Social Work Research &

Foundation and Concepts for

Understanding Statistics
What is the nature of social work research and
the stages of the research process?
What are statistics and how are they used in social work
practice, programs and policy analysis?
July 18, 2023
Lecturer: Cymber Orvie G. Quevedo
cymberquevedo@gmail.com
 PART 1 –
Basic Concepts in Statistics
PART 1 –
Descriptive Statistics
PART 2 –
Inferential Statistics
1. Definition of Statistics
2. Division of Statistics
3. Population and Sample
4. Types of Variable and Data
5. Scales of Data Measurement
6. Data Collection Methods
7. Data Presentation Methods
8. Sampling Techniques
Statistics is a mathematical science pertaining to :

- Collection of data
- Analysis of data
- Interpretation of data
- Presentation of data

in order to arrive at an effective decision.

 Analysis of Data
Collection of Data
refers to the extraction of
refers to the process
relevant information from
of obtaining
the given data where
numerical
numerical description can
measurements.
be formulated.

Interpretation of Data Presentation of Data

referred to as the task of refers to the tabulation of

drawing conclusions. Also data into tables, graphs, or
include the formulation of charts so that logical and
forecasts or predictions statistical conclusions can
about larger groups based de derived from the
on sample collected measurements.
 Division of Statistics
Descriptive Inferential

is used to summarize is used to model patterns in

the data, either the data, accounting for
numerically or randomness and drawing
graphically, and to inferences about the larger
describe the sample. population.

Mean Hypothesis Testing

Standard deviation Correlation & Regression
Frequency ANOVA
Proportion Modeling
 Population vs. Sample
Population is a collection of persons, objects, or
items of interest.
Sample is a portion of the whole.

Population
Population Sample
 What’s a Variable?
➢ a characteristic that varies from one
person or thing to another, i.e., it is any
characteristic that varies from one
individual member of the population
to another.
How variable vary across cases?

Quantitative Variable
- Numerical variable
- assumes data which are expressed in numerical values or obtained from
counting or measurement.

Ex. Height, weight, number of siblings, scores

Qualitative Variable
- Categorical Variable
- assumes data which are classified according to kind or characteristic by
which they differ.

Ex. Sex, marital status, eye color, occupation, college degree

How is quantitative data acquired?

•data acquired by means of

Discrete simple counting such as number
of students in a classroom,
Data number of households,
marriages, etc.

•data acquired through direct or

Continuous indirect measurement such as
Data weight, family income, speed of
a car, etc.
 4 Scales of Data Measurement
Discrete
Ratio Scale Continuous
Quantitative
Discrete
Interval Scale Continuous

Ordinal Scale
Qualitative
Nominal Scale
Levels of Measurement – was first proposed
by the American psychologist Stanley
Smith Stevens in 1946.
Methods of Collecting Data

Direct or
Interview Observation
Registration

Indirect or
Questionnaire
Experiment
Test
Methods of Presenting Data

Textual Method

The data is presented

in paragraph form.
Tabular Method

Classifying and
arranging data
in a table.
Semi-Tabular
Graphical Presentations

Bar Graphs
Line Graph
Pie Chart
Pictograph
Map Graph or Cartogram
Sampling

- is the process of determining the

elements of the sample and
conclusions are drawn about the
population as a part of the
inferential statistics process.
 Save Time

Save Save
Money Product

Reasons for
Sampling
Types of Sampling

Random Sampling Nonrandom Sampling

•Simple • Convenience
• Lottery •Judgment
• Table of Random Numbers
•Stratified • Quota
• Systematic • Snowball
•Cluster
• Multi-stage
Simple Random Sampling

Lottery Table of Random Numbers

Stratified Random Sampling
The population is divided into non-overlapping
subpopulations called strata.

Year Level Sample

First Year 250

Second Year 300

Third Year 40

Fourth Year 300

Systematic Sampling
every kth element is selected to produce a sample
size n from a population. Example: k = 5.
Cluster (Area) Sampling
dividing the population into non-overlapping areas
or clusters.
 Multi-stage Sampling
has several stages or phases in getting the sample
from the general population.
 Nonrandom Sampling Techniques

Convenience Sampling – elements for the

sample are selected for the convenience of the
researcher typically those are readily available
and/or willing to participate.

Judgment Sampling – elements selected for the

sample are chosen by the judgment of the
researcher which will result in saving time and
money.
 Nonrandom Sampling Techniques

Quota Sampling – population is stratified on

some characteristic and then elements selected for
the sample are chosen by nonrandom processes.

Snowball Sampling – survey subjects who fit a

desired profile are selected based on referral from
other survey respondents who also fit the desired
profile.
1. Definition of Statistics
2. Division of Statistics
3. Population and Sample
4. Types of Variable and Data
5. Scales of Data Measurement
6. Data Collection Methods
7. Data Presentation Methods
8. Sampling Techniques
 PART 1 –
Basic Concepts in Statistics
PART 1 –
Descriptive Statistics
PART 2 –
Inferential Statistics
9. Frequency Distribution
10. Statistical Display of Frequency Distribution
11. Measures of Central Tendency
12. Measures of Variation/Dispersion
13. Measures of Position/Location
14. Normal Distribution
15. Standard Normal Distribution
16. Measure of Skewness
17. Measure of Kurtosis
18. Empirical Rule of the Normal Distribution
 Frequency
Distribution
Frequency Distribution
is an arrangement of data in
tabular form where data are
grouped into different classes or
categories and then determining
the number of observations that
fall in each of the classes.
 Class interval is the length of a class
or the range of values it can contain.
Class Interval Frequency Midpoint < cf
83 - 94 4 88.5 60
71 - 82 7 76.5 56
59 - 70 14 64.5 49
47 - 58 19 52.5 35
35 - 46 11 40.5 16
23 - 34 5 28.5 5
Class frequency is the number
of items within a category.
Class Interval Frequency Midpoint < cf
83 - 94 4 88.5 60
71 - 82 7 76.5 56
Class limits – refer to the highest
59 - 70 14
and lowest64.5 49be
value that can
47 - 58 entered in each
19 52.5 class interval.
35
35 - 46 11 40.5 16
23 - 34 5 28.5 5
Class Interval Frequency Midpoint < cf
83 - 94 Class4 boundaries
88.5or exact60limits
71 - 82 7 to values
refer 76.5midway 56 the
59 - 70 14 limit of64.5
upper 49
a certain interval
47 - 58 and19the lower52.5
limit of the35next
35 - 46 11 interval.
40.5 16
23 - 34 5 Ex: 70.5 - 82.5 5
28.5
 Class mark or midpoint
of the class interval
Class Interval Frequency Midpoint < cf
83 - 94 4 88.5 60
71 - 82 7 76.5 56
59 - 70 14 64.5 49
47 - 58 19 52.5 35
35 - 46 11 40.5 16
23 - 34 5 28.5 5

