Lesson 7: Hypothesis Testing & Correlation Regression One Tailed versus Two Tailed

Hypothesis Testing A one-tailed test (either left tail or right tail but never
both tail) shows that the H0 be rejected when test value
- It is a statistical method that is used in making
is in the critical region on one side of the mean.
statistical decisions using experimental data.
- It is basically an assumption that we make about A two-tailed test, the H0 should be rejected when the
the population parameter. test value is in either of the two critical regions.

Introduced by: Sir Ronald Fisher, Jerzy Newman, Karl

Pearson, and Egon Pearson.

3 Methods to Test the Hypothesis

- Traditional method
- P-value
- Confidence interval

Two Types of Statistical Hypothesis

Null Hypotheses, symbolized by H0, is a statistical

hypothesis testing that assumes that the observation is
due to a chance factor.

Alternative hypothesis, symbolized by H1 or Hait states

that there is a difference between two population
means (or parameters)

Level of Significance

The level of significance refers to the degree of

significance in which we accept or reject the null
hypothesis.

Level of significance is the maximum probability of

committing a Type I error.

That is, P(Type I error) = α.

The degree of statistical significance generally varies

depending on the level of significance. For example, a p-
value that is more than 0.05 is considered statistically
significant while a figure that is less than 0.01 is viewed
as highly statistically significant.

The critical or rejection value is the range of the values

of the test value that indicates that there is significant
difference and that the null hypothesis (H0) should be
rejected.

Noncritical or nonrejection region is the range of the

values of the test value that indicates that the difference
was probably due to chance and that the null hypothesis
(H0) should not be rejected.
Steps in Conducting Hypothesis Testing

- State the null hypothesis (H0) and the alternative

hypothesis (H1).
- Choose the level of significance, α, and the sample
size.
- Make a statistical decision.
- Determine the test statistic & sampling distribution.
- Determine the critical values that divide the rejection
and nonrejection regions.
- Collect the data and compute the value of the test
statistic.
- State the conclusion

One Sample z Test

The one sample z testis a statistical test for the mean of

a population. It is used when n 30, or when the
population is normally distributed, and population
standard deviation is known.

One Sample t Test

One Sample t testis a statistical procedure that is used

to know the mean difference between the sample and
the known value of the population mean.

Assumptions in One Sample z test

- Subjects are randomly selected.

- Population distribution is normal. The population
should be known.
- Cases of the samples should be independent. Assumptions in One Sample t test
- Sample size should be greater than or equal to 30
- The population must be approximately normally
- Procedure for One Sample z test distributed.
H0: μ= specified value - Samples drawn from the population should be
H1: μ, ,  specified value random.
- Calculate the sample mean for one sample z test. - Cases of the samples should be independent.
- Calculate the value of the one sample z test - Sample size should be less than 30.
- Statistical decision for hypothesis testing - The population mean should be known.

If zcomputedzcritical, do not reject H0. - Procedure of One Sample t test

If zcomputedzcritical, reject H0. H0: μ= specified value
H1: μ, ,  specified value
Example: - Calculate the sample mean and standard deviation.
A researcher reports that the average salary of College - Calculate the value of the one sample t test
Deans is more than ₧63,000. A sample of 35 College - Calculate the degrees of freedom. df= n –1
Deans has a mean salary of ₧65,700. At α= 0.01, test - Statistical decision for hypothesis testing
the claim that the College Deans earn more than If tcomputedtcritical, do not reject H0. If
₧63,000 a month. The standard deviation of the tcomputedtcritical, reject H0.
population is ₧5,250.
Example: Assumptions in z Test for Proportion

One of the undersecretary of the Department of Labor - Subjects are randomly selected.
and Employment (DOLE) claims that the average salary - Population distribution is normal.
of civil engineer is PHP 18,000. A sample of 19 civil - Observations are dichotomous
engineer’s salary has a mean of PHP 17,350 and a
- Procedure for One Sample z test
standard deviation of PHP 1,230. Is there enough
H0: p = specified value
evidence to reject the undersecretary’s claim at α=
H1: p , ,  specified value
0.01?
- Calculate the sample proportion.
- Calculate the value ofthe z test for proportion.
- Statistical decision for hypothesis testing

If zcomputedzcritical, do not reject H0.

