Ch12 2

643 views

Published on

Published in: Education
0 Comments
0 Likes
Statistics
Notes
  • Be the first to comment

  • Be the first to like this

No Downloads
Views
Total views
643
On SlideShare
0
From Embeds
0
Number of Embeds
2
Actions
Shares
0
Downloads
12
Comments
0
Likes
0
Embeds 0
No embeds

No notes for slide

Ch12 2

  1. 1. Business Research Methods William G. Zikmund Chapter 12:Experimental Research
  2. 2. Copyright © 2000 by Harcourt, Inc. All rights reserved. Requests forpermission to make copies of any part of the work should be mailed to the following address: PermissionsDepartment, Harcourt, Inc., 6277 Sea Harbor Drive, Orlando, Florida 32887-6777.
  3. 3. EXPERIMENT• A RESEARCH INVESTIGATION IN WHICH CONDITIONS ARE CONTROLLED• ONE INDEPENDENT VARIABLE IS MANIPULATED (SOMETIMES MORE THAN ONE)• ITS EFFECT ON A DEPENDENT VARIABLE IS MEASURED• TO TEST A HYPOTHESIS Copyright © 2000 by Harcourt, Inc. All rights reserved
  4. 4. Basic Issues of Experimental Design Manipulation of the Independent Variable Selection of Dependent VariableAssignment of Subjects (or other Test Units) Control Over Extraneous Variables Copyright © 2000 by Harcourt, Inc. All rights reserved
  5. 5. The experimenter has some degreeof control over the independentvariable. The variable isindependent because its value canbe manipulated by the experimenterto whatever he or she wishes it tobe. Copyright © 2000 by Harcourt, Inc. All rights reserved
  6. 6. Experiment TreatmentAlternative manipulations of the independent variable being investigated Copyright © 2000 by Harcourt, Inc. All rights reserved
  7. 7. Independent Variable• The experimenter controls independent variable.• The variable’s value can be manipulated by the experimenters to whatever they wish it to be. Copyright © 2000 by Harcourt, Inc. All rights reserved
  8. 8. MANIPULATION OF INDEPENDENT VARIABLE•Classificatory Vs. Continuous Variables•Experimental and Control Groups•Treatment Levels•More Than One Independent Variable Copyright © 2000 by Harcourt, Inc. All rights reserved
  9. 9. Experimental treatments arethe alternative manipulationsof the independent variablebeing investigated. Copyright © 2000 by Harcourt, Inc. All rights reserved
  10. 10. DEPENDENT VARIABLE• its value is expected to be dependent on the experimenter’s manipulation• criterion or standard by which the results are judged Copyright © 2000 by Harcourt, Inc. All rights reserved
  11. 11. DEPENDENT VARIABLE• SELECTION – e.g... sales volume, awareness, recall• MEASUREMENT Copyright © 2000 by Harcourt, Inc. All rights reserved
  12. 12. Dependent Variable• Selection - e.g., sales volume, awareness, recall• Measurement Copyright © 2000 by Harcourt, Inc. All rights reserved
  13. 13. The dependent variable is socalled because its value isexpected to be dependent on theexperimenter’s manipulation; it isthe criterion or standard by whichthe results are judged. Copyright © 2000 by Harcourt, Inc. All rights reserved
  14. 14. TEST UNITS - subjects or entitieswhose response to theexperimental treatment aremeasured or observed. Copyright © 2000 by Harcourt, Inc. All rights reserved
  15. 15. Two Types of Experimental Error•Constant Error•Random Errors Copyright © 2000 by Harcourt, Inc. All rights reserved
  16. 16. TWO TYPES OF EXPERIMENTAL ERRORS• CONSTANT ERRORS• RANDOM ERRORS Copyright © 2000 by Harcourt, Inc. All rights reserved
  17. 17. FIELD VERSUS LABORATORY EXPERIMENTS Copyright © 2000 by Harcourt, Inc. All rights reserved
  18. 18. Controlling Extraneous Variables• Elimination of Extraneous Variables• Constancy of Conditions• Order of Presentation• Blinding• Random Assignment Copyright © 2000 by Harcourt, Inc. All rights reserved
  19. 19. How May an Experimenter control forExtraneous Variation? •Eliminate Extraneous Variables •Hold Conditions Constant •Randomization •Matching Subjects Copyright © 2000 by Harcourt, Inc. All rights reserved
