View
217
Download
0
Category
Tags:
Preview:
Citation preview
T- TEST
Prof. Dr. Ramez Bedwany
COMPARISON OF TWO INDEPENDENT SAMPLEST- TEST
= mean of the first simple = mean of the second sample = pooled Variance
= pooled Variance
Critical t from table at degree of freedom = n1+ n2-2
If n1+ n2 < 120 use t test
If n1+ n2 ≥120 use z test with the same formula
EXAMPLE (1)
Sample of size 25 was selected from healthy population , their mean BP 125 mm Hg with standard deviation of 10 mm Hg. another sample of size 17 was selected from population of diabetics their mean BP was l32mmHg, with standard deviation of 12 mm Hg Test whether there is significant difference in mean BP of diabetics and healthy individual at I % level of significance
ANSWER
n1=25 X1=125 S1=10 n2=17 X2=132 S2=12 df= n1+n2-2 = 25+17-2=40 Critical t at 40, 1% level of significance 2.704
Decision:
Since the computed t is smaller than critical t so there is no significant difference between mean BP of healthy and diabetic samples at 1 %
EXERCISE
Example 2 and 3
T- TEST FOR PAIRED OBSERVATION (T- DIFFERENCE)
Uses: To compare the means of two paired
samples
Example: Mean pulse rate before and after intake of
drug
di = difference (after-before)Sd = standard deviation of differencen = sample sizeCritical t from table at df = n-1
EXAMPLE (1)
The following data represents the reading of Systolic BP before and after administration of certain drug. Test whether the drug has an effect on BP at 1% level of significance
Serial number BP BP
Before after
I 200
180 2 160
165 3 190
175 4 185
185 5 210
170 6 175
160
ANSWER
= -14.17
= 15.942
Critical t at df=6-1=5 and 1% level of significance = 4.032
Decision Since the computed t is smaller than critical t so
there is no significant difference between mean BP before and after administration of drug so the drug has no effect on BP at 1% level of significance
ASSIGNMENT
احمد فتوح احمد محمدالسيد صالح محمد
خضر عادل محمدرمضن علي محمد
Measures of Dispersion
OUTCOMES
By the end of this lecture, the student will be able to Know definition, uses and types of statistics.
Recommended