Professional Documents
Culture Documents
RESEARCH DESIGN
TYPES OF RESEARCH DESIGN
Causal Research
A. Characteristics
In a causal relationship, one variable directly or indirectly influences another. In other words, changes
in one variable's value directly or indirectly cause changes in a second's value. For example, suppose
you accidentally drop a brick on your toe. In that case, the impact of the brick will probably set off a
chain of events (stimulation of pain receptors in your toe, the avalanche of neural impulses traveling up
your leg to the spinal cord and from there to your brain, registration of pain in your brain, and then
involuntary scream). Although there are several intervening steps between the impact of the brick on
your toe and the scream, it would be proper in this case to conclude that dropping the brick on your toe
causes you to scream. It is possible to trace an unbroken chain of physical influence running from the
initial event (impact of brick on the toe) to the final result (scream).
Causal relationships can be unidirectional, in which case variable A influences variable B but not vice
versa. The impact of the brick (A) may produce a scream (B), but screaming (B) does not cause the
impact of the brick on your toe (A). They also can be bidirectional; in which case each variable influences
the other. Everything else being equal, reducing the amount of exercise a person gets leads to weight
gain. Because of the increased effort involved, heavier people tend to exercise less. Thus, exercise
influences body weight and body weight influences exercise. Even more complex causal relationships
exist, and teasing them out may require considerable ingenuity on the investigator's part. However, in
each case, one can identify a set of physical influences that ties the variables together.
B. Strengths
a. Causal research helps identify the causes behind processes taking place in the system. Having
this knowledge helps the researcher take the necessary actions to fix the problems or optimize
the outcomes.
b. Causal research provides the benefits of replication if there is a need for it.
c. Causal research helps identify the impacts of changing the processes and existing methods.
d. In causal research, the subjects are selected systematically. Because of this, causal research
is helpful for higher levels of internal validity.
C. Limitations
a. The causal research is difficult to administer because sometimes it is impossible to control all
extraneous variables' effects.
b. Causal research is one of the most expensive research to conduct. The management requires
a great deal of money and time to conduct research. Sometimes it costs more than 1 or 2 million
dollars to test real-life two advertising campaigns.
c. One disadvantage of causal research is that it provides information about your plans to your
competitors. For example, they might use your research outcomes to identify what you are up
to and enter the market before you.
d. You can't conclude merely depending on the outcomes of the causal research. You are required
to conduct other types of research alongside the causal research to confirm its output.
Correlational Research
A. Characteristics
In correlational research, your main interest is to determine whether two (or more) variables covary
and, if so, to establish the directions, magnitudes, and forms of the observed relationships. The
strategy involves developing measures of the variables of interest and collecting your data.
Correlational research involves observing the values of two (2) or more variables and determining what
relationships exist between them. In correlational research, you do not attempt to manipulate variables
but observe them "as is." For example, imagine that you wished to determine the nature of the
relationship, if any, between pretest anxiety and test performance in introductory psychology students
on campus. On test day, you have each student rate his or her level of pretest anxiety and, after the
test results are in, you determine the test performances of those same students. Your data consists of
two scores for each student: self-rated anxiety level and test score. You analyze your data to determine
the relationship (if any) between these variables. Note that both the anxiety level and test scores are
observed as found in each student.
In some types of correlational research, you compare some variable's average value across preformed
groups of individuals. Membership in a group depends on the participant's characteristics or
circumstances (such as political party affiliation, eye color, handedness, occupation, economic level,
or age). For example, you might compare Democrats to Republicans on attitudes toward education.
Such a study would qualify as correlational research because group membership (whether Democrat
or Republican) was determined by the participants' choice of party and was not in the researcher's
hands. You can only measure party affiliation; you cannot change a person's party affiliation in your
study.
Establishing that a correlational relationship exists between two (2) variables makes it possible to
predict the value of one (1) variable the probable value of the other variable. For example, if you know
that college grade point average (GPA) is correlated with Scholastic Assessment Test (SAT) scores,
then you can use a student's SAT score to predict (within limits) the student's college GPA.
When you use correlational relationships for prediction, the variable used to predict is called the
predictor variable, and the variable whose value is being predicted is called the criterion variable.
Whether the linkage between these variables is causal remains an open question.
B. Strengths
Correlational research allows researchers to collect much more data than experiments. Furthermore,
because correlational research usually takes place outside of the lab, the results tend to be more
applicable to everyday life. Another benefit of correlational research is that it opens up a great deal of
further research to other scholars. When researchers begin investigating a phenomenon or relationship
for the first time, correlational research provides a good starting position. It allows researchers to
determine the strength and direction of a relationship so that later studies can narrow the findings down
and, if possible, determine causation experimentally.
