Lesson 2 Preoccupations in Quantitative Research

Download as docx, pdf, or txt
Download as docx, pdf, or txt
You are on page 1of 5

Four Preoccupations of Quantitative

a. Face validity - "this measure reflects the content of the concept in


Research question. This may be undertaken by asking other people whether the
Lesson 2 measure seems to be getting at the concept that is the focus of
To further deepen our understanding of quantitative research, we attention."
should look into the preoccupations of quantitative researchers. What Example: "People with expertise or experience in a certain field might
are the things that they are concerned of? What are the areas or be asked to act as judge to determine whether on the face of it, the
elements that matter to them? Bryman (2008) identified four measure seems to reflect the concept concerned."
preoccupations of quantitative researchers, namely, measurement, b. Concurrent validity - "employs a criterion on which cases are
causality, generalization and replication. known to differ and that is relevant to the concept in question."
Example: "A new criterion measure of job satisfaction can be
1. Measurement absenteeism. To establish the concurrent validity of this measure of
Measurement is an important factor in quantitative research, job satisfaction, we might look into how people who are satisfied with
which is why reliability and validity are embedded in its methodology. their job are less likely to be absent from work. If a lack of
Reliability speaks of consistency of a measure of a concept. correspondence was found, such as there being no difference in levels
According to Bryman (2008), measurement is reliable if it contains the of job satisfaction among frequent absentees, doubt might be cast on
following factors: whether our measure is really addressing job satisfaction.
a. Stability - This means there is "very little variation over time c. Predictive validity - "uses a future criterion measure rather than a
in the results obtained if it is administered to a group and contemporary one."
readministered again." Example: "The researcher would take future levels of absenteeism as
b. Internal reliability - This means "consistency of the scale or the criterion against which the validity of a new measure of job
index, whether respondents' scores on any one indicator tend to satisfaction would be examined. The difference of this from concurrent
be related to their scores on the other indicators." validity is that a future rather than a simultaneous criterion measure is
c. Inter-observer consistency - This means "being cautious of the employed" (Bryman 2008)
possibility of the inconsistency of observers when a great deal d. Construct validity - "deduces hypothesis from a theory that is
of subjective judgment is involved, such as in recording of relevant to the concept."
observations or translating of data into categories and when Example: "Drawing upon the impact of technology on the experience
more than one observer is in of work, the researcher might anticipate that people who are satisfied
Validity, on the other hand, refers to the issue of whether an with their job are less likely to work on routine jobs; those who are not
indicator that is developed to measure a concept really gauges that satisfied are more likely to work on routine jobs. We could investigate
concept. Bryman (2008) identified ways to establish validity and these this theoretical deduction by examining the relationship between job
include: face validity, concurrent validity, predictive validity, construct satisfaction and job routine.
validity and convergent validity.
Caution: (1) Either the theory or the deduction made from it might be Indicate if the worksheet is homework or seatwork by checking the
misguided; or (2) the measure of job routine could be an invalid box.
measure of that concept." Homework Seatwork
e. Convergent Validity - "the validity if a measure ought to be gauged
WORKSHEET # 3
by comparing it to measures of the same concept developed through Operationalize the five ways of establishing validity by giving each an
other measures," example.
Example: "If we developed a questionnaire measure of how much time
managers spend on various activities, we might examine its validity by
tracking a number of managers and using a structured observation Ways of Establishing Validity Examples
schedule to record how much time is spent in various activities and
their frequency."
2. Causality Face Validity
Most quantitative research is concerned about explanation.
They are strong on explaining why things happen in certain ways.
Hence they are interested not only about the phenomenon of things but
also the causes of it (Bryman 2008). In connection with causality, you
will encounter the concept of dependent and independent variables Concurrent Validity
which will be highlighted in Lesson 3 of this chapter.
3. Generalization
Quantitative researchers are usually apprehensive about
findings that cannot be generalized. They pursue findings that can be
Predictive Validity
generalized beyond the margins of a certain context in which the
research was undertaken. This area of concern reveals itself in social
survey research, on the attention that is often given to the question of
how one can create a representative sample (Bryman 2008)
4. Replication Construct Validity
Replication is the ability to repeat an important component of
an activity. The attempt to make the procedures highly explicit is an
intervention to make an experiment capable of replication. However,
according to Bryman (2008), "replication is not a high-status activity
in natural and social sciences." It is, most of the time, considers as not Convergent Validity
capable of sustaining interest. In social sciences, it is difficult to
warrant that the settings in a replication are those that are referred to in
the original study.
which is not new, the quality of spring of the two balances may have
Factors Threatening Validity an effect on what is being measured.
Lesson 2
A researcher would try his best to achieve a valid and reliable 4. Statistical Regression - Groups are chosen because of extreme
research study. Unfortunately, there are things that sometimes are scores of measurements; these scores or measurements tend to
beyond the control of the researcher that may threaten the validity of move toward the mean with repeated measurements even
the study. Let us analyze each one of them. without an experimental variable.
1. History- A valid observation is conducted several times to Example: Managers who are performing poorly are selected
eliminate error. There might be events that occur within the for training. Their average post-test scores will be higher than their
period of observation which affect the measurement. pre-test scores because of statistical regression, even if no training
