Top Banner
REGAN REGMI SHEKHAR LAL AMATYA KUSHAL JUNG ADHIKARI
22

Research on sampling

Jan 22, 2018

Download

Education

Alok Upadhayay
Welcome message from author
This document is posted to help you gain knowledge. Please leave a comment to let me know what you think about it! Share it to your friends and learn new things together.
Transcript
Page 1: Research on sampling

REGAN REGMI

SHEKHAR LAL AMATYA

KUSHAL JUNG ADHIKARI

Page 2: Research on sampling

Introduction

Basis of Sampling

Sampling Techniques

Probability based samples

Non-probability based or purposive samples

Planning a sample survey

Summary

Context Of Presentation

2

Page 3: Research on sampling

Introduction

Sample

o Subset of the population

Sampling

o Process of collecting elements

3

Page 4: Research on sampling

Economy

Save time

Accuracy

Why sample

4

Page 5: Research on sampling

A. Reliability

Which measurement is repeatable and consistentI. Precision

o Free from random errorII. Sensitivity

o Do small change in true value invariably lead to changes in the measure value

I. Resolutiono What is the smallest change in the true value that can be detected?

II. Consistencyo Repeated measurement of same thing produce same results

Basis of sampling

5

Page 6: Research on sampling

Contd..

B. Validity

The relation between a variable and what supposed to measure

I. Accuracy

o Free from systematic error

II. Specificity

o Describe that what it supposed to describe

6

Page 7: Research on sampling

The main sampling techniques available to the marketing researcher are

summarized are as follows:

Probability based samples

1. Random samples-unrestricted and simple

2. Stratified samples

3. Cluster samples

4. Systematic sampling

Non-probability based samples

1. Quota

2. Convenience

Sampling Techniques

7

Page 8: Research on sampling

Random samples

Generally preferred and produces more precise estimators

Unrestricted random sample.

Restricted random sample.

Avoid the problems of selection bias.

Two procedure for achieve true randomness

Lottery method

Random number method

Probability based samples

8

Page 9: Research on sampling

Advantages

Ease calculation.

Benchmark method.

Disadvantages

Identify every single sampling units.

Enumerate the sampling units.

Establish physical contact.

Cont.…….

9

Page 10: Research on sampling

Overcome restricted approaches random sampling difficulties.

Splitting population into strata(smaller populations).

Use the two approaches

Proportionate stratified sampling.

Disproportionate stratified sampling.

Use extensively for continuous research activities.

Unduly expensive on data collection.

Stratified Samples

10

Page 11: Research on sampling

Similar to stratified sampling.

Cost effective method.

Major difference are:

Strata defined by selected characteristic – key independent variable (e.g. what year they’re in).

To ensure desired number of households in each district.

Cluster defined by spatial or social linkages – may not have anything to do with study (e.g. what class they’re in).

To make it easier to do door-to-door surveys.

Cluster sampling

11

Page 12: Research on sampling

Advantages

Does not required a precise sampling frame.

Used frequently in conjunction with a geographic frame.

Economically more efficient than other random sample

Disadvantages

Statistically less efficient than other random sample.

Cont.…….

12

Page 13: Research on sampling

Statistical method involving the selection of elements from an ordered sampling

frame. Most common form is an equal-probability method. In this approach, progression through the list is treated circularly, with a return to the

top once the end of the list is passed. The sampling starts by selecting an element from the list at random and then every kth

element in the frame is selected, where k, the sampling interval (sometimes known as

the skip). This is calculated as: k=N/n where n is the sample size, and N is the population size.

For eg:-population=2000, sample=200

K=2000/200 =10 , Here, random sample start = 7 then 7,17,27,37,…….1997.

Systematic sampling

13

Page 14: Research on sampling

Systematic sampling can be divided into

One-stage cluster

E.g.:-one number the days of the week

Multi-stage cluster

E.g.:-population of farmer further stratifying into broad types.

In reality , multi-stage cluster is widely used in national surveys

Cont.…….

14

Page 15: Research on sampling

All items in the universe do not have equal chance of being selected

Useful for quick and cheap studies

Potential for bias

“Inferior”

Quota Sampling and Convenience Sampling

Non Probability Based Sampling

15

Page 16: Research on sampling

Advantages:

Less Time consumingLess expensiveRelatively less complex

Disadvantages:BiasnessQuestionable representativenessInaccurate

Contd.

16

Page 17: Research on sampling

Respondents selected in accordance with population criteria

Two step process:

Develop control categories or quotas

Select sample elements from within the quotas

Proportion based sampling

Quota Sampling

17

Page 18: Research on sampling

Quota Sampling

Management English Maths

Enrollment 80 10 10

Percentage 80 10 10

Quota (n=50) 36 7 7

Quota Sampling considered more scientific and systematic

18

INTERLOCKING PARALLEL

Page 19: Research on sampling

Opportunistic Approach

Entirely focused on convenience of researcher

Helpful in hypothesis formulation

Suitable for when the resources are limited

Quick, convenient and less expensive

Convenience Sampling

19

Page 20: Research on sampling

Define the objectives of the study

Define the relevant population or universe

Identify the sampling frame

Select a sampling procedure

Determine the sample size

Select the sample units

Data Collection

Planning a Sample Survey

20

Page 21: Research on sampling

Sampling

Broad approach to sampling: Probabilistic, Non probabilistic

Proper planning of Survey

Determinants of the type of survey to use

Summary

21

Page 22: Research on sampling

THANK YOU

22