t Test for Hypothesis of the Mean Column1

Data Mean 269.69

Null Hypothesis m= 0 Standard Error 3.809266367
Level of Significance 0.05 Median 272.5
Sample Size 40 Mode #N/A
Sample Mean 269.69 Standard Deviation 24.09191587
Sample Standard Deviation 24.09191587 Sample Variance 580.4204103
Kurtosis 0.236042786
Intermediate Calculations Skewness -0.423923424
Standard Error of the Mean 3.8093 Range 108.2
Degrees of Freedom 39 Minimum 204.4
t Test Statistic 70.7984 Maximum 312.6
Sum 10787.6
Upper-Tail Test Count 40
Upper Critical Value 1.6849 For one-tailed tests:
p-Value 0.0000 T.DIST.RT value 4.105826E-43
Reject the null hypothesis 1-T.DIST.RT value 1

PROBLEM
A manufacturer of plastics wants to evaluate the durability of Brand A plastic blocks that are
to be used in furniture. A random sample of 40 such plastic blocks are examined, and their
hardness is measured. Using 0.05 level of significance, is there evidence that the average
hardness of plastic blocks exceeds 260?

SOLUTION
Ho: x = 260
Ha: x > 260
Level of significance = 0.05, upper-tailed test
Decision rule: p-value (0.00) > (0.05) ∝
Decision: Reject the null hypothesis
Conclusion: the p-value, 0.00, is relatively low, so there is enough evidence to reject the
Ho. There is sufficient evidence to conclude that the average durability of plastic blocks
is higher than 260.
SWS Noli - Loren

PHStat User Note:

Observed Frequencies Enter replacement labels for the
Column variable row and column variables as well as
Calculations
Row variable C1 C2 Total the observed
fo-fe frequency counts in
the table that starts in row 3.
R1 624 1200 1824 62.28374 -62.2837
R2 444 1200 1644 Note: The #DIV/0!
-62.2837 62.28374error messages
Total 1068 2400 3468 will disappear after you enter the
observed frequency counts.

Expected Frequencies (Before continuing, press the Delete

key to delete this note.)
Column variable
Row variable C1 C2 Total (fo-fe)^2/fe
R1 561.7163 1262.284 1824 6.906091 3.073211
R2 506.2837 1137.716 1644 7.662233 3.409694
Total 1068 2400 3468

Data
Level of Significance 0.05
Number of Rows 2
Number of Columns 2
Degrees of Freedom 1

Results
Critical Value 3.841459
Chi-Square Test Statistic 21.05123
p-Value 4.47E-06
Reject the null hypothesis

Expected frequency assumption

is met.
Z Test for Differences in Two Proportions

Data
Hypothesized Difference 0 PROBLEM
Level of Significance 0.05 In the vice presidiential race, Sen. Noli De Castro widened his lead against fellow ABS-CBN
Group 1 broadcaster Loren Legarda, scoring 52% against Legarda's 37%, the report said. The survey
Number of Items of Interest 63 was conducted with a ±3% margin of error and a sample size of 1,200. Test at 0.05 level if
Sample Size 1200 the proportion of Noli's votes is significantly higher than that of Loren.
Group 2
Number of Items of Interest 444
SOLUTION
Sample Size 1200
Ho: �� n = �� l
Intermediate Calculations Ha: � � n > �� l
Group 1 Proportion 0.0525 Level of significance = 0.05 , upper-tailed test
Group 2 Proportion 0.37 Decision rule: p-value (0.00) < ∝ (0.05)
Difference in Two Proportions -0.3175 Decision: Reject the null hypothesis
Average Proportion 0.2113 Conclusion: the p-value, 0.00, is relatively low, so there is enough evidence to reject the
Z Test Statistic -19.0525 Ho. There is sufficient evidence to suggest that Noli De Castro's lead is far higher
compared to Legarda's.
Upper-Tail Test
Upper Critical Value 1.6449
p-Value 1.0000
Do not reject the null hypothesis
Z Test of Hypothesis for the Mean PROBLEM
The Quality Control Division of PepCo Bottling Co. is interested in finding the actual amount
Data of soft drinks in a 2 - liter bottle. The bottling plant has informed the inspection division that
Null Hypothesis m= 0 the standard deviation for a 2 - liter bottle is 0.06 liter. A random sample of 100 2- liter bottles
Level of Significance 0.05 obtained from this plant indicates a sample average of 1.99 liters. At 0.05 level of significance
Population Standard Deviation 15 test If there is evidence that the average amount in bottles is different from 2 liters.
Sample Size 100
Sample Mean 1.99

