Location via proxy:   [ UP ]  
[Report a bug]   [Manage cookies]                
SlideShare a Scribd company logo

Research design

•Download as PPTX, PDF•
•
Abhijeet Birari
Abhijeet Birari

The research design refers to the overall strategy that you choose to integrate the different components of the study in a coherent and logical way, thereby, ensuring you will effectively address the research problem; it constitutes the blueprint for the collection, measurement, and analysis of data.

Related slideshows

Research Methodology - Scientific Research
Research Methodology - Scientific ResearchResearch Methodology - Scientific Research
Research Methodology - Scientific Research
 
Research Method
Research MethodResearch Method
Research Method
 
Chapter three
Chapter threeChapter three
Chapter three
 
1 of 63
Presented by Abhijeet Birari UNIT III RESEARCH DESIGN
RESEARCH DESIGN WHAT? WHERE? WHEN? HOW MUCH? BY WHAT MEANS?
What is the study about? Why is the study being made? Where will the study be carried out? What type of data is required? Where can the required data be found? What periods of time will study include? What will be the sample design? How will the data be analyzed? In what style will the report be prepared? What technique of data collection will be used?
Research Design Sampling Design Observational Design Statistical Design Operational Design Deals with methods of selecting sample Conditions under which observations to be made How the data will be analyzed Techniques which will be used to carry out designs CATEGORIZATION OF RESEARCH DESIGN
FEATURES OF RESEARCH DESIGN It’s a plan specifying sources and types of information Strategy used to gather and analyze the data Also includes time and cost of budget
FEATURES OF GOOD RESEARCH DESIGN Flexible Appropriate Efficient Economical Minimizes bias and maximizes reliability of data Gives smallest experimental error Yield maximum information Considers different aspects within limited resources
IMPORTANT CONCEPTS RELATED TO RESEARCH DESIGN
VARIABLE A variable is defined as anything that has a quantity or quality that varies. Height Weight Temperature Pressure Time
DEPENDENT AND INDEPENDENT VARIABLE
DEPENDENT AND INDEPENDENT VARIABLE Rainfall Crop Yield Marks Hours of study Speed Mileage Energy Food
EXTRANEOUS VARIABLE Independent Dependent Extraneous Fertilizer Soil Atmosphere Quality of seed
EXTRANEOUS VARIABLE Independent Dependent Extraneous ???
EXTRANEOUS VARIABLE Independent variables that are not related to the purpose of the study but may affect the dependent variable are called as extraneous variables.
CONFOUNDED RELATIONSHIP “When dependent variable is not free from influence of extraneous variable, the relation is called confounded relationship.”
CONTROL
CONTROL Fertilizer X Everything same except fertilizer Control is used to minimize the effect of extraneous independent variables. Measure Effect
RESEARCH HYPOTHESIS Hypothesis is a predictive statement that relates an independent variable to a dependent variable.  The fertilizer will significantly improve productivity of plants.  There will be significant difference between IQ of males and females.  The training session will improve performance of workers. EXAMPLE
NON EXPERIMENTAL RESEARCH GROUP OF STUDENTS INTELLIGENCE INDEPENDENT VARIABLE SCORE IN STATISTICAL TEST DEPENDENT VARIABLE
EXPERIMENTAL RESEARCH USUAL STUDY PROGRAM SPECIAL STUDY PROGRAM SCORE IN STATISTICAL TEST SCORE IN STATISTICAL TEST
EXPERIMENTAL NON EXPERIMENTAL Research in which independent variable is manipulated Research in which independent variable is not manipulated
EXPERIMENTAL AND CONTROL GROUPS USUAL STUDY PROGRAM SPECIAL STUDY PROGRAM CONTROL GROUP EXPERIMENTAL GROUP Group is exposed to usual condition Group is exposed to special condition