Cumulative frequency
Class Interval Frequency Midpoint < cf
83 - 94 4 88.5 60
71 - 82 7 76.5 56
Class size is the 14
59 - 70 difference between
64.5 the upper
49
class boundary
47 - 58 and
19 the lower class
52.5 boundary
35 of
a class interval.
35 -
Example:46 11 40.5 16
23 - 34 i =594.5 - 82.528.5
= 12 5
Construction of Frequency Distribution

Step 1: Find the range R using the formula:

R = HV - LV

Step 2: Compute the number of intervals n (no. of

classes) by using this formula: n = 1 + 3.3 log N
where: n = no. of class intervals
N = population or total number of observations
𝑅
Step 3: Compute the class size (i) using the formula: 𝑖 =
𝑛

Step 4: Construct the table.

Step 5: Make an interpretation.

Frequency Distribution

Class Frequency Class < cf Relative

Interval Midpoint Frequency
83 - 94 4 88.5 20 4/20= 0.20
71 - 82 6 76.5 16 6/20=0.30
59 - 70 2 64.5 10 2/20=0.10
47 - 58 5 52.5 8 5/20=0.25
35 - 46 2 40.5 3 2/20=0.10
23 - 34 1 28.5 1 1/20=0.05
Frequency Distribution
Scores of 165 Students in Statistics Exam
Scores f X fX CB < cf
91 – 95 16 93 1488 90.5 – 95.5 165
86 – 90 18 88 1584 85.5 – 90.5 149
81 – 85 25 83 2075 80.5 – 85.5 131
76 – 80 39 78 3042 75.5 – 80.5 106
71 – 75 35 73 2555 70.5 – 75.5 67
66 - 70 20 68 1360 65.5 – 70.5 32
61 - 65 12 63 756 60.5 – 65.5 12
Histogram
• is a bar graph of a frequency distribution.
• bars are used to represent the frequency of each
class.

Frequency Polygon
• is a linear graph where frequencies of each interval
are assumed concentrated at the midpoint of the
interval.

Ogive
• is a line graph of cumulative frequency distribution.
• points plotted correspond to class boundaries and
cumulative frequencies.
 The reasons for constructing a frequency
distribution are as follows:

1. To organize the data in a meaningful, intelligible way.

2. To enable the reader to determine the nature or shape of the
distribution.
3. To facilitate computational procedures for measures of average
and spread.
4. To enable the researcher to draw charts and graphs for the
presentation of data.
5. To enable the reader to make comparisons among different data
sets.
 is a single score or Mean
value that stands for or
represents a group of Median
scores or values of the
items in a set of data.
Mode

Midrange
 A mathematical
Mean ( X ) representation of the
typical value of a
series of numbers.

It is commonly
referred to as
"average" or as
“arithmetic mean".
 is a positional
Median ( Md ) measure and the
middlemost value in
the distribution.
 is the value or item in
a distribution which
occurs most
Mode ( Mo ) frequently or has the
highest frequency.
 For Ungrouped Data
n

 Xi where:

X= i =1 X = individual score
n = sample size
n
Example. Find the mean in the following set of measurements:
16, 23, 17, 2, 23, 25, 17, 17, 20, 23
Solution.

16 + 23 + 17 + 2 + 23 + 25 + 17 + 17 + 20 + 23
X=
10
X = 18.3
 For Ungrouped Data

Weighted mean entails the weighting of

numbers in order to arrive at a value that is more
meaningful for the data set than the arithmetic
mean. n