SOLUTION
Intermediate Calculations
Standard Error of the Mean 1.5000 Ho: average amount of bottles = 2-liter bottle
Z Test Statistic 1.3267 Ha: average amount of bottles ≠ 2-liter bottle
Level of significance = 0.05 , two-tailed test
Two-Tail Test Decision rule: p-value (0.00) < ∝ (0.05)
Lower Critical Value -1.9600 Decision: Reject the null hypothesis
Upper Critical Value 1.9600 Conclusion: the p-value, 0.00, is relatively low, so there is enough evidence to reject the
p-Value 0.1846 Ho. There is sufficient evidence to conclude that the average amount of bottles is not equal
Do not reject the null hypothesis to the 2-liter bottle.
Z Test for Differences in Two Means

Data
Hypothesized Difference 0
Level of Significance 0.01 PROBLEM
Population 1 Sample To gather information on a water conservation drive in a college campus, sample data are
Sample Size 36 collected which show that 50 showers taken by students in dormitory A used an average
Sample Mean 50 of 36 gallons of water while 50 showers taken by students in dormitory B used an average
Population Standard Deviation 2.5 of 35.5 gallons of water. If the population standard deviation is known to be 2.5 gallons, is
Population 2 Sample there a significant difference between the water consumption of students in two
Sample Size 36 dormitories? Use 0.01 level of significance.
Sample Mean 50
Population Standard Deviation 2.5

SOLUTION
Intermediate Calculations
Difference in Sample Means 0 Ho: Da = Db
Standard Error of the Difference in Means 0.5893 Ha: Da ≠ Db
Z Test Statistic 0.0000 Level of significance = 0.01 , two-tailed test
Decision rule: p-value (1.00) > ∝ (0.01)
Two-Tail Test Decision: Do not reject the null hypothesis
Lower Critical Value -2.5758 Conclusion: the p-value, 1.00, is relatively large, so there is not enough evidence to reject
Upper Critical Value 2.5758 the Ho. There is no sufficient evidence to support that the water consumption of two
p-Value 1.0000 dormitories are not equal.
Do not reject the null hypothesis
Z Test for Differences in Two Means

Data
Hypothesized Difference 0.00 PROBLEM
Level of Significance 0.01 An instructor wishes to determine which of two methods is more effective in teaching a
Population 1 Sample certain concept in Statistics. In a class of 36 students, he used Method A and in another class
Sample Size 36.00 of 40 students, he used Method B. At the end of the lesson, he gave the two classes the same
Sample Mean 78.00 examination and obtained the following results:
Population Standard Deviation 4.00
Population 2 Sample Method A X1 = 78 S1 = 4
Sample Size 40.00 Method B X2 = 70 S2 = 6
Sample Mean 70.00 Is he/she correct in assuming that Method A is more effective than Method B? Use 0.01 level.
Population Standard Deviation 6.00

SOLUTION
Intermediate Calculations
Difference in Sample Means 8.00 Ho: Ma = Mb
Standard Error of the Difference in Means 1.16 Ha: Ma > Mb
Z Test Statistic 6.90 Level of significance = 0.01 , upper-tailed test
Decision rule: p-value (0.00) < (0.01) ∝
Upper-Tail Test Decision: Reject the null hypothesis
Upper Critical Value 2.33 Conclusion: the p-value, 0.0000, is relatively low, so there is a strong evidence to reject the Ho.
p-Value 0.00 There is sufficient evidence to conclude that Method A is effective than Method B.
Reject the null hypothesis
 PROBLEM
Two rival manufacturers of penlight batteries claimed that their product lasts longer than the other. 30 samples z-Test: Two Sample for Means
of Brand A and 34 samples of Brand B were tested.
Variable 1 Variable 2
Mean 39.866666667 40.20588235
Known Variance 7.36091954 4.41087344
Observations 30 34
SOLUTION
Hypothesized Mean Difference 0
Ho: � a = � b z -0.553866333
Ha: � a ≠ � b P(Z<=z) one-tail 0.2898351636
Level of significance = 0.05 , two - tailed test z Critical one-tail 1.644853627
Decision rule: p-value (0.57) > ∝ (0.05) P(Z<=z) two-tail 0.5796703273
Decision: Do not reject the null hypothesis z Critical two-tail 1.9599639845
Conclusion: The p-value, 0.57, is relatively high. So there is not enough evidence to reject the
Ho. There is sufficient evidence to conclude that the penlight batteries of both manufacturers equally lasts longer.

