Each problem in the statistics is answered considering the samples only. In statistics, a sample is a subset of a population. Usually, the population is large which makes a census or a complete enumeration of all the values in the population impractical. The sample generally represents a subset of size which can be easily managed.
The samples are collected and statistics are calculated from these samples so that we can make inferences or predictions from the sample to the population. This process of collecting information from a sample is often called sampling.
In every sphere of life you will find importance of Statistics for comparative analysis of a particular item or unknown. These day exit polls are very famous for each news agency and dailies. As soon as elections are over there is prediction of how much seats will particular party will get in the concluded polls. So how does this exit polls are carried on? Exit polls are taken immediately after voters exit polling stations.
These are surveys usually taken of a representative or a number of respondents in a particular population from the overall population. The exit poll analyzer begins its prediction by drawing a random sampling of precincts within a state, selected so that the odds of any district being selected are proportionate to the number that typically vote in that district or region or precinct. One or sometimes two interviewers will report to each sampled district.
The data collection is done by team members who will stand outside the polling station and attempt to randomly select 100 odd voters during the day as they exit from voting process. The interviewer typically accomplishes this task by counting voters as they leave the polling station and chooses voter at a specific interval-(eg every 10th or 20th voter). The interval can be chosen according to the wish of interviewer but it is usually chosen so that approximately 100 interviews will be spread evenly over the course of the day. Once the polls close, the interviewer attempts to obtain actual turnout counts. One of the unique aspects of the exit poll design is the way it gradually incorporates actual turnout and vote data as it becomes available once the polls are over or are closed.
The exit poll designers have developed special weighting schemes and many other algorithms to make all sorts of comparisons to historical data that supports the networks as they decide whether to decide in the favour for a particular candidate. When all of the votes have been counted, the exit poll is weighted by the vote to match the actual result. So we can see that the prediction can be more accurate if large number of samples is collected for the consideration.