 wi xi
X= n i =1

 wi
i =1
 For Ungrouped Data
1. Arrange the data in a particular order.
2. Identify the middle value which is the
median in the distribution.
Example. Find the median in the following set of measurements:
a) 16, 23, 17, 2, 23, 25, 17, 20, 23
b) 85, 90, 60, 84, 65, 60, 86, 83, 76, 74
Solution.
a) 2, 16, 17, 17, 20, 23, 23, 23, 25
Md = 20
b) 60, 60, 65, 74, 76, 83, 84, 85, 86, 90
76 + 83
Md = = 79.5
2
 For Ungrouped Data
Look for the value that occurs most
frequently in the distribution.
Example. Find the mode in the following set of measurements:
a) 15, 20, 30, 15, 20, 20, 24, 32, 18
b) 3.5, 2.5, 3.0, 2.5, 2.5, 2.0, 3.0, 2.0, 3.0, 1.8
c) 5, 8, 10, 12, 13, 7, 6, 11, 14, 15
d) 1, 1, 2, 2, 3, 3, 4, 4, 5
e) 1, 1, 2, 2, 3, 3, 4, 4, 5, 5
Solution.
a) Mo = 20 (unimodal)
b) Mo = 2.5, 3.0 (bimodal)
c) Mo = Does not exist.
d) Mo = 1, 2, 3, 4 (multimodal)
e) Mo = Does not exist.
Measures of Center
Mean – Median – Mode
➢ The mean is easy to compute. You only deal with one
number. It is not so with the median.
➢ The mean is affected by outliers while the median is
resistant. In a sense, the median is able to resist the pull of a
far away value, but the mean is drawn to such values.
➢ A change in any of the numbers changes the mean, and the
mean can be changed drastically by changing an extreme
value.
➢ In contrast, the median and the mode of a set of data are
usually not changed by changing an extreme value.
➢ The mean, the median, and the mode are all averages;
however, they are generally not equal.
 Measures of Center
Which measure of center is most useful?
1.) A shoe manufacturer wants to know the average shoe size of
women.
Answer: _____________
2.) Another teacher wants to know how well her class performed
in a long test.
Answer: ______________
3.) A teacher wants to know about her students family situation.
She asks for the number of children in their families:
6 3 2 3 4 1 2 2 4 3 1 2 2 4
Mean = ___ Median = _____ Mode = ____
Answer: ______________
 Measures of Center
Which measure of center is most useful?
1.) A shoe manufacturer wants to know the average shoe size of
women.
Answer: Mode (pratical)
2.) Another teacher wants to know how well her class performed in
a long test.
Answer: Median (due to outliers)
3.) A teacher wants to know about her students family situation.
She asks for the number of children in their families:
6 3 2 3 4 1 2 2 4 3 1 2 2 4
Mean = 2.79 Median = 2 Mode = 2
Answer: Mean (when the 3 are almost the same, choose the
mean especially because the data is in interval/ratio scale.)
Measures of Center
Compare the mean, the median, and the mode for the
salaries of 5 employees of a small company.

Salaries: P370,000 P60,000 P36,000 P20,000 P20,000

Mean = P101,200
Median = P 36,000
Mode = P 20,000

Most of the employees of this company would probably

agree that the median of P36,000 better represents the average of
the salaries than does either the mean or the mode.
 Measures of Variability

describe the
characteristic of
a set of data

values are used to

determine the
scatter of values in
a distribution
 Variance & Standard Deviation
Variance is the square of the
deviation from the mean.

Standard Deviation is the square root of

variance.
- It is a measure of how far a set of
numbers is spread out.
- It describes how far the numbers lie from
the mean.
- A high standard deviation indicates that
the data points are spread out over a large
range of values.
 Variance & Standard Deviation

Population n
Variance
( X − )
2
i
 =
2 i =1
Population
N
Standard Deviation
n

( X − )
2
i
= i =1
N
 Variance & Standard Deviation

Sample

( X )
n 2
Variance
i −X
s =
2 i =1
n−1 Sample
Standard Deviation

( X )
n 2
i −X
s= i =1
n−1
Example. Find the variance and standard deviation in the following
set of measurements:
2, 4, 4, 4, 5, 5, 7, 9
Solution.
2+4+4+4+5+5+7+9
X= =5
8
For Variance: For Standard Deviation:
32 32
- s =
2
s=
- 7 7
- = 4.57
- = 4.57
= 2.
On average, the scores deviate from the mean of 5 by 2
which implies a bracket of values ranging from 5-2 to
5+2 or from values that lies from 3 to 7.
 is the simplest and
Range the most easiest to
compute among the
measures of variability.

is the difference between

the highest and the lowest R=H–L
score in the distribution.
Example. Find the range in the following set of measurements:

3, 5, 1, 2, 7, 4, 1, 2, 1, 4, 2, 5

Solution.
1, 1, 1, 2, 2, 2, 3, 4, 4, 5, 5, 7

Range = 7 – 1 = 6
 Coefficient of Variation

- the coefficient of variation (CV) is

defined as the ratio of the standard
deviation to the mean.

- it shows the extent of variability in

relation to mean of the population.
- represents the number of standard deviations that a data
value falls above or below the mean.

x−
z=

where
z is the "z-score" (Standard Score)
x is the value to be standardized
μ is the mean
σ is the standard deviation
 1N N N
P1 = th P25 = 4 th P50 = 2 th
100
 1N N 3N
Q1 = th Q2 = 2 th Q3 = 4 th
4
 1N 3N N
D1 = th D3 = 10 th D5 = 2 th
10
Solution:
Q2 = N =
23
= 11.5th = 100
2 2
4N 4(23) 92
D4 = = = = 9.2th = 100
10 10 10
P25 = N =
23
= 5.75th = 98
4 4
Measure of Relative Position
Percentiles and Quartiles
are useful when you want to know where the score is located
in reference to the other scores.
➢ Percentile is a data value for which the specified percentage
of the data is below that value.
➢ The median is the 50th percentile.
➢ The 25th, 50th , 75th percentiles divide the data into lower
quartile Q1, middle quartile Q2, and upper quartile Q3,
respectively.
➢ In using quartiles, there are five numbers to be used
altogether: min value, Q1, median, Q3, and max value.
➢ Quartiles are useful for box plots.
 Normal Distribution
Data can be "distributed" (spread out) in different ways.

It can be spread Or it can be

Or more on the
out all jumbled
right
more on the left up
 There are many cases where the data tends to be around a
central value with no bias left or right, and it gets close to a
"Normal Distribution" like this:

If one has to make observations to natural objects, many tend to

follow the normal distributions.
When variables are investigated, many will cluster around the
central value and there will be few in the extremes.

Examples: weight, height, intelligence, blood pressure, etc.

