Statistics
123456
week_1.pptxPAD 503 Analytical Tools Week 1: Measurement; Research Design
Gary W. Reinbold, Ph.D., J.D.
University of Illinois at Springfield
January 16, 2017
1
Agenda
Introduction to the course
Review MBB Chapters 1 and 2
Sample problems from Chapter 2
Review MBB Chapter 3
Sample problems from Chapter 3
1/16/2017
Gary W. Reinbold, Ph.D., J.D.
University of Illinois at Springfield
2
2
Introduction to the Course
Keys to success in the course:
Know college-level algebra
Use a PC for Excel
Accept course expectations as standard for MPA programs
Focus on learning material, not on grade
Read book and lecture slides before coming to class or watching lecture
Attend class (for onground students) or watch lecture (for online students) and pay attention
Ask questions during class or write down questions while watching lecture and ask them on Blackboard
Work on homework assignments a little on your own first
Then, work on homework assignments in a regular group
Use Blackboard forums to further discuss homework with other students
Write up your own answers to homework assignments and make sure that you understand them
Come to office hours (for onground students) or post additional questions for instructor on Blackboard
Practice writing answers to sample exam problems under timed pressure
Allocate time appropriately each week (during weeks without exams):
2-3 hours: reading book and lecture slides before attending class or watching lecture
2-3 hours: attending class or watching lecture
4-8 hours: doing homework
1/16/2017
Gary W. Reinbold, Ph.D., J.D.
University of Illinois at Springfield
3
3
Introduction to Statistics
MBB: Chapter 1, pp. 3-13
1/16/2017
Gary W. Reinbold, Ph.D., J.D.
University of Illinois at Springfield
4
4
Introduction to Statistics
Key terms:
Sample: subset of the population
The population that you’re interested in might be all clients served by your agency
But you would typically collect and analyze data from only a subset of those clients – collecting data from everyone is often too expensive
Empirical: observable or based on data
Decide to implement a new program based on data showing the need and effectiveness
Not based on untested theory
Variable: measured characteristic or attribute
Income, age, number of visitors, number of clients, cost, etc.
1/16/2017
Gary W. Reinbold, Ph.D., J.D.
University of Illinois at Springfield
5
5
Measurement
MBB: Chapter 2 (except the Performance Measurement Techniques section), pp. 14-29, 37-41
1/16/2017
Gary W. Reinbold, Ph.D., J.D.
University of Illinois at Springfield
6
6
Measurement
Measurement theory – key terms:
Measurement: assigning numbers to a phenomenon that we’d like to analyze
Operational definition: describes how a concept will be measured
Indicator: variable that results from applying the operational definition to the concept
Multiple indicators: using more than one indicator to measure a concept
1/16/2017
Gary W. Reinbold, Ph.D., J.D.
University of Illinois at Springfield
7
7
Measurement
Measurement theory – key concepts:
Reasons to use multiple indicators for a concept:
Concept has multiple dimensions
No single indicator completely measures the concept
1/16/2017
Gary W. Reinbold, Ph.D., J.D.
University of Illinois at Springfield
8
8
Measurement
Measurement validity – key terms:
Validity: accuracy of indicator in measuring the concept
1/16/2017
Gary W. Reinbold, Ph.D., J.D.
University of Illinois at Springfield
9
9
Measurement
Measurement validity –key concepts:
Types of validity:
Indicator completely measures the concept (convergent)
Indicator distinguishes the concept from other similar concepts (discriminant)
Methods to establish validity:
Manager in question accepts the indicator as valid (face)
Numerous people in different situations accept the indicator as valid (consensual)
Indicator agrees strongly with other valid indicators (correlational)
Indicator correctly predicts a specified outcome (predictive)
1/16/2017
Gary W. Reinbold, Ph.D., J.D.
University of Illinois at Springfield
10
10
Measurement
Measurement reliability – key terms:
Reliability: consistency of indicator in assigning same number to same phenomenon
Subjectivity: degree to which indicator relies on judgment of the measurer or the respondent
Precision: accuracy of a sample in representing the underlying population
1/16/2017
Gary W. Reinbold, Ph.D., J.D.
University of Illinois at Springfield
11
11
Measurement
Measurement reliability – key concepts:
Considerations in reducing subjectivity:
Can use objective indicators to capture concept instead
But eliminating subjective component may decrease validity if respondent’s views about concept are important
Can use combination of subjective and objective indicators
Methods to improve precision:
Increase sample size
Use more sensitive indicators
1/16/2017
Gary W. Reinbold, Ph.D., J.D.
University of Illinois at Springfield
12
12
Measurement
Measurement levels – key terms:
Interval level (level 1): indicator is measured in standard units or intervals and yields identical results in repeated measures
Ordinal level (level 2): indicator can rank different observations, but cannot determine how much higher or lower one is than another
Nominal level (level 3): indicator can show only that two observations are different, not that one is higher or lower
1/16/2017
Gary W. Reinbold, Ph.D., J.D.
University of Illinois at Springfield
13
13
Measurement
Measurement levels – key concepts:
Considerations in selecting measurement level:
Can recode higher-level indicators into lower-level indicators
Can not usually recode lower-level indicators into higher-level indicators
Different types of analysis are more effective with different levels of indicators
1/16/2017
Gary W. Reinbold, Ph.D., J.D.
University of Illinois at Springfield
14
14
Measurement
Measurement levels – application:
MBB Table 2.5 (p. 27):
1/16/2017
Gary W. Reinbold, Ph.D., J.D.