C. Limitations
Correlation research only uncovers a relationship; it cannot provide a conclusive reason for why there's
a relationship. A correlative finding doesn't reveal which variable influences the other. For example,
finding that wealth correlates highly with education doesn't explain whether having wealth leads to more
education or whether education leads to more wealth. Reasons for either can be assumed, but
causation can't be determined until more research is done. Also, a third, unknown variable might be
causing both. For instance, living in the state of New York can lead to both wealth and education.
Experimental Research
A. Characteristics
Experimental research has two (2) defining characteristics: manipulating one or more independent
variables and controlling extraneous variables.
An independent variable is a variable whose values are chosen and set by the experimenter.
(Another way to look at it is that the value of the independent variable is independent of the
participant's behavior.) We call these set values the levels of the independent variable. For
example, imagine you want to determine how sleep deprivation affects a person's ability to
recall previously memorized material. To examine this relationship, you might assign
participants to one (1) of three (3) groups defined by the number of hours of sleep deprivation:
zero (0) hours (rested), 24 hours, and 48 hours. These three (3) amounts would constitute the
three (3) levels of sleep deprivation, your independent variable. Notice how this strategy differs
from addressing this question in a correlational study in which you would measure how much
sleep a participant received and then test memory.
To manipulate your independent variable, you must expose your participants to at least two (2)
levels of that variable. The specific conditions associated with each level are called the
treatments of the experiment. Depending on your experiment's design, the independent
variable may be manipulated by exposing a different group of participants to each treatment or
exposing each participant to all the treatments in sequence. By manipulating the independent
variable, you hope to show that changes in the independent variable's level cause changes in
the behavior are recorded.
The variable whose value you observe and measure in experimental designs is called the
dependent variable (or dependent measure). If a causal relationship exists, then the dependent
variable's value depends, at least to some extent, on the level of the independent variable. (Its
value also depends on other factors such as participant characteristics.) Another way to think
about the dependent variable is its value depends on the participant's behavior, rather than
being set by the experimenter.
If allowed to vary on their own, extraneous variables can produce uncontrolled changes in the
dependent variable's value, with two rather nasty possible consequences. First, uncontrolled
variability may make it difficult or impossible to detect any effects of the independent variable.
(In our example, the therapy's effects could be hidden by the alcohol's effects.) Second,
uncontrolled variability may produce chance differences in behavior across the levels of the
independent variable. These differences could make it appear as though the independent
variable produced effects when it did not (the therapy would appear to work even though the
real effect came from the alcohol). To identify clear causal relationships between your
independent and dependent variables, you must control extraneous variables' effects.
You have two (2) ways to control these effects. The first way is to hold extraneous variables
constant. If these variables do not vary throughout your experiment, they cannot cause
uncontrolled variation in your dependent variable. For example, in the anxiety therapy
experiment, you might want to make sure that all your participants are sober (or at least
intoxicated to the same degree). In fact, to the degree possible, you would want to make sure
that all treatments are exactly alike, except for the independent variable level.
The second way to deal with extraneous variables is to randomize their effects across
treatments. This technique deals with the effects of extraneous variables that cannot be held
constant or, for reasons that will be explained later, should not be held constant. For example,
in an experiment assessing the effect of sleep deprivation on memory, it may not be possible
to ensure that your participants had the same amounts of sleep deprivation. Some may have
slept better than others the day before your experiment began) or that their recall abilities are
equivalent. The idea is to distribute the effects of differences across treatments to tend to even
out and thus cannot be mistaken for the independent variable's effects.
B. Strengths
The great strength of the experimental approach is its ability to identify and describe causal
relationships. The correlational approach does not share this ability. Simultaneously, the correlational
approach can tell you only that changes in one variable's value tend to accompany changes in the value
of a second variable. The experimental approach can tell you whether changes in one variable (the
independent variable) caused changes in the other (the dependent variable).
C. Limitations
Despite its power to identify causal relationships, the experimental approach has limitations that restrict
its use under certain conditions. The most serious limitation is that you cannot use the experimental
method to manipulate your hypothesized causal variables. For example, studies of personality disorders
must use correlational approaches to identify possible causal relationships. Exposing people to various
nasty conditions to identify which of those conditions cause personality disorders is not ethical.
