ZQMS-ARC-REC-002

ASSIGNMENT COVER

REGION: HARARE

PROGRAMME: [Link] INTAKE:9

FULL NAME OF STUDENT: CHIPUNGU SONNET PIN:P2579950K

MAILING ADDRESS: chipungusonnet@[Link]

CONTACT TELEPHONE/CELL: 078149899 ID. NO.: 15-197257G31

COURSE NAME: COURSE CODE: BEIA and BEID 103

ASSIGNMENT NO. e.g. 1 or 2: ASSIGNMENT 1 DUE DATE: 20 February 2026

ASSIGNMENT TITLE: RESEARCH METHODS

MARKER’S COMMENTS: ______________________________________________________

______________________________________________________________________________
______________________________________________________________________________

______________________________________________________________________________
OVERALL MARK: _____________ MARKER’S NAME: ________________________

MARKER’S SIGNATURE:_______________________________ DATE: ___________

 QUESTION 1

Research Problem: Barriers to accessing higher education for students with physical disabilities
in Zimbabwean universities.

To collect relevant information, the researcher will use qualitative data instruments as this is a
research. The researcher will use unstructured questionnaires, unstructured interviews, and
observations. These are qualitative data collection instruments that allows the researcher to gain a
comprehensive understanding of the research problem from the insights of participants and their
opinions.

a. Administering Unstructured Questionnaire

The first instrument that would be administered is a structured questionnaire directed to students
with physical disabilities enrolled at selected universities. The questionnaire will contain mostly
open-ended questions to capture opinions. The administration of the questionnaire will take into
consideration accessibility issues that may affect participants (Sapon-Shevin, 2017).
Questionnaires will be provided in large print formats for students with visual challenges, while
digital versions will be distributed through email or online survey platforms such as Google
Forms for students who use assistive technologies. Where necessary, the researcher will assist
respondents by reading the questions aloud and recording their responses. Participants will be
recruited through university disability support offices after obtaining permission from the
institutions. Respondents will be given adequate time to complete the questionnaires voluntarily,
and confidentiality of their responses will be guaranteed.

b. Administering Unstructured Interviews

The researcher will also use in-depth interviews in order to get invaluable deeper understanding
of the problem. In collecting data using this instrument, interviews will be conducted with a
selected group of students with physical disabilities, lecturers, and staff from disability support
units. The purpose of the interviews would be to obtain deeper insights into the lived experiences
of students with disabilities, particularly regarding barriers in teaching methods, physical
infrastructure, and institutional support systems (Seeram, 2019). Interviews will be arranged at
times convenient to the participants and conducted in accessible venues within the university
campuses (Teller and Ogawa, 2020). In some cases, online platforms such as Zoom or WhatsApp
video calls may be used to accommodate participants who have mobility challenges. Before the
interviews begin, participants will be asked to sign informed consent forms and will be informed
about their right to withdraw from the study at any time. With permission from the participants,
the interviews will be audio recorded to ensure accuracy and to allow the researcher to focus on
the conversation rather than extensive note taking. Each interview will last for a maximum of
twenty-five minutes and the interview guide will be followed while still allowing participants to
freely express their experiences.

c. Observation
Another important data collection instrument will be an observation checklist used to assess the
physical accessibility of university facilities. The researcher will conduct direct observations on
selected campuses to evaluate infrastructure such as wheelchair ramps, elevators, accessible
toilets, lecture rooms, and library entrances (Teller and Ogawa, 2020). The observation checklist
will help the researcher systematically record whether facilities meet accessibility standards for
students with physical disabilities (Seeram, 2019). This method is included in order to
complement the information obtained from questionnaires and interviews by providing objective
evidence about the actual physical environment within universities. Field notes will also be
recorded during the observation process to capture important contextual details.

Entering Data

After collecting data, the next step will involve entering the collected data and organizing it. The
responses from questionnaires will be sorted according to themes. These themes will be arranged
according to their section from the objectives. To ensure accuracy, the data entry process will
involve cross-checking entries and conducting data cleaning procedures to identify errors,
inconsistencies, or outliers that may affect the quality of the analysis.