University of Illinois at Springfield
15
| Variable | Level of Measurement |
| 1. Number of children | |
| 2. Opinion of the way the president is handling the economy (strongly approve; approve; neutral; disapprove; st. disapprove) | |
| 3. Age | |
| 4. State of residence | |
| 5. Mode of transportation to work | |
| 6. Perceived income (very low; below average; average; above average; very high) | |
| 7. Income in dollars | |
| 8. Interest in statistics (low; medium; high) | |
| 9. Sector of economy in which you would like to work (public; nonprofit; private) | |
| 10. Hours of overtime per week | |
| 11. Your comprehension of this book (great; adequate; forget it) | |
| 12. Number of memberships in clubs or associations | |
| 13. Dollars donated to nonprofit organization | |
| 14. Perceived success of animal rights association in advocacy (very high; high; moderate; low; very low) | |
| 15. Years of experience as a supervisor | |
| 16. Your evaluation of the level of “social capital” of your community (very low; low; moderate; high; very high) |
15
Measurement
Measurement levels – application:
MBB Table 2.5 (p. 27):
1/16/2017
Gary W. Reinbold, Ph.D., J.D.
University of Illinois at Springfield
15
| Variable | Level of Measurement |
| 1. Number of children | Interval |
| 2. Opinion of the way the president is handling the economy (strongly approve; approve; neutral; disapprove; st. disapprove) | |
| 3. Age | |
| 4. State of residence | |
| 5. Mode of transportation to work | |
| 6. Perceived income (very low; below average; average; above average; very high) | |
| 7. Income in dollars | |
| 8. Interest in statistics (low; medium; high) | |
| 9. Sector of economy in which you would like to work (public; nonprofit; private) | |
| 10. Hours of overtime per week | |
| 11. Your comprehension of this book (great; adequate; forget it) | |
| 12. Number of memberships in clubs or associations | |
| 13. Dollars donated to nonprofit organization | |
| 14. Perceived success of animal rights association in advocacy (very high; high; moderate; low; very low) | |
| 15. Years of experience as a supervisor | |
| 16. Your evaluation of the level of “social capital” of your community (very low; low; moderate; high; very high) |
16
Measurement
Measurement levels – application:
MBB Table 2.5 (p. 27):
1/16/2017
Gary W. Reinbold, Ph.D., J.D.
University of Illinois at Springfield
15
| Variable | Level of Measurement |
| 1. Number of children | Interval |
| 2. Opinion of the way the president is handling the economy (strongly approve; approve; neutral; disapprove; st. disapprove) | Ordinal |
| 3. Age | |
| 4. State of residence | |
| 5. Mode of transportation to work | |
| 6. Perceived income (very low; below average; average; above average; very high) | |
| 7. Income in dollars | |
| 8. Interest in statistics (low; medium; high) | |
| 9. Sector of economy in which you would like to work (public; nonprofit; private) | |
| 10. Hours of overtime per week | |
| 11. Your comprehension of this book (great; adequate; forget it) | |
| 12. Number of memberships in clubs or associations | |
| 13. Dollars donated to nonprofit organization | |
| 14. Perceived success of animal rights association in advocacy (very high; high; moderate; low; very low) | |
| 15. Years of experience as a supervisor | |
| 16. Your evaluation of the level of “social capital” of your community (very low; low; moderate; high; very high) |
17
Measurement
Measurement levels – application:
MBB Table 2.5 (p. 27):
1/16/2017
Gary W. Reinbold, Ph.D., J.D.
University of Illinois at Springfield
15
| Variable | Level of Measurement |
| 1. Number of children | Interval |
| 2. Opinion of the way the president is handling the economy (strongly approve; approve; neutral; disapprove; st. disapprove) | Ordinal |
| 3. Age | Interval |
| 4. State of residence | |
| 5. Mode of transportation to work | |
| 6. Perceived income (very low; below average; average; above average; very high) | |
| 7. Income in dollars | |
| 8. Interest in statistics (low; medium; high) | |
| 9. Sector of economy in which you would like to work (public; nonprofit; private) | |
| 10. Hours of overtime per week | |
| 11. Your comprehension of this book (great; adequate; forget it) | |
| 12. Number of memberships in clubs or associations | |
| 13. Dollars donated to nonprofit organization | |
| 14. Perceived success of animal rights association in advocacy (very high; high; moderate; low; very low) | |
| 15. Years of experience as a supervisor | |
| 16. Your evaluation of the level of “social capital” of your community (very low; low; moderate; high; very high) |
18
Measurement
Measurement levels – application:
MBB Table 2.5 (p. 27):
1/16/2017
Gary W. Reinbold, Ph.D., J.D.
University of Illinois at Springfield
15
| Variable | Level of Measurement |
| 1. Number of children | Interval |
| 2. Opinion of the way the president is handling the economy (strongly approve; approve; neutral; disapprove; st. disapprove) | Ordinal |
| 3. Age | Interval |
| 4. State of residence | Nominal |
| 5. Mode of transportation to work | |
| 6. Perceived income (very low; below average; average; above average; very high) | |
| 7. Income in dollars | |
| 8. Interest in statistics (low; medium; high) | |
| 9. Sector of economy in which you would like to work (public; nonprofit; private) | |
| 10. Hours of overtime per week | |
| 11. Your comprehension of this book (great; adequate; forget it) | |
| 12. Number of memberships in clubs or associations | |
| 13. Dollars donated to nonprofit organization | |
| 14. Perceived success of animal rights association in advocacy (very high; high; moderate; low; very low) | |
| 15. Years of experience as a supervisor | |
| 16. Your evaluation of the level of “social capital” of your community (very low; low; moderate; high; very high) |
19
Measurement
Measurement levels – application:
MBB Table 2.5 (p. 27):
1/16/2017
Gary W. Reinbold, Ph.D., J.D.
University of Illinois at Springfield
15
| Variable | Level of Measurement |
| 1. Number of children | Interval |
| 2. Opinion of the way the president is handling the economy (strongly approve; approve; neutral; disapprove; st. disapprove) | Ordinal |
| 3. Age | Interval |
| 4. State of residence | Nominal |
| 5. Mode of transportation to work | Nominal |
| 6. Perceived income (very low; below average; average; above average; very high) | |
| 7. Income in dollars | |
| 8. Interest in statistics (low; medium; high) | |
| 9. Sector of economy in which you would like to work (public; nonprofit; private) | |
| 10. Hours of overtime per week | |
| 11. Your comprehension of this book (great; adequate; forget it) | |
| 12. Number of memberships in clubs or associations | |
| 13. Dollars donated to nonprofit organization | |
| 14. Perceived success of animal rights association in advocacy (very high; high; moderate; low; very low) | |
| 15. Years of experience as a supervisor | |
| 16. Your evaluation of the level of “social capital” of your community (very low; low; moderate; high; very high) |
20
Measurement
Measurement levels – application:
MBB Table 2.5 (p. 27):
1/16/2017
Gary W. Reinbold, Ph.D., J.D.
