Chapter One
Introduction
What is Statistics?
• Statistics is
–a study of data:
• describing properties of data (descriptive
statistics) and
• drawing conclusions about a population
based on information in a sample
(inferential statistics).
–a collection of methods for collecting,
displaying, analysing, and drawing
conclusions from data.
Types of Statistics
• Statistics
– is a collection of methods for collecting, displaying,
analysing, and drawing conclusions from data.
• Descriptive statistics
– is the branch of statistics that involves organizing,
displaying, and describing data.
• Inferential statistics
– is the branch of statistics that involves drawing
conclusions about a population based on information
contained in a sample taken from that population.
Types of Data and Levels of
Measurement
Level of Measurement
Level of measurement is one of the key
determinants for selecting the correct statistic for
our analysis.
Level of measurement determines whether the
numeric data value can be treated as representing a
numeric measure of a characteristic, representing
the rank or order within the distribution of data
values, or is simply a short-hand substitute for a
category.
Mathematical Attributes of Variables
Three mathematical attributes:
(1) ordering in magnitude,
(2) equal interval between adjacent units, and
(3) an absolute zero point.
Four Levels of Measurement
Level of measurement refers to how much
information a measure conveys about the
differences among values of the measure. The
higher the level of measurement the more
information in conveyed. There are four levels
of measurement:
Nominal
Ordinal
Interval
Ratio
Nominal Level Measures
• Nominal Scales
– Sometimes called categorical measures
– simply categorizes objects on some attribute.
– include any variable used to classify or categorize
objects along some dimension.
– For example, gender, race, marital status, etc.
– We sometimes assign numeric values to the attributes
of nominal variables but the numbers reflect nothing
about the properties of the individuals or objects
other than that they are different.
Ordinal Levels Measures
• Ordinal scales
– consist of rank ordering objects according to
whether they possess more or less of some
attribute.
– allow us to determine if A < B or A > B, but do not
allow us to determine how much more or less.
– Examples might include social class, level of
satisfaction, class rank.
Interval Level Measures
• Interval scales
– possess the added property of having equal intervals
between adjacent units. This means there are equal
amounts of the variable being measured between
adjacent units in the scale.
– The most common example of an interval scale is the
thermometer. Since the units in the scale are one degree
apart, we can go beyond saying that 40 degrees is warmer
than 30 degrees. We can now say that it is 10 degrees
warmers.
• However, the zero point on the scale is arbitrary and does not
reflect absence of the attribute. Hence zero means something
different in the Celsius and Fahrenheit scales. Examples of
variable that might be considered interval level are GPA and IQ.
Ratio Level Measures
• Ratio level
– variables have all the properties of the interval
scale plus they have an absolute zero point.
– Most physical measures such as time, weight, and
length are ratio scales.
• This type of measurement is rare in the social and
behavioral sciences.
Levels of Measurement: Summery
Level of Measurement
Characteristic Nominal Ordinal Interval Ratio
Ordering in no yes yes yes
magnitude
Equal intervals no no yes yes
Absolute zero no no no yes
point
Basic Terms in Statistics
Data and Variable
• Variable: Any property or characteristic
(attribute) of some event, object, or person that
may have different values at different times or
under different conditions. Variables are logical
sets of attributes.
• Data: The end result of the process of
measurement whereby different attributes of
variables are determined by using a specified
measurement scale and procedure for recording
those measurements.
…Basic Terms in Statistics
• Qualitative data
– are measurements for which there is no natural
numerical scale, but which consist of attributes,
labels, or other nonnumeric characteristics.
– For example, gender, disease status, and type of
car
• Quantitative data
– are numerical measurements that arise from a
natural numerical scale.
– For example, survival time, height, age, number of
children, and number of faults
Discrete and Continuous
• Discrete variable: A variable in which there are
no possible values between adjacent units in the
scale. For example, gender. Discrete variables
change in fixed amounts. These are sometimes
referred to as categorical variables because they
classify observations into categories.
• Continuous variable: A variable that can
theoretically have an infinite number of values
between adjacent units on the scale. Examples
include weight, height, time, age.
Independent and Dependent
• Independent variable:
– The variable that is classified or manipulated
and
– is the presumed cause of some effect.
• Dependent variable:
– The variable that is observed as a result of the
manipulation or classification and
– is the presumed effect of the independent
variable.
Populations and Samples
• Population:
– A well-defined group of individuals, objects, or
observations of any size having a unique quality or
characteristic (e.g., social workers in Ethiopia, frail
elderly living alone in a community, children under 18
year living with HIV).
– Sometimes referred to as the "universe" of
observations from which individuals will be selected
and to whom results will be generalized.
• Sample:
– A subset of the study population
– The subject examined
Random Selection and Assignment
• Random sample:
– A sample that is drawn using procedures that give every
element in the population an equal chance of being
selected.
– Sometime referred to as a “probability” sample.
– Very important for generalizing the findings of our
research to the study population (external validity).
• Random assignment:
– Assigning subjects to treatment and control groups so that
all subjects have an equal chance of being assigned to all
groups.
– Critical for ensuring integrity of an experiment (internal
validity).
Parameter and Statistic
• Parameter:
– Numbers that describe the population of individuals, objects, or
observations from which a sample is drawn.
– is a number that summarizes some aspect of the population as a
whole.
• Statistic:
– Numbers that describe the sample, or
– a number computed from the sample data.
• Remember:
• Population Parameter
• Sample Statistic
…Basic Terms in Statistics
• A measurement is
– a number or attribute computed for each member
of a population or of a sample.
– a number or attribute computed for each member
of a set of objects.
• Sample data is
– The collective measurements of sample elements
– The measurements from a sample
