E502 Statistics in Educational Research

Marian Minneli S. Cruz ,Ph.D.

#09950833674
[email protected]
ESTIMATION AND HYPOTHESIS TESTING
Inferential allows testing of hypothesis and drawing conclusions
about a population, based on sample, modeling
Statistics relationships within the data.

E502 Statistics in Educational Research

 Hypothesis is a statement of prediction of the
relationship between or among variables or simply, it is
the most specific statement of a problem.
Hypothesis
Testing The hypothesis can be stated in various ways:

a. No existence or existence of a difference between

groups
b. No existence or existence of an effect of the
treatment
c. No existence or existence of relationship between
the variables

E502 Statistics in Educational Research

 Example:
Let us consider an experiment involving two groups, an
experimental group, and a control group. The experimenter
Hypothesis likes to test whether the treatment (values clarification
lessons) will improve the self-concept of the experimental
Testing group. The same treatment is not given to the control group.
It is presumed that any difference between the two groups
after the treatment can be attributed to the experimental
treatment with a certain degree of confidence.

No existence or existence of a difference between groups

There will be no significant difference in self concept between the group that will be
exposed to values clarification lessons and the group which will not be exposed to
the treatment.

E502 Statistics in Educational Research

 Example:
Let us consider an experiment involving two groups, an
experimental group, and a control group. The experimenter likes
Hypothesis to test whether the treatment (values clarification lessons) will
improve the self-concept of the experimental group. The same
Testing treatment is not given to the control group. It is presumed that
any difference between the two groups after the treatment can
be attributed to the experimental treatment with a certain
degree of confidence.

No existence or existence of an effect of the treatment

There will be no significant effect of the values clarification lessons on the self
concept of the students.

E502 Statistics in Educational Research

 Example:
Let us consider an experiment involving two groups, an
experimental group, and a control group. The experimenter
Hypothesis likes to test whether the treatment (values clarification
lessons) will improve the self-concept of the experimental
Testing group. The same treatment is not given to the control group.
It is presumed that any difference between the two groups
after the treatment can be attributed to the experimental
treatment with a certain degree of confidence.
No existence or existence of relationship of the treatment

There will be no significant relationship in self concept between the group that will
be exposed to values clarification lessons and the group which will not be exposed
to the treatment.

Self concept of the students is not related to the values clarification lessons
conducted .
E502 Statistics in Educational Research
 Null Hypothesis

The null hypothesis, denoted by Ho, is usually the

Hypothesis hypothesis that sample observations result purely from
Testing chance.

It states no existence of relationship between the

variables under study.

It is so stated for the purpose of being accepted or

rejected.

E502 Statistics in Educational Research

 Alternative Hypothesis

Hypothesis The alternative hypothesis, denoted by H1 or Ha, is the

hypothesis that sample observations are influenced by
Testing some non-random cause.

If Ho is rejected, H1 is accepted.

E502 Statistics in Educational Research

 Non-directional Hypothesis
A non-directional hypothesis is a two-tailed hypothesis that does
not predict the direction of the difference or relationship,
Hypothesis predicts that the independent variable will have an effect on the
dependent variable, but the direction of the effect is not
Testing specified.

e.g. there will be a difference in how

many numbers are correctly recalled
by children and adults.

E502 Statistics in Educational Research

 Directional Hypothesis
A directional hypothesis is a one-tailed hypothesis that states the
direction of the difference or relationship , predicts the nature of
Hypothesis the effect of the independent variable on the dependent variable.

Testing
one-tailed test one-tailed test
(left tail) (right tail)

Ho: µ = µo Ho: µ = µo
Ha: µ < µo Ha: µ > µo

Key words that distinguish a directional hypothesis are: higher,

lower, more, less, increase, decrease, positive, and negative.
e.g., adults will correctly recall more words than
children.
E502 Statistics in Educational Research
 EXAMPLES:
There will be a significant difference in mean scores between
Hypothesis boys and girls in a Reading Achievement Test.

Testing The proportion of males will not differ significantly from the
proportion of females in their attitudes toward birth control.

There is a positive relationship between ranks of children on a

social adjustment instrument as judged by two teachers.

There is a gender difference that exists in consumer preferences

of Brand A product.

There is a difference in the number of men and women who

participate in sports.
E502 Statistics in Educational Research
 Results from a statistical test will fall into one of two
regions: the rejection region— which will lead you to
reject the null hypothesis, or the acceptance region,
Hypothesis where you provisionally accept the null hypothesis.
Testing

Acceptance Region

E502 Statistics in Educational Research

 Significance Level

Hypothesis The significance level, also denoted as alpha or α, is a

measure of the strength of the evidence that must be
Testing present in your sample before you will reject the null
hypothesis and conclude that the effect is statistically
significant.
The significance level is the probability of rejecting the
null hypothesis when it is true.

E502 Statistics in Educational Research

 Significance Level
Hypothesis For example, a significance level of 0.05 indicates a
5% risk of concluding that a difference exists when
Testing there is no actual difference. Lower significance levels
indicate that you require stronger evidence before you
will reject the null hypothesis.