University of Illinois at Springfield
15
| Variable | Level of Measurement |
| 1. Number of children | Interval |
| 2. Opinion of the way the president is handling the economy (strongly approve; approve; neutral; disapprove; st. disapprove) | Ordinal |
| 3. Age | Interval |
| 4. State of residence | Nominal |
| 5. Mode of transportation to work | Nominal |
| 6. Perceived income (very low; below average; average; above average; very high) | Ordinal |
| 7. Income in dollars | |
| 8. Interest in statistics (low; medium; high) | |
| 9. Sector of economy in which you would like to work (public; nonprofit; private) | |
| 10. Hours of overtime per week | |
| 11. Your comprehension of this book (great; adequate; forget it) | |
| 12. Number of memberships in clubs or associations | |
| 13. Dollars donated to nonprofit organization | |
| 14. Perceived success of animal rights association in advocacy (very high; high; moderate; low; very low) | |
| 15. Years of experience as a supervisor | |
| 16. Your evaluation of the level of “social capital” of your community (very low; low; moderate; high; very high) |
21
Measurement
Measurement levels – application:
MBB Table 2.5 (p. 27):
1/16/2017
Gary W. Reinbold, Ph.D., J.D.
University of Illinois at Springfield
15
| Variable | Level of Measurement |
| 1. Number of children | Interval |
| 2. Opinion of the way the president is handling the economy (strongly approve; approve; neutral; disapprove; st. disapprove) | Ordinal |
| 3. Age | Interval |
| 4. State of residence | Nominal |
| 5. Mode of transportation to work | Nominal |
| 6. Perceived income (very low; below average; average; above average; very high) | Ordinal |
| 7. Income in dollars | Interval |
| 8. Interest in statistics (low; medium; high) | |
| 9. Sector of economy in which you would like to work (public; nonprofit; private) | |
| 10. Hours of overtime per week | |
| 11. Your comprehension of this book (great; adequate; forget it) | |
| 12. Number of memberships in clubs or associations | |
| 13. Dollars donated to nonprofit organization | |
| 14. Perceived success of animal rights association in advocacy (very high; high; moderate; low; very low) | |
| 15. Years of experience as a supervisor | |
| 16. Your evaluation of the level of “social capital” of your community (very low; low; moderate; high; very high) |
22
Measurement
Measurement levels – application:
MBB Table 2.5 (p. 27):
1/16/2017
Gary W. Reinbold, Ph.D., J.D.
University of Illinois at Springfield
15
| Variable | Level of Measurement |
| 1. Number of children | Interval |
| 2. Opinion of the way the president is handling the economy (strongly approve; approve; neutral; disapprove; st. disapprove) | Ordinal |
| 3. Age | Interval |
| 4. State of residence | Nominal |
| 5. Mode of transportation to work | Nominal |
| 6. Perceived income (very low; below average; average; above average; very high) | Ordinal |
| 7. Income in dollars | Interval |
| 8. Interest in statistics (low; medium; high) | Ordinal |
| 9. Sector of economy in which you would like to work (public; nonprofit; private) | |
| 10. Hours of overtime per week | |
| 11. Your comprehension of this book (great; adequate; forget it) | |
| 12. Number of memberships in clubs or associations | |
| 13. Dollars donated to nonprofit organization | |
| 14. Perceived success of animal rights association in advocacy (very high; high; moderate; low; very low) | |
| 15. Years of experience as a supervisor | |
| 16. Your evaluation of the level of “social capital” of your community (very low; low; moderate; high; very high) |
23
Measurement
Measurement levels – application:
MBB Table 2.5 (p. 27):
1/16/2017
Gary W. Reinbold, Ph.D., J.D.
University of Illinois at Springfield
15
| Variable | Level of Measurement |
| 1. Number of children | Interval |
| 2. Opinion of the way the president is handling the economy (strongly approve; approve; neutral; disapprove; st. disapprove) | Ordinal |
| 3. Age | Interval |
| 4. State of residence | Nominal |
| 5. Mode of transportation to work | Nominal |
| 6. Perceived income (very low; below average; average; above average; very high) | Ordinal |
| 7. Income in dollars | Interval |
| 8. Interest in statistics (low; medium; high) | Ordinal |
| 9. Sector of economy in which you would like to work (public; nonprofit; private) | Nominal |
| 10. Hours of overtime per week | |
| 11. Your comprehension of this book (great; adequate; forget it) | |
| 12. Number of memberships in clubs or associations | |
| 13. Dollars donated to nonprofit organization | |
| 14. Perceived success of animal rights association in advocacy (very high; high; moderate; low; very low) | |
| 15. Years of experience as a supervisor | |
| 16. Your evaluation of the level of “social capital” of your community (very low; low; moderate; high; very high) |
24
Measurement
Measurement levels – application:
MBB Table 2.5 (p. 27):
1/16/2017
Gary W. Reinbold, Ph.D., J.D.
University of Illinois at Springfield
15
| Variable | Level of Measurement |
| 1. Number of children | Interval |
| 2. Opinion of the way the president is handling the economy (strongly approve; approve; neutral; disapprove; st. disapprove) | Ordinal |
| 3. Age | Interval |
| 4. State of residence | Nominal |
| 5. Mode of transportation to work | Nominal |
| 6. Perceived income (very low; below average; average; above average; very high) | Ordinal |
| 7. Income in dollars | Interval |
| 8. Interest in statistics (low; medium; high) | Ordinal |
| 9. Sector of economy in which you would like to work (public; nonprofit; private) | Nominal |
| 10. Hours of overtime per week | Interval |
| 11. Your comprehension of this book (great; adequate; forget it) | |
| 12. Number of memberships in clubs or associations | |
| 13. Dollars donated to nonprofit organization | |
| 14. Perceived success of animal rights association in advocacy (very high; high; moderate; low; very low) | |
| 15. Years of experience as a supervisor | |
| 16. Your evaluation of the level of “social capital” of your community (very low; low; moderate; high; very high) |
25
Measurement
Measurement levels – application:
MBB Table 2.5 (p. 27):
1/16/2017
Gary W. Reinbold, Ph.D., J.D.