  20. 20. Establishing Control Copyright © 2000 by Harcourt, Inc. All rights reserved
  21. 21. DEMAND CHARACTERISTICS• EXPERIMENTAL PROCEDURES THE INTENTIONALLY HINT TO SUBJECTS SOMETHING ABOUT THE EXPERIMENTER’S HYPOTHESIS Copyright © 2000 by Harcourt, Inc. All rights reserved
  22. 22. Demand Characteristics• Guinea Pigs• Hawthorne Effect Copyright © 2000 by Harcourt, Inc. All rights reserved
  23. 23. Field Vs. Laboratory Experiment Copyright © 2000 by Harcourt, Inc. All rights reserved
  24. 24. Laboratory Experiment Field Experiment Artificial-Low Realism Natural-High Realism Few Extraneous Many Extraneous Variables Variables High control Low control Low Cost High Cost Short Duration Long Duration Subjects Aware of Subjects Unaware of Participation Participation Copyright © 2000 by Harcourt, Inc. All rights reserved
  25. 25. CONTROL GROUPS• Isolates Extraneous Variation Copyright © 2000 by Harcourt, Inc. All rights reserved
  26. 26. WHEN IS AN EXPERIMENT INTERNAL VALIDITY?• INTERNAL VALIDITY - THE ABILITY OF AN EXPERIMENT TO ANSWER THE QUESTION OF WHETHER THE EXPERIMENTAL TREATMENT WAS THE SOLE CAUSE OF CHANGES IN A DEPENDENT VARIABLE• DID THE MANIPULATION DO WHAT IT WAS SUPPOSED TO DO? Copyright © 2000 by Harcourt, Inc. All rights reserved
  27. 27. FACTORS INFLUENCING INTERNAL VALIDITY• History • Instrumentation• Maturation • Selection• Testing • Mortality Copyright © 2000 by Harcourt, Inc. All rights reserved
  28. 28. ISOLATING EXTRANEOUS VARIATION WITH A CONTROL GROUP • History Effects • Maturation Effects • Mortality Effects Copyright © 2000 by Harcourt, Inc. All rights reserved
  29. 29. Type of Extraneous Variable ExampleHistory - specific events in the A Major EmployerEnvironment between the Before Closes Its Plant inand After Measurement That Are Test Market Areabeyond the Experimenter’s ControlMaturation - subjects Change Subjects Becomeduring the Course of the Experiment TiredTesting - The Before Measure Alerts Questionnaireor Sensitizes Subject to Nature of about the TraditionalExperiment or Second Measure Role of Women Triggers Enhanced Awareness of Women in an Experiment Copyright © 2000 by Harcourt, Inc. All rights reserved.
  30. 30. Instrument - Changes in New Questions aboutInstrument Result in Response Women are InterpretedBias Differently from Earlier Questions.Selection - Sample Selection Control Group andError Because of Differential Experimental Group IsSelection Comparison Groups Self-Selected Group Based on Preference for Soft DrinksMortality - Sample Attrition; Subjects in One Groupsome Subjects Withdraw from of a Hair Dying StudyExperiment Marry Rich Widows and move to Florida Copyright © 2000 by Harcourt, Inc. All rights reserved.
  31. 31. HOW CAN INTERNALVALIDITY BE INCREASE? Copyright © 2000 by Harcourt, Inc. All rights reserved.
  32. 32. INCREASING INTERNAL VALIDITY • Control Group • Random Assignment • Pre-testing and Post-testing • Posttest Only Copyright © 2000 by Harcourt, Inc. All rights reserved
  33. 33. WHAT ARE THE DIFFERENT BASIC EXPERIMENTAL DESIGNS? Copyright © 2000 by Harcourt, Inc. All rights reserved.
  34. 34. Quasi-Experimental Designs • One Shot Design (After Only) • One Group Pretest-Posttest • Static Group Design Copyright © 2000 by Harcourt, Inc. All rights reserved
  35. 35. ONE SHOT DESIGN (AFTER ONLY) X O1 Copyright © 2000 by Harcourt, Inc. All rights reserved
  36. 36. One Group Pretest-Posttest O1 X O2 Copyright © 2000 by Harcourt, Inc. All rights reserved
  37. 37. Static Group Design Experimental Group X O1 Control Group O2 Copyright © 2000 by Harcourt, Inc. All rights reserved
  38. 38. Three Good Experimental Designs• Pretest - Posttest Control Group Design• Posttest Only Control Group• Solomon Four Group Design Copyright © 2000 by Harcourt, Inc. All rights reserved
  39. 39. Pretest-Posttest Control Group Design Experimental Group R O1 X O2 Control Group R O3 X O4 Copyright © 2000 by Harcourt, Inc. All rights reserved
