QUANTITATIVE ANALYSIS
CHAPTER 1
BUSINESS STATISTICS
 Collection, summarization, analysis & reporting of
numerical findings relevant to a business decision
or situation
 integral parts of our lives
2 TYPES OF STATISTICS
1. DESCRIPTIVE STATISTICS
2. INFERENTIAL STATISTICS
DESCRIPTIVE STATISTICS
 describing the characteristics of a set of data
 summarize & describe data collected
INFERENTIAL STATISTICS (INDUCTIVE STATISTICS)
 proceeding from data characteristics to making
generalizations, estimates, forecasts, or other
judgments based on data
 arrive at inferences regarding the
phenomenon/phenomena for which sample data
were obtained
STATISTIC
 can be a measure of typicalness / central
tendency
 Mean, median, mode or proportion
 Data is measured by:
- Typicalness/center
- Spread
HOW TO MEASURE CENTER?
1. Mean: average
2. Median: middle / physical center
3. Mode: value most frequency observed
HOW TO MEASURE SPREAD?
 How far values are from one another
1. Range: Maximum – Minimum
2. Standard Deviation: Average (distance
between each point and center)
KEY TERMS FOR INFERENTIAL STATISTICS
SAMPLE
 smaller number (a subset) of the people or objects
that exist within the larger population
POPULATION
 the universe, entire set of people or objects of
interest
SAMPLE STATISTIC
 measured characteristic of the sample
 can be a measure of TYPICALNESS or CENTRAL
TENDENCY, such as mean, median, mode or
proportion
 may be a measure of spread or dispersion, such
as range & standard deviation
POPULATION PARAMETER
 numerical characteristic of the population
 typical parameters include mean, median,
proportion & standard deviation
VARIABLES
 DATA: pieces of information about individuals
organized into variables
 INDIVIDUALS: means a particular person or
group
 VARIABLE: a particular characteristic of an
individual (measurable and concrete
characteristics to be analyzed)
 DATA SET: a set of data identified with particular
circumstance
TYPES OF VARIABLES AND SCALES OF
MEASUREMENT
TYPES OF VARIABLES
1. QUALITATIVE VARIABLE
2. QUANTITATIVE VARIABLES
1. QUALITATIVE VARIABLES/CATEGORICAL
VARIABLES
 person or object belongs in a category
 also referred to as attributes, typically involve
counting how much people or objects will fall into
each category
 we describe the percentage or the number of
persons or objects falling into each of the possible
categories
2. QUANTITATIVE VARIABLES
 enables us to determine how much of something
is possessed, not just whether it is possessed
2 TYPES OF QUANTITATIVE VARIABLES
1. DISCRETE QUANTITATIVE VARIABLE
 can take only certain values along an interval, with
the possible values having gaps between them
 usually consists of observations that we can count
and often have integer values
2. CONTINUOUS QUANTITATIVE VARIABLE
 can take on a value at any point along an interval,
possible values with no gaps between them
SCALES OF MEASUREMENT
1. NOMINAL SCALE
2. ORDINAL SCALE
3. INTERVAL SCALE
4. RATIO SCALE
1. THE NOMINAL SCALE
 uses numbers only for the purpose of identifying
membership in a group or category
 numbers have no arithmetic meaning
2. THE ORDINAL SCALE
 numbers represent "greater than" or "less than"
measurements such as preferences or rankings
 numbers are viewed in terms of rank
 ordinal scale has no unit of measurement
3. THE INTERVAL SCALE
 not only includes "greater than" or "less than"
relationships, but also has a unit of measurement
that permits us to describe how much more or less
one object possesses than another
  unit of measurement is arbitrary & there is no
absolute zero level where none of a given
characteristic is present
4. THE RATIO SCALE
 similar to interval scale but has an absolute zero &
multiples are meaningful
CHAPTER 2
RAW DATA
 have not been manipulated or treated in any way
beyond their original collection
 will not be arranged or organized in any
meaningful manner
WHEN RAW DATA ARE QUANTITATIVE, 2 WAYS TO
ADDRESS THIS PROBLEM:
1. Frequency Distribution
2. Histogram
FREQUENCY DISTRIBUTION
 A table that divides the data values into classes &
shows the number of observed values that fall into
each class
RELATIVE FREQUENCY
 Frequency of the ith class / total frequency
 (Frequency of the ith class / total frequency) x100
CUMULATIVE FREQUENCY
 Add previous frequency
CUMULATIVE RELATIVE FREQUENCY
 Cumulative frequency / total frequency
 (Cumulative frequency / total frequency) x 100
HISTOGRAM
 Describes a frequency distribution by using a
series of adjacent rectangles, each of which has a
length that is proportional to the frequency of the
observations within the range of values it
represents
 Represents quantitative data
 y-axis: Frequency ; x-axis: Classes
CLASS
 Each category of the frequency distribution
FREQUENCY
 The number of data values falling within each
class
CLASS LIMITS
 The boundaries for each class
 These determine which data values are assigned
to that class
CLASS INTERVAL
 The width of each class
 This is the difference between the lower limit of the
class & the lower limit of the next higher class
 When a frequency distribution is to have equally
wide classes, the approximate width of each class
is
CLASS MARK
 The midpoint of each class
 Midway between the upper & lower class limits
GUIDELINES FOR THE FREQUENCY DISTRIBUTION
 Set of classes must be mutually exclusive. There
should be no overlap between classes & limits
 The set of classes must be exhaustive. No data
values should fall outside the range covered by
the frequency distribution.