Also, qualitative data that will be collected from interviews will be handled through transcription
and thematic organization. Audio recordings from interviews will be transcribed verbatim into
written text and the researcher will then read through the transcripts several times in order to
identify recurring themes related to accessibility barriers, institutional support, discrimination,
and coping strategies used by students with disabilities. These themes will then be coded and
organized using qualitative data analysis software such as NVivo or through manual thematic
analysis. Observation notes collected from campus visits will be typed and categorized according
to key themes such as infrastructure accessibility and environmental barriers.
How to treat missing numbers

The researcher may miss some important data whereby respondents fail to answer certain
questions. Missing data will be identified first during the data cleaning stage and recorded using
a specific code to indicate that the value is missing. The treatment of missing data will depend on
the extent and importance of the missing responses (Field, 2018). If only a small number of
responses are missing, the researcher may use mean substitution, where the average value of the
variable is used to replace the missing value. However, in cases where respondents have left
many questions unanswered, the researcher will use the listwise deletion which involves
excluding that particular questionnaire from the analysis. Alternatively, pairwise deletion may be
used in statistical analysis so that only the missing values for a specific variable are excluded
while the rest of the respondent’s data remains usable (Kothari, 2019). Where possible, the
researcher may also contact participants to clarify missing responses, particularly if the missing
information is critical to the study.
 QUESTION 2

Test scores Frequency Mid-point

40-49 5 44.5

50-59 6 54.5

60-69 20 64.5

70-79 7 74.5

80-89 4 84.5

90-99 2 94.5

i) Range = Highest Value – Lowest Value

= 99 – 40

= 59

Q3−Q 1 12.86
ii) Quartile deviation = =
2 2

= 6.43

N
−cf
iii) Median = 2
L+ ×h
f

22−11
¿ 59.5+ ×10
20

¿ 65
 =∑
f x 2 ∑ fx
2

iv) Variance −( )
N N

= ∑ f x 2 = 196201 =4459.11
N 44

∑ fx = 2888 =65.64
N 44

= 65.942 = 43008.61

Therefore, Variance = 4459.11 – 4308.61

= 150.50

Standard Deviation
v) Coefficient of variation = ×100
Mean

SD=√ 150.50=12.27

¿ 12.27

12.27
CV = ×100
65.64

¿ 18.7 %

3N
−cf
vi) Upper quartile 4
¿ L+ ×h
4
 33−31
¿ 69.5+ ×100
7
¿ 69.5+2.86
¿ 72.36
vii) Interquartile range ¿ Q 3−Q 1

¿ 72.36−59.5
¿ 12.86
viii) Histogram

The interquartile range is the most appropriate measure of dispersion for the data. This is because
it less likely affected by extreme values as the data contains very low scores such as 40 to 49 and
some very high scores of 90-99 which may distort measures like range and variance (Saunders et
al., 2019). Also, the interquartile range focuses on the middle which is the 50 percent of the data
which measures the spread of the central portion where most students scored (Kothari, 2019).
This measure of dispersion is most appropriate because it is most suitable for grouped data and
work well with class intervals (). Therefore, as the majority of students scored between 60-69,
the interquartile range better reflects the typical spread of the test score results.

QUESTION 3

i) Statistic and Parameter

A parameter is a numerical value that describes a characteristic of an entire population, while a
statistic is a numerical value calculated from a sample drawn from that population (Walpole et
al., 2017). Parameters are usually fixed but unknown because it is often impractical to collect
data from every member of the population. Statistics are therefore used to estimate these
parameters (Triola, 2022). For example, if a researcher calculates the average income of all
households in Zimbabwe, the value obtained represents a parameter because it describes the
entire population. However, if the researcher collects data from 200 households in Harare and
calculates their average income, the result is a statistic because it represents only the sample used
in the study.

ii) Inferential Statistics and Descriptive Statistics

Descriptive statistics refer to methods used to organize, summarize, and present data in a
meaningful form Field, 2018 (Field, 2018). These methods include measures such as the mean,
median, mode, standard deviation, tables, charts, and graphs. Descriptive statistics simply
describe the characteristics of the data collected. In contrast, inferential statistics involve
techniques used to draw conclusions or make generalizations about a population based on a
sample of data. Inferential statistics include hypothesis testing, correlation analysis, regression
analysis, and confidence intervals (Creswell & Creswell, 2018). For example, calculating the
average mark of students in a class is descriptive statistics, while using the results from a sample
of students to predict the academic performance of all students in a university is inferential
statistics.

