SlideShare a Scribd company logo
Sampling techniques
Population versus Sample
Lets assume there was a movie that had been showcased across the globe and 10% of the worlds pouplation has seen that movie. A
production house wants to understand the response of the viewers as they are planning to produce a new movie which is simillar to the
above one, they are in a plan to maximise their viewer for the movie, there by wants to conduct a survey.
Worlds population: 7 billion
10% has seen the movie:
(0.10) * 7,000,000,000 =
700,000,000 viewers
Population of intrest:
700,000,000 viewers
Sample
* Properly selected sample will be the representation of a population and gathering useful information about population.
Why sample?
➔ Surveying sample can save time.
➔ Surveying sample can save money.
➔ Most properly selected samples can give sufficiently accurate results.
➔ Given ceratin amount of resources, the sample can broaden the scope of the study.
➔ Acessing population most of the time remains impossible, the sample can be the option.
➔ Easier to control the quality of sample there by reducing sampling error.
Sampling techniques
Sampling
Random sampling Nonrandom sampling
Simple random sampling Convenience sampling
Probability
sampling
Nonprobability
sampling
Systematic sampling Quota sampling
Stratified random sampling Judgement sampling
Cluster sampling Snowball sampling
Every individual or unit of population has an
equal chance or same probability of being
selected into the sample
Not every individual or unit of population has
an equal chance or same probability of being
selected into the sample
Random sampling (Simple random sampling)
* Simple random sampling is the basis of other random sampling techniques
Frame: Sample is choosen from a population where the population are from a List, Map, Directory or other resources which represent the
population, this List, Map, Directory or other resources are called as the frame from where the sample is choosen.
Steps involved in simple random sampling
Step 1: Provide serial number (1 to N {“N” represents size of the population}) for each individual or unit in a frame.
Step 2: Identify how many sample (n) you require for the study (“n” represents number of sample required for the study).
Step 3: Use random number generator (computer program) to generate “n” random numbers.
Step 4: Choose the serial numbers from the frame, that has been generated by the computer program
Step 5: Perform data analysis from the data selected from “Step 4”
Frame Sample
1. Provide serial number to all the
viewers of the movie.
2. Genearte random numbers
(Required sample size)
3. Pick all those serial numbers which
has been generated by random number
generator.
4. Use the sample for analysis
Random sampling (Stratified random sampling)
Steps involved in stratified random sampling
Step 1: Divide the population or frame into nonoverlapping subpopulation or frame (subpopulation or subframe is called as strata)
* With in the starta individuals or unit are homogeneous in nature and among the starta they are hetrogeneous.
* Strata is generally divided into Sex, Age, Socioeconomic class, Geographic, Region, Religion, etc.
Step 2: Identify how many samples you require from each strata (Protionate or Disproporitinate) .
* Portionate: Sample is choosen according to the proportion of each stratum within the population.
* Disproporniate: Whenever the proportions of the strata in the sample are different from the proportions of the strata in the population.
Step 3: Perform simple random sampling on each strata, to build the sample.
Step 4: Perform data analysis from the data selected from “Step 3”
Frame
Female
strata
Male
strata
Sample
* Stratiied random sampling is used to reduce sampling error
Random sampling (Systematic sampling)
Steps involved in systematic sampling
Step 1: Provide serial number (1 to N {“N” represents size of the population}) for each individual or unit in a frame.
Step 2: Identify how many samples you require “n”.
Step 3: Pick every “ Kth
” individual or unit to produce a sample size “n” from the population “N”
Step 4: Perform data analysis from the data selected from “Step 3”
Example: Assume you have a population of size 1000. You want to produce a sample size of 100.
K = (N/n)
K = (1000/100)
K = 10
Determine a starting point from the list or frame.
Lets say we have choosen the starting point as 8th
element, start picking the 8th
element.
To get the next element into the sample we just go on adding the value of k
So the next element is (8 +10) = 18th
element, next element will be (18+10) = 28th
and so on till the sample size
100 is acheved
* Systematic sampling is used because of its convenience and ease of administration and doesnot help in
reducing sampling error
Random sampling (Cluster sampling)
Steps involved in stratified random sampling
Step 1: Divide the population or frame into “P” nonoverlapping groups or clusters
* Each element of the population can be assigned to only one cluster
* Within the clusters elements are heterogeneous in nature and contains wide variety of elements and cluster is a miniature of the
population
Step 2: Identify how many groups or clusters you require for the study.
Step 3: Use random selection to select the clusters.
Step 4: Once the clusters are selected either all the individual elements can be selected or random selection to produce the sample.
* One stage sampling: All of the elements in the cluster are choosen
* Two stage sampling: Subset of elements within the clusters are randomly selected to the sample
Frame Divide into groups or clusters
Select the cluster or clusters
for the study
Nonrandom sampling
Convenience sampling
Elements for the sample are selected as per the convinence of the researcher.
* Generally elements are choosen that are readily available, Nearby and willing to participate
Judgement sampling
Elements for the sample are selected by the judgement of the researcher.
* Researchers some times believe that they can obtain a representative sample by sound judgement according to the study.
Quota sampling
Convert the population into strata and then instead of randomly sampling from each stratum, use nonrandom sampling method to
gather the elements untill the desired quota of samples is filled.
* Generally quota is based on the proportion of the subclasses and is simillar to proportional stratified sampling
Snowball sampling
Sample elements are choosen on the base of referral from other survey respondents.
* First the researcher identifies the individual who fits the subject wanted for the study and then ask for referrals who would also fit
the profileof subjects wanted for the study.
Sampling error Versus Nonsampling error
Sampling error
Sampling error occurs when the sample is not a good representative of the population.
* While using random sampling techniques to select elements into sample sampling error occurs by chance.
* The statistic computed on the sample some times is not accurate estimate of the population parameter because the sample
selected is not a good representative of the population
Nonsampling error
All errors other than sampling errors are nonsampling errors.
* Generally include Missing data, Data recording errors, Response errors, Analysis errors and some times defective measurement
instruments

