Discussion Questions

1. Describe different data sources, explaining their usefulness and disadvantages.

Secondary sources of data constitute all available sources from which existing information can be
extracted. This could be published or unpublished information in the Library, in Government or Company
records, in data tapes, on the internet, etc. Primary sources of data can be any source which provides
information elicited directly for the first time. This could be organizations, individuals, trash cans, or
whatever source from which the desired information can be obtained. Secondary data sources are useful
because they offer a base on which to build further research without having to reinvent the wheel. Past
findings can spur new research; past data can also offer opportunities to analyze them from a different
perspective or angle. Under certain circumstances, however, secondary data might be misleading if one
does not take the changed circumstances into consideration.
For example, if old archives of national data are utilized to examine and draw conclusions about
gender differences at the workplace, this might become an exercise in futility. The workplace has changed
much now compared to 20 years ago – there are more educated career women, their aspirations are
different, their current expectations of life are in contrast to what they were two decades ago, etc. As such,
one has to be cautious while using secondary data sources. Primary data will offer more correct and
up‐to‐date information when phenomena are investigated. However, it costs more to collect fresh data,
access to organizations is not always readily obtained, and people knowledgeable in research have to be
co‐ opted. Generally, data collected through unobtrusive methods are more reliable than data gathered
through surveys.

2. As a manager, you have invited a research team to come in, study, and offer suggestions on how
to improve the performance of your staff. What steps would you take to allay their apprehensions
even before the research team sets foot in your department?
As the manager, I would inform the employees of the Department, in a meeting called for the
purpose, that unless we can turn around and make some profits, the organization may have to lay off
people. Since management does not see laying off personnel as an acceptable solution, at least at this
stage, we are inviting outside experts to examine our operations and give us some ideas on how we may
be able to increase our profits. If we all cooperate with the research team that will be coming in shortly,
and provide them with whatever information they might need, it would help the company to implement
the steps and processes necessary to increase output, make a profit, and retain the current employees.
3. What is bias and how can it be reduced while interviewing?
Bias is any error that creeps into the information gathered. Biases occur whenever incorrect
information is provided to the researcher by whoever offers the information. Sometimes, genuine
mistakes might be made and hence incorrect information could be provided. However, biases frequently
occur because the researcher phrases the question in a particular way, inflects the voice in a particular
manner, or simply because the respondent, zealous of pleasing the researcher, provides an answer that the
individual believes is what the researcher would like to hear, even though it is not factual.
Bias can be reduced in interviewing by choosing the appropriate environment in which the
interview is conducted, by establishing trust with the respondent, by phrasing questions so that they do
not lead the interviewee to respond in a particular manner, by clarifying issues when the respondent
seems confused, by not coming across as evaluative or judgmental, and by not placing special emphasis
on specific words.