 If possible, the classes should have equal widths.
Unequal class widths make it difficult to interpret
both frequency distributions & their graphical
presentations.
 Selecting the number of classes to use is a
subjective process.
 Whenever possible, class widths should be round
numbers.
 If possible, avoid using open-end classes. These
are classes with either no lower limit or no upper
limit.
STEPS IN CREATING A FREQUENCY DISTRIBUTION
TABLE
1. Find the highest and lowest value.
2. Find the range
- Highest value – lowest value
3. # of classes (number of rows/distinct
classes/groupings): Sturges’ Rule
- K = 1 +3.322(log10n)
4. Class width (thickness of a class):
- Width = Range / K
- Classes should not overlap
- Width should be the same
- All raw data should be slotted in a class
5. Lower limits of 1st class (lesser than the lowest value
in the data)
6. Upper limit (add the width to the lower limit)
7. Define the classes
- First class includes the lowest value in the data
set.
8. Interpretation
FREQUENCY POLYGON
 Consists of line segments connecting the points
formed by the intersections of the class marks with
the class frequencies
 Relative frequencies or percentages may also be
used in constructing the figure
 Empty classes are included at each end so the
curve will interest the horizontal axis
 y-axis: relative frequency ; x-axis: classes / class
marks (midpoints)
OGIVE
 A graphical display providing cumulative values for
frequencies, relative frequencies or percentages
 These values can either be “greater than” or “less
than”
 y-axis: percentage of observations less than upper
limit of each class ; x-axis: class marks (midpoints)
STEM-AND-LEAF DISPLAY
 A variant of the frequency distribution, uses a
subset of the original digits as class descriptors
 A given data value can be represented only once
in a display
 All values must be expressed in terms of the same
stem digit & the same leaf digit
  Shows just 2 figures for each data value
 If placed horizontally, looks like a histogram
DOT PLOT
 Displays each data value as a dot & allows us to
readily see the shape of the distribution as well as
high & low values
BAR CHART
 Represents frequencies according to the relative
lengths of asset of rectangles, but it differs in 2
respects from the histogram:
- (1) the histogram is used in representing
quantitative data, while the bar chart represents
qualitative data
- (2) adjacent rectangles in the histogram share a
common side, while those in the bar chart have
a gap between them
 y-axis: classes; x-axis: frequency
LINE GRAPH
 Is capable of simultaneously showing values of 2 SIMPLE TABULATION
quantitative variables (y, or vertical axis & x, or  Deals with 1 variable
horizontal axis); it consists of linear segments Count of Engine
connecting points observed or measured for each Engine Total
variable 1 17
 y-axis: frequency ; x-axis: classes 2 13
PIE CHART Grand Total 30
 Is a circular display divided into sections based on
either the number of observations within or the CROSS TABULATION
relative values of the segments  Deals with 2 or more variables
 It can be constructed by using the principle that a Engine
Air-conditioning Grand
circle contains 360 degrees 1 2 Total
 The angle for each piece can be calculated as 1 8 9 17
follows 2 5 8 13
Grand
13 17 30
Total

PICTOGRAM CHAPTER 3
 Can describe frequencies or other values of ARITHMETIC MEAN
interest  Arithmetic average / mean
 Can be misleading  Sum of the data divided by the number of
THE SCATTER DIAGRAM OR SCATTERPLOT observations
 2-dimensional dotplot  Most common measures of central tendency
 Each point in the diagram represents a pair of  GROUPED DATA
known or observed values of 2 variables, generally
referred to as y and x, with y represented along μ = Σfimi/Σfi
the vertical axis and x represented along the  RAW DATA
horizontal axis. - For a population
 2 variables are referred to as: μ = Σxi/N
- dependent (y) variable - For a sample
- independent (x) variable
 A direct (positive) linear relationship between the x̅ = Σxi/n
variables THE WEIGHTED MEAN/WEIGHTED AVERAGE
- Positive slope  Each data value is weighted according to its
- X & Y are increasing together relative importance
 An inverse (negative) linear relationship between  RAW DATA
the variables negative slopes - For a population
- Negative slope μ = (Σwixi)/(Σwi)
- Y decreasing & X increasing - For a sample
x̅ = (Σwixi)/(Σwi)
THE MEDIAN
 Value that has just as many values above it as
below it
  GROUPED DATA RANGE
Md = L + (N/2 -Cfp)/(fmed) x w  Simplest measure of dispersion
 Difference between the highest and lowest
 RAW DATA
values
- For odd numbers, median will be halfway
between 2 values in the middle when the values  Weakness of being able to recognize only the
extreme values in the data
are arranged
- If there is even one very extreme values, the
(N+1)/2 range can be a large number that is misleading
- For even numbers to the unwary
N/2 MIDRANGE
THE MODE  Variant of the range
 RAW DATA  The average of the lowest data value and
- A value that occurs with the greatest frequency highest data value
- When there are 2 modes, a distribution of values  Vulnerable to the effects of extremely low or
is referred to bimodal. high outliers in the data
- There can be no mode  Sometimes used as a very approximate
 GROUPED DATA measure of central tendency
- Midpoint of modal class
- Modal class has the greatest frequency QUARTILES
