What is a sample?

• A sample is a finite part of a statistical population whose properties

are studied to gain information about the whole population (e.g.
people) set of respondents selected from a larger pop.
• A population is a group of individuals persons, objects, or items from
which samples are taken for measurement (e.g. a population of
professors, or students or books).
 What is sampling

Sampling is the act, process, or technique of selecting a suitable sample,

or a representative part of a population for the purpose of determining
parameters or characteristics of the whole population.
What is the purpose of sampling
• To draw conclusions about populations.... to determine
characteristics.....
• We obtain a sample rather than a complete enumeration (a census )
of the population for many reasons…..but we should prepare
ourselves to cope with the dangers of using samples.
• There are various kinds of sampling procedures. Some are better
than others but all may yield samples that are inaccurate and
unreliable.
TYPES OF RANDOM SAMPLES
• A simple random sample: Each unit has equal chance of being selected.
Good if you have a small population. Use slips , put numbers, put them in
basket, blindly pick until you get to the sample size required.
• A systematic random sample: Selecting one unit on a random basis and
choosing additional units at evenly spaced intervals..e.g 100 students…20 to
be selected
• A stratified sample: simple random sample from each stratum..e.g.SES ,
education, income etc (NS)
• A cluster sample: Clusters from the population on the basis of simple
random selection.. e.g.State..Schools..teachers…opinions
 Stratified random sample:
The population is divided into multiple strata based on common
characteristics
e.g.;
• Residence (Urban or rural)
• Tribe, ethnicity or race
• Family income (poor, moderate, or wealthy)
A random sample is selected from each stratum. The samples from each
stratum are combined for a single estimate of the population mean and
variance

Quantitative Smpling
Classification of Studies
Classification of studies
Experimental or
Observational studies
intervention studies

Field trials or
Descriptive Randomized community
Analytical studies Community trials
studies controlled trials intervention
(RCT) or clinical studies
trials. (sometimes
Longitudinal Ecological or RCT are unethical:
/Surveys correlational why?
(questionnaire or studies
others)

Cross-sectional or
prevalence
Case studies studies

Case-control
Correlational (retrospective)
studies
Cohort or follow-
up studies
Classification of study designs

There are several different schemes for classifying study

designs, but generally studies are divided into:
• Observational Studies (OS):
• One or more groups of ‘subjects’ /patients are observed and
facts /characteristics of subjects are recorded i.e Descriptive;
later analyze the fact and make acritical evaluation i.e Analytical
• Experimental or Intervention Studies (E orIS):
• Main interest lies in the ‘effect’ of that intervention (drug,
procedure, treatment) on the study subjects
Both OS and EorIS involve animal/objects but in medicine these
involve people.
Observational Studies
There are 4 types:
• 1. case series
• 2. case – control
• 3. cross-sectional ( including surveys)
• 4. cohort studies
When certain characteristics of a group (or series) of patients(or
cases) are described in a published reports the results is called “case
Series” where some interesting /intriguing observations are
described
• Case series studies:
• Frequently lead to generation of Hypotheses that are subsequently
investigated in a case-control, cross-sectional or cohort study
• Generally involve patients seen over a relatively short period of
time. These studies are not planned, no research hypothesis, no
control subjects.. Precursor to other studies
• Case controlled studies:
• Begin with the absence or presence of an outcome and then look
backward in time to try to detect possible causes or risk-factors
that may have suggested in a case series report…. (retrospective
studies) .. What happened
Case studies

• Case studies focus on a few elements that illustrate the

type of unit they are interested in learning about e.g
case studies of neighborhood clinics dealing with cases
of substance abuse, STDs
• Cross –sectional studies:
• Analyze data collected on a group of subjects at ‘one time’ rather than
over a period of time.
• To learn ‘what is happening’ right now. ( prevalence studies) b’cause
focus on a point in time.
• E.g. surveys, polls..
• Cohort Studies:
• A group of people who have something in common and who remain part of
a group over an extended period of time. “ what will happen” direction
is forward in time.. Prospective, incidence, longitudinal, forward looking
studies …..49
Design of a case-control study
Time

Direction of enquiry

Exposed

Cases
Not Exposed

Population

Exposed

Controls

Not Exposed
 Design of a cohort study
Time

Direction of enquiry

Screening to
Develop
exclude those with
Disease a
the condition With the
characteristic

Do not develop
S disease
Population b
A
free of M Time
condition P Develop
L Disease c
E
Without the
characteristic
Do not develop
disease d
Validity and Reliability:
Whatever research design is used in a study, the concern is that the conclusions of the
study must reflect as closely as possible to the true situation, i.e. the conclusion must be
valid and reliable.

• Validity refers to the approximate truth of the propositions,

inferences or conclusions of a study.( the degree to which an
instrument measures what it is supposed to measure)
• Reliability means that some one else using the same method in the
same circumstances should get the same results and reach the same
conclusions. ( the degree to which results are consistent)
Types of Validity
• External Validity is related to generalizable; means that your test or
measure can be generalized beyond what you’re using it for
• Construct Validity degree of inferences made from the
operationalization to the theoretical construct.
• Internal Validity is a measure of how well your test is actually
measuring what you want it to measure ; is the approximate truth
about inferences regarding cause and effect relationship.
• Conclusion Validity analytical tools used in the study.
Types of Validity
• External Validity is related to generalizing. Means that the results/findings of the study are
generalizable /applicable to the whole study population (real world). This is determined by the
sampling method used.
• Construct Validity refers to the degree to which inferences can legitimately be made from the
operationalization in your study to the theoretical construct on which those operationalization
were based. This is reflected by the measurement tools and techniques used. Technique for
establishing the validity of an instrument based on the statistical procedures.
• Internal Validity is concerned with the degree of certainty that is the observed effects in an
experiment are Actually the result of experimental treatment or condition (cause) rather than
Intervening variable, or approximate truth about inferences regarding cause and effect
relationship. Thus internal validity is only relevant in studies that try to establish causal
relationship. The design of the study determines internal validity.
• Conclusion Validity: This is determined by the validity of the analytical tools used in
summarizing the measurements of the study.