Scribd
Upload
6 views

t test ug short

Ush

Uploaded by

Malay B
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
6 views

t test ug short

Ush

Uploaded by

Malay B
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 26

t Test

Dr. Dipesh Zalavadiya


Assistant Professor
Community Medicine Dept.
GMERS Medical College
Junagadh
t - tests
•Compare two means
•W.S. Gossett (1905) first published a t-test.
•He published under the name Student.
• The test was called Student’s t Test
•later shortened to t test.
•All the prerequisites are same as Z test except sample size
•In t test sample size should be less than 30
Types of t-tests

• One sample t-test

• t-test for two independent (uncorrelated) samples


(Unpaired t test)

• t-test for two paired (correlated) samples (paired t test)


t - tests
• The ratio of observed difference between two
means of small samples to the SE of difference is
denoted by later ‘t’

• Gosset showed that the ratio follows different


distribution called ‘t’ distribution

• This ‘t’ corresponds to Z in large samples but the


probability of occurrence ‘p’ of this calculated
value is determined by reference of ‘t’ table
t - tests
• If the calculated ‘t’ value exceed the value given
under p=0.05 in the table, it is said to be significant
at 5% level and null hypothesis (Ho) is rejected and
alternate hypothesis (H1) is accepted.

• Degree of freedom
– In unpaired t-test of difference between two means df=
n1 + n2 – 2, where n1 and n2 are the number of
observations in each of the two series.

– In paired t-test and one sample t test, df = n-1


One group of observations
(One sample t-test)

Compare the mean of a single group of observations with a


specified value.

Example

Data: Average daily energy intake (ADEI) over 10 days of 11 healthy


women

Sub: 1 2 3 4 5 6 7 8 9 10 11

ADEI(KJ) 5260 5470 5640 6180 6390 6515 6805 7515 7515 8230 8770
What can we say about the energy intake of these women
in relation to a recommended daily intake of 7725 KJ?
SD = 1142.1, df= n-1 = 11-1 = 10
= -2.81

P < 0.05

P value suggests that the dietary intake of these women was


significantly less than the recommended level (7725 KJ).
Clinical Significance Vs Statistical Significance
A possible antipyretic is tested in patients with the common cold.
500 receive the candidate drug
500 receive a placebo control
Temperatures measured 4 hours after dosing

p value = 0.011

Yes. Probably there is a reduction in temperature


Statistical Significance? __________________________________
Clinical Significance? NO. Temperature only fell by about 0.1°c
__________________________________

Because the sample size is so large we are able to detect a very


*small change in temperature 11
t-test for two paired (correlated) samples
(paired t test)
• Same individuals are studied more than once in different
circumstances
• E.g. Measurements made on the same people before
and after intervention
• The outcome variable should be continuous
• The difference between pre - post measurements should be
normally distributed

* 12
Uses of paired test:
• To study the role of a factor or cause when the observations are
made before and after its play e.g. pulse rate before and after
exercise, effect of garlic on cholesterol level

• To compare the effect of two drugs given to same individuals in


the sample on two different occasions

• To study the comparative accuracy of two different instruments


e.g. two types of BP instruments

• To compare results of two different laboratory techniques e.g


estimation of Haemoglobin by Tallquist and Sahli’s method

• To compare observations made at two different sites in the same


body e.g. compare To between axilla and mouth or mouth and
rectum
* 13
• Find the degrees of freedom. It should be n – 1

• Refer 't' table and find the probability of the


calculated ‘t’ corresponding to n – 1 degrees of
freedom

• If the probability (P) is more than 0.05, the


difference observed has no significance, because
such a difference can occur commonly due to
chance. Thus, the factor under study may have no
influence on the variable
• But if P is less than 0.05, the difference
observed is significant, because such a
difference is less likely to occur due to chance

• Influence of the factor to which the sample is


exposed may be accepted as an alternative to
null hypothesis.
Example
• Systolic Blood Pressure of 9 normal
individuals, who had been recumbent for 5
minutes, was taken. Then 2 ml of 0.5%
solution of hypotensive drug was given and
BP recorded again. Did the injection of drug
lower the blood pressure?

* 17
Sr No. BP Before BP after
Injection Injection
1 122 120
2 121 118
3 120 115
4 115 110
5 126 122
6 130 130
7 120 116
8 125 124
9 128 125
* 18
Sr BP Before BP after X1-X2=x x2
No. Injection Injection
X1 X2
1 122 120 2 4
2 121 118 3 9
3 120 115 5 25
4 115 110 5 25
5 126 122 4 16
6 130 130 0 0
7 120 116 4 16
8 125 124 1 1
9 128 125 3 9
* Σx= 27 Σx2=105 19
* 20
At 8 df and 5% significant level, by chance highest obtainable
value of ‘t’ is 2.31. The observed ‘t’ value is 5.17 which is very
high. The difference is statistically significant and not by chance.
So, the drug injected produced hypotensive effect.
t- test To examine the difference between two
independent groups

paired t-test To examine the difference between pre &


post measures of the same group

How do we compare more than two groups means??

ANOVA
* 23
• The weight of 10 tuberculosis patients on
admission and at the end of 12 months of
treatment with PAS plus isoniazid daily, are
given below. Examine whether the gain in
weight is statistically significant.
Patient’s Weight on Weight at 12
Serial Admission months
Number
1 49 52
2 41 43
3 37 46
4 41 52
5 42 46
6 37 38
7 39 42
8 38 41
9 41 42
10 35 38
Thank You

You might also like