 Separate the data into equal-size groups in
COMPARISON OF THE MEAN, MEDIAN AND MODE order of numerical value
 Mean  First quartile
- gives equal consideration to even very extreme Q1 = (N+1)/4
values in the data  Second quartile (the median)
- influenced of one or two very low or high values
- Mean makes more complete use of the data Q2 = 2(N+1)/4
 Median  Third quartile
- tends to focus more closely on those in the Q3 = 3(N+1)/4
middle of the data array
 Mode INTERQUARTILE RANGE
- Can have more than one mode, but only one  Difference between the third quartile & the first
value for mean and median quartile
- Tends to be less useful than the mean & median  Distance between 75% and 25% values
as a measure of central tendency
Q3 – Q1
DISTRIBUTION SHAPE AND MEASURES OF
CENTRAL TENDENCY QUARTILE DEVIATION
 SYMMETRICAL DISTRIBUTION: left and right  One-half the interquartile range
sides of the distribution are mirror images of each (Q3 – Q1)/2
other
 NORMAL DISTRIBUTION: single mode, bell- RESIDUALS
shaped  Difference between each data value and the
 SKEWNESS: refers to the tendency of the group mean
distribution to “tail off” to the right or left - Left of the mean - > 0
- SYMMETRICAL DISTRIBUTION: mean, - Right of the mean + < 0
median & mode are the same (only true for  GROUPED DATA
unimodal distribution, not possible for bimodal - For a population
distributions)
- POSTIVIELY SKEWED DISTRIBUTION: mean Residuals = xi - μ
is greater than the median, which in turn is - For a sample
greater than the mode Residuals = xi - x̅
*median will tend to be a better measure of
central tendency than the mean MEAN ABSOLUTE DEVIATION (MAD)
- NEGATIVELY SKEWED DISTRIBUTION: less  Average deviation or average absolute deviation
than the median which in turn is less than the
 The average of the absolute values of
mode
differences from the mean
*median is less influenced by extreme values
- For a population
and tends to be a better measure of central
tendency than the mean MAD = Σ|xi – μ| / N
- For a sample
 MAD = Σ|xi – x̅| / n  About 95% of the observations will fall within 2
standard deviations of the mean
VARIANCE
 Practically all of the observations will fall within 3
 Common measure of dispersion, includes all
standard deviations of the mean
data values
 GROUPED DATA
STANDARDIZED DATA
- For a population
 Based on this concept & involves expressing
σ2 = Σ[fi (mi – μ)2] / N each data value in terms of its distance (in
σ2 = Σfi(mi)2 – N(μ)2 / N standard deviations) from the mean
- For a sample  Have no units
 How far above or below the individual value is
s2 = Σ[fi (mi – x̅)2] / (n-1) composed to be population mean in units of
s2 = Σfi (mi)2 – n(x̅)2 / (n-1) standard deviation
 RAW DATA  A negative z means the data value falls below
- For a population the mean
 Mean will always be zero (0)
σ2 = Σ(xi – μ)2 / N  For the population
σ2 = Σ(xi)2 – N(μ)2 / N zi = (xi - μ)/σ
- For a sample  For the sample
s2 = Σ(xi – x̅)2/(n-1) zi = (xi - x̅)/s
s2 = Σ(xi)2 – n(x̅)2/(n-1)
THE COEFFICIENT OF VARIATION
STANDARD DEVIATION  Indicated relative amount of dispersion in the
 Positive square root of the variance of either a data
population or a sample  Enables us to easily compare the dispersion of 2
 Important measure of dispersion because it is sets of data that involve different measurement
the basis for determining the proportion of data units or differ substantially in magnitude
values within certain distances on either side of  For a population
the mean for certain types of distribution CV = (σ/μ) x 100
 GROUPED DATA & RAW DATA  For a sample
- For a population
σ = √σ 2 CV = (s/x̅) x 100
- For a sample CHAPTER 4: DATA COLLECTION AND SAMPLING
s = √s2 METHODS
TYPES OF STUDIES
CHEBYSHEV’S THEOREM 1. Exploratory Research
 When either a population or sample has a small 2. Descriptive Research
standard deviation, individual observation will 3. Causal Research
tend to be closer to the mean 4. Predictive Research
 A large standard deviation will result when
individual observations are scattered widely EXPLORATORY RESEARCH
about their mean  Helps us become familiar with the problem situation,
 Specifies the minimum percentage of identify important variables & use these variables to
observations that will fall within a given number form hypotheses that can be tested in subsequent
of standard deviations from the mean, research
regardless of the shape of distribution  Can also be of a qualitative nature
 For either a sample or a population, the  Understand the problem, identify relevant variables,
percentage of observations that fall within k (for formulate hypothesis
k>1) standard deviations of the mean will be at  No prior study has been done before
least DESCRIPTIVE RESEARCH
2
(1-1/k ) x 100  Needs exploratory study, more information than
exploratory
 Establish reliable measurements
THE EMPIRICAL RULE
CAUSAL RESEARCH
 Standard deviation rule
 Determine the relationship among variables
 Applies only to distribution that are ball shaped
 To determine whether one variable has an effect on
& symmetrical
another
 About 68% of the observations will fall within 1
standard deviation of the mean
 Should be pointed out that statistical techniques
alone cannot prove causality
 Proof must be established on the basis of
quantitative findings along with logic
PREDICTIVE RESEARCH
 Needs causal study
 Use analysis to forecast
 Attempt to forecast some situation or value that will