We say the data is "normally distributed":

The Normal Distribution has:

➢ Mean = Median = Mode
➢ Symmetry about the center
➢ 50% of values less than the mean and 50% greater
than the mean
 is a measure of the degree of departure from the symmetry of a
distribution.
Types of Skewness:
1) Positively skewed (skewed to the right)
The right tail is longer; the mass of the distribution is
concentrated on the left of the figure. It has relatively few high
values.
2) Negatively skewed (skewed to the left)
The left tail is longer; the mass of the distribution is
concentrated on the right of the figure. It has relatively few low
values.
  ( x − x)
3

3
skm = s
n −1
If skm > 0, the distribution is positively skewed.
If skm < 0, the distribution is negatively skewed.
If skm = 0, the distribution is symmetrical.
 is a measure of the degree of peakedness or flatness of the
distribution.
Types of Kurtosis:
1) Leptokurtic (tall distribution) - is symmetrical in shape but the
center peak is much higher; that is, there is a higher frequency of
values near the mean.
2) Platykurtic (flat distribution)- is one in which most of the
values share about the same frequency of occurrence. As a result,
the curve is very flat, or plateau-like.
3) Mesokurtic (normal distribution) - is symmetrical distribution.
 ( x − x)
4

4
km = s
n −1

If km > 3, the distribution is leptokurtic.

If km < 3, the distribution is platykurtic.
If km = 3, the distribution is mesokurtic.
Normal Distribution and Probability
Standard Normal Distribution

If the original distribution

of x values is a normal
distribution, then the
corresponding distribution of
z-scores will also be a normal
distribution. This normal
distribution of z-scores is
called the standard normal
distribution.

The standard normal distribution is the normal distribution that

has a mean of 0 and a standard deviation of 1.
The number of standard deviations from the mean is also called
the "Standard Score", "sigma" or "z-score".

And doing that is called "Standardizing":

Here is the formula for z-score that we have been using:

x−
z=

where
z is the "z-score" (Standard Score)
x is the value to be standardized
μ is the hypothesized mean
σ is the standard deviation

Why Standardize ... ?

It can help us make decisions about our data.
Normal Distribution and Probability
Empirical Rule for a Normal Distribution
In a normal distribution, approximately
➢ 68% of the data lie within 1 standard deviation of the mean.
➢ 95% of the data lie within 2 standard deviations of the mean.
➢ 99.7% of the data lie within 3 standard deviations of the mean.
Normal Distribution and Probability

Empirical Rule for a Normal Distribution

Example. The heights of a large group of people
are assumed to be normally distributed. Their
mean height is 66.5 inches, and the standard
deviation is 2.4 inches. Find and interpret the
intervals representing one, two, and three
standard deviations of the mean.
Normal Distribution and Probability
One standard deviation of the mean:
Approximately 68% of the people are between 64.1 and 68.9 inches tall.
Two standard deviations of the mean:
Approximately 95% of the people are between 61.7 and 71.3 inches tall.
Three standard deviations of the mean:
Nearly all of the people (99.74%) are between 59.3 and 73.7 inches tall.

𝑥 − 𝜇 64.1 − 66.5
𝑧= = = −1
𝜎 2.4

59.3 61.7 64.1 66.5 68.9 71.3 73.7

 Problem. (Use the Empirical rule)
A vegetable distributor knows that during the month of
August, the weights of its tomatoes are normally distributed
with a mean of 0.61 kg and a standard deviation of 0.15 kg.
a. What percent of the tomatoes weigh less than 0.76 kg?
b. In a shipment of 6000 tomatoes, how many tomatoes
can be expected to weigh more than 0.31 kg?
c. In a shipment of 4500 tomatoes, how many tomatoes
can be expected to weigh from 0.31 kg to 0.91 kg?
Solution. (Use the Empirical rule)
a. 0.76 kg is 1 standard deviation above the mean of 0.61 kg. In a normal
distribution, 34% of all data lie between the mean and 1 standard deviation
above the mean, and 50% of all data lie below the mean. Thus, 34% + 50%
= 84% of the tomatoes weigh less than 0.76 kg.
b. 0.31 kg is 2 standard deviations below the mean of 0.61 kg. In a normal
distribution, 47.5% of all data lie between the mean and 2 standard
deviations below the mean, and 50% of all data lie above the mean. This
gives a total of 47.5% + 50% = 97.5% of the tomatoes that weigh more
than 0.31 kg. Therefore 97.5% of 6000 = 5850 of the tomatoes can be
expected to weigh more than 0.31 kg.
c. 0.31 kg is 2 standard deviations below the mean of 0.61 kg and 0.91 kg is 2
standard deviations above the mean of 0.61 kg. In a normal distribution,
95% of all data lie within 2 standard deviations of the mean. Therefore 95%
of 4500 = 4275 of the tomatoes can be expected to weigh from 0.31 kg to
0.91 kg.
Hypothesis is a proposition made as a basis for
reasoning, without any assumption of
its truth.
This is a statement that cannot be
accepted to be true unless proven.

Hypothesis Testing refers to the formal

procedures used by statisticians to
accept or reject statistical hypotheses.
Two Types of Hypotheses:

1. Null hypothesis. The null hypothesis, denoted by H0, is

usually the hypothesis that sample observations result
purely from chance.

