MASINDE MULIRO UNIVERSITY OF SCIENCE AND

TECHNOLOGY

(MMUST)

COURSE CODE : DSC/DCR058

COURSE TITLE : SOCIAL RESEARCH

METHODS

NAME OF THE LECTURER : COLLINS NGAUNYA

NAME OF STUDENT : SALOME M. SIKHOLE

REG. NO : SWC/D/57958/2019

CAT TYPE : ASSIGNMENT

DATE OF SUBMISSION : 29TH APRIL, 2021

 1. A)
i. Experimental research

This is one of the research design type that establishes relation between the cause and effect of a
particular happening.

The research observes the influence of as independent variable on the dependent one. For instant you
can observe the impact of the price (an independent variable ) on a customer satisfaction ( adependent
variable).

This kind of research designs contributes to solving a particular problem by manipulating the
independent variable to observe the change they have on the independent one.

For example you can experiment with changing the price and observe the effect it has on customer
satisfaction.

ii. Diagnostic research designs

This research design aims to examine the underlying cause of a certain situation or phenomena. It can
help you find out to specific issue or challenges your customer might be facing.

It consist of 3 research phase

1) Problem inception
2) Problem diagnosis
3) Problem solution
iii. Naturalistic design

This research design grew out of the need to study phenomena as they naturally occurs in the field.

The goal of naturalistic study is to understand the phenomena being observed. A major feature of this
design has been the use of humans instrument (the observer) to collect, filter and organize incoming
data.

The design differs from others because it evolves during the Course of the study.
 iv. Case study design

Case study design is qualitative research approach where multiple methods of data collection are used
for a detailed examination of a single case.

A case is a single unit in a study. It can be a person or an organization like a clinic factory or a
hospital.

A case can also be a community or group of people

In social science, sometimes a life history is considered a case study as it is detailed analysis of a
single case.

v. Correlation design

Orodho (2003) notes that correlation designs enables us to access the degree of relationship that exists
between two more variables. For example a researcher might be interested in finding out correlation
between students’ scores in KCPE Mathematics or Physics.

If a positive correlation is established, one could suggest that KCPE Mathematics grade are better
indicators of the students future performance in Physics at Secondary school level.
 1. B) Probabilistic

Involve random selection of participants

Random sampling includes

i. Simple Random sampling

ii. Strained Random sampling
iii. Systematic sampling
I. In simple random sample entry

Member of the population has an equal chance of being selected in the study

Participants selected for the study would be determined through some kind of random process such as
assigning a number to every member of the population and picking the number out of that or using a
table of randomly generated numbers.

II. Strained random sampling involve

Randomly selected individual from sub-group of the population to ensure those group are
appropriately represented in the study sample.

In any case, the goal of probability sampling is to obtain a sample that is representative of the
population of interest so that the result of the study may be generalized to the population. This makes
probability sampling an ideal choice for qualitative studies in which the goal is to draw conclusion
about the population.

III. Systematic sampling

Is when you choose every “nth” individuals to be a part of the sample.

For example you can select every 5th person to be in the sample.

Systematic sampling is an extended implementation of the same old probability technique in which
each member of the group is selected at regular periods to form a sample.

There is an equal opportunity for every member of population to be selected using this sampling
technique.
 IV. Random cluster sampling

Is a way to select participants randomly that are spread out geographically for example if you wanted
to choose 100 participants (country wide) from the entire population of Kenya it’s likely impossible to
get a complete list of every one. Instead the researcher randomly selects counties and randomly selects
from within those boundaries.

Cluster sampling usually analyzes a participant population in which the sample consists of more than a
few elements for example city, family university etc. Researchers then select the cluster by dividing
the population into various smaller section.

2. b) There is no assumption while evaluating a relationship between two different vanables

and statistical analysis techque Calculate the relationship between them.

Non probability sampling does not involve random processes for selecting particintas

Member of the population will not have an equal chance of being selected and in many cases here will
be members of the population who have no chance of being selected.

For example if your population interest is college professors but you. Only intre professors from your
school to participant this would be a non-chance of participate.

This method of conveniences sampling which involves selecting only participants who are readily
accessible is one of the most common types of non-probability sampling keep in mind that an
procedure that does not involves random selection from the population by the researcher or involves
self-selection of participants would be considered non probability sampling methods.

Non probability sampling is often used in quantratire research

Non probability sampling is well suited for many types of qualitative research is not always considered
with generalizing the results to a larger population

i. Qualitative researches often use purposive sampling a non-probability sampling rechque in

which the researcher chooses participants because they have specific expertise or insight

C. Statistics solution 2021

ii. Connence sampling of non-probabilistic sample. The researcher choose these sample just
because they are easy to result and the researcher did not consider selecting sample that
represents the entire population
iii. Consecutive Sampling

Very similar to convenience sampling method with a slight venation.

There a researcher pick a single person or group of a sample conducts research over a period analyzes
the result and then more on to another subjects group if needed.

iv. Quarto sampling

There researcher uses quarto sampling in dividing the population into strata or groups.

For example there are 500 employees in the organization also known as the population the researcher
will need about a population rather than the entire population snow ball sample.

Nethe researchers find a sample when they are difficult to locate.

Researchers use this techque when the sample size is usually and not easily available.

These sampling system work like the referral program.

Once the researcher find suitable subjects he asks them for assistance to seek similar subject for them
considerably good size.

For example a researcher want to coming out a researcher on respians and he only knows one of them,
the researcher will use the known to reach out other through questionnaire

REFERENCE

© 2021Question pro survey software/ 800-531-0228