occur in the future
THE RESEARCH PROCESS
1. Define the problem
2. Decide on the type of data required
3. Determine through what means the data will be
obtained
4. Plan collection of data/select a sample
5. Collect & analyze data
6. Draw conclusion & report findings
7. Make decisions in terms of research
SOURCES OF DATA
PRIMARY DATA
 Data generated by the researcher of this study
 Survey, experimental, observational research
 Tend to require more time & expense than
secondary data
SECONDARY DATA
 Gathered by someone else for some other purpose
- INTERNAL: sources within the researcher’s
organization
- EXTERNAL: sources including governmental,
trade, commercial & internet sources
SURVEY RESEARCH
 Communication with a sample of individuals in order
to generalize on the characteristics of the population
from which they were drawn
TYPES OF SURVEYS
THE MAIL SURVEY
 A mailed questionnaire is typically accompanied by
a cover letter & a postage-paid return envelope for
the respondent’s convenience
THE PERSONAL INTERVIEW
 An interviewer personally secures the respondent’s
cooperation & carries out what could be described
as “purposeful conversation” in which the
respondent replies to the questions asked.
TELEPHONE INTERVIEW
 Similar to the personal interview, but uses the
telephone instead of personal interaction.
 An interview conducted over the telephone
WEB SURVEY
 A questionnaire completed over the internet
QUESTIONNAIRE DESIGN
 Also referred to as DATA COLLECTION
INSTRUMENT
 Either filled out personally by the respondent or
administered & completed by an interviewer
 May contain 3 types of questions:
- (1) multiple choice – several alternatives to
choose from
- (2) dichotomous – only 2 alternatives available
- (3) open-ended – respondent is free to formulate
own answer & expand on the subject of the
questions
 Problems with questionnaires
- (1) The vocabulary level may be inappropriate
for the type of person being surveyed
- (2) the respondent may assume a frame of
reference other than the one the researcher
intended
- (3) the question may contain “leading” words or
phrases that unduly influence the response
- (4) the respondent may hesitate to answer a
question that involves a sensitive topic
ERRORS IN SURVEY RESEARCH
 Survey research may lead to several different kinds
of errors
 Sampling error is a random error
- Nondirectional or nonsystematic, because
measurements exhibiting random error are just
as likely to be too high as they are to be too low
 Response & nonresponse errors
- Directional or systematic type
1. Sampling Error
2. Non-sampling Error
SAMPLING ERROR
 Occurs because a sample has been taken instead of
a complete census of the population
 Determination of the sample size is necessary to
have a given level of confidence that the sample
proportion will not be in error by more than a
specified amount
RESPONSE ERROR
 Some respondents may distort the truth (to put it
kindly) when answering a question
 Biased questions can encourage such response
errors
NONRESPONSE ERROR
 Not everyone in the sample will cooperate in
returning the questionnaire or in answering an
interviewer’s questions
 Those who respond may be different from those who
don’t
EXPERIMENTATION & OBSERVATIONAL
RESEARCH
EXPERIMENTS
 Purpose: to identify cause-and-effect relationships
between variables
 2 key variables in an experiment:
- (1) independent variable or treatment
- (2) dependent variable or measurement
EXPERIMENTAL GROUP
 Persons or objects receiving a treatment
CONTROL GROUP
 Those who are not exposed to the treatment
EXTRANEOUS VARIABLES
 Outside variables that are not part of the experiment,
but can influence the results
2 KINDS OF VALIDITY:
INTERNAL VALIDITY
 Refers to whether T really made the difference in the
measurements obtained
EXTERNAL VALIDITY
 Even if T did make the difference, asking whether
the results can be generalized to other people or
settings
SECONDARY DATA
 Collected by someone other than the researcher, for
purposes other than the problem or decision at
hand; such data can be either internal or external
2 TYPES OF SECONDARY DATA:
1. Internal
2. External
INTERNAL SECONDARY DATA
 Generated by your own firm or organization
 Internal secondary data have traditionally existed in
the form of accounting or financial information
 Anything in written form that has ever been
generated within the company falls within the real of
internal secondary data
EXTERNAL SECONDARY DATA
 Gathered by someone outside the firm or
organization
SAMPLING METHODS
 Can be categorized as probability or nonprobability
 PROBABILITY SAMPLING
- each person or element in the population has a
known (or calculable) chance of being included
in the sample
- Allow us to estimate the maximum amount of
sampling error between our sample statistic &
the true value of the population parameter being
estimated
- Each person or element in the population has
some (nonzero) known or calculable chance of
being included in the sample
- However, every person or element may not have
an equal chance for inclusion
 NONPROBABILITY
- Primarily used in exploratory research studies
where there is no intention of making statistical
inferences from the sample to the population
PROBABILITY SAMPLING
1. Simple random sampling
2. Systematic sample
3. Two-way stratified sample
4. Cluster sample
THE SIMPLE RANDOM SAMPLING
 Every person or element in the population has an
