Statistical

Analysis
Urmia University
Faculty of Economics and Management
Department of Accounting & Finance

Master Program in Accounting

By
Dr. Gholamreza Mansourfar
 Evaluation
Assignments 30%
Project 30%
Final Exam 40%
Basic Concepts
What is a variable?
A variable is a characteristic that can take on different values for different members of the
group under study.

Continuous
Category of Variables
Discrete
Independent

Measurement Dependent
The process of assigning numbers to characteristics according to a defined rule

Not all measurement is the same

The measurement scale of the dependent variable is one of the important factors in
determining the appropriate statistical methods used to analyze the data of a
particular research study.
Basic Concepts
Nominal scale

The process of classifying different objects into

categories based upon some defined characteristics.
Examples are sex, color of hair/eyes, ethnic background,
makes ofOrdinal
car andScale
so on.
Data categories have some logical order.
Level of Measurement Scale

Interval Scale

Data categories have some logical order.

Equal differences in the characteristic are represented by
Ratio Scale
equal differences in the numbers assigned to the categories.
The point zero is just another point on the scale
Data categories are mutually exclusive.
Data categories have some logical order.
Equal differences in the characteristic are represented by equal
differences in the numbers assigned to the categories.
The point zero reflects an absence of the characteristic.
Basic Concepts

What Factors determine the most appropriate statistical techniques?

•Research objectives/questions/purpose of your study.

•Measurement scales you use in your research.

•Research design of your studies.

•Nature of your data – meeting normality and/or equality of variance

assumptions for parametric tests.
Basic Concepts
Table for selecting Descriptive Measures Based on Scales of Measurement
MEASURES OF CENTRAL
CLASSIFICATION GRAPHICAL MEASURES
TENDENCY
MEASURES OF DISPERSION

Binomial or Multinomial
NOMINAL Bar graphs Mode
variance

ORDINAL Histogram or Bar Median Range P25 – P75

Histogram with
INTERVAL Mean Standard Deviation (s)
normal curve

Histogram with Geometric mean Standard Deviation (s)

RATIO
normal curve Harmonic mean Variance
Basic Concepts
NUM BER OF S T A T IS T IC A L
M E A SU R M E N T PU R PO SE
V A R IA B L E PR O C ED U R E
SC A LE
T w o variab le s C h i-sq uare test of In d ep end ent
M u tlip le variables S p earm an R h o
R elatio n sh ip /
P red ictio n Lo gistic R egression
C ategorical D iscrim inan t A n alysis
N o m in al/O rd in al (Y = C atego rical &
X o r X 's= N o n -catego rical)
O ne variab le C h i-squ are test o f G oodn ess o f Fit
D ifferen ce/ T w o variab les C h i-sq uare test o f H o m ogene ity
S im iliarity
T w o G rou p s M an n -W h itney T est
V A R IA B L E (S )
M o re th an tw o gro up s K ru skal W allis
M u tlip le variab les Lo glin ear M o d el

O ne variab le O n e-sam ple T -test

D ifference/
S im iliarity T w o variab les P aired S am ples T -test
T w o G rou p s In d ep end ent-S am p les T -test
N o n -categorical M o re th an tw o grou ps ANOVA
R atio /In terval
M u tlip le variab les MANOVA

T w o variab les P earso n 's r,

R elatio nsh ip / S im ple Lin ear R egression
P red ictio n
M utlip le variab les M u ltip le Lin ear R egression
P ath A nalysis
C an n o nical C o rrelation s
Basic Concepts
Normal Distribution

1- The most widely known and used of all distributions is Normal Distribution.

2- Many variables in business and industries are normally distributed.

3- When large enough sample sizes are taken, many statistics are normally
distributed regardless of the shape of the underlying distribution from which they
are drawn.