More Related Content

PDF
3. data visualisations
PPT
050 sampling theory
PPTX
Statistical sampling
PPT
Sampling methods
PPT
Sampling design ppt
PDF
Research Method for Business chapter 10
PPTX
MEASUREMENT AND SAMPLING TECHNIQUES
3. data visualisations
050 sampling theory
Statistical sampling
Sampling methods
Sampling design ppt
Research Method for Business chapter 10
MEASUREMENT AND SAMPLING TECHNIQUES

What's hot (20)

DOC
Sampling error; the need for sampling distributions
PPT
Sampling Design
PPTX
Sampling techniques in Research
PPT
Sampling Techniques
PPTX
Sampling design
PPTX
Complex random sampling designs
PPT
Chp11 - Research Methods for Business By Authors Uma Sekaran and Roger Bougie
PDF
Lecture7.1 data sampling
DOCX
Sampling and methods of doing sampling Assignment
PPT
Chapter 4 sampling procedure
PPTX
Sampling design
PDF
Sampling and Sampling Distribution
PPT
Introduction to basic concept in sampling and sampling techniques
PPTX
PPTX
Systematic ranom sampling for slide share
PPTX
Errors in research
PPTX
SAMPLING MEANING AND TYPES
PPT
Sampling and Inference_Political_Science
PPTX
Sampling, measurement, and stats(2013)
Sampling error; the need for sampling distributions
Sampling Design
Sampling techniques in Research
Sampling Techniques
Sampling design
Complex random sampling designs
Chp11 - Research Methods for Business By Authors Uma Sekaran and Roger Bougie
Lecture7.1 data sampling
Sampling and methods of doing sampling Assignment
Chapter 4 sampling procedure
Sampling design
Sampling and Sampling Distribution
Introduction to basic concept in sampling and sampling techniques
Systematic ranom sampling for slide share
Errors in research
SAMPLING MEANING AND TYPES
Sampling and Inference_Political_Science
Sampling, measurement, and stats(2013)
Ad

Similar to 2. sampling techniques (20)

PDF
samplingdesignppt.pdf
PPTX
chapter-2 Elementary Sampling Theory.pptx
PPT
Sampling Design in Applied Marketing Research
PPTX
Selecting a sample: Writing Skill
PPTX
Sampling techniques 2
DOC
Sampling Design
PPTX
Sampling Design
PPTX
sampling.pptxhhhhbvhyghgughbhghvhvgjvnvfg
PPTX
Maneesh (economics)
PPT
Rm 6 Sampling Design
PPTX
Chapter business research sampling design.pptx
PPT
Sample Designs and Sampling Procedures
PPT
Sampling and sampling distribution
PPTX
Types of sampling design
PPTX
Sampling techniques.pptx
PPT
Sampling design
PPTX
sampling technique
PPTX
Sampling Technique - Anish
PPTX
Sampling distribution concepts
samplingdesignppt.pdf
chapter-2 Elementary Sampling Theory.pptx
Sampling Design in Applied Marketing Research
Selecting a sample: Writing Skill
Sampling techniques 2
Sampling Design
Sampling Design
sampling.pptxhhhhbvhyghgughbhghvhvgjvnvfg
Maneesh (economics)
Rm 6 Sampling Design
Chapter business research sampling design.pptx
Sample Designs and Sampling Procedures
Sampling and sampling distribution
Types of sampling design
Sampling techniques.pptx
Sampling design
sampling technique
Sampling Technique - Anish
Sampling distribution concepts
Ad