The experimental approach's second limitation entails the tight control over extraneous factors required
to reveal the independent variable's effects. Such control tends to reduce your ability to apply your
findings to situations that differ from your original experiment's conditions. A rather unpleasant trade-off
exists in experimental research. As you increase the degree of control you exert over extraneous
variables (and thus your ability to establish causal relationships), you decrease your ability to generalize
your findings beyond the conditions assessed in your experiment.
TYPES OF RESEARCH
Market Analysis
When it comes to making an important business decision or implementing a strategic plan, companies often
turn to a toolbox of resources to determine the best possible action course. One of the most important tools in
this box is the market analysis. This assessment incorporates quantitative and qualitative data to paint a clear
picture of the tangible and intangible factors at play in the industry.
Financial Analysis
Financial analysis is the process of evaluating businesses, projects, budgets, and other finance-related
transactions to determine their performance and suitability. Typically, financial analysis is used to analyze
whether an entity is stable, solvent, liquid, or profitable enough to warrant a monetary investment.
Financial analysis is used to evaluate economic trends, set financial policy, build long-term plans for business
activity, and identify projects or companies for investment. Financial analysis is done by synthesizing financial
numbers and data and conducting corporate finance and investment finance settings. A financial analyst will
thoroughly examine a company's financial statements—the income statement, balance sheet, and cash flow
statement. Financial analysis
One of the most common ways to analyze financial data is to calculate ratios from the financial statements' data
to compare those of other companies or their historical performance.
Basic financial ratios:
a. Working capital ratio: Assessing the health of a company in which you want to invest involves
understanding its liquidity—how easily that company can turn assets into cash to pay short-term
obligations. The working capital ratio is calculated by dividing current assets by current liabilities.
b. Quick ratio: Also called the acid test, this ratio subtracts inventories from current assets before dividing
that figure into liabilities.2 The idea is to show how well current liabilities are covered by cash and items
with a ready cash value. Inventory, on the other hand, takes time to sell and convert into liquid assets.
c. Earnings per share: When buying a stock, you participate in the company's future earnings (or risk of
loss). Earnings per share (EPS) measures the net income earned on each share of a company's
common stock. The company's analysts divide its net income by the weighted average number of
common shares outstanding during the year.
d. Price-earnings ratio: Called P/E for short, this ratio reflects investors' assessments of those future
earnings. You determine the company's stock price and divide it by EPS to obtain the P/E ratio.
e. Debt-equity ratio: This can reduce the safety margins behind what it owes, jack up its fixed charges,
reduce earnings available for dividends for folks like you and even cause a financial crisis.
f. Return on equity: Common shareholders want to know how profitable their capital is in the businesses
they invest in. Return on equity is calculated by taking the firm's net earnings (after taxes), subtracting
preferred dividends, and dividing the result by common equity dollars in the company.
Competitor Analysis
Evaluate your competitors by placing them in strategic groups according to how directly they compete for a
share of the customer's peso. For each competitor or strategic group, list their product or service, profitability,
growth pattern, marketing objectives and assumptions, current and past strategies, organizational and cost
structure, strengths and weaknesses, and size (in sales) of the competitor's business. Answer questions such
as:
a. Who are your competitors?
b. What products or services do they sell?
c. What is each competitor's market share?
d. What are their past strategies?
e. What are their current strategies?
f. What type of media is used for marketing their products or services?
g. How many hours per week do they purchase to advertise through the media used in this market?
h. What are each competitor's strengths and weaknesses?
i. What potential threats do your competitors pose?
j. What potential opportunities do they make available for you?
REFERENCES
Bordens, K. S., & Abbott, B. B. (2017). Research Design and Methods: A Process Approach (10th ed.). New
York: McGraw-Hill Education.
Mudassir, H., Soccolich, A., & Angel, B. (n.d.). Competitive Analysis Definition - Entrepreneur Small Business
Encyclopedia. Retrieved March 27, 2020, from
https://www.entrepreneur.com/encyclopedia/competitive-analysis
Parsons, N. (2019, September 12). Market Analysis in 4 Steps. Retrieved March 27, 2020, from
https://www.liveplan.com/blog/market-analysis-in-4-steps/
Tuovila, A. (2020, February 5). Financial Analysis Definition. Retrieved March 27, 2020, from
https://www.investopedia.com/terms/f/financial-analysis.asp
Wilkins, G. (2020, March 7). 6 Basic Financial Ratios and What They Reveal. Retrieved March 27, 2020, from
https://www.investopedia.com/financial-edge/0910/6-basic-financial-ratios-and-what-they-tell-you.aspx