## Question:

We have the scientific method as a tool to help us solve our problems.

* This method’s core is the testing and formulation of hypotheses

* Hypotheses can be loosely defined as ‘potential answers to questions’

* Geographers employ quantitative methods within the context of scientific method in at most two distinct ways:

The aim is to examine the commute patterns of UCC students within the context of climate change and greenhouse gas emissions.

3) Use explanatory methods for analysis

4) Use confirmatory methods to verify a hypothesis.

## Answer:

It is necessary to compute the descriptive statistics related the commutation distance of each variable student.

The descriptive statistics relating to the commutation time for each variable student must be computed.

The following graph summarizes the bar chart regarding the sensitivity of UCC students to carbon footprint.

The majority of responses are from those who don’t consider carbon footprint.

There are a lot of students who are sensitive to carbon environment when making commuting choices.

Students may also consider their carbon footprint when making commutation decisions to university.

These pie charts show the necessary pie-charts. It is clear that many students who live in rented accommodation tend to walk to university.

This could be because these students rent near the university campus to reduce transportation costs and time.

Contrary to this, those who live in close proximity to the university are able to commute more easily by walking and have a higher percentage of success.

This is because most students’ homes are not in the same vicinity as the university, so walking would not be an option.

Below is the required histogram. There does not appear to be a significant difference in the commute distances of students who are members or not of UCC Clubs and Societies.

Scale differences can cause a difference in the distributions. Once adjusted, this would be similar.

Medhi (2016) also states that neither of these distributions are normal due to right skew.

Below are the steps required for hypothesis testing.

Step 1: Determining the null hypothesis

There is no significant difference between the B.A. and B.Sc in average commute distances.

Students and B.Sc.

Step 2: Specify the alternative hypothesis

Ha: uBAuBSc, i.e.

There is a significant difference in the average commute distance between the B.A.

Students and B.Sc.

Step 3: The significance threshold for this test is assumed to be 5%. This would be appropriate for the hypothesis in question, where higher accuracy is not required.

Step 4: The pertinent test statistic for the case would be t statistics.

The given for both samples, i.e.

Distance to B.A.

Students and the commuting distance to B.Sc.

The population standard deviation is unknown.

If the population standard deviation had been known, the relevant test statistics would have shown z (Flick 2015).

Given that the two samples are independent, a two-sample independent t test would be performed.

In this case, you have two choices: equal or unequal variance.

Given that the samples are not equal in size, unequal variance is assumed. (Hair and.

Excel output can be used to determine the value of the test statistic.

The above output shows that the t statistics came out to be 0.344.

Step 5: It is important to highlight the critical values of the test.

This test is a two-tail test because the alternative hypothesis includes the “not equal” sign.

There would then be two critical values: one at the lower and one at the higher ends.

The output above shows that the t critical value for the upper end of the spectrum is 1.9655, while the equivalent value at lower end would be 0.9655 (Hillier 2016, Hillier).

Step 6: If the test statistic falls within the range defined by the critical values then the null hypothesis will not be rejected. Alternate hypothesis will not be accepted.

The computed t statistic in the case is 0.344. It tends to lie between 1.9655 and -1.9655.

Accordingly, null hypothesis rejection is not justified by the evidence (Lieberman and.

It can therefore be concluded that there is not a significant difference in the average commute distance for B.A.

and BSc students.

This is the research question that was chosen for this analysis.

“Is there a relationship between the mode used to commute to the university and the number of students?”

This research question was chosen to examine whether students’ level influences their choice of transport system.

The research question explores the preferences of both levels of students in relation to their choices for commute. This can then be used to further analyze the reasons and possibly other variables like distance, location, etc.

An inferential test would be used to determine the relevant statistical analysis. The underlying objective of the statistical analysis is to identify the population parameter from the sample statistics.

Hypothesis testing would be used. The Chi-square test for independence would be the best test.

This is because both variables of interest are categorical in their measurement and non-numerical in their underlying data types.

In this situation, the chi square test statistics would prove to be most suitable (Hastie Tibshirani, Friedman, 2014).