iii) Probability Sampling and Non-Probability Sampling

Probability sampling is a sampling method in which every member of the population has a
known and equal probability of being selected. This method relies on random selection
techniques and helps reduce sampling bias, making it possible to generalize results to the entire
population (Creswell & Creswell, 2018). Examples include simple random sampling, stratified
sampling, cluster sampling, and systematic sampling. For instance, a researcher may randomly
select 100 students from a university registration list using a computer-generated random
process. In contrast, non-probability sampling refers to sampling methods where not every
member of the population has a known or equal chance of being selected. Participants are chosen
based on accessibility, convenience, or the researcher’s judgement (Saunders et al., 2019).
Examples include convenience sampling, purposive sampling, quota sampling, and snowball
sampling. For example, a researcher might interview students who are available in the university
library because they are easy to reach.

iv) Population and Sample

A population refers to the entire group of individuals, objects, or observations that a researcher is
interested in studying, while a sample is a subset of the population selected to represent it in the
study. Since studying the entire population is often costly and time-consuming, researchers
collect data from a sample and use the results to make inferences about the population (Kothari,
2019). For example, all students enrolled at universities in Zimbabwe may represent the
population of interest. If a researcher selects 300 students from several universities to participate
in a survey, those students constitute the sample (Walpole et al., 2017). The accuracy of research
findings largely depends on how well the sample represents the population.

v) Grouped Data and Ungrouped Data

Ungrouped data refers to raw data presented as individual observations without classification. It
typically appears as a simple list of numbers (Triola, 2022). For example, test scores such as 45,
50, 62, 67, 70, 73, 85 represent ungrouped data. In contrast, grouped data refers to data that has
been organized into categories or class intervals to make analysis easier, especially when dealing
with large datasets. For example, the same scores may be grouped into intervals such as 40–49,
50–59, 60–69, 70–79, and 80–89, along with the number of students in each category. Grouping
data helps simplify large datasets and makes it easier to construct graphs such as histograms.

vi) Ratio Scale and Interval Scale

Measurement scales determine how variables are measured and analyzed. A ratio scale has equal
intervals between values and includes a true zero point that indicates the absence of the measured
quantity (Field, 2018). Because of the true zero, meaningful ratio comparisons can be made.
Examples of ratio scale variables include height, weight, income, and age. For example, a person
weighing 80 kg is twice as heavy as a person weighing 40 kg. On the other hand, an interval
scale also has equal intervals between values but lacks a true zero point (Walpole et al., 2017).
As a result, ratios between values are not meaningful. A common example of an interval scale is
temperature measured in Celsius or Fahrenheit, where zero does not represent the absence of
temperature.

vii) One-Tailed Test and Two-Tailed Test

A one-tailed test is used when the researcher predicts the direction of the relationship or
difference being tested (Walpole et al., 2017). In this case, the rejection region is located in only
one tail of the probability distribution. For example, a researcher may test whether a new
teaching method increases students’ examination scores compared to the traditional method. A
two-tailed test, however, is used when the researcher does not specify the direction of the
expected effect (Field, 2018). The rejection regions are located in both tails of the distribution
because the test checks whether there is any difference, whether positive or negative. For
example, a researcher may investigate whether a new teaching method affects students’
performance either positively or negatively.

viii) Rejection Region and Acceptance Region

In hypothesis testing, the rejection region refers to the range of values of the test statistic that
leads to the rejection of the null hypothesis. This region corresponds to the chosen level of
significance (α), which represents the probability of making a Type I error (Field, 2018). If the
calculated test statistic falls within the rejection region, the null hypothesis is rejected. In
contrast, the acceptance region (or non-rejection region) refers to the range of values where the
null hypothesis is not rejected because there is insufficient evidence to support the alternative
hypothesis (Triola, 2022). For example, in a z-test conducted at a 5% level of significance, values
that fall beyond the critical limits form the rejection region.