University of Illinois at Springfield
15
| Variable | Level of Measurement |
| 1. Number of children | Interval |
| 2. Opinion of the way the president is handling the economy (strongly approve; approve; neutral; disapprove; st. disapprove) | Ordinal |
| 3. Age | Interval |
| 4. State of residence | Nominal |
| 5. Mode of transportation to work | Nominal |
| 6. Perceived income (very low; below average; average; above average; very high) | Ordinal |
| 7. Income in dollars | Interval |
| 8. Interest in statistics (low; medium; high) | Ordinal |
| 9. Sector of economy in which you would like to work (public; nonprofit; private) | Nominal |
| 10. Hours of overtime per week | Interval |
| 11. Your comprehension of this book (great; adequate; forget it) | Ordinal |
| 12. Number of memberships in clubs or associations | |
| 13. Dollars donated to nonprofit organization | |
| 14. Perceived success of animal rights association in advocacy (very high; high; moderate; low; very low) | |
| 15. Years of experience as a supervisor | |
| 16. Your evaluation of the level of “social capital” of your community (very low; low; moderate; high; very high) |
26
Measurement
Measurement levels – application:
MBB Table 2.5 (p. 27):
1/16/2017
Gary W. Reinbold, Ph.D., J.D.
University of Illinois at Springfield
15
| Variable | Level of Measurement |
| 1. Number of children | Interval |
| 2. Opinion of the way the president is handling the economy (strongly approve; approve; neutral; disapprove; st. disapprove) | Ordinal |
| 3. Age | Interval |
| 4. State of residence | Nominal |
| 5. Mode of transportation to work | Nominal |
| 6. Perceived income (very low; below average; average; above average; very high) | Ordinal |
| 7. Income in dollars | Interval |
| 8. Interest in statistics (low; medium; high) | Ordinal |
| 9. Sector of economy in which you would like to work (public; nonprofit; private) | Nominal |
| 10. Hours of overtime per week | Interval |
| 11. Your comprehension of this book (great; adequate; forget it) | Ordinal |
| 12. Number of memberships in clubs or associations | Interval |
| 13. Dollars donated to nonprofit organization | |
| 14. Perceived success of animal rights association in advocacy (very high; high; moderate; low; very low) | |
| 15. Years of experience as a supervisor | |
| 16. Your evaluation of the level of “social capital” of your community (very low; low; moderate; high; very high) |
27
Measurement
Measurement levels – application:
MBB Table 2.5 (p. 27):
1/16/2017
Gary W. Reinbold, Ph.D., J.D.
University of Illinois at Springfield
15
| Variable | Level of Measurement |
| 1. Number of children | Interval |
| 2. Opinion of the way the president is handling the economy (strongly approve; approve; neutral; disapprove; st. disapprove) | Ordinal |
| 3. Age | Interval |
| 4. State of residence | Nominal |
| 5. Mode of transportation to work | Nominal |
| 6. Perceived income (very low; below average; average; above average; very high) | Ordinal |
| 7. Income in dollars | Interval |
| 8. Interest in statistics (low; medium; high) | Ordinal |
| 9. Sector of economy in which you would like to work (public; nonprofit; private) | Nominal |
| 10. Hours of overtime per week | Interval |
| 11. Your comprehension of this book (great; adequate; forget it) | Ordinal |
| 12. Number of memberships in clubs or associations | Interval |
| 13. Dollars donated to nonprofit organization | Interval |
| 14. Perceived success of animal rights association in advocacy (very high; high; moderate; low; very low) | |
| 15. Years of experience as a supervisor | |
| 16. Your evaluation of the level of “social capital” of your community (very low; low; moderate; high; very high) |
28
Measurement
Measurement levels – application:
MBB Table 2.5 (p. 27):
1/16/2017
Gary W. Reinbold, Ph.D., J.D.
University of Illinois at Springfield
15
| Variable | Level of Measurement |
| 1. Number of children | Interval |
| 2. Opinion of the way the president is handling the economy (strongly approve; approve; neutral; disapprove; st. disapprove) | Ordinal |
| 3. Age | Interval |
| 4. State of residence | Nominal |
| 5. Mode of transportation to work | Nominal |
| 6. Perceived income (very low; below average; average; above average; very high) | Ordinal |
| 7. Income in dollars | Interval |
| 8. Interest in statistics (low; medium; high) | Ordinal |
| 9. Sector of economy in which you would like to work (public; nonprofit; private) | Nominal |
| 10. Hours of overtime per week | Interval |
| 11. Your comprehension of this book (great; adequate; forget it) | Ordinal |
| 12. Number of memberships in clubs or associations | Interval |
| 13. Dollars donated to nonprofit organization | Interval |
| 14. Perceived success of animal rights association in advocacy (very high; high; moderate; low; very low) | Ordinal |
| 15. Years of experience as a supervisor | |
| 16. Your evaluation of the level of “social capital” of your community (very low; low; moderate; high; very high) |
29
Measurement
Measurement levels – application:
MBB Table 2.5 (p. 27):
1/16/2017
Gary W. Reinbold, Ph.D., J.D.
