TMA II OF ADVANCED RESEARCH METHODS

1. List and discuss two of the most commonly used random sampling techniques used in
survey research.
There are two most commonly used random types of sampling methods:

Probability sampling involves random selection, allowing you to make strong statistical
inferences about the whole group.
Non-probability sampling involves non-random selection based on convenience or other criteria,
allowing you to easily collect data.
2. Write a brief description of Cross-Sectional Surveys
A cross-sectional study is defined as a type of observational research that analyzes data of
variables collected at one given point in time across a sample population or a pre-defined subset.
This study type is also known as cross-sectional analysis, transverse study, or prevalence study.

3. Give some examples of correlation research:

Correlational research is something that we do every day; think about how you establish a
connection between the doorbell ringing at a particular time and the milkman's arrival. As such,
it is expedient to understand the different types of correlational research that are available and
more importantly, how to go about it. There are 3 types of correlational research type is defined
by peculiar characteristics.
1. Positive correlational research is a research method involving 2 variables that are statistically
corresponding where an increase or decrease in 1 variable creates a like change in the other. An
example is when an increase in workers' remuneration results in an increase in the prices of
goods and services and vice versa.
2. Negative correlational research is a research method involving 2 variables that are statistically
opposite where an increase in one of the variables creates an alternate effect or decrease in the
other variable. An example of a negative correlation is if the rise in goods and services causes a
decrease in demand and vice versa.
3. Zero correlational research is a type of correlational research that involves 2 variables that are
not necessarily statistically connected. In this case, a change in one of the variables may not
trigger a corresponding or alternate change in the other variable.
Zero correlational research caters for variables with vague statistical relationships. For example,
wealth and patience can be variables under zero correlational research because they are
statistically independent.
4. Why can causal inferences not be drawn from correlation research results?
It refers to the inability to legitimately deduce a cause-and-effect relationship between two
events or variables solely on the basis of an observed association or correlation between them.
The idea that "correlation implies causation" is an example of a questionable-cause logical
fallacy, in which two events occurring together are taken to have established a cause-and-effect
relationship. This fallacy is also known by the Latin phrase cum hoc ergo propter hoc ('with this,
therefore because of this'). This differs from the fallacy known as post hoc ergo propter
hoc ("after this, therefore because of this"), in which an event following another is seen as
a necessary consequence of the former event, and from conflation, the errant merging of two
events, ideas, databases, etc., into one.

5. Discuss the methods of data analysis appropriate to causal comparative research

Qualitative Analysis
This approach mainly answers questions such as ‘why,’ ‘what’ or ‘how.’ Each of these questions
is addressed via quantitative techniques such as questionnaires, attitude scaling, standard
outcomes, and more. Such analysis is usually in the form of texts and narratives, which might
also include audio and video representations.
Quantitative Analysis
Generally, this analysis is measured in terms of numbers. The data here present themselves in
terms of measurement scales and extend themselves for more statistical manipulation.

6. What problems arise in interpreting results of causal comparative research?

a) Lack of researcher control.
b) An apparent cause and effect relationship may not be what it seems.
c) Causes and effects may be reversed.
d) An external third factor may actually be responsible for both the hypothesized case and the
hypothesized effect.

7. How is quasi-experimental research different from experimental research?

"Quasi-experimental research is similar to experimental research in that there is manipulation of
an independent variable. It differs from experimental research because either there is no control
group, no random selection, no random assignment, and/or no active manipulation."With an
experimental research study, the participants in both the treatment (product users) and control
(product non-users) groups are randomly assigned. Quasi-experimental research designs do not
randomly assign participants to treatment or control groups for comparison.

8. Discuss some of the limitations of this mode of research design

The limitations of the study are those characteristics of design or methodology that impacted or
influenced the interpretation of the findings from your research. Issues with samples and
selection. Other limitations are: Insufficient sample size for statistical measurements, Lack of
previous research studies on the topic, Limited access to data, Time constraints, Conflicts arising
from cultural bias and other personal issues.

9. Compare and contrast the simple experiment to the randomized posttest only control group
design
Simple experiment Randomized posttest only control group design
A simple experiment is one The posttest-only control group design is a research
researchers often use to determine if design in which there are at least two groups, one of
changes in one variable might lead to which does not receive a treatment or intervention, and
changes in another variable—in other data are collected on the outcome measure after the
words, to establish cause-and-effect. In treatment or intervention.
a simple experiment looking at the The group that does not receive the treatment or
effectiveness of a new medication, for intervention of interest is the control group.
instance, study participants may The general process for this design is that
be randomly assigned to one of two (a) Two or more groups are formed;
groups: one of these would be (b) The treatment or intervention is administered;
the control group and receive (c) Data are collected after the treatment or intervention
no treatment, while the other group has been administered, commonly using a behavioral,
would be the experimental group that cognitive, or psychological assessment; and
receives the treatment being studied. (d) The data are compared between groups to determine
whether the treatment or intervention was effective.