TREATMENTS FERTILIZER A FERTILIZER B FERTILIZER C CONDITIONS CONDITIONS under which groups are put is called as Treatments
EXPERIMENT Process of examining truth is called as ‘Experiment’ Absolute Experiment Comparative Experiment Effect of fertilizer X on crop yield Impact of fertilizer X compared to Y on crop yield
DIFFERENT RESEARCH DESIGNS
EXPLORATORY DESCRIPTIVE EXPERIMENTAL
EXPLORATORY RESEARCH DESIGN
 Simplest and most loosely structured.  Objective is to explore and obtain clarity about problem situation.  Discovery of ideas and insights.  Flexible in approach.  Mostly involve qualitative investigation.  Sample size is not strictly representative. EXPLORATORY
TECHNIQUES FOR CONDUCTING EXPLORATORY RESEARCH: 1. Secondary Resource Analysis:  Previously collected findings  Easy to collect and less expensive  Points out that proposed research is redundant and already made 2. Structured and unstructured observations:  Exploring problem through observations  Example: Customer behavior for a window display of a shop EXPLORATORY
TECHNIQUES FOR CONDUCTING EXPLORATORY RESEARCH: 3. Expert Opinion Survey:  No previous information is available  Seek help from expert 4. Focus Group Discussion  Discussion with individuals associated with problem under study  Carefully selected small set of individuals EXPLORATORY
LEARNING THROUGH DISCUSSION
Research design
ASSESSMENT CRITERIA 1. Quality of discussion 2. Variety of points discussed 3. Number of students discussing in each group 4. Discipline and decorum maintained by the group 5. Speaking and listening ability of group
You are a business manager with the ITC group of hotels. You receive a customer satisfaction report on your international hotels from the research agency to which you had outsourced the work. What or how will you evaluate the quality of work done in the study?
 Concerned with describing the characteristics of a particular individual, group, situation, problem etc.  More structured and formal in nature than exploratory EXAMPLE: DISCRIPTIVE Businessman wants to design advertising and promotion campaign for high end watches Descriptive Research Who? What? When? Where? Why? How?
 Narration of facts  Characteristics concerning individual, group or situation  Social research comes under this category DISCRIPTIVE
DISCRIPTIVE CONDUCTING DESCRIPTIVE RESEARCH Cross- Sectional Longitudin al
DISCRIPTIVE Cross- Sectional
CASE STUDY Danish Ice-Cream Reference : Research Methodology by Deepak Chawla, Page No. 54
DISCRIPTIVE Cross- Sectional  Selection of current subdivision of population and study the nature of variables.  Carried out at a single moment in time  Applicable for specific period. EXAMPLE: Attitude/perception of Americans towards Asian-Americans, pre- and post- 9/11
DISCRIPTIVE Cross- Sectional Situations in which population is not homogenous (Religion, Gender, rural-urban etc.) Multiple cross-sectional studies May be carried out at same moment in time May be carried out at different time interval Cohort Analysis called as called as examples Attitude of adult Vs teenage Americans towards Asians post event Predicting election results
DISCRIPTIVE Longitudi nal Group of Consumers Study of this group over a stretched period of time (purchase frequency, amount, behavior, pattern, types of products purchased, medium of purchase etc.) A study of single sample of the identified population that is studied over a stretched period of time
DISCRIPTIVE Longitudi nal FEATURES:  Selection of representative panel which represents population.  Repeated measurement of group.  Selected sample stays constant over a period of study.
EXPERIMENTAL SALES MANAGER (Pepsico India.) Sales Personnel 3 Month Training 20% increase in sales Conclusion by manager Training programme is effective Sales force from other territories should also be sent for same training Decision IS IT A GOOD DECISION ???