Column1 BRAND A Column1 BRAND B

Mean 39.8666666667 Mean 40.2058823529

Standard Error 0.4953422904 Standard Error 0.3601826922
Median 40 Median 40
Mode 38 Mode 40
Standard Deviation 2.7131014615 Standard Deviation 2.1002079517
Sample Variance 7.3609195402 Sample Variance 4.4108734403
Kurtosis -0.7422939408 Kurtosis 0.044451346
Skewness -0.0713023544 Skewness 0.0653386212
Range 10 Range 9
Minimum 35 Minimum 36
Maximum 45 Maximum 45
Sum 1196 Sum 1367
Count 30 Count 34
Z Test of Hypothesis for the Mean
PROBLEM
Data An Electric company claims that the lives of the light bulbs it manufactures are normally
Null Hypothesis m= 1000.0 distributed with a mean 1000 hours and a standard deviation of 100 hours. Test if this claim
Level of Significance 0.05 is true, if a random sample of 100 bulbs produce by this company has a mean life of 980 hours.
Population Standard Deviation 15.0 use 0.05 level of significance.
Sample Size 100.0
Sample Mean 980.0
SOLUTION

Intermediate Calculations Ho: � = 1000

Standard Error of the Mean 1.50 Ha: � ≠ 1000
Z Test Statistic -13.33 Level of significance = 0.05 , two-tailed test
Decision rule: p-value (0.0455) < ∝ (0.05)
Two-Tail Test Decision: Reject the null hypothesis
Lower Critical Value -1.9600 Conclusion: the p-value, 0.0455, is relatively low, so there is enough evidence to reject the
Upper Critical Value 1.9600 Ho. There is sufficient evidence to conclude that the lives of the light bulbs is not equal to
p-Value 0.0000 1000 hours.
Reject the null hypothesis
 3T/Wk 2T/Wk
80 66 t-Test: Two-Sample Assuming Unequal Variances
85 98
74 87 Variable 1 Variable 2
75 84 Mean 75.5 64.66666667
65 85 Variance 102.2692308 433.1515152
66 56 Observations 14 12
80 59 Hypothesized Mean Difference 0
77 25 df 15
75 53 t Stat 1.644419868
95 45 P(T<=t) one-tail 0.060439379
66 66 t Critical one-tail 2.602480295
55 52 P(T<=t) two-tail 0.120878759
79 t Critical two-tail 2.946712883
85

PROBLEM
A teacher wants to find out if there is a significant difference in the academic performance of two groups of students. One group meets
thrice a week while the other meets twice a week. Use level of significance of 0.01.

SOLUTION
Ho: � 3T = � 2T
Ha: � 3T ≠ � 2T
Level of significance = 0.01 , two-tailed test
Decision rule: p-value (0.12) > ∝ (0.01)
Decision: Do not reject the null hypothesis
Conclusion: the p-value, 0.12, is relatively high, so there is not enough evidence to reject the
Ho. There is no sufficient evidence to conclude that the one of the two groups of students has a better academic performance than the
other.
Z Test of Hypothesis for the Mean PROBLEM
1. The average newspaper sold by Mang Tomas a day, for the past 70 days is 800 copies with
Data a standandard deviation of 25. Last Sunday, he was able to sell only 750 copies because
Null Hypothesis m= 800.00 of bad weather. Is it significantly lower than his average daily sale? Use a level of
Level of Significance 0.05 significance of 0.05.
Population Standard Deviation 15.00
Sample Size 70.00
SOLUTION
Sample Mean 750.00
Ho: � = 800
Intermediate Calculations Ha: � < 800
Standard Error of the Mean 1.79 Level of significance = 0.05 , lower - tail test
Z Test Statistic -27.89 Decision rule: p-value (0.00) < ∝ (0.05)
Decision: Reject the null hypothesis
Lower-Tail Test Conclusion: The p-value, 0.00, is relatively low. So there is strong evidence to reject the
Lower Critical Value -1.64 Ho. There is sufficient evidence to conclude that the news paper sold last Sunday is lesser
p-Value 0.00 than the average sale.
Reject the null hypothesis
 Gogo Yokoo
10 12 t-Test: Two-Sample Assuming Unequal Variances
8 15
15 20 Variable 1 Variable 2
16 25 Mean 7.5 11
5 8 Variance 28.722222222 49.77777778
11 9 Observations 10 10
3 6 Hypothesized Mean Difference 0
1 5 df 17
4 3 t Stat -1.249203568
2 7 P(T<=t) one-tail 0.1142590411
t Critical one-tail 1.7396067261
P(T<=t) two-tail 0.2285180823
t Critical two-tail 2.1098155778

PROBLEM
A computer teacher wants to find out if GOGO search engine is more efficient than YOKOO in downloading heavy graphics materials. Ten
sample materials were downloaded at the same time; the result is given in minutes. Level of significance: 0.05.

SOLUTION
Ho � G = � Y
Ha: � G ≠ � Y
Level of significance = 0.05 , two-tailed test
Decision rule: p-value (0.23) > ∝ (0.05)
Decision: Do not reject the null hypothesis
Conclusion: the p-value, 0.23, is relatively high, so there is no enough evidence to reject the
Ho. There is no sufficient evidence to conclude that GOGO search engine is more efficient than YOKOO.