equal chance of being included in the sample
 A practical alternative to placing names in hat or box
is to identify each person or element in the
population with a number, then use a random
number table to select those who will make up the
sample
THE SYSTEMATIC SAMPLE
 We randomly select a starting point between 1 & k,
then sample every kth element from the population
 PROBLEMS:
- PERIODICITY: a phenomenon where the order
in which the population appears happens to
include a cyclical variation in which the length of
the cycle is the same as the value of k that we
are using in selecting the sample
o Not a common problem, the possibility of its
existence should be considered when
undertaking a systematic sample
STRATIFIED SAMPLE
 The population is divided into layers or strata then a
simple random sample of member s from each
stratum is selected
 Strata members have the same percentage
representation in the sample as they do in the
population
TWO-WAY STRATIFIED SAMPLE
 A sample can also be stratified on the basis of 2 or
more variables at the same time the sample has
been forced to take on the exact percentage
breakdown as the population in terms of 2 different
measurements or characteristics
 Forces the composition of the sample to be the
same as that of the population, at least in terms of
the stratification variable(s) selected
o Important if some strata are likely to differ
greatly from others with regard to the variable(s)
of interest
CLUSTER SAMPLE
 Involves dividing the population into groups then
randomly selecting some of the groups & taking
either a sample or census of the members of the
groups selected
 Members of the population may not have the same
probability of inclusion, but these probabilities could
be determined if we wished to exert the time & effort
NONPROBABILITY SAMPLING
 Not every unit in the population has a chance of
being included in the sample & the process involves
at least some degree of personal subjectivity instead
of following predetermined, probabilistic rules for
selection.
4 TYPES OF NONPROBABILITY SAMPLING:
1. Convenience Sample
2. Quota Sample
3. Purposive Sample
4. Judgment Sample
CONVENIENCE SAMPLE
 Members of such samples are chosen primarily
because they are both readily available & willing to
participates
QUOTA SAMPLE
 This is similar to stratified probability sample
described previously, except that members of the
various strata are not chosen through the use of a
probability sampling technique
 This type of sample is far inferior to the stratified
sample in terms of representativeness
PURPOSIVE SAMPLE
 Members are chosen specifically because they’re
not typical of the population
JUDGMENT SAMPLE
 This sample is selected on the basis that the
researcher believes the members to be
representative of the population
CHAPTER 5: PROBABILITY
EXPERIMENT
 An activity or measurement that results in an
outcome
SAMPLE SPACE
 All possible outcome of an experiment
EVENT
 One or more of the possible outcomes of an
experiment; a subset of the sample space
 The probability for any event will be a number
between 0 and 1
PROBABILITY
 A number between 0 and 1 that expresses the
chance that an event will occur
0 ≤ P(A) ≤ 1
For any event, the probability will be no less than 0 and
no greater than 1.
P(A) + P(A’) = 1
Either the event will occur (A) or it will not occur (A’). A’
is called the complement of A.
3 APPROACHES TO PROBABILITIES
1. Classical approach
2. Relative Frequency Approach
3. Subjective Approach
THE CLASSICAL APPROACH
 Describes a probability in terms of the proportion of
times that an event can be theoretically expected to
occur
 Classical probabilities find their greatest application
in games of chance, but they are not so useful when
we are engaged in real-world activities where either:
- (1) the possible outcomes are not equally likely
- (2) the underlying process are less well known
THE RELATIVE FREQUENCY APPROACH
 Probability is the proportion of times an event is
observed to occur in a very large number of trials:
Relative frequency probability
For a very large number of trials,
 The relative frequency approach to probability
depends on what is known as the law of large
numbers
LAW OF LARGE NUMBERS
 Over a large number of trials, the relative frequency
with which an event occurs will approach the
probability of its occurrence for a single trial
THE SUBJECTIVE APPROACH
 The subjective approach to probability is judgmental,
representing the degree to which one happens to
believe that an event will or will not happen
SUBJECTIVE PROBABILITIES
 Hunches or educated guesses
 Neither based on mathematical theory nor
developed from numerical analyses of the
frequencies of past events
PROBABILITIES & ODDS
ODDS
 Sometimes used as a way of expressing the
likelihood that something will happen
 Chance of the event occurring is ___ times the
chance that it will not occur
 Typically expressed in terms of the lowest applicable
integers
 Odds against the occurrence of the event are
reverse of the odds in favor
Conversion from odds to probability & vice versa:
1. If the odds in favor of an event happening are A
to B, or A:B, the probability being expressed is
2. If the probability of an event is x (with 0 ≤ x ≤ 1),
the odds in favor of the event are “x to (1 – x)” or
“x:(1-x)”
UNIONS & INTERSECTIONS OF EVENTS
MUTUALLY EXCLUSIVE EVENTS
 If one event occurs, the other cannot occur.