E502 Statistics in Educational Research

Hypothesis
Testing

E502 Statistics in Educational Research

 P-value (Probability value)

The p-value is used to determine the statistical

Hypothesis significance of the results.

Testing If p < α , reject the null hypothesis.

E502 Statistics in Educational Research

 Critical Value

Hypothesis A critical value is a point (or points) on the scale of the

test statistic beyond which we reject the null
Testing hypothesis, and, is derived from the level of
significance α of the test. Critical value can tell us,
what is the probability of two sample means
belonging to the same distribution. The higher the
critical value means lower the probability of two
samples belonging to same distribution.

E502 Statistics in Educational Research

Hypothesis
Testing Acceptance Region

Critical Value* Critical Value*

If the computed value ( statistic computed as a result of the

statistical test applied to the data )that is within +critical value
and –critical value falls within the region of acceptance, the null
hypothesis is to be accepted.

E502 Statistics in Educational Research

Hypothesis
Testing

Rejection Region Rejection Region

Acceptance Region
Acceptance Region 0.05

Critical Region for One-tailed test

E502 Statistics in Educational Research

Hypothesis
Testing

E502 Statistics in Educational Research

 Steps in Hypothesis Testing

1. State the null and alternative hypotheses

Hypothesis 2. Specify α and the sample size
Testing 3. Select an appropriate statistical test
4. Collect data (note that the previous steps should be
done prior to collecting data)
5. Compute the test statistic based on the sample data
6. Determine the p-value associated with the statistic
7. Decide whether to reject the null hypothesis by
comparing the p-value to α (i.e. reject the null
hypothesis if p < α)

E502 Statistics in Educational Research

Hypothesis
Testing A z-test is a statistical test used to determine
whether two means are different.

z-TEST

E502 Statistics in Educational Research

Hypothesis
Testing

z-TEST Acceptance
Region
Acceptance
Region

*critical value for a two-tailed test which is based on the fact that 95% of the area
of a normal distribution is within 1.96 standard deviations of the mean. This
means that any computed value( statistic computed as a result of the statistical
test applied to the data )that is within +1.96 and -1.96 falls within the region of
acceptance. Hence , the null hypothesis is to be accepted.

E502 Statistics in Educational Research

Hypothesis Problem:
Testing
A group of 150 students took an entrance test for
college. Their group mean is 56 and the standard
z-TEST deviation is 12. If the college mean is 58.5, is the
sample mean significantly lower than the college
mean?

E502 Statistics in Educational Research

Hypothesis Solution:
Testing 1. State the null and alternative hypotheses
H0: There is no significant difference between the
z-TEST college mean and the group mean.

H1: There is a significant difference between the

college mean and the group mean.
2. Specify α
α = 0.05

E502 Statistics in Educational Research

Hypothesis Solution:
Testing 3. State Decision Rule

z-TEST

If Z is less than -1.96 or greater than 1.96 , reject the

null hypothesis

E502 Statistics in Educational Research

Hypothesis
Solution:
Testing 3. Calculate Test Statistic

z-TEST
Z= -2.55

E502 Statistics in Educational Research

Hypothesis
Testing 3. Decision

Reject the Null Hypothesis.

z-TEST There is a significant difference between the college

mean and the group mean.

E502 Statistics in Educational Research

Hypothesis
Testing
t-Tests are hypothesis tests that assess the means of
t-TEST one or two groups.
The t test tells how significant the differences between
groups are.

E502 Statistics in Educational Research

Hypothesis Depending on the t-test and how you configure it, the
Testing test can determine whether:
• One mean is different from a target value.
• Two group means are different.
t-TEST • Paired means are different.

https://datatab.net/

E502 Statistics in Educational Research

Hypothesis One Sample t-Test
Testing • One mean is different from a target value.
The one-sample t-test is calculated to
test whether the variable values of a
sample differ from those of the
t-TEST population.
The research question is: Are there
statistically significant differences
between a sample mean value and the
https://datatab.net/ mean value of the population?

E502 Statistics in Educational Research

Hypothesis One Sample t-Test

Testing Problem :

Test to determine ( at α =0.05) whether the population

t-TEST mean age is significantly greater than 20 given the
following ages:

E502 Statistics in Educational Research

Hypothesis The Independent Samples t Test
(Two-Sample t-Tests )
Testing • Two group means are different.
The Independent Samples t Test
t-TEST compares the means of two
independent groups in order to
determine whether there is
statistical evidence that the
associated population means are
significantly different.
The research question is: Is there a
https://datatab.net/ statistically significant difference
between the mean values of two
groups?

E502 Statistics in Educational Research

Hypothesis The Independent Samples t Test
(Two-Sample t-Tests )
Testing
Example :
Do students who learn using Method A have a
t-TEST different mean score than those who learn using
Method B?

Measuring the weight of people who have been on a

diet and people who have not been on a diet.