2. Alternative hypothesis. The alternative hypothesis,

denoted by H1 or Ha, is the hypothesis that sample
observations are influenced by some non-random cause.
Concepts of Hypothesis Testing
In our judicial system in the prosecution of criminal cases:
“When a person is charged of a crime, the hypothesis that
we can make is that he is presumed innocent until
proven otherwise. The prosecution has now the burden
of proof to gather enough evidence to disprove the
hypothesis and send the person charged of a crime to jail.
On the basis of the evidence presented, the judge has to
render a verdict whether to reject presumption of
innocence or not.”
Concepts of Hypothesis Testing
There are two possible decisions that can be made:

Conclude that there is enough evidence to support the

alternative hypothesis (also stated as: rejecting the null
hypothesis in favor of the alternative)
Conclude that there is not enough evidence to support
the alternative hypothesis (also stated as: not rejecting the
null hypothesis in favor of the alternative)

NOTE: we do not say that we accept the null hypothesis…

1. Which of the following statements is an appropriate null
hypothesis?

a) The mean of a population is equal to 60.

b) The mean of a sample is equal to 60.
c) The mean of a population is not equal to 60.
d) All of these choices are true.
1. Which of the following statements is an appropriate null
hypothesis?

a) The mean of a population is equal to 60.

b) The mean of a sample is equal to 60.
c) The mean of a population is not equal to 60.
d) All of these choices are true.
Types of Alternative Hypothesis:
1) Directional or predictive
2) Non-directional or non-
predictive

Types of Tests:
1) One-tailed Test – a test of
statistical hypothesis where the
region of rejection is on only
one side of the sampling
distribution.
1) Two-tailed Test – a test of
statistical hypothesis where the
region of rejection is on both side
of the sampling distribution.
2. Which of the following statements exhibits a non-predictive
alternative hypothesis?

a) H1: µ = µo
b) H1: µ ≠ µo
c) H1: µ > µo
d) H1: µ < µo
2. Which of the following statements exhibits a non-predictive
alternative hypothesis?

a) H1: µ = µo
b) H1: µ ≠ µo
c) H1: µ > µo
d) H1: µ < µo
Concepts of Hypothesis Testing

Two possible errors can be

made in any test:

A Type I error occurs

when we reject a true null
hypothesis and
A Type II error occurs
when we don’t reject a false
null hypothesis.
3. What type of error is committed by the researcher if the
sample data caused him to reject HO where it is true in the
population?

a) Type I b) Type II c) Type III d) Type IV

4. In a criminal trial, which of the following decisions of the

judge where he made Type I error?

a) a guilty defendant is acquitted

b) an innocent person is convicted
c) a guilty defendant is convicted
d) an innocent person is acquitted
 Concepts of Hypothesis Testing
Level of significance
is the maximum probability of committing a type I error. This
probability is symbolized by α (Greek letter alpha).
The probability of a type II error is symbolized by β, the Greek
letter beta.
In most hypothesis-testing situations, β cannot be easily
computed; however, α and β are related in that decreasing
one increases the other.
Statisticians generally agree on using three arbitrary
significance levels: the 0.10, 0.05, and 0.01 levels.
Conclusions of a Test of Hypothesis

If we reject the null hypothesis, we conclude that there

is enough evidence to infer that the alternative hypothesis is
true.
If we do not reject the null hypothesis, we conclude
that there is not enough statistical evidence to infer that the
alternative hypothesis is true.

Remember: The alternative hypothesis is the more important

one. It represents what we are investigating.
Methods Used to Test Hypothesis

1) p-Value of a Test
The p-value of a test provides a measure of how much
statistical evidence exists to support the alternative hypothesis.
Interpreting the p-value
➢ If the p-value is less than 1%, there is overwhelming
evidence that supports the alternative hypothesis.

➢ If the p-value is between 1% and 5%, there is a strong

evidence that supports the alternative hypothesis.

➢ If the p-value is between 5% and 10% there is a weak

evidence that supports the alternative hypothesis.

➢ If the p-value exceeds 10%, there is no evidence that

supports the alternative hypothesis.
Interpreting the p-value
Overwhelming Evidence
(Highly Significant)
Strong Evidence
(Significant)

Weak Evidence
(Not Significant)

No Evidence
(Not Significant)

0 .01 .05 .10

p-value=.0359
Interpreting the p-value

Compare the p-value with the selected value of the

significance level:
If the p-value is less than α, we judge the p-value to be
small enough and thereby we to reject the null hypothesis.
If the p-value is greater than α, we do not reject the null
hypothesis.

Since p-value = .0359 < α = .05, we reject H0 in favor of H1

Methods Used to Test Hypothesis

2) Traditional (Manual Calculations)

Steps in Hypothesis Testing
1) Formulate the null and alternative hypotheses.
2) Determine the level of significance of the study.
3) Determine the critical value of the test statistics.
4) Compute the value of the test statistics.
5) Make decision.
“Reject H0 if the absolute computed value of the test
statistics is greater than the absolute critical value.
Otherwise, do not reject H0.”
5. What shall be your decision on HO if the absolute computed
value of the test statistics is greater than the absolute critical
value?
a) do not reject
b) reject
c) neither accept nor reject
d) need further test
5. What shall be your decision on HO if the absolute computed
value of the test statistics is greater than the absolute critical
value?
a) do not reject
b) reject
c) neither accept nor reject
d) need further test
The z-test and t-test
These test statistics are used for quantitative data. They are
used to compare sample mean with population mean or are
used to compare between two sample means.
1) Testing the Population Mean: Population Standard
Deviation is known. Use the z-test.
2) Testing the Population Mean: Population Standard
Deviation is Not known. If the sample size is large (n 
30), use z-test.
3) Testing the Population Mean: Population Standard
Deviation is Not known and Small Sample. Use t-test.
The z-test and t-test
4) Two Sample Test: Independent Samples – if a sample
taken from one population is unrelated with another sample
taken from another population.