More from Debasish Padhy (6)

PDF
1. introduction to statistics
PDF
4. descriptive statistics (central tendency)
PPTX
CISCO presentation
PPTX
Cisco Case study
PPT
Steam powered robots
PPTX
Garnier fructis
1. introduction to statistics
4. descriptive statistics (central tendency)
CISCO presentation
Cisco Case study
Steam powered robots
Garnier fructis

Recently uploaded (20)

PPTX
Data_Analytics_and_PowerBI_Presentation.pptx
PPTX
The THESIS FINAL-DEFENSE-PRESENTATION.pptx
PPTX
Acceptance and paychological effects of mandatory extra coach I classes.pptx
PPTX
Business Acumen Training GuidePresentation.pptx
PDF
annual-report-2024-2025 original latest.
PPTX
climate analysis of Dhaka ,Banglades.pptx
PDF
Fluorescence-microscope_Botany_detailed content
PPTX
Microsoft-Fabric-Unifying-Analytics-for-the-Modern-Enterprise Solution.pptx
PPTX
1_Introduction to advance data techniques.pptx
PDF
22.Patil - Early prediction of Alzheimer’s disease using convolutional neural...
PDF
“Getting Started with Data Analytics Using R – Concepts, Tools & Case Studies”
PDF
TRAFFIC-MANAGEMENT-AND-ACCIDENT-INVESTIGATION-WITH-DRIVING-PDF-FILE.pdf
PPTX
Introduction-to-Cloud-ComputingFinal.pptx
PDF
Foundation of Data Science unit number two notes
PPTX
STUDY DESIGN details- Lt Col Maksud (21).pptx
PPTX
Introduction to Firewall Analytics - Interfirewall and Transfirewall.pptx
PPTX
ALIMENTARY AND BILIARY CONDITIONS 3-1.pptx
PPTX
Introduction to Knowledge Engineering Part 1
PPT
Miokarditis (Inflamasi pada Otot Jantung)
PDF
Clinical guidelines as a resource for EBP(1).pdf
Data_Analytics_and_PowerBI_Presentation.pptx
The THESIS FINAL-DEFENSE-PRESENTATION.pptx
Acceptance and paychological effects of mandatory extra coach I classes.pptx
Business Acumen Training GuidePresentation.pptx
annual-report-2024-2025 original latest.
climate analysis of Dhaka ,Banglades.pptx
Fluorescence-microscope_Botany_detailed content
Microsoft-Fabric-Unifying-Analytics-for-the-Modern-Enterprise Solution.pptx
1_Introduction to advance data techniques.pptx
22.Patil - Early prediction of Alzheimer’s disease using convolutional neural...
“Getting Started with Data Analytics Using R – Concepts, Tools & Case Studies”
TRAFFIC-MANAGEMENT-AND-ACCIDENT-INVESTIGATION-WITH-DRIVING-PDF-FILE.pdf
Introduction-to-Cloud-ComputingFinal.pptx
Foundation of Data Science unit number two notes
STUDY DESIGN details- Lt Col Maksud (21).pptx
Introduction to Firewall Analytics - Interfirewall and Transfirewall.pptx
ALIMENTARY AND BILIARY CONDITIONS 3-1.pptx
Introduction to Knowledge Engineering Part 1
Miokarditis (Inflamasi pada Otot Jantung)
Clinical guidelines as a resource for EBP(1).pdf