EXPERIMENTAL Sales manager is trying to infer that sales training has caused increase in sales. i.e. Training is a Causal Variable and Sales growth is an Effect Variable ::: This may not be true because ::: It may be caused due to:  Reduction in price of soft drink  Strike at the competitor’s plant  Increase in price of competitor’s product  Reduction in quality of competing product  Weather conditions etc.
EXPERIMENTAL WHAT IS EXPERIMENT? “It is used to infer causality.”  In an experiment, researcher manipulated one or more causal variables (independent variables) and measure its effect on dependent variables.  Relation is probabilistic in nature.  Impossible to prove causality.  Can only infer cause and effect relationship.
Experimental Design Pre- Experimental One Shot Case Study One Group Pre test-post test Static Group Quasi- Experimental Time Series Multiple Time Series True- Experimental Pre-test-post- test Control Group Post-test-only Control Group Solomon Four Group Statistical Completely Randomized Randomized Blocks Latin Square Factorial Pre-experimental Quasi Experimental True-experimental Statistical No Randomization Randomization
RANDOMIZATION Suppose you have five chocolates bars and total 8 friends to distribute these 5 chocolates to. Now how you are going to do this so the whole distribution process is with a minimum of bias? You may write down names of each of your friends on a separate small piece of paper, fold all small pieces of papers so no one know what name is on any paper. Then you ask someone to pick 5 names and give chocolates to first 5 names. This will remove the bias without hurting any of your friend's feelings. This is called as Randomization.
Experimental Design Pre- Experimental One Shot Case Study One Group Pre test-post test Static Group Quasi- Experimental Time Series Multiple Time Series True- Experimental Pre-test-post- test Control Group Post-test-only Control Group Solomon Four Group Statistical Completely Randomized Randomized Blocks Latin Square Factorial Treatment (X) and measurement of effect (O) on dependent variable Measurement before (O1) and after (O2) the Treatment (X) Group 1 – X O1 Group 2 – O2 O1 X O2 X O1 O = Measurement X = Treatment Do not use randomization procedure to control extraneous variable.
LEARNING BY DOING
Research design
NORMAL DISTRIBUTION Data can be "distributed" (spread out) in different ways. There are many cases where the data tends to be around a central value with no bias left or right, and it gets close to a "Normal Distribution"
Experimental Design Pre- Experimental One Shot Case Study One Group Pre test-post test Static Group Quasi- Experimental Time Series Multiple Time Series True- Experimental Pre-test-post- test Control Group Post-test-only Control Group Solomon Four Group Statistical Completely Randomized Randomized Blocks Latin Square Factorial O1 O2 O3 O4 X O5 O6 O7 O8 Experimental Group : O1 O2 O3 O4 X O5 O6 O7 O8 Control Group : O1 O2 O3 O4 O5 O6 O7 O8 O = Measurement X = Treatment Do not use randomization procedure to control extraneous variable.
Experimental Design Pre- Experimental One Shot Case Study One Group Pre test-post test Static Group Quasi- Experimental Time Series Multiple Time Series True- Experimental Pre-test-post- test Control Group Post-test-only Control Group Solomon Four Group Statistical Completely Randomized Randomized Blocks Latin Square Factorial R = Randomization O = Measurement X = Treatment Researcher is able to eliminate effect of extraneous variables from experimental and control group. Experimental Group : R O1 X O2 Control Group : O3 O4 Experimental Group : R X O1 Control Group : O2 Experimental Group 1 : R O1 X O2 Control Group 1 : O3 O4 Experimental Group 2 : R X O1 Control Group 2 : O2
