Chapter Four

1
Chapter Four

• Research Design and Implementation - 2

2
Four types of Data

• Alphabetical / Categorical / Nominal data
• Information falls only in certain categories, not
  in-between categories
• No inferences possible between groups except that
  one group may contain more / less observations
  than the other
• Only reporting frequencies, percentages and mode
  makes sense (descriptive statistics)
• Chi Square measure of Association (inferential
  Statistics)
• Examples gender, age groups, income groups, etc.

3
Four types of data

• Rank order data
• Ranked according to some logic, e.g. preference,
  etc.
• Again an in-between rank does not make sense.
• Difference between say rank 1 and 2 need not
  necessarily be of the same magnitude as the
  difference between rank 3 and 4.
• Only reporting frequencies, percentages and mode
  makes sense (descriptive statistics) Spearman
  Rho coefficient of correlation (Inferential
  statistics)
• Examples brand preferences, class rank on test,
  etc.

4
Four types of data

• Interval Level
• Numerical data in which the numbers denote the
  amount of presence / absence of a trait.
• zero point does not necessarily mean complete
  absence of the trait
• In-between numbers make sense
• Magnitude of difference between numbers on the
  scale is constant.
• All descriptive and inferential statistics
  possible
• Examples attitude, satisfaction, temperature,
  etc.

5
Four types of data

• Ratio level data
• Interval level data with a meaningful zero point
  meaning complete absence of the trait
• Magnitude of the difference between numbers of
  the scale is constant AND the zero point denotes
  complete absence of the trait being measured.
• All descriptive and inferential statistics
  possible
• Examples sales, profits, weight, height, etc.

6
Type of data?
Age in years Recall order of brands
Age groups Ad. costs
Income Number of students in various classes
Income groups Time
Name Test grades
SAT scores Number of players in a team
Attitude to brand Number of students in WU
Number of ads recalled Calories
7
Data Collection Methods

• Table 4-2
• Relationship between Data Collection Method and
• Category of Research
• Category of Research
• Data Collection Method Exploratory
  Descriptive Causal
• Secondary Sources
• Information System a b
• Databanks of other a b
• organizations
• Syndicated Services a b b
• Primary Sources
• Qualitative Research a b
• Surveys b a b
• Experiments b a

8
Research Tactics

• Measurement Generally what questions do we ask
  so that we get the information we want
• Sampling Plan How do we select a sample for the
  study such that we maximize its chances of
  faithfully representing the population of
  interest
• Analysis confirming that all information being
  obtained is appropriate and adequate for
  addressing the RQ / hypothesis

9
Errors in Research Design

• Assume you are interested in knowing what
  Winthrop undergrad students feel about the
  quality of the faculty
• What is the population? Size?
• Assume you take a sample of 100 students and find
  the sample mean
• Would your sample mean match the population mean?
• If not, what is the difference?

10
Errors in Research Design

• Assume you get a mean figure of 4.0 on a 1 (low
  quality) to 5 (high quality) scale
• The population mean is an unknown figure
• Always wise to acknowledge that it may different
  from the sample mean
• assume it is 4.5
• The difference of 0.5 (4.5 4.0) is the total
  error in the research design

11
Errors in Research design

• Sampling errors difference between measure
  obtained from the sample and true measure
  obtained from the population from which the
  sample is drawn (assuming random sampling is
  used)
• Non-sampling errors
• Design errors
• Administering errors
• Response errors
• Non-response errors

12
Non-sampling errors Design Errors

• Selection errors biased sample selection
• E.g. you may have used a convenience sample
• Population specification error drawing a sample
  from the wrong population
• E.g. Did you accidentally include even graduate
  students?

13
Non-sampling errors Design Errors

• Sampling frame error using inaccurate sampling
  frame to create the sample
• E.g. Did the list of students you took from the
  university include even those who were not
  active, recently graduated, etc?
• Surrogate information error difference between
  information required for the study and what the
  researcher seeks
• E.g. The study required a measure of quality of
  faculty but your question asked how much do you
  like the faculty at Winthrop

14
Non-sampling errors Design Errors

• Measurement error difference between
  information sought by the researcher and
  information generated by a particular measurement
  procedure used by the researcher
• E.g. You wanted a measure of quality you chose
  to measure that by finding out how quickly each
  instructors classes closed during registration.
• Problems?

15
Non-sampling errors Design Errors

• Experimental error improper experimental design
• PREs (History, maturation, etc. need to be
  controlled)
• Data Analysis error e.g. wrong data coding or
  wrong statistical analysis
• Mistakes made while entering data into Excel /
  SPSS and using the wrong statistical procedure
  e.g. using the median instead of the mean

16
Non-sampling errors Administering Errors

• Questioning error incorrect phrasing of
  questions to respondents
• Did you say quality of faculty or quality of
  teaching?
• Recording error improperly recording the
  respondents answers
• Did you hear 5 when the respondent mentioned
  4?
• Interference error does not follow the exact
  procedure while collecting data
• Did you forget to say your responses will remain
  anonymous before asking the question?
• Problems?

17
Non-sampling errors Response Errors

• Respondent supplies (intentionally or
  unintentionally) incorrect answers to questions
• Does not understand the question
• Quality? Quality of what teaching, research,
  advising, etc.?)
• Fatigue or boredom
• Did you catch the respondent after a long hard
  day?

18
Non-sampling errors Response Errors

• Unwillingness to give information
• Did you tell the respondent that his/hers was the
  last questionnaire and that he/she had to supply
  the data?
• Social desirability bias
• Did the respondent want to project a favorable
  picture of him/herself?

19
Non-sampling errors Non-Response Errors

• Respondents who did not respond may think
  differently on the issue
• Did you do your survey during the Spring Break?
• Some members of the sample may have provided
  incomplete information
• Was your questionnaire too long and boring so a
  few dropped it after a while and left it
  incomplete?

20
RESEARCH DESIGN PROCESS
Compare Cost and Timing Estimates
with Anticipated Value Proceed
Terminate
Revise
Implementation
Data Collection and Analysis Data
collection Field work Data
processing Data analysis Statistical
analysis Interpretation
Conclusions and Recommendations