Example: A group of high school researcher tried to were given.
investigate if x-ray film fixer can trap energy from the sun. The amount
of energy generated by exposing the x-ray film fixer was measured. 5. Differential Selection - Different individuals or groups would
Exposure to sunlight if the set-ups were done for five days from 10:00 have different previous knowledge or ability which would
A.M. to 3:00 PM. for one week. For one week, the intensity of the sun affect the final measurement if not taken into account.
differs and there was days that were raining. So the measurement of Example: A group of subjects who have viewed a TV program
energy produced was not also consistent. is compared with a group who has not. There is no way of knowing
that the groups would have been equivalent since they were not
2. Maturation - The process if maturing which takes place in the randomly assigned to view the TV program
individual during the duration of the experiment which is not a .
result of specific events but of simply growing older, growing 6. Experimental Mortality - The loss of subjects from
more tired or similar changes. comparison groups could greatly affect the comparisons
Example: The perception if one person changes due to because of unique characteristics of those subjects. Groups to
maturation. What is acceptable today might not be acceptable be compared need to be the same after as before the
tomorrow. This might be the case especially for long term research. experiment.
Example: This is very common especially if you are using
3. Measuring Instruments - changes in instruments, calibration animals in your study. Sudden death of test organism due to reasons
of instruments, observers, or scores may cause changes in the which is beyond your control will force you to get a new organism.
measurements. This decision will have an impact to result of the study
Example: In the conduct of study especially laboratory
experiments by students, changing of laboratory instrument may cause
little change in the result. If today, you use spring balance which is
new in measuring the force tomorrow you use another spring balance
Indicate if the worksheet is homework or seatwork by checking the
box. 3. A researcher decides to test whether cooperative group testing
Homework Seatwork (CGT) makes an increase in learning among college students. The
researcher uses his two classes if EDR 751 to test whether CGT
WORKSHEET # 3
What to do: increases learning. Class A is the control group and they receive
Each of these research scenarios has at least one feature that might no special treatment. Class B will use CGT. The researcher tells
reduce its validity. Read through each scenario and identify the class B that he expects CGT to increase learning, and that he will
problematic areas. Why is it a problematic area? try it on them. He also tells class A that class B is trying a new
1. Patricia is doing an observational study of shopping behavior. She method of teaching which is expected to increase learning, and
positioned herself outside a shop that sells both women's and that they will be used as a comparison group to see if they learn
men's clothing. She observed how long a male or female look at less.
the windows display before entering a shop. _____________________________________________________
_____________________________________________________ _____________________________________________________
_____________________________________________________ _____________________________________________________
_____________________________________________________ _____________________________________________________
_____________________________________________________ _____________________________________________________
_____________________________________________________ _____________________________________________________
_____________________________________________________ _____________________________________________________
_____________________________________________________ _____________________________________________________
_____________________________________________________
2. Irene is conducting an experimental study about memory. She has 4. A researcher wishes to know whether the dynamic or static
recruited a sample of students from top section. She then gave assessment will increase teachers' expectations for mentally -
them a word learning task. They first di the task while listening to handicapped (intellectually - challenged) children. The researcher
music and then in silence. She equates a memory in terms of the randomly assigns the teachers to two groups. The first group of
number words recalled from the learning task. teachers views the child via a dynamic assessment procedure.
_____________________________________________________ Following this viewing, both groups of teachers view the child via
_____________________________________________________ a static assessment. After this viewing, both sets if teachers
_____________________________________________________ complete an instrument designed to measure the teachers'
_____________________________________________________ expectations of the child's likely academic performance.
_____________________________________________________ _____________________________________________________
_____________________________________________________ _____________________________________________________
_____________________________________________________ _____________________________________________________
_____________________________________________________ _____________________________________________________
_____________________________________________________
_____________________________________________________
_____________________________________________________
_____________________________________________________

5. A research is interested in determining whether Cooperative


Group Testing (CGT) really increases academic performance
(achievement). In each of the following studies, he uses a
Solomon Four Group design. In the first study, he looks at the
effect of CGT on final exam scores in educational research
classes. In the second study he looks at final class scores in
several calculus classes to see if CGT had an effect. In a third
study, which takes much longer, he looks gains on Iowa Test of
Basic Skills for middle school students who used CGT for one
year versus those who did not use CGT.
_____________________________________________________
_____________________________________________________
_____________________________________________________
_____________________________________________________
_____________________________________________________
_____________________________________________________
_____________________________________________________
_____________________________________________________

You might also like