ix) p-Value Approach and Classical Approach in Hypothesis Testing

The p-value approach and the classical approach are two common methods used to make
decisions in hypothesis testing. The p-value approach involves calculating the probability of
obtaining a test statistic as extreme as the observed value under the assumption that the null
hypothesis is true (Triola, 2022). The p-value is then compared with the level of significance (α).
If the p-value is less than or equal to α, the null hypothesis is rejected (Walpole et al., 2017). In
contrast, the classical approach involves comparing the calculated test statistic with a critical
value obtained from statistical tables. If the test statistic lies in the rejection region defined by the
critical value, the null hypothesis is rejected. Although the procedures differ, both approaches
lead to the same conclusion regarding the hypothesis.

x) Parametric Test and Non-Parametric Test

Parametric tests are statistical tests that rely on certain assumptions about the population
distribution from which the sample is drawn. These tests typically assume that the data follow a
normal distribution and are measured on interval or ratio scales (Kothari, 2019). Examples of
parametric tests include the t-test, analysis of variance (ANOVA), and Pearson correlation
coefficient. Parametric tests are powerful and efficient when their assumptions are satisfied. In
contrast, non-parametric tests do not rely on strict assumptions about the population distribution
and are often used when data are measured on ordinal or nominal scales or when the assumptions
of parametric tests are violated (Kothari, C2019). Examples include the chi-square test, Mann–
Whitney U test, and Wilcoxon signed-rank test. For instance, comparing mean examination
scores between two groups of students may involve a t-test, whereas comparing students’
preferences for different subjects may require a chi-square test.

QUESTION 4

i. The two properties of the Normal Distribution

The normal distribution is asymmetrical about the mean, meaning the left side of the curve is a
mirror image of the right side (Field, 2018). In this case, the mean, median, and mode are equal
and located at the center of the distribution.

ii. The Z-score for students with 36 percent sore

 36−50
¿
10

¿−1.4

The Z-score for students with 75

75−50
¿
10

¿ 2.5

iii. Proportion of Scores

a. Less than 65
65−50
Z score is ¿ =1.5
10

Therefore, P (Z < 1.5) = 0.9332

The proportion of scores less than 65 is 93.32 percent

b. Between 36 and 75

Z36 = 1.4

Z75 = 2.5

Therefore, P (Z < 2.5) = 0.9938

P (Z < -1.4) = 0.0808

P (-1.4 < Z < 2.5) = 0.9938 – 0.0808

= 0.913
This means that the proportion between 36 and 75 is 91.3 percent

iv) Students expected to score above 50

Mean = 50

P(X > 50) = 0.50

N = 150

Therefore, 0.5 × 150 = 75

The expected number of students scoring above 50 marks is 75 students.

4b) Hypothesis Test

H0 = µ ≤ 60

H1 = µ > 60

Level of significance is a = 0.05

Zcritical = 1.645

Reject H0 if Z > 1.645

x=58 minutes , μ=60 minutes , σ =10.5 , n=200

10.5
Standard error = =0.743
√200
58−60
The Z value is Z= =−2.69
0.743
Therefore, we fail to reject the null hypothesis and conclude that at 5 percent level of
significance, the is no evidence that the average registration time exceeds 60 minutes which
supports the belief by the Dean that students at most one hour at MyVista platform.

REFERENCES

Creswell, J. W., & Creswell, J. D. (2018). Research design: Qualitative, quantitative, and mixed

‘methods approaches (5th ed). SAGE Publications.

Field, A. (2018). Discovering statistics using IBM SPSS statistics (5th ed). SAGE Publications.

Kothari, C. R. (2019). Research methodology: Methods and techniques (3rd ed). New Age

International Publishers

Saunders, M., Lewis, P., & Thornhill, A. (2019). Research methods for business students (8th
ed).

Pearson Education.

Seeram. A, (2019). Research in Disability Studies: An overview. Radiology Technology, 91(2)

Teller. T. C and Ogawa. M, (2020). Collecting field data in disability studies. AI Practioner
22(4)

Triola, M. F. (2022). Elementary statistics (14th ed). Pearson Education.

Walpole, R. E., Myers, R. H., Myers, S. L., & Ye, K. (2017). Probability and statistics for

engineers and scientists (9th ed). Pearson Education.

Seeram. A, (2019). Research in Disability Studies: An overview. Radiology Technology, 91(2)