2. sampling techniques

  • 2. Population versus Sample Lets assume there was a movie that had been showcased across the globe and 10% of the worlds pouplation has seen that movie. A production house wants to understand the response of the viewers as they are planning to produce a new movie which is simillar to the above one, they are in a plan to maximise their viewer for the movie, there by wants to conduct a survey. Worlds population: 7 billion 10% has seen the movie: (0.10) * 7,000,000,000 = 700,000,000 viewers Population of intrest: 700,000,000 viewers Sample * Properly selected sample will be the representation of a population and gathering useful information about population.
  • 3. Why sample? ➔ Surveying sample can save time. ➔ Surveying sample can save money. ➔ Most properly selected samples can give sufficiently accurate results. ➔ Given ceratin amount of resources, the sample can broaden the scope of the study. ➔ Acessing population most of the time remains impossible, the sample can be the option. ➔ Easier to control the quality of sample there by reducing sampling error.
  • 4. Sampling techniques Sampling Random sampling Nonrandom sampling Simple random sampling Convenience sampling Probability sampling Nonprobability sampling Systematic sampling Quota sampling Stratified random sampling Judgement sampling Cluster sampling Snowball sampling Every individual or unit of population has an equal chance or same probability of being selected into the sample Not every individual or unit of population has an equal chance or same probability of being selected into the sample
  • 5. Random sampling (Simple random sampling) * Simple random sampling is the basis of other random sampling techniques Frame: Sample is choosen from a population where the population are from a List, Map, Directory or other resources which represent the population, this List, Map, Directory or other resources are called as the frame from where the sample is choosen. Steps involved in simple random sampling Step 1: Provide serial number (1 to N {“N” represents size of the population}) for each individual or unit in a frame. Step 2: Identify how many sample (n) you require for the study (“n” represents number of sample required for the study). Step 3: Use random number generator (computer program) to generate “n” random numbers. Step 4: Choose the serial numbers from the frame, that has been generated by the computer program Step 5: Perform data analysis from the data selected from “Step 4” Frame Sample 1. Provide serial number to all the viewers of the movie. 2. Genearte random numbers (Required sample size) 3. Pick all those serial numbers which has been generated by random number generator. 4. Use the sample for analysis
  • 6. Random sampling (Stratified random sampling) Steps involved in stratified random sampling Step 1: Divide the population or frame into nonoverlapping subpopulation or frame (subpopulation or subframe is called as strata) * With in the starta individuals or unit are homogeneous in nature and among the starta they are hetrogeneous. * Strata is generally divided into Sex, Age, Socioeconomic class, Geographic, Region, Religion, etc. Step 2: Identify how many samples you require from each strata (Protionate or Disproporitinate) . * Portionate: Sample is choosen according to the proportion of each stratum within the population. * Disproporniate: Whenever the proportions of the strata in the sample are different from the proportions of the strata in the population. Step 3: Perform simple random sampling on each strata, to build the sample. Step 4: Perform data analysis from the data selected from “Step 3” Frame Female strata Male strata Sample * Stratiied random sampling is used to reduce sampling error
  • 7. Random sampling (Systematic sampling) Steps involved in systematic sampling Step 1: Provide serial number (1 to N {“N” represents size of the population}) for each individual or unit in a frame. Step 2: Identify how many samples you require “n”. Step 3: Pick every “ Kth ” individual or unit to produce a sample size “n” from the population “N” Step 4: Perform data analysis from the data selected from “Step 3” Example: Assume you have a population of size 1000. You want to produce a sample size of 100. K = (N/n) K = (1000/100) K = 10 Determine a starting point from the list or frame. Lets say we have choosen the starting point as 8th element, start picking the 8th element. To get the next element into the sample we just go on adding the value of k So the next element is (8 +10) = 18th element, next element will be (18+10) = 28th and so on till the sample size 100 is acheved * Systematic sampling is used because of its convenience and ease of administration and doesnot help in reducing sampling error
  • 8. Random sampling (Cluster sampling) Steps involved in stratified random sampling Step 1: Divide the population or frame into “P” nonoverlapping groups or clusters * Each element of the population can be assigned to only one cluster * Within the clusters elements are heterogeneous in nature and contains wide variety of elements and cluster is a miniature of the population Step 2: Identify how many groups or clusters you require for the study. Step 3: Use random selection to select the clusters. Step 4: Once the clusters are selected either all the individual elements can be selected or random selection to produce the sample. * One stage sampling: All of the elements in the cluster are choosen * Two stage sampling: Subset of elements within the clusters are randomly selected to the sample Frame Divide into groups or clusters Select the cluster or clusters for the study
  • 9. Nonrandom sampling Convenience sampling Elements for the sample are selected as per the convinence of the researcher. * Generally elements are choosen that are readily available, Nearby and willing to participate Judgement sampling Elements for the sample are selected by the judgement of the researcher. * Researchers some times believe that they can obtain a representative sample by sound judgement according to the study. Quota sampling Convert the population into strata and then instead of randomly sampling from each stratum, use nonrandom sampling method to gather the elements untill the desired quota of samples is filled. * Generally quota is based on the proportion of the subclasses and is simillar to proportional stratified sampling Snowball sampling Sample elements are choosen on the base of referral from other survey respondents. * First the researcher identifies the individual who fits the subject wanted for the study and then ask for referrals who would also fit the profileof subjects wanted for the study.
  • 10. Sampling error Versus Nonsampling error Sampling error Sampling error occurs when the sample is not a good representative of the population. * While using random sampling techniques to select elements into sample sampling error occurs by chance. * The statistic computed on the sample some times is not accurate estimate of the population parameter because the sample selected is not a good representative of the population Nonsampling error All errors other than sampling errors are nonsampling errors. * Generally include Missing data, Data recording errors, Response errors, Analysis errors and some times defective measurement instruments