ZQMS-ARC-REC-002

ASSIGNMENT COVER

REGION: HARARE

PROGRAMME: BACHELOR OF SCIENCE IN SOFTWARE ENGINEERING INTAKE: 3:2

FULL NAME OF STUDENT: TAWANDA MAGWENZI PIN:P2135871A

MAILING ADDRESS: [email protected]

CONTACT TELEPHONE/CELL 0788322034 ID. NO.: 59-178085E18

COURSE NAME: RESEARCH METHODS : BSIT382

ASSIGNMENT NO. : 2 DUE DATE: OCTOBER

ASSIGNMENT TITLE: ASSIGNMENT 2

______________________________________________________________________________
______________________________________________________________________________

MARKER’S COMMENTS: ______________________________________________________

______________________________________________________________________________
______________________________________________________________________________

______________________________________________________________________________
OVERALL MARK: _____________ MARKER’S NAME: ________________________

MARKER’S SIGNATURE:_______________________________ DATE: ___________

Issue Date
QUESTION 1

a) In recent years, the mean age of all Z.O.U students in Bulawayo city has been 23. A
random sample of 42 students revealed a mean age of 23.8. Suppose their ages are
normally distributed with a population standard deviation of σ=2.4. Can we infer at
α=0.02 that the population mean has changed? [10 marks]

1. State the Hypotheses:

• Null Hypothesis (H0H_0): The population mean age has not changed (μ=23\mu =
23).

• Alternative Hypothesis (H1H_1): The population mean age has changed (μ≠23\m
u \neq 23).

2. Significance Level:

• α=0.02\alpha = 0.02

3. Test Statistic:

• Since the population standard deviation (σ\sigma) is known, we'll use the Z-test.

• Formula: Z=Xˉ−μσ/nZ = \frac{\bar{X} - \mu}{\sigma / \sqrt{n}}

4. Calculate the Test Statistic:

• Sample mean (Xˉ\bar{X}) = 23.8

• Population mean (μ\mu) = 23

• Population standard deviation (σ\sigma) = 2.4

• Sample size (nn) = 42

5. Determine the Critical Value:

• For a two-tailed test at α=0.02\alpha = 0.02, the critical Z-

values are approximately ±2.33\pm 2.33.
 6. Decision Rule:

• If ∣Z∣>2.33|Z| > 2.33, we reject the null hypothesis.

7. Compare and Conclude:

• Calculated ZZ-value = 2.16

• Since 2.16 is not greater than 2.33, we fail to reject the null hypothesis.

Conclusion:

At the 0.02 significance level, there is not enough evidence to conclude that the population me
an age of Z.O.U students in Bulawayo city has changed. The sample data does not provide suffic
ient support to infer a change in the population mean.

b) With the aid of examples explain the following study designs in quantitative research
i. Experimental [5 marks]
ii. Non-experimental [5 marks]
iii. quasi- or semi-experimental. [5 marks]

Study Design Description Example

N]
Experimental Involves active manipulation Testing a new drug's effect on blood
of variables and random pressure by randomly assigning
assignment to groups participants to drug or placebo groups
Non-Experimental Observes and measures Examining the relationship between
variables as they naturally sleep hours and academic performance
occur without manipulation by observing students' sleep patterns and
grades.
Quasi-Experimental Similar to experimental but Evaluating a new teaching method's
lacks random assignment; effectiveness by comparing one class
involves manipulation of using the new method to another using
variables the traditional method
 a) The percentage of adults who are men and alcoholics is 2.25%. What is the probability
of being an alcoholic, given being a man? [5 marks]

• The percentage of adults who are men and alcoholics is 2.25%.

• Let P(A∩B)P(A \cap B) be the probability of being both a man and an alcoholic.

This can be expressed as:

P(A∩B)=0.0225P(A \cap B) = 0.0225

• Let P(B)P(B) be the probability of being a man.