A simple experiment is composed of several key elements including this one of control group:

 The Experimental Hypothesis: This is a statement that predicts that the treatment will
cause an effect and so will always be phrased as a cause-and-effect statement. For
example, researchers might phrase a hypothesis in this way: "Administration of Medicine
A will result in a reduction of symptoms of Disease B."
 The Null Hypothesis: This is a hypothesis that the experimental treatment will have no
effect on the participants or dependent variables. It's important to note that failing to find
an effect of the treatment does not mean that there is no effect. The treatment might
impact another variable that the researchers are not measuring in the current experiment.
 The Independent Variable: The treatment variable that is manipulated by the
experimenter.
 The Dependent Variable: This refers to the response the researchers are measuring.
 The Control Group: These are the individuals who are randomly assigned to a group but
do not receive the treatment. The measurements taken from the control group will be
compared to those in the experimental group to determine if the treatment had an effect.
 The Experimental Group: This group of study participants is made up of the randomly-
selected subjects who will receive the treatment being tested.
 10. What are the limitations of the experimental research method?
Among the limitations we may talk of that: participants aware of experiment, may change
behavior, artificial environment - low realism, they may be more expensive and time consuming
than lab experiments. There is no control over extraneous variables that might bias the results.
This makes it difficult for another researcher to replicate the study in exactly the same way.

11. Outline and evaluate the main types of factorial design

There are three main types of factorial designs, namely a) “Within Subject Factorial
Design”,b) “Between Subject Factorial Design”, and c) “Mixed Factorial Design”. Factorial
designs may be experimental, nonexperimental, quasi-experimental or mixed.

In a within-subjects factorial design, all of the independent variables are manipulated within
subjects. All participants could be tested both while using a cell phone and while not using a cell
phone and both during the day and during the night. This would mean that each participant was
tested in all conditions.

In a between-subjects factorial design, all of the independent variables are manipulated between
subjects. For example, all participants could be tested either while using a cell phone or while not
using a cell phone and either during the day or during the night.

A mixed factorial design involves two or more independent variables, of which at least one is a
within-subjects (repeated measures) factor and at least one is a between-groups factor. In the
simplest case, there will be one between-groups factor and one within-subjects factor.

12. Discuss some of the advantages, as well as limitations, of factorial design

FACTORIAL DESIGN
Advantages Limitation
The primary advantages of factorial designs are The main disadvantage is the difficulty of
that they allow for the evaluation of experimenting with more than two factors, or
interrelationships and that they are more many levels. A factorial design has to be
efficient than conducting multiple studies with planned meticulously, as an error in one of the
one variable at a time. levels, or in the general operationalization, will
jeopardize a great amount of work.
The factorial design allows research on the
working mechanisms and mediators that allows The main disadvantage is the difficulty of
strong causal inference because each factor experimenting with more than two factors, or
associated with a hypothesized specific many levels. A factorial design has to be
mechanism is manipulated and the effect of planned meticulously, as an error in one of the
manipulating this factor can be tested directly levels, or in the general operationalization, will
on secondary measures indexing the putative jeopardize a great amount of work.
mediator.
Factorial designs are extremely useful to Other than these slight detraction’s, a factorial
design is a mainstay of many scientific
psychologists and field scientists as a
preliminary study, allowing them to judge disciplines, delivering great results in the field.
whether there is a link between variables,
whilst reducing the possibility of experimental
error and confounding variables.
The factorial design, as well as simplifying the
process and making research cheaper, allows
many levels of analysis. As well as
highlighting the relationships between
variables, it also allows the effects of
manipulating a single variable to be isolated
and analyzed singly.

13. What is a cross-over study?

A crossover study compares the effects of the single treatments not the effects of the sequences
to which the subjects are randomized. The main advantage of a crossover design over the parallel
group is the opportunity it provides to compare the effects of treatments within subjects.

It is a type of clinical trial in which the study participants receive each treatment in a random
order. Crossover studies are often used when researchers feel it would be difficult to recruit
participants willing to risk going without a promising new treatment.

14. What are “practice effects” in repeated measures design?

In repeated measures design, each participant is measured for multiple conditions in an
experiment. For example, a group of people might be given extra help to see if it improves their
math ability, and then they might be given access to an online help program.

Practice effects, defined as improvements in cognitive test performance due to repeated exposure
to the test materials, have traditionally been viewed as sources of error. However, they might
provide useful information for predicting cognitive outcome.

15. Describe the classical methodology used in twin studies research

The classic twin design aims to quantify the roles of genetic and environmental causes of
variation in traits and in disease susceptibility.

The classical twin design compares the similarity of monozygotic (identical) and dizygotic
(fraternal) twins. By comparing many hundreds of families with twins, researchers can then
understand more about the roles of genetic effects, shared environment, and unique environment
in shaping behavior. Twin research is a key tool in the field of behavioral genetics, and twin
studies are part of the broader methodology used in behavior genetics, which uses genetically
informative data to track a variety of traits ranging from personal behavior to the presentation of
severe mental illness such as schizophrenia.