University of Illinois at Springfield
15
| Variable | Level of Measurement |
| 1. Number of children | Interval |
| 2. Opinion of the way the president is handling the economy (strongly approve; approve; neutral; disapprove; st. disapprove) | Ordinal |
| 3. Age | Interval |
| 4. State of residence | Nominal |
| 5. Mode of transportation to work | Nominal |
| 6. Perceived income (very low; below average; average; above average; very high) | Ordinal |
| 7. Income in dollars | Interval |
| 8. Interest in statistics (low; medium; high) | Ordinal |
| 9. Sector of economy in which you would like to work (public; nonprofit; private) | Nominal |
| 10. Hours of overtime per week | Interval |
| 11. Your comprehension of this book (great; adequate; forget it) | Ordinal |
| 12. Number of memberships in clubs or associations | Interval |
| 13. Dollars donated to nonprofit organization | Interval |
| 14. Perceived success of animal rights association in advocacy (very high; high; moderate; low; very low) | Ordinal |
| 15. Years of experience as a supervisor | Interval |
| 16. Your evaluation of the level of “social capital” of your community (very low; low; moderate; high; very high) |
30
Measurement
Measurement levels – application:
MBB Table 2.5 (p. 27):
1/16/2017
Gary W. Reinbold, Ph.D., J.D.
University of Illinois at Springfield
15
| Variable | Level of Measurement |
| 1. Number of children | Interval |
| 2. Opinion of the way the president is handling the economy (strongly approve; approve; neutral; disapprove; st. disapprove) | Ordinal |
| 3. Age | Interval |
| 4. State of residence | Nominal |
| 5. Mode of transportation to work | Nominal |
| 6. Perceived income (very low; below average; average; above average; very high) | Ordinal |
| 7. Income in dollars | Interval |
| 8. Interest in statistics (low; medium; high) | Ordinal |
| 9. Sector of economy in which you would like to work (public; nonprofit; private) | Nominal |
| 10. Hours of overtime per week | Interval |
| 11. Your comprehension of this book (great; adequate; forget it) | Ordinal |
| 12. Number of memberships in clubs or associations | Interval |
| 13. Dollars donated to nonprofit organization | Interval |
| 14. Perceived success of animal rights association in advocacy (very high; high; moderate; low; very low) | Ordinal |
| 15. Years of experience as a supervisor | Interval |
| 16. Your evaluation of the level of “social capital” of your community (very low; low; moderate; high; very high) | Ordinal |
31
Sample Problem
MBB Problem 2.9: The director of the Art Institute would like to present some data on the size of donations in this year’s annual report. He selects the following four categories to summarize donations:
Friend of the Institute ($25 to $99)
Silver Member ($100 to $249)
Gold Member ($250 to $499)
Platinum Member ($500 and above)
To get a sense of what the data will look like, the director gives you a sample of donations measured at the interval level and asks you to apply the coding scheme. Create an ordinal-level variable for donations using the data below.
1/16/2017
Gary W. Reinbold, Ph.D., J.D.
University of Illinois at Springfield
16
32
Sample Problem
MBB Problem 2.9 (cont.):
Friend of the Institute ($25 to $99)
Silver Member ($100 to $249)
Gold Member ($250 to $499)
Platinum Member ($500 and above)
Create an ordinal-level variable for donations using the data below.
1/16/2017
Gary W. Reinbold, Ph.D., J.D.
University of Illinois at Springfield
17
| Interval Version (in $) | Ordinal Version |
| 25 | |
| 150 | |
| 75 | |
| 450 | |
| 100 | |
| 750 | |
| 90 | |
| 175 | |
| 250 | |
| 50 |
33
Sample Problem
MBB Problem 2.9 (cont.):
Friend of the Institute ($25 to $99)
Silver Member ($100 to $249)
Gold Member ($250 to $499)
Platinum Member ($500 and above)
Create an ordinal-level variable for donations using the data below.
1/16/2017
Gary W. Reinbold, Ph.D., J.D.
University of Illinois at Springfield
17
| Interval Version (in $) | Ordinal Version |
| 25 | 1 |
| 150 | |
| 75 | |
| 450 | |
| 100 | |
| 750 | |
| 90 | |
| 175 | |
| 250 | |
| 50 |
34
Sample Problem
MBB Problem 2.9 (cont.):
Friend of the Institute ($25 to $99)
Silver Member ($100 to $249)
Gold Member ($250 to $499)
Platinum Member ($500 and above)
Create an ordinal-level variable for donations using the data below.
1/16/2017
Gary W. Reinbold, Ph.D., J.D.
University of Illinois at Springfield
17
| Interval Version (in $) | Ordinal Version |
| 25 | 1 |
| 150 | 2 |
| 75 | |
| 450 | |
| 100 | |
| 750 | |
| 90 | |
| 175 | |
| 250 | |
| 50 |
35
Sample Problem
MBB Problem 2.9 (cont.):
Friend of the Institute ($25 to $99)
Silver Member ($100 to $249)
Gold Member ($250 to $499)
Platinum Member ($500 and above)
Create an ordinal-level variable for donations using the data below.
1/16/2017
Gary W. Reinbold, Ph.D., J.D.
University of Illinois at Springfield
17
| Interval Version (in $) | Ordinal Version |
| 25 | 1 |
| 150 | 2 |
| 75 | 1 |
| 450 | |
| 100 | |
| 750 | |
| 90 | |
| 175 | |
| 250 | |
| 50 |
36
Sample Problem
MBB Problem 2.9 (cont.):
Friend of the Institute ($25 to $99)
Silver Member ($100 to $249)
Gold Member ($250 to $499)
Platinum Member ($500 and above)
Create an ordinal-level variable for donations using the data below.
1/16/2017
Gary W. Reinbold, Ph.D., J.D.
University of Illinois at Springfield
17
| Interval Version (in $) | Ordinal Version |
| 25 | 1 |
| 150 | 2 |
| 75 | 1 |
| 450 | 3 |
| 100 | |
| 750 | |
| 90 | |
| 175 | |
| 250 | |
| 50 |
37
Sample Problem
MBB Problem 2.9 (cont.):
Friend of the Institute ($25 to $99)
Silver Member ($100 to $249)
Gold Member ($250 to $499)
Platinum Member ($500 and above)
Create an ordinal-level variable for donations using the data below.
