Research Methods and Research
– Research Method Vs Research Design
• Qualitative Research Methods
• Quantitative Research Methods
• Research Designs
– Descriptive Designs
– Analytic Designs
• Selecting Methods and Designs
– Internal vs. External validity ….. the concept of sampling and inference
– Refer to the way how the required information or data is
– Example; through interview, using questionnaires, observations,
record reviews, measurements.
– Refers to the overall methodology as to how the study should be
– It defines the way and the pattern of data collection to be cross-
sectional or longitudinal, it states the selection of study units,
and sample allocation, it defines the data analysis…
Qualitative Research Methods
Qualitative research methods utilize
– In-depth interview /IDI/
– Focus group discussions /FGD/
– Record review or Document Analysis
• Qualitative data are not countable and can not be
expressed in numbers.
• Qualitative methods are used to capture individuals
feeling, attitude, interest, opinion, and thought.
Quantitative Research Methods
Quantitative research methods utilize
– Structured questionnaires
• Quantitative data are expressed in the form of counts
and other statistical parameters like mean, mode
variance, SD, correlation…
• Quantitative study designs have two broad classification
Observational and Experimental Designs with in which there exist a
number of study designs.
• Observational-investigaters stand apart from events taking place in
the study ,they simply observe &record.
• Expermental-investigater introduce intervention &observe the event
Randomized Controlled Trials
Descriptive Vs. Analytic Studies
• Descriptive study designs are limited to description of the
subject under consideration in a particular population and
are the first step in any study.
• However pure descriptive studies are rarely done,
descriptive data is presented usually for the purpose of
health statistics or comparison of population health status.
• Analytical study designs goes further by analyzing the
relationship between the interest variable and other
Cross-sectional Study Design
• Measurements are made on a single occasion
• Are also called prevalence studies.
• Used to measure the prevalence of a particular health
condition at a point in time.
• Both the exposure and effect are measured at the
same time, and difficult to present whether the effect
or the exposure precede.
• Determining casual relationships is difficult.
• Used to generate hypothesis.
• Very useful in investigating the cause of sudden
outbreaks or health conditions and compare fixed
exposure characters like sex, blood group.
• Used to assess health care needs of a population.
• Used to provide trend estimates when done in a
representative and repeated periods of time in a
particular population for the same objectives.
• Conducted in national level to estimate the health
status of the population. Example; DHS
• Measurements are made over a period of time
• May retrospective or prospective
• In retrospective study investigators study past
and present events
• In prospective study investigators follow
subjects for future event
Case-Control Study Design
• It is a popular retrospective study, since the investigator
is looking backward from the disease to a possible cause.
• Used to investigate the cause of rare diseases or health
• Involve people with the health outcome (referred as
cases) and those with no health outcome or the disease
(referred as controls).
• Compare the occurrence of the possible cause in cases
and in controls.
• The investigator collects disease occurrence at one point
in time and the exposure at previous point of time.
• The association of an exposure and disease in case
control study is measured by calculating the Odds
• It is the ratio of the odds of exposure among cases to
the odds of exposure among controls.
Case-control study designs flow chart
Cohort Study Designs
• Also called follow-up or Incidence rate studies.
• The study begins with a group of people who are free of
disease and who are classified into subgroups according
to exposure to a potential cause of a disease or outcome.
• Variables of interest are specified and measured and the
whole cohort is followed up to see how the subsequent
development of new cases of the disease or the outcome
differs between the groups with and without exposure.
• Start with healthy people and look for the occurrence of
• Cohort studies are therefore longitudinal studies.
• Provide best information on the causation of an
outcome and the risk of developing an outcome or
• Expensive compared with other study designs.
• Relative risk is measured to estimate the incidence of
the outcome among the exposed groups.
• Ex-study by bradford and rechard to investigate
relation ship between smoking &lung cancer
• Followed 40,000 british docters who were
devided in to four cohort:non smokers,light
moderate and heavy smokers.
• Death was the out come they recorded
• Used both all cause death(any death) and cause
• Finding-more death from all cause &from lung
cancer in smokers
Experimental Study Designs
• Are also called interventional studies.
• Attempt to change a variable in one or more groups
• Here the investigator manipulates the status of
exposure on subjects, then the effects of the
intervention are measured by comparing the outcome
in the experimental group with that in a control
• Ethical considerations have paramount importance.
• Informed consent has to be taken.
Randomized Controlled Trials
• Usually used to study the effect of a particular
intervention, treatment, for a specific disease or
outcome (clinical trail)
• Subjects are randomly allocated to intervention and
control groups, outcomes are then compared.
• Random allocation is made to ensure the comparisons
groups are equivalent .
• Any difference between groups is considered as
chance occurrence and unaffected by the conscious or
unconscious biases of the investigators.