5) Two Sample Test: Dependent Samples – also called

paired sample, if each element or member of one sample is
paired or match with an element or member in the other
sample.
6. A researcher refutes the claim that the average income
of households in Barangay Makopa is P12,000 . She
thinks it is more than that. Which hypotheses are used
to test the claim?

a) H0: µ ≠ P12,000 vs. H1: µ > P12,000

b) H0: µ = P12,000 vs. H1: µ > P12,000
c) H0: µ ≠ P12,000 vs. H1: µ = P12,000
d) H0: µ = P12,000 vs. H1: µ < P12,000
6. A researcher refutes the claim that the average income
of households in Barangay Makopa is P12,000 . She
thinks it is more than that. Which hypotheses are used
to test the claim?

a) H0: µ ≠ P12,000 vs. H1: µ > P12,000

b) H0: µ = P12,000 vs. H1: µ > P12,000
c) H0: µ ≠ P12,000 vs. H1: µ = P12,000
d) H0: µ = P12,000 vs. H1: µ < P12,000
7. A political analyst surveys a random sample of registered
voters from District 1 in Davao City and compares the results
with those obtained from a random sample of registered
voters from District 2. This would be an example of what
type of test?

a) independent samples
b) independent samples only if the sample sizes are equal
c) dependent samples
d) dependent samples only if the sample sizes are equal
7. A political analyst surveys a random sample of registered
voters from District 1 in Davao City and compares the results
with those obtained from a random sample of registered
voters from District 2. This would be an example of what
type of test?

a) independent samples
b) independent samples only if the sample sizes are equal
c) dependent samples
d) dependent samples only if the sample sizes are equal
8. Which of the following assumptions can be done for the
t-test for the difference between the means of two
independent populations?

a) sample sizes are equal.

b) populations are normal.
c) means are equal
d) All of these choices are true.
8. Which of the following assumptions can be done for the
t-test for the difference between the means of two
independent populations?

a) sample sizes are equal.

b) populations are normal.
c) means are equal
d) All of these choices are true.
 Analysis of Variance (ANOVA)
• is a statistical technique that is intended to analyze
variability in data in order to infer the inequality among
population means.
• The purpose of ANOVA is much the same as the t – tests;
that is, to determine whether the mean differences that are
obtained for sample data are sufficiently large to justify a
conclusion that there are mean differences between the
populations from which the samples were obtained.
• The difference between ANOVA and the t – tests is that
ANOVA can be used in situations where there are two or
more means being compared, whereas the t – tests are
limited to situations where only two means are involved.
 Analysis of Variance (ANOVA)

Illustration. Consider an experiment in which three variances of

rice are planted on several plots of equal size and their
yields per plot were recorded.

Denorado Milagrosa Masipag

56 55 48
One-Way 45 50 56
Classification 55 49 53
48 51 54
46 53 52
53 48 50
Mean 50.5 51.0 52.17
 Analysis of
Variance

One-Way Classification

• Random samples of size n are selected from each of k

populations. It will be assumed that the k populations are
independent and normally distributed with means 1, 2, …, k
and common variance 2. We wish to derive appropriate methods
for testing the hypothesis

H0 : 1 = 2 = … = k
H1 : at least two of the means are not equal.
9. Which of the following is NOT a required condition for
one-way ANOVA?
a) The sample sizes must be equal.
b) The populations must all be normally distributed.
c) The population variances must be equal.
d) The samples for each treatment must be selected
randomly and independently.
9. Which of the following is NOT a required condition for
one-way ANOVA?
a) The sample sizes must be equal.
b) The populations must all be normally distributed.
c) The population variances must be equal.
d) The samples for each treatment must be selected
randomly and independently.
10. One-way ANOVA is applied to independent samples
taken from three normally distributed populations with
equal variances. Which of the following is the null
hypothesis for this procedure?

a) H0: μ1 + μ 2 + μ 3 = 0
b) H0: μ1 + μ 2 + μ 3 ≠ 0
c) H0: μ1 = μ 2 = μ 3 = 0
d) H0: μ1 = μ 2 = μ 3
10. One-way ANOVA is applied to independent samples
taken from three normally distributed populations with
equal variances. Which of the following is the null
hypothesis for this procedure?

a) H0: μ1 + μ 2 + μ 3 = 0
b) H0: μ1 + μ 2 + μ 3 ≠ 0
c) H0: μ1 = μ 2 = μ 3 = 0
d) H0: μ1 = μ 2 = μ 3
 Measures of Relationship
o Statistics are widely used in the social sciences in
making predictions which are based upon the fact
that two variables are related.
o The process of obtaining the measure of the degree
of relationship or association between variables is
called correlation analysis.
o When a known measure of one variable is used to
make estimates of a second variable, the process is
known as regression analysis.
 Regression Analysis
o Regression analysis is the process by which one
variable Y is predicted from another variable X.
o The variable Y is called the dependent variable and
X is called the independent variable or the predictor.

llustration. Predicting the level of satisfaction of IP and the

extent of the implementation of the program.

Independent variable = extent of implementation

Dependent variable = level of satisfaction
 Linear Regression
o this linear relationship can be expressed in an
equation of the form
Y = a + bx

where Y = predicted score

a = the y-intercept
b = the slope of the line
 Scatter Diagram
o Visual representation of the relationship between
two variables. In this method, values of the two
variables are plotted on a two-dimensional
coordinate system.