1/16/2017
Gary W. Reinbold, Ph.D., J.D.
University of Illinois at Springfield
17
| Interval Version (in $) | Ordinal Version |
| 25 | 1 |
| 150 | 2 |
| 75 | 1 |
| 450 | 3 |
| 100 | 2 |
| 750 | |
| 90 | |
| 175 | |
| 250 | |
| 50 |
38
Sample Problem
MBB Problem 2.9 (cont.):
Friend of the Institute ($25 to $99)
Silver Member ($100 to $249)
Gold Member ($250 to $499)
Platinum Member ($500 and above)
Create an ordinal-level variable for donations using the data below.
1/16/2017
Gary W. Reinbold, Ph.D., J.D.
University of Illinois at Springfield
17
| Interval Version (in $) | Ordinal Version |
| 25 | 1 |
| 150 | 2 |
| 75 | 1 |
| 450 | 3 |
| 100 | 2 |
| 750 | 4 |
| 90 | |
| 175 | |
| 250 | |
| 50 |
39
Sample Problem
MBB Problem 2.9 (cont.):
Friend of the Institute ($25 to $99)
Silver Member ($100 to $249)
Gold Member ($250 to $499)
Platinum Member ($500 and above)
Create an ordinal-level variable for donations using the data below.
1/16/2017
Gary W. Reinbold, Ph.D., J.D.
University of Illinois at Springfield
17
| Interval Version (in $) | Ordinal Version |
| 25 | 1 |
| 150 | 2 |
| 75 | 1 |
| 450 | 3 |
| 100 | 2 |
| 750 | 4 |
| 90 | 1 |
| 175 | |
| 250 | |
| 50 |
40
Sample Problem
MBB Problem 2.9 (cont.):
Friend of the Institute ($25 to $99)
Silver Member ($100 to $249)
Gold Member ($250 to $499)
Platinum Member ($500 and above)
Create an ordinal-level variable for donations using the data below.
1/16/2017
Gary W. Reinbold, Ph.D., J.D.
University of Illinois at Springfield
17
| Interval Version (in $) | Ordinal Version |
| 25 | 1 |
| 150 | 2 |
| 75 | 1 |
| 450 | 3 |
| 100 | 2 |
| 750 | 4 |
| 90 | 1 |
| 175 | 2 |
| 250 | |
| 50 |
41
Sample Problem
MBB Problem 2.9 (cont.):
Friend of the Institute ($25 to $99)
Silver Member ($100 to $249)
Gold Member ($250 to $499)
Platinum Member ($500 and above)
Create an ordinal-level variable for donations using the data below.
1/16/2017
Gary W. Reinbold, Ph.D., J.D.
University of Illinois at Springfield
17
| Interval Version (in $) | Ordinal Version |
| 25 | 1 |
| 150 | 2 |
| 75 | 1 |
| 450 | 3 |
| 100 | 2 |
| 750 | 4 |
| 90 | 1 |
| 175 | 2 |
| 250 | 3 |
| 50 |
42
Sample Problem
MBB Problem 2.9 (cont.):
Friend of the Institute ($25 to $99)
Silver Member ($100 to $249)
Gold Member ($250 to $499)
Platinum Member ($500 and above)
Create an ordinal-level variable for donations using the data below.
1/16/2017
Gary W. Reinbold, Ph.D., J.D.
University of Illinois at Springfield
17
| Interval Version (in $) | Ordinal Version |
| 25 | 1 |
| 150 | 2 |
| 75 | 1 |
| 450 | 3 |
| 100 | 2 |
| 750 | 4 |
| 90 | 1 |
| 175 | 2 |
| 250 | 3 |
| 50 | 1 |
43
Sample Problem
MBB Problem 2.11: The Wildlife Conservation Center has put together a database to keep track of the attributes of its employees. Specifically, numerical codes are assigned to variables as follows:
Gender 1 = female 2 = male
Job Status 1 = full time 2 = part time
Job Description 1 = professional 2 = administrative 3 = general labor
Use the variable codes above to describe in words the attributes of each employee.
Employee 1 is a female, full-time professional
Employee 2 is a male, full-time general laborer
Employee 3 is a female, part-time, administrator
1/16/2017
Gary W. Reinbold, Ph.D., J.D.
University of Illinois at Springfield
18
| Employee | Gender | Job Status | Job Description |
| 1 | 1 | 1 | 1 |
| 2 | 2 | 1 | 3 |
| 3 | 1 | 2 | 2 |
| 4 | 2 | 1 | 2 |
| 5 | 1 | 2 | 1 |
| 6 | 1 | 2 | 1 |
| 7 | 2 | 2 | 3 |
| 8 | 1 | 1 | 3 |
44
Research Design
MBB: Chapter 3, pp. 42-66
1/16/2017
Gary W. Reinbold, Ph.D., J.D.
University of Illinois at Springfield
19
45
Research Design
Causal explanations – key terms:
Concept: summarizes the critical aspects in a class of events
Effectiveness, seniority, expertise, resources are concepts
Nominal or conceptual definition: defines a concept in terms of other concepts
Effectiveness might be defined as how well an agency uses its resources to achieve its goals
Operational definition: describes how a concept will be measured
You might measure effectiveness as the number of clients served by an agency per dollar of budget
Dependent variable: the variable you are trying to explain changes or variation in
Independent variable: a variable that might affect the dependent variable
Graphically:
1/16/2017
Gary W. Reinbold, Ph.D., J.D.
University of Illinois at Springfield
20
Independent Variable
Dependent Variable
46
Research Design
Causal explanations – key terms:
Hypothesis: proposes a relationship between an independent variable and a dependent variable
Positive relationship: independent variable and dependent variable move in the same direction
A person’s income is positively related to their health
Negative (or inverse) relationship: independent variable and dependent variable move in opposite directions
The number of hours that a person works is negatively related to their leisure time
Theory: integrated set of propositions intended to explain a given phenomenon
Assumption: an untested proposition
Often assume that people will continue to behave the same as in the past
Model: simplified version of a theory used for empirical testing
Often presented graphically, with arrows to show independent and dependent variables and plus and minus signs to show positive and negative relationships
1/16/2017
Gary W. Reinbold, Ph.D., J.D.