  40. 40. Posttest Only Control GroupExperimental Group R X O1Control Group R O2 Copyright © 2000 by Harcourt, Inc. All rights reserved
  41. 41. One-Shot Design Internal Validity Problems• History • Instrumentation – weak – not relevant• Maturation • Selection – weak – weak• Testing • Mortality – not relevant – weak Copyright © 2000 by Harcourt, Inc. All rights reserved
  42. 42. One-Group Pretest-Posttest Internal Validity Problems• History • Instrumentation – weak – weak• Maturation • Selection – weak – controlled• Testing • Mortality – weak – controlled Copyright © 2000 by Harcourt, Inc. All rights reserved
  43. 43. Static-Group Design Internal Validity Problems• History • Instrumentation – controlled – controlled• Maturation • Selection – possible source of – weak concern • Mortality• Testing – weak – controlled Copyright © 2000 by Harcourt, Inc. All rights reserved
  44. 44. Pretest-Posttest Control Internal Validity Problems• History • Instrumentation – controlled – controlled• Maturation • Selection – controlled – controlled• Testing • Mortality – controlled – controlled Copyright © 2000 by Harcourt, Inc. All rights reserved
  45. 45. Solomon Four-Group Design Internal Validity Problems• History • Instrumentation – controlled – controlled• Maturation • Selection – controlled – controlled• Testing • Mortality – controlled – controlled Copyright © 2000 by Harcourt, Inc. All rights reserved
  46. 46. Posttest-Only Control Internal Validity Problems• History • Instrumentation – controlled – controlled• Maturation • Selection – controlled – controlled• Testing • Mortality – controlled – controlled Copyright © 2000 by Harcourt, Inc. All rights reserved
  47. 47. Solomon four Group DesignExperimental Group 1: R O1 X O 2Control Group 1: R O3 O4Experimental Group 2: R X O5Control Group 2: R X O6 Copyright © 2000 by Harcourt, Inc. All rights reserved
  48. 48. ADVANCED EXPERIMENTAL DESIGNS ARE MORE COMPLEX• COMPLETELY RANDOMIZED• RANDOMIZED BLOCK DESIGN• LATIN SQUARE• FACTORIAL Copyright © 2000 by Harcourt, Inc. All rights reserved
  49. 49. Completely randomized design• An experimental design that uses a random process to assign subjects (test units) and treatments to investigate the effects of only one independent variable. Copyright © 2000 by Harcourt, Inc. All rights reserved
  50. 50. Completely Randomized Designs Control: Experimental Experimental no music treatment: treatment: slow music fast musicAverage minutes 16 18 12shopper spendsin store Copyright © 2000 by Harcourt, Inc. All rights reserved
  51. 51. INDEPENDENT VARIABLE A Level 1 Level 2 Level 3 Group A Group B Group C Copyright © 2000 by Harcourt, Inc. All rights reserved
  52. 52. Completely Randomized DesignWith a pretest posttest Group A R O1 X1 O2 Group A R O3 X2 O4 Group A R O5 X3 O6 Copyright © 2000 by Harcourt, Inc. All rights reserved
  53. 53. Completely Randomized DesignWith a posttest Group A R X1 O1 Group B R X2 O2 Group C R X3 O3 Copyright © 2000 by Harcourt, Inc. All rights reserved
  54. 54. Randomized block design• An extension of the completely randomized design in which a single extraneous variable that might affect test units’ response to the treatment has been identified and the effects of this variable are isolated by blocking out its effects. Copyright © 2000 by Harcourt, Inc. All rights reserved
  55. 55. Randomized Block Design Independent Variables Control: Experimental Experimental no music treatment treatment: slow music fast musicBlocking variable Mornings and afternoons Evening hours Copyright © 2000 by Harcourt, Inc. All rights reserved
  56. 56. Factorial design• An experiment that investigates the interaction of two or more variables on a single dependent variable. Copyright © 2000 by Harcourt, Inc. All rights reserved
  57. 57. Independent Variable 1 No Music Slow Music Fast MusicIndependent Variable 2 No Music cart signs Grocery cart signs Copyright © 2000 by Harcourt, Inc. All rights reserved