4. Explain the principles of wording, stating how these are important in questionnaire design, citing
examples not in the book.
a. The wording of the question and the level of sophistication of the language used are important. These
are important because, if the respondent does not understand the words, obviously, he or she is not
going to be able to respond to the questions. An underground coal miner and a top business executive
 may need to be asked some of the same issues differently. Thus, using words that fit the level of
sophistication of understanding of the respondent is necessary. To take an extreme example, to assess
the experienced quality of family life, a poorly educated farm hand may be first asked to list the
activities he normally engages in when he gets home from work, and then asked to rate the extent of
satisfaction gained from each of these activities. An index of quality of family life might then be
calculated by examining the family‐related activities listed by the respondent. With a business
executive, on the other hand, the same concept can be tapped by asking the individual to rate his or
her satisfaction to questions such as: Balance between work and family life; the impact of travelling
on experiencing quality time with the family, and the like.
b. Both positively and negatively worded questions need to be asked in the questionnaire so that the
respondent does not mechanically answer the items without much mental engagement. For example,
if one question asks for the level of excitement that a particular advertisement evoked, another could
ask the extent to which that same advertisement seemed irrelevant. Obviously, when both are tapped
on the same scale, the response to both cannot be the same. This break in the way the questions are
worded, both positively and negatively, helps to enhance the attention span of the respondents who
might otherwise respond mechanically.
c. Double‐barreled questions should be avoided. If one asks the question, “Do you value and manage a
diverse workforce well”? there may be no clear response given to the question because one may value
a diverse workforce, but hardly know how to manage it! In such cases, it would be better to ask two
separate questions rather than one.
d. Ambiguous questions should also be avoided. Questions such as “Do you discuss your work with the
president regularly”? or “Do you go to the movies frequently”? are ambiguous, because the terms
regularly and frequently are left open to the interpretation of each respondent. One individual might
discuss work with the president on a daily basis, and another every six months. Both are “regularly”
(or at regular intervals) discussing work! But is this what the researcher is looking for? Similarly,
frequently going to the movies might mean one movie every week to one person, one movie every
month to another, and three times a week to a third person! Since these terms are not defined, biased
data will be procured from the respondents.
e. Recall‐dependent questions will also introduce biases. For example, not many people remember when
exactly they started smoking, or why they quit a particular school and joined another when they were
10 years old.
f. Leading questions also result in biased responses because the interviewee might be led to believe that
a particular type of answer is sought and might try to oblige the interviewer, even if the response is
not what the individual believes to be true. An example of a leading question is: Don’t you think that
more women should be promoted to decision‐making line positions in organizations? Such a question
is likely to elicit the obvious response, “Surely, Yes”!
g. Loaded questions should also be avoided because of the emotionality it invokes, thus eliciting biased
responses. As an example: “Don’t you think that the L.A.P.D. is biased against blacks?” is a question
with racial overtones which will bring forth emotional, rather than objective responses to the
question.
h. Questions invoking social desirability will also produce biased responses. An example would be to
ask if anyone felt that workforce diversity is bad for the system. In the context of the changing
demographics of the workforce, even if some felt that diversity at the workplace is disastrous, they
would tend not to disagree because it is not a socially acceptable response.
i. It is also important to avoid lengthy questions which might confuse the respondent and introduce
several types of bias. An example of a long question is: To what extent would asking for responses
from different groups of employees, such as for instance, production, marketing, R & D, advertising,
and sales, on such issues as the policy governing the organization, the organizational culture, staff
discipline and other related matters, provide valid data to the president, to enable him to make some
critical decisions on how to run the company effectively and efficiently?
5. What are projective techniques and how can they be profitably used?
Projective techniques help the respondent to offer answers to questions which might otherwise be
rather difficult or cumbersome to respond to. Projective methods which include such techniques as word
association, sentence completion, thematic apperception, and ink‐blot tests, usually tap the deep‐seated
motivations of the respondent and provide relevant answers to difficult questions. However, the responses
have to be analyzed by individuals well trained in interpreting the answers if they are to be meaningfully
utilized for research purposes. Marketing research can benefit substantially by using projective
techniques, as for example, in developing products, designing ads, and selecting appropriate media.

6. How are multiple methods of data collection from multiple sources related to reliability and
validity of the measures?
If there is convergence or strong correlation among the data obtained from different data
collection methods on the same variable, then one can establish convergent validity because the data
converge even when collected by different methods. The same holds true when there is a strong and
significant correlation between the data obtained on the same variable from different sources. Though
reliability cannot be directly assessed from multi‐methods or multi‐sources of data collection, usually,
since a valid instrument is reliable (though the converse may not necessarily be true), one can presume
reliability if validity is established through the multi‐trait, multi‐matrix method.

7. Every data collection method has its own built‐in biases. Therefore, resorting to multi‐methods of
data collection is only going to compound the biases. Critique this statement.
It is true that most data collection methods in the social sciences have their own built‐in biases.
For instance, interviews are susceptible to interviewer and respondent biases, observational data will have
observer and actor biases, and so on. But when data are collected through multiple methods and
compared, if the correlations among the several types of responses received through the different data
collection methods are high, we can be fairly confident that the data have good validity and reliability –
i.e. they are “good.” If the correlations are low, however, we would start wondering about the goodness of
our data. We would then pay closer attention to the methods used. For instance, if respondents say that
they experience a high level of meaningfulness in their jobs when they are interviewed, and when the
concept is measured through several items in the questionnaire, we would be inclined to treat these as
acceptable data even though both may have a low correlation to data obtained from a sentence completion
motivational research. If, however, there is no correlation at all among any of the methods, the goodness
of the data collected will be highly suspect.
Thus, multi‐methods of data collection help us to make certain judgments about the goodness of our data
and serves to make decisions on which sets of data may perhaps be more acceptable than others.

8. One way to deal with discrepancies found in the data obtained from multiple sources is to
average the figures and take the mean as the value on the variable. What is your reaction to this?
Wherever possible “objective” data, through unobtrusive methods, need to be obtained. For
instance, if an employee’s performance is to be measured, it is better to go through the person’s records
and evaluation forms of the superiors (in case more objective measures of output are not available).
However, such records are usually confidential in nature and are not likely to be made accessible to the
researcher.
Hence data will be sought from multiple sources–for example, from the subject, the co‐workers,
the immediate supervisor, other superiors, and perhaps even the subordinates. If there is not much
consistency in the data obtained through these various sources, there is no option left but to average these.
However, the researcher should point out the biases inherent in this and acknowledge this limitation in the
report.
9. How has the advancement of technology helped data gathering?
Hand‐held computers used in field interviews are very useful for collecting and recording
information from many individuals. The recorded information can be checked for accuracy the same day.
Electronic surveys by way of interviews or questionnaires, have the advantage of self correction in data,
in the sense that out of range responses etc., are automatically corrected on the spot, and skip patterns can
be conveniently applied. The only drawback is that people might ignore and not respond to electronic
surveys, and some may not have the requisite facilities.