Experimental Design Pre- Experimental One Shot Case Study One Group Pre test-post test Static Group Quasi- Experimental Time Series Multiple Time Series True- Experimental Pre-test-post- test Control Group Post-test-only Control Group Solomon Four Group Statistical Completely Randomized Randomized Blocks Latin Square Factorial It allows for statistical control and analysis of external variable. Used to investigate effect of one independent variable on dependent variable. Independent Variable should be nominal scale Example: Measurement of sales for different price level Price Level : Low Medium High Stores : A B C Use ANOVA technique to measure effect
Experimental Design Pre- Experimental One Shot Case Study One Group Pre test-post test Static Group Quasi- Experimental Time Series Multiple Time Series True- Experimental Pre-test-post- test Control Group Post-test-only Control Group Solomon Four Group Statistical Completely Randomized Randomized Blocks Latin Square Factorial Limitation of Completely Randomized Design: Extraneous Variables are assumed to be constant Using Randomized Blocks to minimize influence of one extraneous variable
1 2 3 4 5 6 7 8 9 10 11 12 LOW MEDIUM HIGH SMALL SIZE 1 2 3 4 5 6 7 8 9 10 11 12 LOW MEDIUM HIGH MEDIUM SIZE 1 2 3 4 5 6 7 8 9 10 11 12 LOW MEDIUM HIGH LARGE SIZE STORES PRICE STORES PRICE STORES PRICE
Experimental Design Pre- Experimental One Shot Case Study One Group Pre test-post test Static Group Quasi- Experimental Time Series Multiple Time Series True- Experimental Pre-test-post- test Control Group Post-test-only Control Group Solomon Four Group Statistical Completely Randomized Randomized Blocks Latin Square Factorial Used to separate influence of 2 Extraneous Variables Example: Sales Would be influenced by 2 extraneous variables. Store Size Packaging I II III 1 (Small) X1 X2 X3 2 (Medium) X2 X3 X1 3 (Large) X3 X1 X2 Here, X1=Low price, X2=Medium, X3=High
Experimental Design Pre- Experimental One Shot Case Study One Group Pre test-post test Static Group Quasi- Experimental Time Series Multiple Time Series True- Experimental Pre-test-post- test Control Group Post-test-only Control Group Solomon Four Group Statistical Completely Randomized Randomized Blocks Latin Square Factorial Used to measure effect of 2 or more independent variable. Allows interaction between 2 variables. Ex. An individual may like mango as well as ice cream but may not like Mango Ice Cream Price Stores Small (B1) Big (B2) Low (A1) A1B1 A1B2 Medium (A2) A2B1 A2B2 High (A3) A3B1 A3B2
SUMMARY
• Research Design is a plan specifying sources and types of information • Categories of research design – Sampling, Observational, Statistical, operational • A variable is defined as anything that has a quantity or quality that varies. • Independent Variable influences change in dependent variable. • Extraneous Variables - Variables that are not related to the purpose of the study but may affect the dependent variable • Control is used to minimize the effect of extraneous independent variables.
• Hypothesis is a predictive statement that relates an independent variable to a dependent variable. • Research in which independent variable is manipulated – Experimental • Research in which independent variable is not manipulated – Non Experimental • Conditions under which groups are put is called as Treatments • Process of examining truth is called as ‘Experiment’ • Exploratory Design - Objective is to explore and obtain clarity about problem situation.
• Descriptive Design - Concerned with describing the characteristics of a particular individual, group, situation, problem etc. • Cross Sectional - Selection of current subdivision of population and study the nature of variables. • Longitudinal - Study of a group over a stretched period of time • Experiment - It is used to infer causality • Experimental Design – Pre experimental, Quasi experimental, True Experimental, Statistical
Research design

