलेजमा 2,000 विद्यार्थी छन्। सबै विद्यार्थीको वास्तविक औसत मासिक खर्च रु. 5,000 छ। अनुसन्धानकर्ताले 200 विद्यार्थीको Sample लिएर अध्ययन गर्दा औसत खर्च रु. 5,500 देखियो।

यहाँ:

Population Mean = रु. 5,000
Sample Mean = रु. 5,500
Difference = रु. 500

यो फरक Sampling Error का कारण हुन सक्छ।

चित्रमा देखाइएका Sampling Error का स्रोतहरू

तपाईंको चित्रअनुसार Sampling Error मुख्यतः छनोट प्रक्रियामा भएका विभिन्न गल्तीहरूका कारण उत्पन्न हुन सक्छ।

1. Faulty Selection of Sample

(नमुना छनोटमा भएको त्रुटि)

यदि अनुसन्धानकर्ताले Population लाई राम्रोसँग प्रतिनिधित्व नगर्ने Sample छनोट गर्छ भने Sampling Error हुन सक्छ।

उदाहरण:
कलेजका सबै विद्यार्थीको सन्तुष्टि अध्ययन गर्दा केवल धेरै राम्रो नतिजा ल्याउने विद्यार्थीलाई मात्र Sample मा राख्नु।

यसले सम्पूर्ण विद्यार्थीको वास्तविक विचार प्रतिनिधित्व नगर्न सक्छ।

कारण: Sample उचित तरिकाले छनोट नगर्नु।

2. Selection of Convenient Unit

(सुविधाजनक एकाइ छनोट)

अनुसन्धानकर्ताले Random वा वैज्ञानिक विधि प्रयोग नगरी सजिलै भेटिने वा पहुँचमा रहेका व्यक्तिहरूलाई मात्र Sample मा छनोट गर्दा यस्तो त्रुटि आउन सक्छ।

उदाहरण:
कलेजका सबै 1,000 विद्यार्थीको अध्ययन गर्नुपर्नेमा Researcher ले आफूलाई सजिलै भेटिएका 50 जना विद्यार्थीलाई मात्र छनोट गर्नु।

यसलाई Convenience Sampling भनिन्छ र यसबाट Sample मा Bias आउन सक्छ।

3. Faulty Determination of Sample Units

(नमुना एकाइ निर्धारणमा त्रुटि)

Sampling Unit भनेको Population बाट छनोट गरिने आधारभूत एकाइ हो।

यदि अनुसन्धानकर्ताले Sampling Unit नै गलत रूपमा निर्धारण गर्यो भने Sampling Error हुन सक्छ।

उदाहरण:
“BBS विद्यार्थीहरूको अध्ययन” गर्नुपर्ने अवस्थामा विद्यार्थीलाई Sampling Unit मान्नुपर्ने हो। तर विद्यार्थीको सट्टा कक्षा मात्रलाई Sampling Unit मानेर अध्ययन गरियो भने अनुसन्धानको उद्देश्यसँग नमिल्न सक्छ।

त्यसैले Sampling Unit स्पष्ट र उपयुक्त हुनुपर्छ।

4. Improper Choice of Statistics

(अनुपयुक्त Statistics छनोट)

Sample बाट प्राप्त तथ्याङ्कलाई विश्लेषण गर्न अनुपयुक्त Statistical Method प्रयोग गर्दा पनि अनुसन्धानको निष्कर्ष गलत हुन सक्छ।

उदाहरणका लागि:

Mean प्रयोग गर्नुपर्ने अवस्थामा गलत Statistical Measure प्रयोग गर्नु
आवश्यक नभएको अवस्थामा कुनै विशेष Test प्रयोग गर्नु
Data को प्रकृतिसँग नमिल्ने statistical technique प्रयोग गर्नु

यसले Sample बाट Population सम्बन्धी गलत निष्कर्ष निकाल्न सक्छ।

5. Improper Sample Design

(अनुपयुक्त Sample Design)

Sample Design भन्नाले Population बाट Sample कसरी छनोट गर्ने भन्ने सम्पूर्ण योजना हो।

यदि Sample Design नै उचित छैन भने Sample प्रतिनिधिमूलक नहुन सक्छ।

उदाहरण:
कुनै विश्वविद्यालयका विद्यार्थीहरूको अध्ययन गर्दा सबै Faculty का विद्यार्थी समावेश हुनुपर्नेमा केवल Management Faculty का विद्यार्थीलाई Sample बनाउनु।

यसले सम्पूर्ण Population को सही प्रतिनिधित्व गर्दैन।

6. Improper Sample Size

(अनुपयुक्त Sample Size)

Sample Size धेरै सानो वा अनुसन्धानको प्रकृतिका लागि अपर्याप्त भयो भने पनि Sampling Error बढ्न सक्छ।

उदाहरण:
कुनै जिल्लाका 50,000 विद्यार्थीको अध्ययन गर्नुपर्ने अवस्थामा केवल 10 जना विद्यार्थीलाई Sample बनाउनु।

१० जनाले 50,000 विद्यार्थीको विचारलाई राम्रोसँग प्रतिनिधित्व नगर्न सक्छन्।

त्यसैले अनुसन्धानको उद्देश्य, Population Size, variability, accuracy आदि हेरेर उचित Sample Size निर्धारण गर्नुपर्छ।

चित्रको मुख्य अर्थ

तपाईंको चित्रलाई यसरी सम्झन सकिन्छ:

Sampling Error

⬇️

Sample छनोटमा गल्ती
→ Faulty Selection of Sample

सुविधाको आधारमा एकाइ छनोट
→ Selection of Convenient Unit

Sampling Unit गलत निर्धारण
→ Faulty Determination of Sample Units

गलत Statistical Method/Measure
→ Improper Choice of Statistics

अनुपयुक्त Sampling Design
→ Improper Sample Design

Sample Size गलत निर्धारण
→ Improper Sample Size

Sampling Error का मुख्य कारणहरू

Sample को गलत छनोट
Convenience का आधारमा Sample छनोट
Sampling Unit को गलत निर्धारण
अनुपयुक्त Statistical Technique प्रयोग
गलत Sample Design
अपर्याप्त वा अनुपयुक्त Sample Size

निष्कर्ष

Sampling Error अनुसन्धानमा Sample र Population बीचको प्रतिनिधित्वसम्बन्धी फरकका कारण उत्पन्न हुने त्रुटि हो। उचित Sampling Method, सही Sampling Unit, उपयुक्त Sample Design र पर्याप्त Sample Size प्रयोग गरेमा Sampling Error लाई कम गर्न सकिन्छ, यद्यपि Sample-based research मा यसलाई पूर्ण रूपमा हटाउन सधैँ सम्भव हुँदैन।