Probability Density Function of the Normal Distribution

Basic Concepts
Standard Normal Distribution (z distribution)
The standard normal distribution is a normal distribution with a mean of 0 and a
standard deviation of 1. Normal distributions can be transformed to standard normal
distributions by the formula:

where X is a score from the original normal distribution, μ is the mean of the original normal
distribution, and σ is the standard deviation of original normal distribution. A z score always
reflects the number of standard deviations above or below the mean a particular score is.
For instance, if a person scored a 70 on a test with a mean of 50 and a standard deviation of
10, then converting the test scores to z scores, an X of 70 would be:

So, a z score of 2 means the original score was 2 standard deviations above the mean. Note
that the z distribution will only be a normal distribution if the original distribution (X) is
normal.
Examples:
What is the probability of obtaining a score greater than 700 on a GMAT test that has
a mean of 494 and a standard deviation of 100? Assume GMAT scores are normally
distributed.
x   700  494 z  2 .06  f ( z  2.06 )  0 .9803
z    2 . 06
 100 f ( z  2 .06 )  1  0 .9803  0 .0197

For the same GMAT examination, what is the probability of randomly drawing a score that
is 550 or less?

z
x   550  494
  0.56 z  0.56 f (z  0.56)  0.7123
 100
What is the probability of randomly obtained a score between 300 and 600 on the GMAT
exam?
600  494
z 600   1 . 06
100
and
300  494
z 300    1 . 94
100

f (z 1.06)  0.8554 and f (z  1.941 f (z 1.94) 1 0.9738 0.0262

f (1.94  z  1.06)  0.8554  0.0262  0.8292

Examples:
What is the probability of getting score between 350 and 450 on the same GMAT exam?
A company produces lightbulbs whose lifetimes follow a normal distribution with mean 1.200 hours and
standard deviation 250 hours. If a lightbulb is chosen randomly from the company's output, what is the
probability that its lifetime will be between 900 and 1.300 hours'?

An investment portfolio contains stocks of a large number of corporations. Over the last year the rates of
return on these corporate stocks followed a normal distribution, with mean 12.2%, and standard
deviation 7.2%.
(a) For what proportion of these corporations was the rate of return higher than 20%?
(b) For what proportion of these corporations was the rate of return negative?
(c) For what proportion of these corporations was the rate of return between 5% and 15%?
I am considering two alternative investments. In both cases, I am unsure about the percentage return but
believe that my uncertainty can be represented by normal distributions with the means and standard
deviations shown in the accompanying table. I want to make the investment that is more likely to produce
a return of at least 10%. Which should I choose?
Basic Concepts
Sampling Reasons for Sampling Random Versus Nonrandom Sampling

Techniques of Random Sampling

Techniques of Nonrandom Sampling

Distribution of Sample Means:

In the inferential statistics process, a researcher selects a random sample from the population, computes a statistic on the
sample, and reaches conclusion about the population parameter from the statistics. In attempting to analyze the sample
statistics it is essential to know the distribution of the statistic.
In this section we the sample mean as the statistic.

Suppose we have a population: 6 7 8 9   7 .5

Let’s take all possible samples of size n = 2 from this population:

Important properties of the sampling distribution of means:

1- Mean:
The mean of the distribution of sample means is the mean of the population:  x  

2- Standard Deviation:

3- Shape:
 Non-normal Distribution of X
(Population)

Distribution of x

sample size is 2 sample size is 3

sample size is 4 sample size is 8

sample size is 16 sample size is 32

 Non-normal Distribution of X
(Population)

Distribution of x

sample size is 2 sample size is 3

sample size is 4 sample size is 8

Central Limit Theorem:

Distribution of sample means will
approach a normal distribution
as the sample size increases,
sample size is 16
though the distribution of
sample size is 32
population is not normal.
Basic Concepts
Z formula for Sample Means

Suppose that annual percentage salary increases for the chief executive officers of all mid-
x   size corporations are normally distributed with mean 12.2% and standard deviation 3.6%. A
z 
 random sample of nine observations from this population of percentage salary increases is
taken. What is the probability that the sample mean will be less than 10%?
n
10  12 . 2
z    1 . 83  P ( z   1 . 83 )  f z (  1 . 83 )  1  f (1 . 83 )  1  0 . 9664  0 . 0336
3 .6
9

If sample size is less x  

than 5% of the finite z  Finite correction
population size or  N  n factor
n<5%N n N 1
Basic Concepts

Distribution of Sample Proportion:

^
If p be the proportion of successes in a random sample of n observations from a
population in which the proportion of successes is p. Then
^
 ^ 
1- The sampling distribution of hasp mean p; that is: E p  p
 

^
p (1  p )
2- The sampling distribution of has
p standard deviation, that is: ^ 
p n
^

3- Z formula for sample proportions for n.p>5 would be: p p

z
p.q
n