More Related Content

Research design

  • 1. Presented by Abhijeet Birari UNIT III RESEARCH DESIGN
  • 3. What is the study about? Why is the study being made? Where will the study be carried out? What type of data is required? Where can the required data be found? What periods of time will study include? What will be the sample design? How will the data be analyzed? In what style will the report be prepared? What technique of data collection will be used?
  • 4. Research Design Sampling Design Observational Design Statistical Design Operational Design Deals with methods of selecting sample Conditions under which observations to be made How the data will be analyzed Techniques which will be used to carry out designs CATEGORIZATION OF RESEARCH DESIGN
  • 5. FEATURES OF RESEARCH DESIGN It’s a plan specifying sources and types of information Strategy used to gather and analyze the data Also includes time and cost of budget
  • 6. FEATURES OF GOOD RESEARCH DESIGN Flexible Appropriate Efficient Economical Minimizes bias and maximizes reliability of data Gives smallest experimental error Yield maximum information Considers different aspects within limited resources
  • 8. VARIABLE A variable is defined as anything that has a quantity or quality that varies. Height Weight Temperature Pressure Time
  • 10. DEPENDENT AND INDEPENDENT VARIABLE Rainfall Crop Yield Marks Hours of study Speed Mileage Energy Food
  • 13. EXTRANEOUS VARIABLE Independent variables that are not related to the purpose of the study but may affect the dependent variable are called as extraneous variables.
  • 14. CONFOUNDED RELATIONSHIP “When dependent variable is not free from influence of extraneous variable, the relation is called confounded relationship.”
  • 16. CONTROL Fertilizer X Everything same except fertilizer Control is used to minimize the effect of extraneous independent variables. Measure Effect
  • 17. RESEARCH HYPOTHESIS Hypothesis is a predictive statement that relates an independent variable to a dependent variable.  The fertilizer will significantly improve productivity of plants.  There will be significant difference between IQ of males and females.  The training session will improve performance of workers. EXAMPLE
  • 18. NON EXPERIMENTAL RESEARCH GROUP OF STUDENTS INTELLIGENCE INDEPENDENT VARIABLE SCORE IN STATISTICAL TEST DEPENDENT VARIABLE
  • 19. EXPERIMENTAL RESEARCH USUAL STUDY PROGRAM SPECIAL STUDY PROGRAM SCORE IN STATISTICAL TEST SCORE IN STATISTICAL TEST
  • 20. EXPERIMENTAL NON EXPERIMENTAL Research in which independent variable is manipulated Research in which independent variable is not manipulated
  • 21. EXPERIMENTAL AND CONTROL GROUPS USUAL STUDY PROGRAM SPECIAL STUDY PROGRAM CONTROL GROUP EXPERIMENTAL GROUP Group is exposed to usual condition Group is exposed to special condition
  • 22. TREATMENTS FERTILIZER A FERTILIZER B FERTILIZER C CONDITIONS CONDITIONS under which groups are put is called as Treatments
  • 23. EXPERIMENT Process of examining truth is called as ‘Experiment’ Absolute Experiment Comparative Experiment Effect of fertilizer X on crop yield Impact of fertilizer X compared to Y on crop yield
  • 27.  Simplest and most loosely structured.  Objective is to explore and obtain clarity about problem situation.  Discovery of ideas and insights.  Flexible in approach.  Mostly involve qualitative investigation.  Sample size is not strictly representative. EXPLORATORY
  • 28. TECHNIQUES FOR CONDUCTING EXPLORATORY RESEARCH: 1. Secondary Resource Analysis:  Previously collected findings  Easy to collect and less expensive  Points out that proposed research is redundant and already made 2. Structured and unstructured observations:  Exploring problem through observations  Example: Customer behavior for a window display of a shop EXPLORATORY
  • 29. TECHNIQUES FOR CONDUCTING EXPLORATORY RESEARCH: 3. Expert Opinion Survey:  No previous information is available  Seek help from expert 4. Focus Group Discussion  Discussion with individuals associated with problem under study  Carefully selected small set of individuals EXPLORATORY
  • 32. ASSESSMENT CRITERIA 1. Quality of discussion 2. Variety of points discussed 3. Number of students discussing in each group 4. Discipline and decorum maintained by the group 5. Speaking and listening ability of group
  • 33. You are a business manager with the ITC group of hotels. You receive a customer satisfaction report on your international hotels from the research agency to which you had outsourced the work. What or how will you evaluate the quality of work done in the study?
  • 34.  Concerned with describing the characteristics of a particular individual, group, situation, problem etc.  More structured and formal in nature than exploratory EXAMPLE: DISCRIPTIVE Businessman wants to design advertising and promotion campaign for high end watches Descriptive Research Who? What? When? Where? Why? How?