16. Explain the following terms found in twin studies research: 1)“equal environments”;
2)“random mating”; 3)“ACE model”
1)The traditional twin method is predicated on the equal-environment assumption (EEA)--that
monozygotic (MZ) and dizygotic (DZ) twins are equally correlated in their exposure to
environmental events of etiologic importance for the trait under study. In 1968, Scarr proposed a
test of the EEA which examines the impact of phenotypic similarity in twins of perceived versus
true zygosity. We apply this test for the EEA to five common psychiatric disorders (major
depression, generalized anxiety disorder, phobia, bulimia, and alcoholism), as assessed by
personal interview, in 1030 female-female twin pairs from the Virginia Twin Registry with
known zygosity. We use a newly developed model-fitting approach which treats perceived
zygosity as a form of specified familial environment. In 158 of the 1030 pairs (15.3%), one or
both twins disagreed with the project-assigned zygosity. Model fitting provided no evidence for a
significant influence of perceived zygosity on twin resemblance for any of the five disorders.
Although limited in power, these results support the validity of the EEA in twin studies of
psychiatric disorders. Twin studies operate under the equal environments assumption (EEA),
which posits that the environments of MZ twins are no more alike than DZ twins; if this
assumption were violated, MZ twin correlations could be inflated, thus increasing heritability
estimates.

2) Random mating. Twin researchers assume that people are as likely to choose partners who are
different from themselves as they are to choose partners who are similar for a particular trait. But
some research suggests that parents, teachers, peers and others may treat identical twins more
similarly than fraternal twins.

3) The ACE model is a statistical model commonly used to analyze the results of twin studies. It
aims to decompose sources of phenotypic variation into three categories: additive genetic
variance (A), common (or shared) environmental factors (C), and specific (or nonshared)
environmental factors plus measurement error (E). It is widely used in genetic
epidemiology and behavioural genetics. The basic ACE model relies on several assumptions,
including the absence of assortative mating, that there is no genetic dominance or epistasis, that
all genetic effects are additive, and the absence of gene-environment interactions. In order to
address these limitations, several variants of the ACE model have been developed, including an
ACE-β model, which emphasizes the identification of causal effects, and the ACDE model,
which accounts for the presence of dominant genetic effects.

17. What advantages does ANOVA have over a two-sample t-test?

I would argue that: While the t-test is used to compare the means of response variable
between two groups of predictor variable, ANOVA is used to compare means between two or
more groups of predictor variable.
So for two groups, we can use both t-test and ANOVA and the results would be the same.

Assumptions of both t-test and ANOVA, include normality of response variable for each
category of predictor variable, which can be tested by one sample k-s test or Shipro-Wilk test.
[both are quite robust methods. Even in absence of normality, if we have almost equal data in
each group of predictor, these tests can be used.] Assumptions of both t-test and ANOVA,
include homogeneity of variance, which can be tested by Leven's test.

If you run an ANOVA routine with two groups, you will get the same result as a t-test. The t-test
is a special case of one way ANOVA. So no advantage of one over the other.

If you run an ANOVA routine with two groups where you can match measurements across the
two groups (paired t-test), you will get the same result as a two way ANOVA on groups and
subjects (the units of comparison). So again, no advantage of one over the other.

However, many packages allow a t-test to be run with unequal variances in the two groups. The
problem of unequal variances (heteroscedasticity in stats jargon) can be handled easily with t-test
routines. This is the only advantage I know of for t-test routines over ANOVA routines.

18. Elaborate on the meaning of F-ratio and how it is applied in ANOVA

The F ratio is the ratio of two mean square values. If the null hypothesis is true, you expect F to
have a value close to 1.0 most of the time. A large F ratio means that the variation among group
means is more than you'd expect to see by chance. Analysis of variance (ANOVA) can
determine whether the means of three or more groups are different. ANOVA uses F-tests to
statistically test the equality of means.
What are F-statistics and the F-test?
F-tests are named after its test statistic, F, which was named in honor of Sir Ronald Fisher. The
F-statistic is simply a ratio of two variances. Variances are a measure of dispersion, or how far
the data are scattered from the mean. Larger values represent greater dispersion.
Variance is the square of the standard deviation. For us humans, standard deviations are easier to
understand than variances because they’re in the same units as the data rather than squared units.
However, many analyses actually use variances in the calculations.
F-statistics are based on the ratio of mean squares. The term “mean squares” may sound
confusing but it is simply an estimate of population variance that accounts for the degrees of
freedom (DF) used to calculate that estimate.
Despite being a ratio of variances, you can use F-tests in a wide variety of situations.
Unsurprisingly, the F-test can assess the equality of variances. However, by changing the
variances that are included in the ratio, the F-test becomes a very flexible test. For example, you
can use F-statistics and F-tests to test the overall significance for a regression model, to compare
the fits of different models, to test specific regression terms, and to test the equality of means.
Using the f-test in one-way anova
To use the F-test to determine whether group means are equal, it’s just a matter of including the
correct variances in the ratio. In one-way ANOVA, the F-statistic is this ratio:
 F = variation between sample means / variation within the samples

19. Define, in your own words, multivariate analysis

Multivariate analysis (MVA) is a statistical procedure for analyzing data involving more than
one type of measurement or observation. It can also mean solving problems where more than one
dependent variable is analyzed simultaneously along with other variables.