Survey is a technique where the general opinion of a Population is generalized. To survey a whole Population is a DIRECT RESPONSE TECHNIQUE, which is the best option for a REAL ANSWER. However in real time such an activity cannot be carried out due to various reasons.

Hence a sample is tested of the population which has a better representation of the Population. There are various techniques which "Better represent" a population, Mostly random sampling is the approach, for example in a classroom set-up.

Survey is a technique where the general opinion of a Population is generalized. To survey a whole Population is a DIRECT RESPONSE TECHNIQUE, which is the best option for a REAL ANSWER. However in real time such an activity cannot be carried out due to various reasons.

Hence a sample is tested of the population which has a better representation of the Population. There are various techniques which "Better represent" a population, Mostly random sampling is the approach, for example in a classroom set-up.

It´s not my profession. But it´s impossible to survey a whole population. You must take a scientifically defined selection, which is representative for your research objective. I know there are criteria to find the right way.

Dear "Islam, we do survey of the entire population in case when such demands exist. Here are some examples of Serbia, as well as publications.

http://webrzs.stat.gov.rs/WebSite/

http://webrzs.stat.gov.rs/WebSite/Public/PageView.aspx?pKey=162

http://popis2011.stat.rs/?lang=en

Dear Kamal,

large sample may be easy, but I know, the representative sample works better. The choice of the right criteria is the problem.

You may survey the entire population when the population is small. Suppose that the number of employees working in a small size company is 30, you may survey the entire population or universal.

In case you are conducting a type of research which is a kind of Case Study (descriptive research type) of a limited population (e.g. population size is only 30, or so), say,  to describe entrepreneurial characteristics of, say, home based women fish processors around a lake), or exploratory type of research to explore some phenomenon to provide initial information for further research, you may like to consider entire population to include in survey.

But, in general survey, you need to consider sufficient sample size (also based on objectives of your study), sample mush be representative of entire population under study.

You need to use appropriate statistical (random) sampling method(s) to choose sample objects. Hope this helps.

Hi Faisal,

If you survey entire population, its' more like Censes. So, you do not need to do any parameter estimate. 

dear Mr.suranga

thanks this is what am waiting for.

do you have any reference for further reading.

appreciate it

Census is the most credible source of information on Demography (Population characterstics), Economic Activity, Literacy and Education, Housing & Household Amenities, Urbanisation, Fertility and Mortality, Scheduled Castes and Scheduled Tribes, Language, Religion, Migration, Disability and many other socio-cultural data.

http://www.ndtv.com/article/india/india-s-total-population-is-1-21-billion-final-census-reveals-361056

It was the Census I was speaking about in my previous answer. 

http://webrzs.stat.gov.rs/WebSite/Public/PublicationView.aspx?pKey=41&pLevel=1&pubType=2&pubKey=2282

Collection of data from a whole population rather than just a sample.

Example: surveying travel time by ...

... asking everyone at school is a census (of the school).

... but asking only the first 50 people you meet is a sample.

Gathering information is an important way to help people make decisions about topics of interest.

Surveys can help decide what needs changing, where money should be spent, what products to purchase, what problems there might be, or lots of other questions you may have at any time.

The best part about surveys is that they can be used to answer any question about any topic.

You can survey people (through questionnaires, opinion polls, etc) or things (like pollution levels in a river, or traffic flow).

Dear Islam,

why did you ask this question? Do you want to study a whole population (e.g. a population of humans on an a small island) ? 

Dear Lambrechts

The  population in my study is a combination of top administrators in private universities (University president, Deputy president, Deans and Head of Departments), thus its is a small population.

To identify practices and work towards simplifying research administration processes etc., among the University administrators network. The site of International Alliance of Research Universities, can add value to your research. The aim of this group is to play an influential role in the enhancement of research collaboration. Current topics that are discussed within the network are barriers for research mobility, global funding opportunities and staff exchange. The network also plans to establish a dictionary on the terms used in research management as each institution uses quite different terms.