  • 35.  Narration of facts  Characteristics concerning individual, group or situation  Social research comes under this category DISCRIPTIVE
  • 38. CASE STUDY Danish Ice-Cream Reference : Research Methodology by Deepak Chawla, Page No. 54
  • 39. DISCRIPTIVE Cross- Sectional  Selection of current subdivision of population and study the nature of variables.  Carried out at a single moment in time  Applicable for specific period. EXAMPLE: Attitude/perception of Americans towards Asian-Americans, pre- and post- 9/11
  • 40. DISCRIPTIVE Cross- Sectional Situations in which population is not homogenous (Religion, Gender, rural-urban etc.) Multiple cross-sectional studies May be carried out at same moment in time May be carried out at different time interval Cohort Analysis called as called as examples Attitude of adult Vs teenage Americans towards Asians post event Predicting election results
  • 41. DISCRIPTIVE Longitudi nal Group of Consumers Study of this group over a stretched period of time (purchase frequency, amount, behavior, pattern, types of products purchased, medium of purchase etc.) A study of single sample of the identified population that is studied over a stretched period of time
  • 42. DISCRIPTIVE Longitudi nal FEATURES:  Selection of representative panel which represents population.  Repeated measurement of group.  Selected sample stays constant over a period of study.
  • 43. EXPERIMENTAL SALES MANAGER (Pepsico India.) Sales Personnel 3 Month Training 20% increase in sales Conclusion by manager Training programme is effective Sales force from other territories should also be sent for same training Decision IS IT A GOOD DECISION ???
  • 44. EXPERIMENTAL Sales manager is trying to infer that sales training has caused increase in sales. i.e. Training is a Causal Variable and Sales growth is an Effect Variable ::: This may not be true because ::: It may be caused due to:  Reduction in price of soft drink  Strike at the competitor’s plant  Increase in price of competitor’s product  Reduction in quality of competing product  Weather conditions etc.
  • 45. EXPERIMENTAL WHAT IS EXPERIMENT? “It is used to infer causality.”  In an experiment, researcher manipulated one or more causal variables (independent variables) and measure its effect on dependent variables.  Relation is probabilistic in nature.  Impossible to prove causality.  Can only infer cause and effect relationship.
  • 46. Experimental Design Pre- Experimental One Shot Case Study One Group Pre test-post test Static Group Quasi- Experimental Time Series Multiple Time Series True- Experimental Pre-test-post- test Control Group Post-test-only Control Group Solomon Four Group Statistical Completely Randomized Randomized Blocks Latin Square Factorial Pre-experimental Quasi Experimental True-experimental Statistical No Randomization Randomization
  • 47. RANDOMIZATION Suppose you have five chocolates bars and total 8 friends to distribute these 5 chocolates to. Now how you are going to do this so the whole distribution process is with a minimum of bias? You may write down names of each of your friends on a separate small piece of paper, fold all small pieces of papers so no one know what name is on any paper. Then you ask someone to pick 5 names and give chocolates to first 5 names. This will remove the bias without hurting any of your friend's feelings. This is called as Randomization.
  • 48. Experimental Design Pre- Experimental One Shot Case Study One Group Pre test-post test Static Group Quasi- Experimental Time Series Multiple Time Series True- Experimental Pre-test-post- test Control Group Post-test-only Control Group Solomon Four Group Statistical Completely Randomized Randomized Blocks Latin Square Factorial Treatment (X) and measurement of effect (O) on dependent variable Measurement before (O1) and after (O2) the Treatment (X) Group 1 – X O1 Group 2 – O2 O1 X O2 X O1 O = Measurement X = Treatment Do not use randomization procedure to control extraneous variable.
  • 51. NORMAL DISTRIBUTION Data can be "distributed" (spread out) in different ways. There are many cases where the data tends to be around a central value with no bias left or right, and it gets close to a "Normal Distribution"
  • 52. Experimental Design Pre- Experimental One Shot Case Study One Group Pre test-post test Static Group Quasi- Experimental Time Series Multiple Time Series True- Experimental Pre-test-post- test Control Group Post-test-only Control Group Solomon Four Group Statistical Completely Randomized Randomized Blocks Latin Square Factorial O1 O2 O3 O4 X O5 O6 O7 O8 Experimental Group : O1 O2 O3 O4 X O5 O6 O7 O8 Control Group : O1 O2 O3 O4 O5 O6 O7 O8 O = Measurement X = Treatment Do not use randomization procedure to control extraneous variable.