A line could be fitted and we A curve instead of a line will fit

could conclude that there is a the plotted points, so that we
linear relationship between the can say that there is a non-
two variables. linear relationship.
 Method of Least Square
o The line obtained by the method of least square is
known as the regression line and also referred to as
the line of best fit.
Y = a + bx
n XY −  X  Y
where b=
n X − (  X )
2
2

a=
 Y  X 
−b  = Y − bX
n  n 
 Correlation Analysis
o Correlation analysis is used to measure the linear
relationship or association between two variables.
o The measure of the degree of association between
two variables is known as the coefficient of
correlation (r).
o The value of r varies from –1 to +1. This can
expressed in the interval – 1  r  1.
o For perfectly positive correlation, r = 1, while in a
perfectly negative correlation, r = –1 .
o If r = 0, then there is no linear relation existing
between the two variables.
 Correlation Analysis
o A positive correlation is present when high values in one
variable are associated with high values of another variable or
vice versa.
o On the other hand, when high values on one variable are
associated with low values of the other variable or vice versa,
a negative correlation is present.
 Correlation Analysis
o The degree of linear relationship can be interpreted
by using the following range of values:
Range of Value of r Description
0.90 to 1.00 or (-0.90 to -1.00) Very high positive (negative) correlation
0.70 to 0.89 or (-0.70 to -0.89) High positive (negative) correlation
0.50 to 0.69 or (-0.50 to -0.69) Moderate positive (negative) correlation
0.30 to 0.49 or (-0.30 to -0.49) Low positive (negative) correlation
0.00 to 0.29 or ( 0.00 to -0.29) Little, if any correlation
 Correlation Analysis
Pearson Product Moment Correlation Coefficient
o is a measure of the linear correlation (dependence) between
two variables X and Y, giving a value between +1 and −1
inclusive, where 1 is total positive correlation, 0 is no
correlation, and −1 is total negative correlation.
o is widely used in the sciences as a measure of the degree of
linear dependence between two variables. It was developed
by Karl Pearson from a related idea introduced by Francis
Galton in the 1880s.

n XY −  X  Y
Pearson r =
n X − ( x )  n Y − ( Y ) 
       
2 2
2 2
11. Assuming that a linear relationship exists between Age
(X) and Job Satisfaction (Y), if the coefficient of
correlation (r) equals -0.95, what does this means?
a) there is very weak correlation.
b) if the value of X is low, the value of Y is high.
c) the value of X is always greater than the value of Y.
d) if the value of X is high, so as the value of Y.
11. Assuming that a linear relationship exists between Age
(X) and Job Satisfaction (Y), if the coefficient of
correlation (r) equals -0.95, what does this means?
a) there is very weak correlation.
b) if the value of X is low, the value of Y is high.
c) the value of X is always greater than the value of Y.
d) if the value of X is high, so as the value of Y.
12. A regression analysis between weight (y in pounds) and
height (x in inches) resulted in the following least squares
line: y = 120 + 5x. This implies that if the height is
increased by 1 inch, the weight is expected to which of
the following?
a) increase by 1 pound.
b) decrease by 1 pound.
c) increase by 5 pounds.
d) increase by 24 pounds.
12. A regression analysis between weight (y in pounds) and
height (x in inches) resulted in the following least squares
line: y = 120 + 5x. This implies that if the height is
increased by 1 inch, the weight is expected to which of
the following?
a) increase by 1 pound.
b) decrease by 1 pound.
c) increase by 5 pounds.
d) increase by 24 pounds.
13. In the simple linear regression model, what does the y-
intercept represents?
a) change in y per unit change in x.
b) change in x per unit change in y.
c) value of y when x = 0.
d) value of x when y = 0.

14. In the least squares regression line y = 3 – 2x, what is

the predicted value of y equal to?
a) 1.0 when x = -1.0 b) 2.0 when x = 1.0
c) 2.0 when x = -1.0 d) 1.0 when x = 1.0
13. In the simple linear regression model, what does the y-
intercept represents?
a) change in y per unit change in x.
b) change in x per unit change in y.
c) value of y when x = 0.
d) value of x when y = 0.

14. In the least squares regression line y = 3 – 2x, what is

the predicted value of y equal to?
a) 1.0 when x = -1.0 b) 2.0 when x = 1.0
c) 2.0 when x = -1.0 d) 1.0 when x = 1.0
15. If all the points in a scatter diagram lie on the least
squares regression line, what must be the coefficient of
correlation equal to?
a) 1.0 b) -1.0
c) either 1.0 or -1.0 d) 0.0
Parametric vs. Non-Parametric Tests
• Parametric tests assume that the data has come from a type
of probability distribution and makes inferences about
the parameters of the distribution. Most well-known elementary
statistical methods are parametric.
• Nonparametric tests are sometimes called distribution-free
tests because they are based on fewer assumptions (e.g., they do not
assume that the outcome is approximately normally distributed).
Parametric vs. Non-Parametric Tests
There are two types of test data and consequently different
types of analysis. As the table below shows, parametric data
has an underlying normal distribution which allows for more
conclusions to be drawn as the shape can be mathematically
described. Anything else is non-parametric.
Parametric Non-parametric

Assumed distribution Normal Any

Assumed variance Homogeneous Any

Typical data Ratio or Interval Ordinal or Nominal

Data set relationships Independent Any

Usual central measure Mean Median

Simplicity; Less affected by

Benefits Can draw more conclusions
outliers
The Chi-Square Test, 2
• The chi-square test is not based on the assumption of a normal
distribution in the population.
• It is used as a test of significance when the data are expressed in
frequencies, or are in terms of percentages or proportions that can
be reduced to frequencies.
• Most of the application of the chi-square are with discrete data.
However, it may also be used to any continuous data that can be
reduced to categories and the data are tabulated.
The Chi-Square Test, 2
• In order to use the chi-square statistic,
a) the data must be independent, that is, no response is related to
any other responses,
b) that a frequency may be placed in one and only one category, &
c) all data must be used.
The Chi-Square Test, 2
• There are three types of chi-square test:

1) Goodness-of- Fit Test

2) Test for Homogeneity
3) Test for Independence

All these tests are however similar in that they provide decision-
making information about the population and all are based upon the
difference between the observed sample frequencies and some
expected or theoretical frequencies of a population.
The Chi-Square Test, 2
The Test for Goodness - of – Fit
To determine if a set of observed data corresponds to some
theoretical distribution, a chi-square goodness-of-fit test is
performed. It is used to determine whether a set of observed
frequencies of one variable is the same as the expected frequencies
on the same variable.
The basic formula for the chi-square is

