Location via proxy:   [ UP ]  
[Report a bug]   [Manage cookies]                

STATISTIC

Download as docx, pdf, or txt
Download as docx, pdf, or txt
You are on page 1of 6

Republic of the Philippines

CEBU TECHNOLOGICAL UNIVERSITY


MOALBOAL CAMPUS: Poblacion West, Moalboal, Cebu
Tel. No. 474-8196; 474-8104 http: //www.ctu.edu.ph
Tel. Fax No.: 474-8196; 474-8383; 474- Email: ctumoalboalcampus@gmail.com
8104

College of Education, Arts, and Sciences


VISION: MISSION: GOALS: OUTCOMES:

A premier The University shall primarily


provide advanced professional and The University shall 1. Relevant, effective and quality
produce scientifically and education for sustainable growth.
multidisciplinary- technical instruction for special purposes,
advanced studies in industrial trade, technologically oriented human 2. Access to quality education for
technological agriculture, fishery, forestry, engineering,
aeronautics and land-based programs,
capital equipped with appropriate the underprivileged students.
3. Relevant research for
knowledge, skills and attitude. It
university. education, arts and sciences, health
shall likewise pursue relevant
economic, environmental and
sciences, and other relevant fields of sustainable development.
study. It shall also undertake research, research, strengthen linkage with
4. Expanded community
and extension services, and production, the industry, community and other engagement.
and provide progressive leadership in its institutions and maintain sustainable 5. Effective and efficient
area of specialization. technology for the preservation of management of resources.
the environment.

ADVANCED STATISTICS

Test the claims. Provide the following:


a) identify the claim and state H0 and Ha;
b) determine the statistical treatment based on the different assumptions;
c) find the P-value;
d) decide whether to reject or fail to reject the null hypothesis; and
e) interpret the decision in the context of the original claim.

Problem 1.
The average family size was reported as 3.18. A random sample of families in a particular school district resulted in the
following family sizes:

At 𝛼 = 0.05, does the average family size differ from the national average?

a.) H0: There is no significant difference in average family size.


Ha: There is significant difference in average family size. (claim)
b.) One-Sample T-test
 The dependent variable is continuous.
 The observations are independent of one another.
 The dependent variable is normally distributed.
 There is no significant outlier.

c.) P = 0.036
d.) Reject H0
e.) There is significant difference between the average family size and national average.
Reporting:
A one-sample t-test was run to determine whether the average family size was different to national average, reported
as 3.18. The family sizes were normally distributed as assessed by the Shapiro-wilk test (p>0.05) and there were no outliers
in the data, as assessed by inspection of a boxplot. Mean score (M=3.83, SD=1.43) was higher than the national average of
3.18, a statistically significant mean difference of 0.65, 95% CI[0.04 to 0.51], t(23)= 2.231, p= 0.036.

Problem 2.
A sample of legal costs (in thousands of dollars) for school districts for two recent consecutive years is shown. At 𝛼 =
0.05, is there a difference in the costs?

a) H0: There is no significant difference of the legal cost for school districts.
Ha: There is a significant difference of the legal cost for school districts. (claim)

b) Wilcoxon Sign Test


 The two dependent samples are continuous.
 The independent variable in this problem consist of two categorical groups.
 The distribution of the differences between the two related groups are symmetrical.
 There is a significant outlier on the difference of the two groups based on the test.

c) P=0.001
d) Reject H0
e) There is a significant difference of the legal cost for school districts.

Hypothesis Test Summary


Null Hypothesis Test Sig. Decision
1 The distributions of Year1, Year2 and Related-Samples Friedman's Two- .001 Reject the null hypothesis.
difference are the same. Way Analysis of Variance by Ranks
Asymptotic significances are displayed. The significance level is .050.

Ranks
N Mean Rank Sum of Ranks
Year2 - Year1 Negative Ranks 1a 2.50 2.50
b
Positive Ranks 7 4.79 33.50
c
Ties 0
Total 8
a. Year2 < Year1
b. Year2 > Year1
c. Year2 = Year1

Report
Median
Year1 Year2 difference
76.0000 82.0000 18.5000

Reporting:
A Wilcoxon signed rank test determined that there was a statistically significant difference in two consecutive
years (Mdn= 18.5), when the legal costs of the first year (Mdn= 76) compared to the cost of the second year (Mdn=
82), z= -2.173, p <0.05.
Problem 3.
The table shows assessment scores of two different classes who are being taught computer skills using two different
methods. At 𝛼 = 0.05, determine which was better for teaching computer skills. Report your findings.

a.) H0: There is no significant difference between the assessment scores.