If zcomputedzcritical, reject H0.

Example:

A recent survey done by Philippine Housing Authority

found that 35% of the population owns their homes. In
a random sample of 240 heads of households, 78
responded that they owned their homes. At the 0.01
level of significance, does that indicate a difference from
the national proportion?

Z for Proportion

This test can be considered as a binomial experiment

when there are only two outcomes and the probability
of success does not change from trial to trial (the
outcomes of each trial are independent). Z Test for Two Large Independent Samples
Assumptions in z test

- Subjects are randomly selected and independently

assigned to groups.
- Population distribution is normal.
- Population standard deviations are known.

- Procedure for z test.

H0: μ1= μ2
H1: μ1μ2, μ1≤μ2, μ1≥μ2
T Test for Two Small Independent Samples
-Calculate the sample mean.
- Calculate the value z test Student’s t test (or t test for independent samples) of
- Statistical decision for hypothesis testing difference of means is used to test the significance of
the difference between two sample.
If zcomputedzcritical, do not reject H0.
If zcomputedzcritical, reject H0. The sample size should be less than 30.

Example: It was developed by G.W. Gossetin 1908 and published

the pseudonym Student.
A real estate agent compares the selling price of
townhouses in two major cities in National Capital
Region to see if there is a difference in price. The results
of the study are shown. Is there enough evidence to
reject the claim that the average price of a townhouse
in Quezon City is higher than Makati City? Use α= 0.05.

Assumptions in T Test

- Subjects are randomly selected and independently

assigned to groups.
- Population distribution is normal.
- Population standard deviations are known.

- Procedure for t test

H0: μ1= μ2
H1: μ1μ2, μ1≤μ2, μ1≥μ2
- Calculate the sample mean & standard deviation and
df.
- Calculate the value t test
- Statistical decision for hypothesis testing

If tcomputedtcritical, do not reject H0. If

tcomputedtcritical, reject H0.

Example:

A researcher wishes to determine whether the monthly

salary of professional elementary teachers in private
schools and elementary teachers in public schools
differs. He selects a sample of elementary teachers.
From each type of school calculate the mean and
standard deviations of their salaries. At α =0.01, can he
conclude that the private school teachers does not
received the same salary with the public school
teachers? Assume that the populations are - Only the matched pair can be used to perform the
approximately normally distributed paired sample t test.
- In the paired sample t test, normal distributions are
assumed.
- The variance of two samples is same.
- The observations must be independent of each other.

- Procedure for Paired t test.

H0: μ1= μ2
H1: μ1μ2, μ1≤μ2, μ1≥μ2
- Calculate the sample mean, standard deviation & df= n
-1.
- Calculate the value t test
- Statistical decision for hypothesis testing

If tcomputedtcritical, do not reject H0.

If tcomputedtcritical, reject H0.

Example:

The management of Resale Furniture, a change of

second hand furniture stores in Metro Manila, designed
an incentive plan for salespeople. To evaluate this
innovative incentive plan, 10 salespeople were selected
at random, and their weekly incomes before and after
the incentive plan were recorded.

Was there a significant increase in the typical

salesperson’s weekly income due to the innovative
incentive plan? Use the 0.05 significance level.

T Test for Paired Samples

Paired sample t testis a statistical technique that is used

to compare two population means in the case of two
samples that are correlated. It is used in “before after”
studies, or when the samples are the matched pairs, or
the case is a control study

Assumptions in Paired t test

 Introduction to Correlation & Regression

In the analysis of experimental data, it is almost always

Z Test between Two Proportions important to know something about the relationship
between two variables.
It deals with the procedures for drawing inferences
about the difference between populations whose data The nature and strength of relationship between
are nominal variables like height and weight may be examined by
regression and correlation analysis.

The term regression analysis refers to the method by

which estimates are made out of the values of a variable
from the knowledge of the values of one or more other
Z is approximately standard normally distributed variables. It is useful in determining the possible from of
relationship between variables to predict or estimate
the value of another variable.

