Sampling in research
66 likes44,386 views
This document provides an overview of sampling techniques used in research. It defines key terms like population, sample, and sampling. It discusses characteristics of good sampling like being representative and free from bias. Probability sampling techniques like simple random sampling, stratified sampling, and systematic sampling are explained. Advantages of sampling like reducing time and costs are highlighted. The document outlines the sampling process and essentials of sampling. Types of sampling and various sampling methods are also summarized.
Sampling in research
- 1. Sampling process in Research Dr. Madhuri Sadgir. Assist professor Dept. Phy. Edu. University of Mumbai. professor.madhuri@gmail.com 1
- 2. Outline of presentation ➤ Population ➤ Sampling ➤ Definition of key terms ➤ Sampling techniques ➤ Sampling procedure 2
- 3. TERMINOLOGY • Population :- A group of elements having similar characteristics. It can be human being, living or non- living object. Populations gets as per the study area. • Example :- men, women, children's, elderly adult, sports person, drunks addicts, supplements. Etc. • Sample :- it is subset of the population. To study the characteristics of the entire population. Therefore, it is very important to that sample should represent entire population. Which can be possible only by applying appropriate sampling technique. • Sampling :- it is a Procedure to draw a representative sample from the population in such a way that the sample elements selected represent the population. • Sampling. Bias :- sampling bias is said to occur if the sample unit does not possess the population characteristics. Due to which result may be inaccurate. 3Dr. Madhuri Sadgir
- 4. 4
- 5. CHARACTERISTICS OF GOOD SAMPLING 1. The sample must represent the population correctly. 2. It must be free from bias 3. It must possess the least sampling error 4. It must be optimum in size • Keywords • Hypothesis :- guessing, assumption, tentative answer • Bias :- neutral, without favouring any side 5 ADVANTAGES OF SAMPLING 1. Reduce time and cost to collect data 2. More comprehensive data is obtained than in a census. 3. Administrative control 4. Better motivation 5. Reliability of data 6. Less non response error 7. Conclusion Dr. Madhuri Sadgir
- 6. PRINCIPLES OF SAMPLING 1. Selection of sample must be systematic and objective manner 2. Sample unit must be clearly define and easily identifiable 3. Sample units must be independent of each other 4. Same units of sample must be used through out the study 5. The selection process must be on sound criteria. 6. It should avoid error, bias • Keywords • Hypothesis :- guessing, assumption, tentative answer • Bias :- neutral, without favouring any side • Research question :- The problem which need to study and solve. • asserting :- believe confidently 6Dr. Madhuri Sadgir
- 7. PROCESS OF SAMPLING 1. Defining the population concern 2. Specifying a sampling frame. (Listing the elements of the population) 3. Specifying a sampling method 4. Determining a sample size 5. Implementing the sampling plan 6. Sampling and data collecting • Keywords • Hypothesis :- guessing, assumption, tentative answer • Bias :- neutral, without favouring any side • Research question :- The problem which need to study and solve. • asserting :- believe confidently 7 ESSENTIAL OF SAMPLING 1. Representative :- ensure by random selection 2. Adequate :- sample size 3. Independence :- same chance of selection 4. Homogeneity :- No basic difference in nature of units. Dr. Madhuri Sadgir
- 8. TYPES OF SAMPLING • There are main two types of sampling based on chances of being selected or not selected the population unit into the sample. 1.probability sampling 2. Non Probability sampling. 8 PROBABILITY SAMPLING • Probability sampling is one in which every unit of the population has an equal probability / chance of being selected for the sample. • The list of every unit of population must be available. • It offers high degree of representativeness. • This method is expensive , time consuming and relatively complicated since its requires a large no. Of size • This method enable to generalise its finding. NON- PROBABILITY SAMPLING • Non-Probability sampling is one in which every unit of the population doesn't have an equal probability / chance of being selected for the sample. • It doesn't claim of representativeness. • The list of entire population is not available to draw a random sampling. • The researcher who decides which sample unit has to be selected. Dr. Madhuri Sadgir
- 9. Sampling Techniques / Methods ➤ Judgement / purposive / Determinant ➤ Quota ➤ Convenient ➤ Snowball 9 ➤ Simple Random ➤ Stratified ➤ Systematic ➤ Cluster ➤ Multistage ➤ Multiphase ➤ Low Quality Assurance Probability Non- Probability Mixed Dr. Madhuri Sadgir