University of Illinois at Springfield
21
47
Research Design
Causal explanations – key concepts:
Rules for conceptual definitions:
Cannot define a concept in terms of itself
Should define what a concept is, not what it is not
Should not deviate from prior definitions of the concept without good reason
Requirements for a good hypothesis:
The concepts and the variables must be measurable
Must precisely state the proposed relationship between the independent and dependent variables (including the direction, in most cases)
1/16/2017
Gary W. Reinbold, Ph.D., J.D.
University of Illinois at Springfield
22
48
Research Design
Causal relationships – key concepts:
Criteria to establish a causal relationship:
Time order – the independent variable must happen before the dependent variable
Covariation – the independent variable must vary together with the dependent variable
Nonspuriousness – the covariation between the independent variable and dependent variable can’t be explained by other variables
Theory-based – the relationship between the independent variable and dependent variable must be explained by a theory
1/16/2017
Gary W. Reinbold, Ph.D., J.D.
University of Illinois at Springfield
23
49
Research Design
Causal relationships – key concepts:
Multiple causation:
Most dependent variables are affected by more than one independent variable
So, the relationship between an independent variable and a dependent variable may be partially spurious and partially nonspurious
This means that models can be complicated
Statistical techniques are used to determine how much of the relationship between an independent variable and a dependent variable is nonspurious
1/16/2017
Gary W. Reinbold, Ph.D., J.D.
University of Illinois at Springfield
24
50
Research Design
Research design – key terms:
Research design: systematic program for empirically evaluating proposed causal relationships that guides the collection, analysis, and interpretation of relevant data
Internal validity: whether the independent variable had a causal effect on the dependent variable in that one particular study
External validity: whether results from a particular study might hold true in other settings, time periods, and populations
1/16/2017
Gary W. Reinbold, Ph.D., J.D.
University of Illinois at Springfield
25
51
Research Design
Research design – key terms:
Experimental research design: randomizes subjects into an experimental group that receives the treatment and a control group that doesn’t, with measurement of the dependent variable pretest and posttest
Quasi-experimental research design: typically lacks randomization of subjects and/or pretest measurement
Random assignment: the process of randomly assigning subjects to experimental and control groups
1/16/2017
Gary W. Reinbold, Ph.D., J.D.
University of Illinois at Springfield
26
52
Research Design
Research design – key concepts:
Threats to internal validity in experimental research design:
Can usually establish time order and covariation
May be more difficult to establish nonspuriousness:
Subjects in both groups may show changes in the dependent variable over time for reasons unrelated to changes in the independent variable
The two groups may be initially different in a way that affects changes in the dependent variable (selection bias)
Subjects assigned to one group may move to the other group (crossover)
Subjects in the experimental group may drop out of extended treatments (attrition)
1/16/2017
Gary W. Reinbold, Ph.D., J.D.
University of Illinois at Springfield
27
53
Research Design
Research design – key concepts:
Threats to external validity in experimental research designs:
The context of a controlled experiment may be different than real world conditions
Subjects that have been pretested may behave differently than other subjects
Research subjects usually consist of unnatural populations, like students, hospital patients, or prisoners
1/16/2017
Gary W. Reinbold, Ph.D., J.D.
University of Illinois at Springfield
28
54
Research Design
Research design – key concepts:
Types of quasi-experimental research designs:
Cross-sectional studies:
Measure subjects at only one point in time
Always lack pretest measures
Usually also lack randomization of subjects
Case studies:
In-depth examination of a few subjects
Usually lacks randomization of subjects
Panel studies:
Measures same subjects repeatedly over time
Usually lack randomization of subjects
1/16/2017
Gary W. Reinbold, Ph.D., J.D.
University of Illinois at Springfield
29
55
Research Design
Research design – key concepts:
Types of quasi-experimental research designs:
Trend studies:
Measure the same indicators repeatedly over time, but with different subjects
Usually lack both pretest measures and randomization of subjects
Mixed research designs:
Combine elements from multiple research designs
1/16/2017
Gary W. Reinbold, Ph.D., J.D.
University of Illinois at Springfield
30
56
Research Design
Research design – key concepts:
Internal validity in quasi-experimental research designs:
Many statistical methods to establish covariation
May be more difficult to establish covariation in case studies, due to smaller number of subjects
Can establish time order in panel studies and trend studies
Can usually establish time order in case studies that follow subjects over time
Can only argue that time order is satisfied in cross-sectional studies
Can use statistical methods to control for other variables to attempt to establish nonspuriousness
But ultimately can only argue that nonspuriousness is satisfied
Even more difficult to establish nonspuriousness in case studies
1/16/2017
Gary W. Reinbold, Ph.D., J.D.
University of Illinois at Springfield
31
57
Research Design
Research design – key concepts:
External validity in quasi-experimental research designs:
Usually stronger than in experimental designs:
Can use samples that are representative of larger populations
Usually conducted in real world settings
But subjects in panel studies may change their behavior due to the repeated measurements
Case studies are usually more difficult to generalize
1/16/2017
Gary W. Reinbold, Ph.D., J.D.
University of Illinois at Springfield
32
58
Research Design
Research design – key concepts:
Often a tradeoff between internal and external validity
Adding more structure improves internal validity, but decreases external validity
Some methods can increase both internal and external validity:
Using larger samples
Replicating the same study with different samples
Using mixed research designs
Difficult to convincingly establish a causal relationship
1/16/2017
Gary W. Reinbold, Ph.D., J.D.
University of Illinois at Springfield
33
59
Sample Problem
MBB Problem 3.1 (modified): A researcher asserts that the relationship between attitude toward the field of public administration and taking courses in a public administration degree program is causal.
(a) What are the concepts involved in the researcher’s assertion?
The concepts are the italicized terms:
Attitude toward the field of public administration
Taking courses in a public administration program
1/16/2017
Gary W. Reinbold, Ph.D., J.D.