  • 53. Experimental Design Pre- Experimental One Shot Case Study One Group Pre test-post test Static Group Quasi- Experimental Time Series Multiple Time Series True- Experimental Pre-test-post- test Control Group Post-test-only Control Group Solomon Four Group Statistical Completely Randomized Randomized Blocks Latin Square Factorial R = Randomization O = Measurement X = Treatment Researcher is able to eliminate effect of extraneous variables from experimental and control group. Experimental Group : R O1 X O2 Control Group : O3 O4 Experimental Group : R X O1 Control Group : O2 Experimental Group 1 : R O1 X O2 Control Group 1 : O3 O4 Experimental Group 2 : R X O1 Control Group 2 : O2
  • 54. Experimental Design Pre- Experimental One Shot Case Study One Group Pre test-post test Static Group Quasi- Experimental Time Series Multiple Time Series True- Experimental Pre-test-post- test Control Group Post-test-only Control Group Solomon Four Group Statistical Completely Randomized Randomized Blocks Latin Square Factorial It allows for statistical control and analysis of external variable. Used to investigate effect of one independent variable on dependent variable. Independent Variable should be nominal scale Example: Measurement of sales for different price level Price Level : Low Medium High Stores : A B C Use ANOVA technique to measure effect
  • 55. Experimental Design Pre- Experimental One Shot Case Study One Group Pre test-post test Static Group Quasi- Experimental Time Series Multiple Time Series True- Experimental Pre-test-post- test Control Group Post-test-only Control Group Solomon Four Group Statistical Completely Randomized Randomized Blocks Latin Square Factorial Limitation of Completely Randomized Design: Extraneous Variables are assumed to be constant Using Randomized Blocks to minimize influence of one extraneous variable
  • 56. 1 2 3 4 5 6 7 8 9 10 11 12 LOW MEDIUM HIGH SMALL SIZE 1 2 3 4 5 6 7 8 9 10 11 12 LOW MEDIUM HIGH MEDIUM SIZE 1 2 3 4 5 6 7 8 9 10 11 12 LOW MEDIUM HIGH LARGE SIZE STORES PRICE STORES PRICE STORES PRICE
  • 57. Experimental Design Pre- Experimental One Shot Case Study One Group Pre test-post test Static Group Quasi- Experimental Time Series Multiple Time Series True- Experimental Pre-test-post- test Control Group Post-test-only Control Group Solomon Four Group Statistical Completely Randomized Randomized Blocks Latin Square Factorial Used to separate influence of 2 Extraneous Variables Example: Sales Would be influenced by 2 extraneous variables. Store Size Packaging I II III 1 (Small) X1 X2 X3 2 (Medium) X2 X3 X1 3 (Large) X3 X1 X2 Here, X1=Low price, X2=Medium, X3=High
  • 58. Experimental Design Pre- Experimental One Shot Case Study One Group Pre test-post test Static Group Quasi- Experimental Time Series Multiple Time Series True- Experimental Pre-test-post- test Control Group Post-test-only Control Group Solomon Four Group Statistical Completely Randomized Randomized Blocks Latin Square Factorial Used to measure effect of 2 or more independent variable. Allows interaction between 2 variables. Ex. An individual may like mango as well as ice cream but may not like Mango Ice Cream Price Stores Small (B1) Big (B2) Low (A1) A1B1 A1B2 Medium (A2) A2B1 A2B2 High (A3) A3B1 A3B2
  • 60. • Research Design is a plan specifying sources and types of information • Categories of research design – Sampling, Observational, Statistical, operational • A variable is defined as anything that has a quantity or quality that varies. • Independent Variable influences change in dependent variable. • Extraneous Variables - Variables that are not related to the purpose of the study but may affect the dependent variable • Control is used to minimize the effect of extraneous independent variables.
  • 61. • Hypothesis is a predictive statement that relates an independent variable to a dependent variable. • Research in which independent variable is manipulated – Experimental • Research in which independent variable is not manipulated – Non Experimental • Conditions under which groups are put is called as Treatments • Process of examining truth is called as ‘Experiment’ • Exploratory Design - Objective is to explore and obtain clarity about problem situation.
  • 62. • Descriptive Design - Concerned with describing the characteristics of a particular individual, group, situation, problem etc. • Cross Sectional - Selection of current subdivision of population and study the nature of variables. • Longitudinal - Study of a group over a stretched period of time • Experiment - It is used to infer causality • Experimental Design – Pre experimental, Quasi experimental, True Experimental, Statistical

Editor's Notes

  1. This presentation demonstrates the new capabilities of PowerPoint and it is best viewed in Slide Show. These slides are designed to give you great ideas for the presentations you’ll create in PowerPoint 2010! For more sample templates, click the File tab, and then on the New tab, click Sample Templates.
  2. Ref: Chawla pn 53
  3. Ref: Chawla pn 63