- 10. PROBABILITY SAMPLING • This is technique draw a sample from population on the basis of simple random. • The list of entire units of the population is available • Each and every unit of the population has probability of getting equally selected as a sample. • This technique is used when population is homogeneous • It can be used by applying three methods 10 1. Lottery system 2. Random Number Table System 3. Using the computer:- 4. Using mixing well method Dr. Madhuri Sadgir
- 11. LOTTERY SAMPLING METHOD • It is most powerful method to selecting simple random sampling. • All the units / member of the population are enlisted from 1. to N number, this is known as sample frame. • For the purpose of performing lottery method, first the all numbers are written on small size of paper. • These papers then kept in small bowl, All the paper size must be of same size otherwise the select sample will not be truly random. • Thereafter mix it well and pick up any one slip and mention in sample list. • After first slip pick up again mix the slip well and pick up second slip and mention it in sample list. • I this manner select slips till the sample size is not getting complete. ( I.e, 30 sample size - select sample till 30 numbers get done) • Lottery method is usually used when the population is small in numbers. 11Dr. Madhuri Sadgir
- 12. RANDOM NUMBER TABLE METHOD 12Dr. Madhuri Sadgir
- 13. USING COMPUTER METHOD • The facility of selecting a simple random sample is available in the computer. 13 Advantages 1. Free from personal bias 2. Provides more representative sample 3. Prior knowledge of population is not required 4. Sample errors can be easily calculated. Disadvantages 1. Not suitable for heterogeneous population 2. In many situation it is not possible to have a complete sampling frame. Dr. Madhuri Sadgir
- 14. STRATIFIED SAMPLING • A stratified random sample is a population sample that requires the population to be divided into smaller groups, called 'strata'. Random samples can be taken from each stratum, or group. 14Dr. Madhuri Sadgir
- 15. • It is used when the population is heterogeneous. • In this method whole population is divided into small homogeneous group known as strata. • A random sample from each strata is drawn in proposition to its size. • The subset of sample is drawn from each stratum and form the random sample. • The most important consideration is to identify the criteria on the basis of which the population is divided into homogeneous strata • If the proper stratification not done or strata is not homogeneous within itself, then the sample obtained would not be the proper representation of the population. 15 STRATIFIED SAMPLING Dr. Madhuri Sadgir
- 16. Advantages It provides more representative sample if stratification done properly. It can provides greater precision than a simple random of the same size. It reduce bias in the sample Stratified sampling provides greater precision, it often requires a smaller sample, which becomes economical 16 STRATIFIED SAMPLING Disadvantages The technique is more complex and requires greater efforts than simple random. If stratification criteria is faulty than the stratified sample is not purely representative. Requires more administrative efforts than a simple random sample. Knowledge about complete sampling frame is required. Dr. Madhuri Sadgir
- 17. SYSTEMATIC SAMPLING • A systematic is appropriate in situation where complete population unit is available in sequential and systematic order. • In this sampling every K element from the list is selected from a randomly selected starting point. • This method is mix of random sampling and stratified sampling. Because first unit is selected randomly and thereafter every K unit of the population list is included in the sample. • In this way whole population is divided into K strata and out of each tratum every k unit is considered as strata and out of each stratum,one sample is drawn. • Thus systematic sampling includes the characteristics of simple random sampling as well as stratified sampling. 17Dr. Madhuri Sadgir
- 18. SYSTEMATIC SAMPLING K = N/n K - sample interval N - population size n - sample size Example : K = 200 / 30 K = 6.67 so round up 7 Now take complete 200 population and collect 30 sample with interval number of 7. By randomly selecting starting unit within 1-7 numbers. 18 How to get K (interval between sample unit) Advantage 1. It possess the characteristics of simple random sampling as well as stratified sampling. 2. The sample is drawn from each and every segment of the population and hence it may be considered to be more representative. Disadvantages 1. The entire population units must be available in a systematic and sequential manner. 2. Only the first unit is drawn at random and thereafter every K unit is selected and therefore, it may lead to systematic bias in the sample. Dr. Madhuri Sadgir