University of Illinois at Springfield
34
60
Sample Problem
A researcher asserts that the relationship between attitude toward the field of public administration and taking courses in a public administration degree program is causal.
(b) What indicators is the researcher using to measure those concepts?
The question doesn’t say what the indicators are
For attitude toward the field, you would probably use one or more survey questions with an ordinal-level scale (strongly negative, negative, neutral, positive, strongly positive)
For taking courses in a PA program, you could use an interval-level variable of the number of courses taken, or you could just use a nominal-level, yes-or-no variable for whether the person has taken any courses
1/16/2017
Gary W. Reinbold, Ph.D., J.D.
University of Illinois at Springfield
35
61
Sample Problem
A researcher asserts that the relationship between attitude toward the field of public administration and taking courses in a public administration degree program is causal.
(c) What evidence must the researcher provide about this relationship to prove that it is causal?
The researcher would need to provide evidence relating to:
Time order – that taking courses in a PA program comes before a change in the person’s attitude toward the field
Covariation – that people who take courses in a PA program generally have more positive attitudes toward the field
Nonspuriousness – that there aren’t any other significant variables that could explain the change in the person’s attitude – such as aging or education generally
Theory-based – that a theory explains why people who take courses in a PA program should have more positive attitudes toward the field
1/16/2017
Gary W. Reinbold, Ph.D., J.D.
University of Illinois at Springfield
36
62
Sample Problem
A researcher asserts that the relationship between attitude toward the field of public administration and taking courses in a public administration degree program is causal.
(d) Given your answer, what aspects of the researcher’s argument are likely to be strongest, and what aspects of her argument are likely to be weakest?
Theory-based seems easy to establish, because people who learn more about any field might be expected to have more positive attitudes about it
Time order would also be relatively easy – you could just survey students before they start a PA program and then again after they complete the program
Covariation would also be easy then – you could just compare the survey results before and after the program to see if students’ attitudes changed
Nonspuriousness would be most difficult (as usual) –the change in attitude could be related to education or aging generally. To rule those possibilities out, you would need data on another group of similar students in other degree programs, so you could compare the changes between groups. Of course, the students who decided to study PA might already have been developing more positive attitudes toward the field and might have continued to do so even without taking any courses – there wouldn’t be any easy way to rule that possibility out.
1/16/2017
Gary W. Reinbold, Ph.D., J.D.
University of Illinois at Springfield
37
63
Sample Problem
MBB Problem 3.3: Professor George A. Buldogski has taught social graces to athletic teams at a major southeastern university for the past 15 years. Based on this experience, he insists that table manners are causally related to leadership. Professor Buldogski has data showing that athletes who have better table manners also demonstrate greater leadership in athletic competition. The university gymnastics coach, who wants to build leadership on her team, is considering asking Professor Buldogski to meet regularly with her team. She hopes that after he teaches table manners to team members, they will become better leaders. Should she invite Professor Buldogski to meet with the gymnastics team?
So the question is whether learning better table manners results in better leadership skills. To answer that question, you would need to consider the four factors:
Time order – Buldogski’s data don’t seem to address this issue. The athletes might have had better leadership skills before they had better table manners.
Covariation – Buldogski’s data do address this issue, as they show that better table manners are correlated with better leadership skills
Nonspuriousness – Buldogski’s data don’t address this issue and it would be very difficult to rule this out without a randomized study. There are a lot of background factors that might cause people to both have better table manners and better leadership skills.
Theory-based – Buldogski probably has a theory to support his hypothesis, such as that athletes who learn better table manners become more confident, which results in better leadership skills
So, you probably shouldn’t invite Buldogski to meet with the team – it isn’t at all clear from his data that learning better table manners results in better leadership skills
1/16/2017
Gary W. Reinbold, Ph.D., J.D.
University of Illinois at Springfield
38
64
Sample Problem
MBB Problem 3.5: The head of the Teen Intervention Center believes that troubled youth are not getting the message if they complete the center’s 5-week education program but still have subsequent encounters with law enforcement. When they first come to the center, teens are broken up into groups of 15 to meet with a counselor and answer questions about what society defines as acceptable versus unacceptable behaviors.
(a) If you were the head of counseling at the center, what knowledge might you gain by asking each group of teens similar questions at the end of the 5-week program?
You could see whether the teens’ answers changed as a result of the program, although you wouldn’t know if those changes would result in any behavior changes. Also, you could see whether there were any differences in those changes across counselors. Maybe some counselors are more effective than others.
1/16/2017
Gary W. Reinbold, Ph.D., J.D.
University of Illinois at Springfield
39
65
Sample Problem
The head of the Teen Intervention Center believes that troubled youth are not getting the message if they complete the center’s 5-week education program but still have subsequent encounters with law enforcement. When they first come to the center, teens are broken up into groups of 15 to meet with a counselor and answer questions about what society defines as acceptable versus unacceptable behaviors.
(b) Is there any reason to expect different responses to the initial questions and those asked at the end of the program?
If the program is effective, you would expect the teens to have a better understanding of what is acceptable and unacceptable after they complete the program. Of course, other factors might also cause changes in the responses – teens might respond differently the second time just because they’ve heard the question before and have had more time to think about it.
1/16/2017
Gary W. Reinbold, Ph.D., J.D.
University of Illinois at Springfield
40
66
Sample Problem
The head of the Teen Intervention Center believes that troubled youth are not getting the message if they complete the center’s 5-week education program but still have subsequent encounters with law enforcement. When they first come to the center, teens are broken up into groups of 15 to meet with a counselor and answer questions about what society defines as acceptable versus unacceptable behaviors.
(c) What type of research design would you be using if you administered a questionnaire to the same group of individuals at the outset of treatment, at the end of treatment, and 6 months after treatment?
That would be a panel study – you’re collecting data on the same variables from the same people at multiple points in time.
1/16/2017
Gary W. Reinbold, Ph.D., J.D.
University of Illinois at Springfield
41
67