10. How will you use the data from observational study to reach scientific conclusions?
Observational studies have been profitably used for providing descriptive information. However,
by categorizing the responses in a meaningful way, and also developing ordinal or Likert‐type scales
therefrom, (e.g. High Frequency to Low Frequency, etc.), scientific conclusions can be reached applying
parametric or non‐ parametric statistics, as appropriate.

11. The fewer the biases in measurement and in the data collection procedures, the more scientific
the research. Comment on this statement.
This observation is correct. When reliable and valid measures are used to tap concepts, and when
the data collection methods have less built‐in biases, we would have good data, provided that, of course,
the sample is representative. Thus, replicability, accuracy and precision, and generalizability, become
possible. The research then becomes more scientific.
Summary Previous Meeting + Previous Chapter

Types of variable
1. Dependent Variable
 For Example : Stock Return (Monthly)
Rs = Rf + βs (Rm – Rf)
2. Independent Variable
The example :
 Inflation : the data can be gotten in Bank Indonesia
 GDP : the data can be gotten in BPS
 Unemploy Rasio : can be gotten on BPS
3. Control Variable
 Currency Rate : can be gotten on BI
4. Mediating Variable / Moderating Variable
 Political Orientatim the example is infrasteucture, => can be proved by calculate ROA

Variable VS Construct
1. Variable =
- Vary,
- Change,
- Measureabl,
- Observable
- Calculable
Example :
 ROA
 ROE
 Auditors Ethics => can be used Likert Scale
2. Construct :
- Unobservable
CHAPTER 7
1. Scale
 The way we differ of one measurement toi the other measurement.
 There are four basic types of scales: nominal, ordinal, interval, and ratio.
a. Nominal Scale
One that allows the reseacher to assign subjects to certain catagories or groups.
For Example
 Gender : Male and Female
 Class : Teacher and Student
- nominal scales categorize individuals or objects into mutually exclusive and collectively
exhaustive groups.
b. Ordinal Scale
- An ordinal scale not only categorizes the variables in such a way as to denote differences
among the various categories, it also rank-orders the categories in some meaningful way.
For Example
 Level the quality of cleaning environment : 1. Best, 2. So So 3. Worst
-
c. Interval Scale
 - the interval scale not only groups individuals according to certain categories and taps the
order of these groups, it also measures the magnitude of the differences in the
preferences among the individuals.
- If, for instance, employees think that (1) it is more important for them to have a variety
of skills in their jobs than to complete a task from beginning to end, and (2) it is more
important for them to serve people than to work independently on the job, then the
interval scale would indicate whether the first preference is to the same extent, a lesser
extent, or a greater extent than the second.

d. Rasio Scale
- the ratio scale not only measures the magnitude of the differences between points on the
scale but also taps the proportions in the differences.
 Dichotomous Scale (It Means 2)
The dichotomous scale is used to elicit a Yes or No answer,
 The category scale
uses multiple items to elicit a single response as per the following example. This also uses the
nominal scale.
 The semantic differential scale
is used to assess respondents' attitudes toward a particular brand, advertisement, object, or
individual.
The bipolar adjectives used might employ such terms as Good–Bad; Strong–Weak; Hot–
Cold.
Responsive ———— Unresponsi
—— ve
Beautiful ———— Ugly
——
Courageous ———— Timid
——

 The numerical scale

is similar to the semantic differential scale, with the difference that numbers on a five-point
or seven-point scale are provided, with bipolar adjectives at both ends, as illustrated below.
- How pleased are you with your new estate agent?
Extremely Pleased
7654321
Extremely Displeased

 Itemized rating scale

A five-point or seven-point scale with anchors, as needed, is provided for each item and the
respondent states the appropriate number on the side of each item, or circles the relevant
number against each item,

 The Likert scale

 is designed to examine how strongly subjects agree or disagree with statements on a five-
point scale with the following anchors:

e. Ranking Scale
- The paired comparison scale is used when, among a small number of objects,
respondents are asked to choose between two objects at a time.
 For Example : If there is Yes-No. Question, If you said yes, you can contiue
the survey to the next question. If not the survei will be finished.
- The forced choice enables respondents to rank objects relative to one another, among the
alternatives provided. This is easier for the respondents, particularly if the number of
choices to be ranked is limited in number.
- The comparative scale provides a benchmark or a point of reference to assess attitudes
toward the current object, event, or situation under study.
2. VALIDITY
- Accurate
- Measure Real Condition
- Represent The Truth
- The tool is the right to
3. Reliability
- Accurate but also Consistent
- Represent the truth
- The ability of measurement to measure consistently