To find the conditional probability P(A∣B)P(A|B) (probability of being an alcoholic given being a man):

P(A∣B)=P(A∩B)P(B)P(A|B) = \frac{P(A \cap B)}{P(B)}

Without additional information about the probability of being a man (P(B)P(B)), we typically assume P(B)
P(B) is the percentage of men in the population. For simplicity, let's assume P(B)P(B) is around 50%, or 0.
5.

P(A∣B)=0.02250.5=0.045P(A|B) = \frac{0.0225}{0.5} = 0.045

The probability of being an alcoholic, given being a man is 0.045 or 4.5%.

Distinguish between Quantitative and Qualitative study design [10

Quantitative research is a systematic investigation that collects and analyzes numerical data to
understand a phenomenon.

Key Characteristics:
• Objective and numerical data collection
• Large sample sizes
• Hypothesis-testing
• Statistical analysis
• Generalizability to a larger population
• Focus on measurement and quantification
• Experimental or quasi-experimental designs
Examples Surveys, Experiments ,Longitudinal studies and Correlational studies
Qualitative research is an exploratory investigation that collects and analyzes non-numerical
data to gain insight into a phenomenon.

Key Characteristics:

• Subjective and non-numerical data collection

• Small, purposeful sample sizes
• Exploratory, open-ended approach
• Thematic analysis (e.g., coding, content analysis)
• In-depth understanding of a specific context
• Focus on meaning and interpretation
• Non-experimental designs

Examples: Case studies, Interviews

Attrribute Quantitative Qualitative

Data type numerical Non numerical
Sample size large Small
analysis statistical thematic
purpose generalizability uunderstanding

3.The average number of homes sold by a Realty Company is 2 homes per day. Using Poisson
distribution, what is the probability that exactly 3 homes will be sold tomorrow? [5 marks]

V= (X = k) = (e−λ x (λk )) / k!
where:
P(X = k) is the probability of selling k homes
λ (lambda) is the average number of homes sold per day = 2
k is the number of homes sold = 3
e is the base of the natural logarithm ≈ 2.718
Substituting the values:
P(X = 3) = e−2 x (23 )) / 3!
P(X = 3) = (0.1353 x 8) / 6
P(X = 3) ≈ 0.1804

The probability that exactly 3 homes will be sold tomorrow is approximately 0.1804 or 18.04%.
b. The metal discs produced by a certain machine have mean diameter 30.01mm and standard
deviation 0.08mm.A sample of 100 discs are taken .Find the probability that the mean diameter
of the discs in this sample is less than 30mm [10 mark]

Population mean (μ) = 30.01 mm

- Population standard deviation (σ) = 0.08 mm
- Sample size (n) = 100

First, find the standard error (SE) of the sample mean:

SE = σ / √n
= 0.08 / √100
= 0.08 / 10
= 0.008

Next, convert the desired sample mean (30mm) to a Z-score:

Z = (X̄ - μ) / SE
= (30 - 30.01) / 0.008
= -0.01 / 0.008
= -1.25

Now, use a Z-table or calculator to find the probability that the sample mean is less than 30mm
(Z < -1.25):

P(Z < -1.25) ≈ 0.1056

The probability that the mean diameter of the discs in this sample is less than 30mm is
approximately 10.56%.

c. Differentiate between Stratified sampling and area sampling [10 marks]

Characteristics Stratified Sampling Area Sampling

Definition Divide population into Divide population into
subgroups geographical areas
Sampling frame SRS from each stratum SRS from selected areas
Sample size Determined by research Determined by population
question
 precision High reduces sampling errors Varies dependent on area
selection
Representation High ensures representation Voting behavior by age

a) The time to travel to work by 50 students in minutes is given below

7 19 5 35 22 14 49 38 19 28
13 49 37 45 11 6 26 18 35 18
45 23 27 15 47 43 9 9 26 19
40 9 16 10 33 24 37 32 17 13
21 31 50 25 8 32 18 23 37 16

Using a class width of 10 and starting from 1, construct a frequency distribution table for the data
above

