Ge4 Hypothesis 1

Download as pdf or txt
Download as pdf or txt
You are on page 1of 17

TESTING OF

HYPOTHESIS
A hypothesis is a conjectural statement
of the relation between two or more
variables. Hypotheses are always in
declarative sentence form, and they
relate either generally or specifically,
variables to variables.
TWO TYPES OF
HYPOTHESIS
 A null hypothesis (Ho) is primarily for
statistical purposes. It is a statement that
we expect that there will be no
connection among variables.
 An alternative hypothesis (Ha) states the
nature of the connection between or
among variables that we expect on theory
and/or prior research.
EXAMPLE
A new method of teaching was
introduced by Prof. Cortez in his tutorial
class in Statistics. Prior to the
implementation of the new teaching
method, a pre-test was given and after the
chapter is through a post test was also
administered.
The table below shows the data.
Students # Pre-test Post-test
1 101 113
2 89 89
3 112 121
4 105 99
5 90 104
6 91 94
7 89 99
a. Calculate the Pearson’s r.
b. Is there a significant positive or
negative correlation between the pre-
test and post-test results?
c. State the Ho and Ha. Which of the
two hypothesis will you accept at 5%
level of significance.
SOLUTION
Students # Pre-test Post-test xy x2 y2
(x) (y)

1 101 113 11413 10201 12769


2 89 89 7921 7921 7921
3 112 121 13552 12544 14641
4 105 99 10395 11025 9801
5 90 104 9360 8100 10816
6 91 94 8554 8281 8836
7 89 99 8811 7921 9801
TOTAL 677 719 70006 65993 74585
N  xy   x y
r
 N  x   x  N  y   y  
2 2 2 2

7  70006    677  719 


r
7  65993   677   7  74585    719  
2 2
  
3279 3279
r   0.76
 3622  5134  18595348

High Positive Correlation.


• Ho: There is no significant
correlation between the pre-test and
post-test result.
• Ha: There is a significant correlation
between the pre-test and post-test
result.
Testing the significance of r:
The formula for t-test:
n2
tr
1 r 2

where t = t-test
r = value of Pearson’s r
n = sample size
72
t   0.76 
1  (0.76) 2

t  2.615   2.571
COMPUTED T-VALUE TABULATED T-VALUE
df = n - 2
df = 7 - 2
df = 5
The difference between means is
significant, since the computed t-value
of 2.615 is greater than the tabulated t-
value of 2.571. Therefore, there is a
significant correlation between the pre-
test and post-test result. The null
hypothesis is rejected.
Prepared by:
JOSAN ROSELLE M. CORTEZ, M.A.
Math Teacher

You might also like