E502
STATISTICS
E502 Statistics in Educational Research
Hypothesis The Paired Samples t –Test
(Dependent t-Test)
Testing • Paired means are different.
The Paired Samples t-Test
compares two means that are
t-TEST from the same individual, object,
or related units.
The research question is: Is there a
statistically significant difference
between the mean value of two
https://datatab.net/
dependent groups?

E502 Statistics in Educational Research

Hypothesis The Paired Samples t –Test
(Dependent t-Test)
Testing
A measurement taken at two different times (e.g., pre-
test and post-test with an intervention administered
t-TEST between the two time points)
A measurement taken under two different conditions
(e.g., completing a test under a "control" condition and
an "experimental" condition)
Measurements taken from two halves or sides of a
subject or experimental unit (e.g., measuring hearing
loss in a subject's left and right ears).

E502 Statistics in Educational Research

Hypothesis Problem:
Testing Fifteen students completed an Attitudes Toward
Statistics (ATS) scale at the beginning and at the end
of a basic statistics course. Test the hypothesis that
t-TEST the ATS after statistics course is significantly higher
than the score at the beginning.

E502
STATISTICS
E502 Statistics in Educational Research
Hypothesis Student Time1 Time 2
a) What is the computed t?
Testing
1 84 88
2 45 54 Critical t-value?
3 32 43
b) What would be the null
4 48 42
5 53 51 hypothesis in this study?
t-TEST 6
7
64
45
73
58
c) What would be the
8 74 79 alternative hypothesis?
9 68 72 d) Interpret the results.
10 54 52
11 90 92
12 84 89
13 72 82
14 69 82
15 72 73

E502
STATISTICS
E502 Statistics in Educational Research
Hypothesis Problem:
Testing A research study was conducted to examine the differences
between older and younger adults on perceived life satisfaction.
A pilot study was conducted to examine this hypothesis. Ten
t-TEST older adults (over the age of 70) and ten younger adults
(between 20 and 30) were give a life satisfaction test (known to
have high reliability and validity). Scores on the measure range
from 0 to 60 with high scores indicative of high life satisfaction;
low scores indicative of low life satisfaction. The data are
presented below. Compute the appropriate t-test.

E502 Statistics in Educational Research

Hypothesis
Testing
Older Younger a) What is the computed t?
Adults Adults Critical t-value?
45 34 b) What would be the null
38 22
hypothesis in this study?
t-TEST 52
48
15
27 c) What would be the
25 37 alternative hypothesis?
39 41 d) Interpret the results.
51 24
46 19
55 26
46 36

E502 Statistics in Educational Research

Hypothesis
ANOVA (F-test)can be used to determine if there is a
Testing statistically significant difference between the means
of groups, due to some influence factor.
ANOVA
(Analysis of The calculation of the F-statistic, which is simply the
Variance) ratio of the variation between sample means to the
variation within the samples, is the basis of ANOVA
calculations. The higher this ratio, the weaker the
evidence supporting H0.

E502 Statistics in Educational Research

Hypothesis One-Way ANOVA
Testing
A one-way ANOVA compares three or more than
ANOVA three categorical groups to establish whether there
(Analysis of is a difference between them.
Variance)
One-way ANOVA looks at the effects of one factor,
also referred to as unifactor ANOVA or single factor
ANOVA.

E502 Statistics in Educational Research

Hypothesis One-Way ANOVA
Testing
The null and the alternative can be stated as follows:
ANOVA
(Analysis of Null Hypothesis (HO):
Variance) There is no difference in the means due to a factor.

Alternative Hypothesis (H1):

There is a significant difference in the means due to a
factor.

E502 Statistics in Educational Research

Hypothesis One-Way ANOVA
Testing Example:
ANOVA You have a group of individuals randomly split into smaller groups
and completing different tasks. For example, you might be
(Analysis of studying the effects of tea on weight loss and form three groups:
Variance) green tea, black tea, and no tea.

You might be studying leg strength of people according to

weight. You could split participants into weight categories
(obese, overweight and normal) and measure their leg strength
on a weight machine.

E502
STATISTICS
E502 Statistics in Educational Research
Hypothesis Two-Way ANOVA
Testing
The two-way ANOVA compares the mean differences between
ANOVA groups that have been split on two independent variables (called
factors). The primary purpose of a two-way ANOVA is to
(Analysis of understand if there is an interaction between the two
Variance) independent variables on the dependent variable.

Two-way ANOVA determines whether the interaction effect

between the two factors is statistically significant. The separate
effects are called main effects while the combined effects are
called interaction.

E502 Statistics in Educational Research

Hypothesis Two-Way ANOVA

Testing A factor is an independent variable. A k factor ANOVA

addresses k factors.
ANOVA A level is some aspect of a factor; these are what we
(Analysis of called groups or treatments in the one factor analysis.
Variance)
Wheat Corn Soy Rice
Fertilizer A
Fertilizer B
Fertilizer C

In this example there are two factors: fertilizers and crops. The fertilizer factor has
3 levels and the crop factor has 4 levels.

E502 Statistics in Educational Research