 An event (A) and its complement (A’) are always
mutually exclusive.
EXHAUSTIVE EVENTS
 A set of events is exhaustive if it includes all the
possible outcomes of an experiment
 The mutually exclusive events A and A’ are
exhaustive because one of them must occur
 When the events within a set are both mutually
exclusive & exhaustive the sum of their probabilities
is 1.0
- One of them must happen & they include all the
possibilities
- Entries within a relative frequency table are
mutually exclusive & exhaustive, their sum will
always be 1.0
INTERSECTIONS OF EVENTS
 2 or more events occur at the same time
 Represented by “A and B”

UNION OF EVENTS
 At least 1 of a number of possible events occurs
 Represented by “A or B”
ADDITION RULES FOR PROBABILITY
WHEN EVENTS ARE MUTUALLY EXCLUSIVE
 When events are mutually exclusive, the occurrence
of one means that none of the others can occur
 The probability that one of the events will occur is
the sum of their individual probability
Rule of addition when events are mutually exclusive:
P(A or B) = P(A) + P(B)
WHEN EVENTS ARE NOT MUTUALLY EXCLUSIVE
 When events are not mutually exclusive, 2 or more
of them can happen at the same time
 The general rule of addition can be used in
calculating probabilities
General rule of addition when events are not mutually
exclusive:
P(A or B) = P(A) + P(B) – P(AB)
MULTIPLICATION RULES FOR PROBABILITY
MARGINAL PROBABILITY
 The probability that a given event will occur
 No other events re taken into consideration
 Typical expression is P(A)
CONDITIONAL PROBABILITY
 The probability that an event will occur, given that
another event has already happened
 A typical expression is P(A|B), with the verbal
description, “the probability of A, given B”
Conditional probability of event A, given that B has
occurred:
P(A|B) =
MULTIPLICATION RULES
 Determine the probability that 2 events will both
happen or that 3 or more events will all happen
 Depend on whether the events are INDEPENDENT
or DEPENDENT
INDEPENDENT EVENTS
 Events are independent when the occurrence of one
event has no effect on the probability that another
will occur
 When events are independent, their joint probability
is the product of their individual probability
Multiplication rule when events are independent:
P(A and B) =P(A) x P(B)
DEPENDENT EVENTS
 Events are dependent when the occurrence of one
event changes the probability that another will occur
WHEN EVENTS ARE NOT INDEPENDENT
 When events are not independent, the occurrence of
one will influence the probability that another will
take place
 Under these conditions, a more general
multiplication rule applies:
Multiplication rule when events are not independent
P(A and B) = P(A) x P(B|A)
BAYES’ THEOREM
 Deals with sequential events, using information
obtained about a second event to revise the
probability that a first event occurred
Bayes’ theorem for the revision of probability:
General form
Probability of event A, given that event B has occurred
COUNTING: PERMUTATIONS & COMBINATIONS
THE PRINCIPLE OF MULTIPLICATION
 If following a first event that can happen n1 ways, a
second event can then happen n2 ways, the total
number of ways both can happen is n1n2
 Alternatively, if each of k independent events can
occur in n different ways, the total number of
possibilities is nk
FACTORIAL
 Exclamation point is just a mathematical way of
saving space
n! = n x (n – 1) x (n – 2) x … x 1
Note: 0! Is defined as 1
PERMETUATIONS
 Refer to the number of different ways in which
objects can be arranged in order
 In a permutation, each item can appear only once &
each order of the items arrangement constitutes a
separate permutation
 The number of possible arrangements can be
determined as follows:
Number of permutations of n objects taken r at a time:
COMBINATIONS
 Consider only the possible set of objects, regardless
of the order in which the members of the set are
arranged
 The number of possible combinations of n objects
taken r at a time will be as follows:
Number of combinations of n objects taken r at a time:
CHAPTER 6: DISCRETE PROBABILITY
DISTRIBUTIONS
PROBABILITY DISTRIBUTIONS
 As the relative frequency distribution that should
theoretically occur for observations from a given
population
 It can be helpful to proceed from (1) basic
understanding of how a natural process seems to
operate in generating events to (2) identifying the
probability that a given event may occur
RANDOM VARIABLES: DISCRETE V.S.