Ha: There is significant difference between the assessment scores. (claim)

b.) Independent T-test


 The dependent variable should be continuous.
 The independent variable consists of two categorical independent variables.

 The dependent variable is not normally distributed
 There is no significant outlier.
 There is homogeneity of variances.

Mann-Whitney U-Test
c.) P = 0.401
d.) Accept H0
e.) There is no significant difference between the assessment scores.

Reporting:
A Mann-Whitney U Test was run to determine if there were differences in the assessment scores between method 1 and
method 2. Assessment scores of two different classes for method 1 and method 2 were not similar, as assessed by visual
inspection. Assessment scores for method 1 (mean rank = 9.50) and method 2 (mean rank = 7.50) were not statistically
significantly different, U = 24, z = -0.840, p = 0.401
Problem 4.
A sample of non-English majors at a selected college was used in a study to see if the student retained more from reading
a 19th-century novel or by watching it in DVD form. Each student was assigned one novel to read and a different one to
watch, and then they were given a 20-point written quiz on each novel. The test results are shown below. At 𝛼 = 0.05,
can it be concluded that the book scores are higher than the DVD scores?

a.) H0: There is no significant difference between the scores of students who read books and student who watch DVD.
Ha: There is significant difference between the scores of students who read books and student who watch DVD. (claim)
b.) Paired sample T-test
 The two dependent samples are continuous
 The independent variable in this problem consist of two categorical groups.

c.) P = 0.051
d.) Accept H0
e.) There is no significant difference between the scores of students who read books and student who watch DVD.
Paired Samples Statistics
Mean N Std. Deviation Std. Error Mean
Pair 1 book 84.1429 7 6.06709 2.29314

DVD 77.4286 7 5.28700 1.99830

Test Statisticsa

DVD - book
Z -1.951b
Asymp. Sig. (2-tailed) .051
a. Wilcoxon Signed Ranks Test
b. Based on positive ranks.

Hypothesis Test Summary


Null Hypothesis Test Sig. Decision
1 The median of differences between Related-Samples Wilcoxon Signed .051 Retain the null hypothesis.
book and DVD equals 0. Rank Test
Asymptotic significances are displayed. The significance level is .050.

Ranks
N Mean Rank Sum of Ranks
a
DVD - book Negative Ranks 6 4.25 25.50
b
Positive Ranks 1 2.50 2.50
Ties 0c
Total 7
a. DVD < book
b. DVD > book
c. DVD = book

Report
Median
book DVD Difference
84.0000 80.0000 -8.0000
Reporting:

A wilcoxon signed rank test determined that it is not statistically significant different in studying using books and DVD, (Mdn= -8),
when the students who retained more from reading (Mdn= 84) compared to the students who retained more from watching DVD
(Mdn= 80), z= -1.95, p >0.05.

Problem 5.
The weights in ounces of a sample of running shoes for men and women are shown. Test the claim that the means are
different at 𝛼 = 0.05.

a.) H0: There is no significant difference between weights of running shoes.


Ha: There is significant difference between weights of running shoes. (claim)
b.)
Mann-Whitney U Test
 The dependent variable is continuous.
 The independent variable consists of two categorical, independent groups.
 The observations are independent of one another.
 The dependent variable is normally distributed.
 There are no significant outliers.
 There is no homogeneity of variances.
c.) P = 0.0001

d.) Reject H0

e.) There is significant difference between weights of running shoes.

Reporting
A Mann-Whitney U Test was run to determine if there were
differences in the weight of the running shoes between men and women.
Weights of the running shoes of men and women were not similar as assessed by
visual inspection. Weights of running shoes for men (mean
rank = 19.90) were statistically significantly higher than for women (mean
rank = 8.40), U = 6, z =- 3.831, p = 0.0001

You might also like