Below are the necessary hypotheses to pass this test.

Null Hypothesis: There’s no relationship between the mode of commutation and the level of course.

Alternative Hypothesis

Assumed significance of the hypothesis test is 5%

To calculate the chi-square statistic the first step is to indicate what the actual frequency is of each mode of transport, divided according to the student’s level. Next is to use this data to determine the expected frequencies for the different modes of commutation, based on the student’s level.

This is shown below.

The chi-square has been highlighted below.

The chi square test statistic (21.05) was used in the calculation. Also, the degrees of freedom (9-1*(2-1)) were added to calculate the p value.

The chi square test statistic (21.05) from the above computation was used to calculate the p value. Also, the degrees of freedom (9-1)*(2-1) = 8.

The alternative hypothesis would therefore be accepted (Hillier 2016,).

Acceptance of the alternative hypothesis suggests that students’ level and commutation modes are interrelated.

It is important to further analyze the inter-relationship of the student level with the commutation means from the university. This will also consider the potential impact of distance from the university on the relationship observed in the hypothesis testing.

It is also important to examine any existing empirical support to provide more insight into the relationship. (Eriksson and Kovalainen 2015).

This section aims to critically examine the methodology and the underlying findings.

1) The survey questionnaire worked really well.

The key reason the survey worked was because the questions were structured in an objective way and all options were available to respondents.

The survey took respondents less time and the results were more accurate due to the lack of subjectivity that is common in open-ended questions.

It was notable that only a few comments were collected in other comments regarding improvements.

Mechanisms should be implemented to improve the responses to the survey. It provides valuable information that could prove useful.

The questionnaire could also be improved by reducing the number of questions, especially if they are not relevant. Respondents expressed concerns about the length.

It would have been beneficial if respondents were briefed prior to the survey about the purpose and the questions.

This could increase the accuracy of data collected from respondents.

It would also be a good idea for respondents to complete the survey and to be passed on to them.

This is particularly important in the contexts of some information, especially the distance from the UCC that not everyone would know.

The sample that was used to respond to the survey is another important aspect.

This is crucial because it is important to ensure that the sample used for the survey is representative of the entire population.

Students at UCC would have a negative impact on the reliability of the results.

The current survey attempted to include all key characteristics of the population in the random selection of respondents.

It would be more practical to use stratified sampling, which would ensure a more representative sample, and increase the reliability of the observed trends.

2) A fascinating aspect of commutation trends in relation to rented students is that more than 75% prefer to walk to get to the university.

The distance from the university is the most important factor in deciding the mode of commute.

The UCC should invest in a hostel or other residential facility on campus to help reduce carbon emissions.

This is especially important for students from outstation and those who live far away from campus.

It may also make sense for UCC to encourage students to commute by bicycle.

You can do this by allowing only one vehicle on campus, and parking it for them.

The university might also consider plying buses, if there are routes that students are able to assess. This would allow students to travel together in one mode of transport.

It is important to discourage individual car travel. Therefore, UCC students should have access to car pooling forums so that students can collaborate to lower their transportation costs and carbon footprint.

The best option is one that offers students housing near campus. This would make it convenient for them and save money.

Refer to

Eriksson (P.) and Kovalainen (A.

(2015) Quantitative methods for business research.

London: Sage Publications.

Grossman, G., and Fehr, F. H.

A primer on sets, probability, and hypothesis testing.

(2015) Introduction to research methodology: A beginner’s guide for conducting a project.

New York: Sage Publications.

Hair, J. F. Wolfinbarger M., Money A. H. Samouel P., Page M. J.

(2015) The essentials of business research methods.

New York: Routledge.

Hastie T., Tibshirani R., and Friedman J.

(2014) The Elements of Statistical Learning.

Hillier, F. (2016) Introduction to Operations Research.

McGraw Hill Publications, New York.

(2012) Introduction to Operations Research.

New Delhi: Tata McGraw Hill Publishers.

(2016). Statistical Methods: An Introduction Text.

Sydney: New Age International.