CONTINUOUS
RANDOM VARIABLE
 A variable that can take on different values
according to the outcome of an experiment
 Random because we don’t know ahead of time
exactly what value it will have following the
experiment
 Can either be:
- DISCRETE RANDOM VARIABLE
o A random variable that an take on only
certain values along an interval, with the
possible values having gaps between them
- CONTINUOUS RANDOM VARIABLE
o A random variable that can take on a value
at any point along an interval
NATURE OF DISCRETE PROABIBILITY
DISTRIBUTION
DISCRETE PROBABILITY DISTRIBUTION
 A listing of all possible outcomes of an experiment,
along with their respective probabilities of
occurrence
 Discrete probability distributions can be expressed
as histograms, where the probabilities for the
various x values are expressed by heights of a
series of vertical bar
CHARACTERISTICS OF A DISCRETE PROBABILITY
DISTRIBUTION
1. For any value of x, 0 ≤ P(x) ≤ 1
2. The values of x are exhaustive: The probability
distribution includes all possible values
3. The values of x are mutually exclusive: Only one
value can occur for a given experiment
4. The sum of their probabilities is one or
ΣP(x) = 1.0
THE MEAN & VARIANCE OF A DISCRETE
PROBABILITY DISTRIBUTION
 Used measures of central tendency & dispersion to
describe typical observations & scatter in the data
values
 It can be useful to describe a discrete probability
distribution in terms of its central tendency &
dispersion
 EXPECTED VALUE: mean of a discrete probability
distribution for a discrete random value
- Referred to as E(x) or μ
- Weighted average of all the possible outcomes
with each outcome weighted according to its
probability occurrence
 VARIANCE: the expected value of the squared
difference between the random variable & mean or
E[(x – μ)2]
General formulas for the mean & variance of a discrete
probability formula
Mean
μ = E(x) or μ = ΣxP(x) for all possible values of x
Variance
σ2 = E[(x – μ)2] or σ2 = Σ(x – μ)2P(x)
For all possible values of x & the standard
deviation is
σ = √σ2
THE BINOMIAL DISTRIBUTION
 Deals with consecutive trials, each of which has 2
possible outcomes
 The binomial distribution relies on what is known as
the BERNOULLI PROCESS
 Family of distributions & the exact member of the
family is determined by the values of n & π
 The following observations may be made regarding
the Bernoulli process & the requirement that the
probability of success (π) remain unchanged
1. If sampling is done with replacement, the
person or other item selected from the
population observed then put back into the
population), π will remain constant from
one trial to the next
2. If sampling is done without replacement,
the number of trials (n) is very small
compared to population (N) of such trials
from which the sample is taken, as a
practical matter π can be considered to be
constant from 1 trial to the next
CHARACTERISTICS OF A BERNOULLI PROCESS:
1. There are 2 or more consecutive trials
2. In each trial, there are just 2 possible outcomes
– usually denoted as success or failure
3. The trials are substantially independent; that is
the outcome in any trial is not affected by the
outcomes of earlier trials & it does not affect the
outcomes of later trials
4. The probability of success remains the same
from 1 trial to the next
 The discrete random variable, x, is the number of
successes that occur in n consecutive trails of the
Bernoulli process.
The binomial probability distribution:
The probability of exactly x successes in n trials is
πx(1- π)n-x
Mean
μ = E(x) = nπ
Variance
σ2 = E[(x – μ)2] = nπ(1 – π)
CHAPTER 7: CONTINOUS PROBABILITY
DISTRIBUTIONS
 Describe probabilities associated with random
variables that are able to assume any of an infinite
number of values along an interval
 Are smooth curves where probabilities are
expressed as areas under the curves
- Curve is a function of x
- F(x) is referred to as a probability density
function
 Probabilities in terms of the probability that x will be
within a specified interval of values
THE PROBABILITY DISTRIBUTION FOR A
CONTINUOUS RANDOM VARIABLE
1. The vertical coordinate function of x, described
f(x) & referred to as the probability density
function
2. The range of possible x values along the
horizontal axis
3. The probability that x will take on a value
between a & b will be the area under the curve
between points a & b
- The probability density function f(x) for a given
continuous distribution is expressed in algebraic
terms & the areas beneath are obtained through
the mathematics of calculus
4. The total area under the curve will be equal to
1.0
NORMAL DISTRIBUTION
 A bell-shaped, symmetrical curve, the use of which
is facilitated by a standard table listing the
cumulative areas beneath
1. Many natural & economic phenomena tend to be
approximately normally distributed
2. It can be used in approximating other
distributions including binomial
3. Sample means & proportions tend to be
normally distributed whenever repeated samples
are taken from a given population of any shape
 Mean, median & mode are all at the same position
on the horizontal axis
 The curve is asymptotic, approaching the horizontal
axis at both ends, but never intersecting with it
 Total area beneath the curve is equal to 1.0
The normal distribution for the continuous random
variable, x (with -∞ ≤ x ≤ +∞)
e-(1/2)[(x-μ)/ σ]2
 The shape of the curve & its location along the x
axis will depend on the values of the standard
deviation & mean
AREAS BENEATH THE NORMAL CURVE
 Regardless of the shape of a particular normal
curve, the areas beneath it can be described for any
interval of our choice
 For any normal curve, the areas beneath the curve
will be as follows
- About 68.5% of the area is in the interval
μ- σ to μ+ σ
- About 95.5% of the area is in the interval
μ- 2σ to μ+ 2σ
- Nearly all pf the area (about 99.7%) is in the
interval μ- 3σ to μ+ 3σ
STANDARDIZING
 The normal curve & expressing the original x values
in terms of their number of standard deviations away
from the mean
 Result is referred to as a STANDARD (OR
STANDARDIZED) normal distribution, & it allows us
to use a single table to describe areas beneath the
curve
 The process is z-score:
z = the distance from the mean, measured in standard
deviation units
x = the value of x in which we are interested
μ = the mean of the distribution
σ = the standard deviation of the distribution
USING THE STANDARD NORMAL DISTRIBUTION
TABLE
1. Convert the information provided into one or two
more z-scores
2. Use the standard normal table to identify the
area(s) corresponding to the z-score(s). The
table provides cumulative areas to the z value of
interest
3. Interpret the result in such a way as o answer
the original question
CHAPTER 8: SAMPLING DISTRIBUTIONS
SAMPLING DISTRIBUTION OF THE MEAN OR
DISTRIBUTION OF SAMPLE MEANS
 The probability distribution of these sample means
for all possible samples of that particular size
4 IMPORTANT CHARACTERISTICS OF SAMPLING
DISTRIBUTIONS:
1. The sampling distribution of the mean will have
the same mean as the original population from
which the samples were drawn
2. The standard deviation of the sampling
distribution of the mean is referred to as the
standard error of the mean, or σx̅.