[5

b) Using the table constructed in (i) above, estimate the;

i. Mean [5 marks]
ii. Median [5 marks]
iii. Variance [5 marks]

a) Frequency Distribution Table

To create the frequency distribution table, we'll start from 1 minute and use a class width of 10
minutes:
Time Interval (minutes) Frequency
1 - 10 5
11 - 20 11
21 - 30 14
31 - 40 11
41 - 50 9
b) Calculations
i. Mean:
To estimate the mean, we'll use the midpoint of each class interval and multiply it by the freque
ncy of that interval:
Midpoint=Lower Bound+Upper Bound2
Mean=∑(f⋅x)N
Where:
• f is the frequency
• x is the midpoint
• N is the total number of observations
Time Interval (minutes)Midpoint (x)Frequency (f)f⋅x1−105.5527.511−2015.511170.521−3025.51
435731−4035.511390.541−5045.59409.5Total501355
Mean=135550=27.1 minutes
ii. Median:
The median is the value separating the higher half from the lower half. Here’s how we calculate
it for grouped data:
Median=L+(N2−CFf)⋅w
Where:
• L is the lower boundary of the median class
• N is the total frequency
• CF is the cumulative frequency before the median class
• f is the frequency of the median class
• w is the class width
For N=50: n/2 = 25 ]
The cumulative frequency just before 21 - 30 (the median class) is 16 (5 + 11):
Median=20.5+(25−1614)⋅10≈20.5+(914)⋅10≈26.9 minutes
iii. Variance:
Variance measures how much the values in a dataset differ from the mean. For grouped data, u
se:
σ2=∑f⋅(x−xˉ)2N
Where:
• xˉ is the mean
• x is the midpoint of each class
Time Interval (minutes)Midpoint (x)Frequency (f)(x−xˉ)f⋅(x−xˉ)21−105.55−21.62332.811−2015.5
11−11.61473.621−3025.514−1.635.8431−4035.5118.4775.4441−5045.5918.43044.16Total5076
61.84
σ2=7661.8450=153.24 minutes2
So, the mean is approximately 27.1 minutes, the median is approximately 26.9 minutes, and the
variance is approximately 153.24 minutes squared.
 c) With the aid of a practical example, discuss the Case Study research design [5 marks]

Case Study: Investigating the Implementation of Cloud Computing in a Small Software

Development Company
Research Question: How does a small software development company successfully migrate its
infrastructure to cloud computing, and what benefits and challenges does it experience?
Methodology:
• Site selection: Choose a small software development company that has recently migrated to
cloud computing.
• Data collection:
✓ Interviews with IT managers, developers, and employees.
✓ Observations of cloud infrastructure usage.
✓ Review of company documents, reports, and metrics.
• Data analysis: Thematic analysis to identify key themes, benefits, and challenges.
Objectives:
• Identify motivations for cloud migration.
• Analyze technical and non-technical challenges faced.
• Evaluate benefits (cost savings, scalability, flexibility).
• Document best practices and lessons learned.
Data Sources:
• Semi-structured interviews with 10 employees.
• Observations of cloud infrastructure usage (6 months).
Company documents (migration plan, cost-benefit analysis).
Expected Outcomes:
• Insights into successful cloud migration strategies.
• Identification of common challenges and solutions.
• Evaluation of cost savings and scalability benefits.
• Recommendations for small software development companies considering cloud migration.
Case Study Type: Instrumental (studying the case to inform practice)
Best Practices:
• Ensure data triangulation (multiple sources).
• Maintain researcher objectivity.
• Document detailed findings.
• Consider generalizability limitations.
By conducting this case study, researchers can provide valuable insights into cloud computing
adoption in small software development companies.

References

"The Research Methods Knowledge Base" by William M.K. Trochim (online resource)

"Research Design: Qualitative, Quantitative, and Mixed Methods Approaches" by John W.

Creswell

Daly, L., & Bourke, G. J. (2008). Interpretation and uses of medical statistics. John Wiley & Sons.

Mahoney, J., & Goertz, G. (2006). A tale of two cultures: Contrasting quantitative and
qualitative research. Political analysis, 14(3), 227-249.