The term correlation analysis refers to the method of

measuring the strength of association (correlation)
Example: among variables. It is a descriptive statistical method
that measures the relationship between two different
In a sample of 240 store customers, 72 used Visa card. In variables.
another sample of 190, 76 used a MasterCard. At α=
0.10, is there a difference in the proportion of people Correlation
who use each type of credit card?
Correlation refers to the departure of two random
variables from independence.

Pearson product-moment correlation (PPMC) is the

most widely used in statistics to measure the degree of
the relationship between the linear related variables.

The correlation coefficient is defined as the covariance

divided by the standard deviations of the variables.
Pearson product-moment correlation Assumptions

Pearson’s product-moment correlation coefficient of Subjects are randomly selected and independently
simply correlation coefficient (or Pearson’s r) is a assigned to groups. Both populations are normally
measure of the linear strength of the association distributed.
between two variables.
Procedure for Pearson Product-Moment Corr. test
- Founded by Karl Pearson.
- Set up the hypotheses.
- The value of the correlation coefficient varies
H0: = 0 (The correlation in the population is zero.)
between +1 and –1.
H1: 0, 0, 0 (The correlation in the population is
different from zero.)
- Calculate the value of Pearson’s r.
- Calculate the value of t value.
- Statistical decision for hypothesis testing

If tcomputedtcritical, do not reject H0.

If tcomputedtcritical, reject H0.

Example:

The owner of a chain of fruit shake stores would like to

study the correlation between atmospheric temperature
and sales during the summer season. A random sample
of 12 days is selected with the results given as follows:

Plot the data on a scatter diagram. Does it appear there

is a relationship between atmospheric temperature and
sales? Compute the coefficient of correlation.
Determine at the 0.05 significance level whether the
correlation in the population is greater than zero.

Correlation Coefficient & Strength of Relationships

0.00 – no correlation, no relationship

±0.01 to ±0.20 – slight correlation, almost negligible

relationship

±0.21 to ±0.40 – slight correlation, definite but small

relationship

±0.41 to ±0.70 – moderate correlation, substantial

relationship

±0.71 to ±0.90 – high correlation, marked relationship

±0.91 to ±0.99 – very high correlation, very dependable

relationship ±1.00 –perfect correlation, perfect
relationship
 Plot the data on a scatter diagram. Does it appear there
is a relationship between atmospheric temperature and
sales? Compute the coefficient of correlation.
Determine at the 0.05 significance level whether the
correlation in the population is greater than zero.

CORRELATION BETWEEN ORDINAL VARIABLES

SPEARMAN RANK ORDER CORRELATION COEFFICIENT

The spearman rank order correlation coefficient is used

to calculate the correlation of ordinal data which are
classified according to order or rank. The spearman
correlation coefficient formula which was developed by
Spearman is

Example:

The owner of a chain of fruit shake stores would like to

study the correlation between atmospheric temperature
and sales during the summer season. A random sample
of 12 days is selected with the results given as follows:
Simple Regression Equation Standard Error of Estimate

Regression analysis is a simple statistical tool used to The standard error of estimateis the standard deviation
model the dependence of a variable on one (or more) of the observed Y values about the predicted Ŷ values.
explanatory variables.

A simple linear regression is the least estimator of a

linear regression model with a single predictor (or one
independent variable) Coefficient of Determination

The least square model determines a regression The coefficient of determination is the measure of
equation by minimizing the sum of squares of the variation of the dependent variable that is explained by
vertical distances between the actual Y values and the the regression line and the independent variable
predicted values of Y.

Assumptions of Linear Regression Equation

Linearity – The mean of each error component is zero.

Independence of Error Terms – The errors are Coefficient of non-determination is the proportion in
independent of each other. the dependent variable that is left unexplained by the
independent variable, determined by 1 –r^2.
Normally Distributed Error Terms – Each error
component (random variable) follows an approximate
normal distribution.

Homoscedasticity – The variance of the error

components is the same for each value of the
independent variable.