- Standard deviation can be calculated as the
positive square root of its variance
3. If the original population is normally distributed,
the sampling distribution of the mean will also be
normal.
4. If the original population is not normally
distributed, the sampling distribution of the mean
will be approximately normal for large sample
sizes & will more closely approach the normal
distribution as the sample size increases.
- Known as the central limit theorem
SAMPLE PROPORTION
 When a discrete random variable is the result of a
Bernoulli process, with x = the number of successes
in n trials, the result can be expressed as a sample
proportion, p:

 Sample proportion or sample mean can be
considered a random variable that will take on
different values as the procedure leading to the
sample proportion is repeated
SAMPLING DISTRIBUTION OF THE PROPORTION
 The result of the probability distribution
 It will have an:
- EXPECTED VALUE (π)
o Probability of success on any given trial
- STANDARD DEVIATION σp
WHEN THE POPULATION IS NORMALLY
DISTRIBUTED
 When a great many simple random samples of size
n are drawn from a population that is normally
distributed, the sample means will also be normally
distributed
 This will be true regardless if the sample size
 Standard error of the distribution of these means will
be smaller for larger values of n
SAMPLING DISTRIBUTION OF THE MEAN, SIMPLE
RANDOM SAMPLE FROM A NORMALLY
DISTRIBUTED POPULATION
 Regardless of the sample size, the sampling
distribution of the mean will be normally distributed
with
Mean
E(x) = μx̅ = μ
Standard Error
μ = population mean
σ = population standard deviation
n = sample mean
 z-score for the sampling distribution of the
mean, normally distributed population
z = distance from the mean, measured in standard error
units
x = value of the sample mean in which we are interested
μ = population mean
σx̅ =standard error of the sampling distribution of the
mean or σ/√n
WHEN THE POPULATION IS NOT NORMALLY
DISTRIBUTED
 Provided that the sample size is large (n≥30) the
sampling distribution of the mean can still be
assumed to be normal
 This is because of what is known as the central limit
theorem:
- For large, simple random samples from a
population that is not normally distributed, the
sampling distribution of the mean will be
approximately normal, with the mean μx̅ = μ &
the standard error σx̅ = σ/√n. As the sample size
(n) is increased, the sampling distribution of the
mean will more closely approach the normal
distribution.
- Basic to the concept of statistical inference
because it permits us to draw conclusions about
the population based strictly on sample data &
without having any knowledge about the
distribution of the underlying population.
THE SAMPLING DISTRIBUTION OF THE
PROPORTION
The proportion of successes in a sample consisting of n
trials will be
 Whenever both nπ & n(1 – π) are ≥ 5, the normal
distribution can be used to approximate the
binomial.
 When these conditions are satisfied & the procedure
leading to the sample outcome is repeated a great
many times, the sampling distribution of proportion
(p) will be approximately normally distributed, with
this approximation becoming better for larger values
of n & for values of π closer to 0.5
- Sampling distribution of the proportion has an
expected value & a standard error
- Size of sample becomes larger, the standard
error becomes smaller
Sampling distribution of the proportion, p:
Mean = E(p) = π
Standard Error
π = population proportion
n = sample size
z-score for a given value of p:
SAMPLING DISTRIBUTIONS WHEN THE
POPULATION IS FINITE
 When sampling is without replacement & from a
finite population
 Whether we are dealing with the sampling
distribution of the mean (x̅) or the sampling
distribution of proportion (p), the same correction
factor is applied
 Depends on the sample size (n) versus the size of
the population (N) & as a rule of thumb, should be
applied whenever the sample is at least 5% as large
as the population
 n < 0.05N, the correction will have very little effect
 Finite correction factor is applied when n ≥ 0.05N
 Purpose: to reduce the standard error according to
how large the sample is compared to the population
- The purpose is to arrive at a corrected (reduced)
value of the standard error of the sampling
distribution