  58. 58. Factorial Design -- Roller Skates Price Red Gold $25 Cell 1 Cell 4 $30 Cell 2 Cell 5 $35 Cell 3 Cell 6Package Design Copyright © 2000 by Harcourt, Inc. All rights reserved
  59. 59. EFFECTS• Main effect • Interaction effect• The influence of a • The influence on a single independent dependent variable by variable on a combinations of two dependent variable. or more independent variables. Copyright © 2000 by Harcourt, Inc. All rights reserved
  60. 60. 2 x 2 Factorial Design Ad A Ad B Men 65 > Main Effects of GenderWomen 65 70 60 > Main Effects of Ad Copyright © 2000 by Harcourt, Inc. All rights reserved
  61. 61. Interaction Between Gender and Ad Copy 100 90 Wo 80 me n 70 Believability 60 Men 50 40 30 20 10 Ad A Ad B Copyright © 2000 by Harcourt, Inc. All rights reserved
  62. 62. INDEPENDENT VARIABLE 1 Level 1 Level 2 Level 1 Group A Group BINDEPENDENT VARIABLE 2 Level 2 Group D Group C Copyright © 2000 by Harcourt, Inc. All rights reserved
  63. 63. 2 x 2 Factorial with a Pretest Posttest Group A R O1 X11 O2 Group B R O3 X21 O4 Group C R O5 X12 O6 Group D R O7 X22 O8 Copyright © 2000 by Harcourt, Inc. All rights reserved
  64. 64. 2 x 2 Factorial Design with a Posttest Measure Group A R X11 O1 Group B R X21 O2 Group C R X12 O3 Group D R X22 O4 Copyright © 2000 by Harcourt, Inc. All rights reserved
  65. 65. A Test Market Experiment on Pricing Sales in Units (thousands) Regular Price Reduced Price Cents-Off Coupon $.99 $.89 Regular PriceTest Market A, B, or C 130 145 153Test Market D, E, or F 118 143 129Test Market G, H, or I 87 120 96Test Market J, K, or L 84 131 99Mean X1=104.75 X2=134.75 X1=119.25Grand Mean X=119.58 Copyright © 2000 by Harcourt, Inc. All rights reserved
  66. 66. LATIN SQUARE DESIGN• A balanced, two-way classification scheme that attempts to control or block out the effect of two or more extraneous factors by restricting randomization with respect to the row and column effects. Copyright © 2000 by Harcourt, Inc. All rights reserved
  67. 67. Order of UsageSUBJECT 1 2 3 1 A B C 2 B C A 3 C A B Copyright © 2000 by Harcourt, Inc. All rights reserved
  68. 68. TEST MARKETING Not just trying But scientific something testing outControlled experimentation Copyright © 2000 by Harcourt, Inc. All rights reserved
  69. 69. TEST MARKETING• AN EXPERIMENTAL PROCEDURE• THAT PROVIDES AN OPPORTUNITY TO TEST A NEW PRODUCT OR A NEW MARKETING PLAN• UNDER REALISTIC MARKET CONDITIONS• TO MEASURE SALES OR• PROFIT POTENTIAL Copyright © 2000 by Harcourt, Inc. All rights reserved
  70. 70. FUNCTONS OF TEST MARKETING IDENTIFY ANDESTIMATE CORRECTOUTCOMES WEAKNESSES IN PLANS Copyright © 2000 by Harcourt, Inc. All rights reserved
  71. 71. A Lengthy and Costly Procedure $$$$$ When not to Test? How Long Loss of Should a Secrecy Test Last? Copyright © 2000 by Harcourt, Inc. All rights reserved
  72. 72. SELECTING A TEST MARKET• POPULATION SIZE• DEMOGRAPHIC COMPOSITION• LIFESTYLE CONSIDERATIONS• COMPETITIVE SITUATION• MEDIA• SELF-CONTAINED TRADING AREA• OVERUSED MARKETS - SECRECY Copyright © 2000 by Harcourt, Inc. All rights reserved
  73. 73. CONTROL METHOD OF TEST MARKETING• SMALL CITY• LOW CHANCE OF BEING DETECTED• DISTRIBUTION IS FORCED (GUARANTEED) Copyright © 2000 by Harcourt, Inc. All rights reserved
  74. 74. The advantages of using the controlmethod of test marketing• Reduced costs• Shorter time period needed for reading test market results• Increased secrecy from competitors• No distraction of company salespeople from regular product lines Copyright © 2000 by Harcourt, Inc. All rights reserved
  75. 75. SOME PROBLEMS ESTIMATING SALES VOLUME• OVERATTENTION• UNREALISTIC STORE CONDITIONS• READING COMPETIVE ENVIRONMENT INCORRECTLY• INCORRECT VOLUME FORECASTS – ADJUSTED DATA – PENETRATION AND REPEAT PURCHASE RATE• TIME LAPSE Copyright © 2000 by Harcourt, Inc. All rights reserved
  76. 76. High Tech Test MarketsElectric TestMarkets Simulated Test Markets Virtual-reality Simulated Test Markets Copyright © 2000 by Harcourt, Inc. All rights reserved

×