( OF −EF )
2

 =
2

EF
where OF = observed frequency
EF = expected frequency
The Chi-Square Test, 2
Degrees of Freedom
The number of degrees of freedom is based on the number of cells in
the contingency table. The formula for degrees of freedom is
df = (c – 1)(r – 1)
where c is the number of columns and r is the number of rows in the
contingency table.
If c = 1, df = (r – 1) or if r = 1, df = (c – 1)

To obtain the critical value for the chi-square, use the chi-square
distribution table. The tabular value can be obtained by getting the
intersection of the level of significance and the degrees of freedom.
The Chi-Square Test, 2
Computing Expected Frequencies

Total Row
Observed A B C X
Frequency D E F Y
G H I Z
Total Column Q R S T

Total Row

Expected QX/T RX/T SX/T X

QY/T RY/T SY/T Y
Frequency
QZ/T RZ/T SY/T Z
Total Column Q R S T
Other Non-Parametric Tests

Tests
Choosing a non-
Choosing Choosing parametric test
parametric test
Correlation test Pearson Spearman
Independent measures,
Independent-measures t-test Mann-Whitney test
2 groups
Independent measures, One-way, independent-
Kruskal-Wallis test
>2 groups measures ANOVA
Repeated measures,
Matched-pair t-test Wilcoxon test
2 conditions
Repeated measures, One-way, repeated
Friedman's test
>2 conditions measures ANOVA
Other Non-Parametric Tests
Spearman's rank correlation coefficient or Spearman's
rho,
• named after Charles Spearman and often denoted by the
Greek letter ρ (rho), is a non-parametric measure of
statistical dependence between two variables.
• It assesses how well the relationship between two variables
can be described using a monotonic function.
• Spearman's coefficient, like any correlation calculation, is
appropriate for both continuous and discrete variables,
including ordinal variables.
• The Spearman correlation coefficient is defined as
the Pearson correlation coefficient between the ranked
variables.
Other Non-Parametric Tests
Mann–Whitney U test
• is a non-parametric test of the null hypothesis that two
populations are the same against an alternative hypothesis,
especially that a particular population tends to have larger
values than the other.
• It has greater efficiency than the t-test on non-normal
distributions, such as a mixture of normal distributions, and it
is nearly as efficient as the t-test on normal distributions.
• It was named after Henry Berthold Mann and Donald
Ransom Whitney.
Other Non-Parametric Tests
Kruskal–Wallis one-way analysis of variance by ranks
(named after William Kruskal and W. Allen Wallis) is a non-
parametric method for testing whether samples originate
from the same distribution.
• It is used for comparing two or more samples that are
independent, and that may have different sample sizes, and
extends the Mann-Whitney U test to more than two groups.
• The parametric equivalent of the Kruskal-Wallis test is
the one-way analysis of variance (ANOVA).
Other Non-Parametric Tests
Wilcoxon signed-rank test
• is a non-parametric statistical hypothesis test used when
comparing two related samples, matched samples, or
repeated measurements on a single sample to assess
whether their population mean ranks differ (i.e. it is a paired
difference test).
• It can be used as an alternative to the paired Student t-
test, t-test for matched pairs, or the t-test for dependent
samples when the population cannot be assumed to
be normally distributed.
• The test is named for Frank Wilcoxon (1892–1965) who, in a
single paper, proposed both it and the rank-sum test for two
independent samples .
Other Non-Parametric Tests
Friedman test
• is a non-parametric statistical test developed by
the U.S. economist Milton Friedman.
• Similar to the parametric repeated measures ANOVA, it is
used to detect differences in treatments across multiple test
attempts.
• The procedure involves ranking each row (or block) together,
then considering the values of ranks by columns.
16. A researcher read that firearm-related deaths for people
aged 1 to 18 were distributed as follows: 74% were
accidental, 16% were homicides, and 10% were
suicides. In her city, there were 68 accidental deaths, 27
homicides, and 5 suicides during the past year. What
statistical test she should use if she wants to test the
claim that the percentages are equal?
a) t-test on dependent sample
b) Anova
c) chi-square
d) pearson r
16. A researcher read that firearm-related deaths for people
aged 1 to 18 were distributed as follows: 74% were
accidental, 16% were homicides, and 10% were
suicides. In her city, there were 68 accidental deaths, 27
homicides, and 5 suicides during the past year. What
statistical test she should use if she wants to test the
claim that the percentages are equal?
a) t-test on dependent sample
b) Anova
c) chi-square
d) pearson r
17. In a large department store, the owner wishes to see
whether the number of shoplifting incidents per day will
change if the number of uniformed security officers is
doubled. The number of shoplifting incidents were
recorded 7 days before security was increased and 7
days after the increased. The owner wants to find out if
there is a difference in the number of shoplifting
incidents before and after the increase in security. What
test will he perform?
a) Kruskal Wallis b) Spearman rho
c) Mann-Whitney d) Wilcoxon signed-rank test
 References
Alston, M., & Bowles, W. (2020). Research for social workers: An introduction
to methods. Routledge.
Aufmann et al (2013). Mathematical Excursions 3ed. Brooks/Cole, Cengage
Learning.
Bluman, A. G. (2012). Elementary statistics: a step by step approach 8ed. New
York: McGraw-Hill.
COMAP, Inc. (2013). For all practical purposes: mathematical literacy in today’s
world. New York: W.H Freeman and Company.
Johnson & Mowry (2012). Mathematics: a practical odyssey. Brooks/Cole,
Cengage Learning