NIT6130 Introduction to Research

a. Identify the available data sources for collection.
b. Select the most appropriate data source(s) and start data collection. You are asked to record the data sources that you have found, brief description of the available data

 

Design and implement experiments
a. Adopt data pre-processing. Not all the collected raw data are available as direct input of your methodology.
b. Feature selection or dimension reduction. You may need to select some of data features or data records from the entire data collection, not to use all the collected data. In other case, you may need to reduce the dimensionality
of the collected data to simplify the data processing in the later stages. You need to save the result data set into a new file.

 

Design your experiment based on the proposed methodology. The main purpose of experiments is to prove that your methodology can provide expected outcomes. You can follow the experiments that you have read from literatures or any other ways that is suitable for your case. Your experiments procedure need to be detailed recorded, including instruction steps, input data, expected output, potential problems and other related issues. When state the procedure of experiment, you can use extra table, figure, chart, diagram to provide better description. 

 

To implement your experiment, normally you need to use software/tools or write your own program. Record your experiment results for each run as the references of the following analysis task.
What are the expected results that you want to obtained from the experiment You need to have a rough idea of what you may have in advance; you cannot wait until the experiment is done.Plan your result analysis by thinking of what result you may have first.

 

Write a summary of why you expected to have that results, how they can be linked to your research problems. Write up your experiment and result analysis chapter.
a. Provide an outline of your experiment and result analysis chapter, including up to four levels of subsections. 

Before we conduct any research, it is required to collect the data which will be used in the research. Therefore, data collection is normally the first step which should be applied in any research process. We have various methods which can be used in the data collection process. The most commonly used data collection methods include questionnaire or survey data collection method, conducting interviews, direct observation, and experimentation (Sullivan-Bolyai, Bova, and Singh, 2014). The researchers should choose the best data collection method which will meet their needs at a low cost and without spending so much of their time. Questionnaire or survey method is the most common method of data collection used by many researchers. In the data collection process, the researchers should also identify the best sources which contain the required data. After collection of the required data, the data is normally recorded in data collection tables for easier analysis of the data. The data may also be stored in data storage tables for future references (Yamada and Wuttig, 2007, pp.824-832).

1.1 The sources of data

Before starting the experiment, the researchers should identify the available sources of the required data. They should choose the best sources for them to have an easy time in the data collection process. Our research aims to study the impacts of E-commerce on the behavior of customers in business. The customers who use the internet to study about businesses and purchase their products or services over the internet can be found in malls, in businesses which use E-commerce services, in institutions, in the social media or many other places or organizations. Therefore, the malls, the businesses which use E-commerce services, the institutions, and the social media will be the main sources of the data to be used in our research.

1.2 Collection of data

After identifying the best sources of data, the researchers should go to the field to collect the required data. In our research, we shall collect data from various malls, businesses, institutions, and other places or organizations such as people’s parks or supermarkets within Australia. We shall also use the social media to gather some data. The data is collected and recorded in tables before it can be used in the experimental research. A sample table which can be used to record the collected data is shown below:

Table 1: Data collection table

1.3 Storage of data

The process of data collection is usually a very expensive and tiresome process. Therefore, it is very necessary to store the collected data safely for future references (Scott, 2007). The stored data will also help to give the future researchers a rough idea of what they expect to find in the field if they intend to carry out a similar research. It is advisable to store the collected data in its raw form to make it easily understood by different researchers.  A sample table which can be used to store the collected data is shown below:

Table 2: Data storage table

Experiment design and implementation

Before implementing the actual experiment, the researchers are required to do a complete design of the experiment. In the design process, the researcher plans how he or she will carry out the whole experiment and identifies all the requirements of the experiment. He/she also makes sure all the materials needed for the experiment are available and ready to be used in the experiment. He/she goes further to specify all the variables which will be used in the experiment. The design process is meant to prepare the researcher to conduct the experiment smoothly without many obstacles (Taylor, Stouffer, and Meehl, 2012). In the implementation of the experiment, the researcher carries out the actual experimental process for him/her to obtain the results of the research or experiment process. The design and implementation of the research is a major stage any experiment, and we have many activities associated with this stage. Some of the major activities done in the design and implementation of experiment or research include data pre-processing, feature selection or dimension reduction, and analysis of the results either manually or by use of some special computer software such as SPSS or Ms. Excel. We have many other activities meant to achieve the best results from the research or experimental process (Mancini, Mansart, and Pagano, 2012, pp.113-122).

 Data pre-processing

Data pre-processing involves modifying the collected data to obtain the required format and type of data needed for the experiment to be conducted. We have various techniques which are used in data pre-processing. The most commonly used pre-processing techniques include data reduction, data cleaning, data integration and data transformation (Delen and Olson, 2008).

Data reduction is done to remove the unnecessary data which could have been collected. It also helps in removing redundancy in the collected data. Data cleaning is done to cleanse and polish the data to make it suitable for use in the experiment. Data cleaning may involve filling of the missing data, smoothening of the noisy data or resolving of some inconsistency issues in some sets of data (Dallachiesa, Ebaid, and Eldawy, 2013, pp.541-552).

Data integration is the process of combining different sets of data which have some differences in their representations. Combining the different sets of data helps to solve the differences between the data sets easily, and by doing so, the combined data sets can be used together without any problems. Data transformation involves aggregation, normalization, and generalization of the data to improve its usability in experiments or researches.

Feature selection or dimension reduction

Feature selection or dimension reduction is the process which aims to streamline the data further for the data to fit in the experiment. This process will make sure the researcher selects and uses only the required which has been modified completely to meet all the requirements of the experiment. After data pre-processing and feature selection or dimension reduction, the researchers normally creates a table to store the fully modified data ready to be used in the experiment. A sample table which can be used to record pre-processed and dimension reduced data is shown below. This data is now ready to be used in the experiment.

Table 3: A table of pre-processing, selection and reduction of data

 2.3 Experiment designing

This is the step which outlines the methodology to be used in details. In our case, we shall use hybrid methodology also referred to as mixed methods research which is a combination of both qualitative and quantitative research methodologies (Tashakkori and Creswell, 2007,pp.2-5). Hybrid research methodology is suitable for our research as it overcomes the limitations of each of the individual research methodologies. In our research methodology, we shall use questionnaire data collection method to collect the data of customers who use different malls, businesses, and institutions which offer E-commerce services in different places within Australia. We shall also collect the data of customers who use the social media to determine which malls, businesses or institutions to purchase their products or services.

2.3.1 The steps of designing the questionnaire

Our questionnaire method will be aimed at collecting the data about the customers who have been influenced by the use of E-commerce mostly in businesses. Our questionnaire shall categorize the customers who will be our respondents on the basis of their gender, age range, and background. A table showing the categorization of our respondents by their gender, age range, and their background is shown below:

 Table 4: A table showing the classification of the respondents according to their gender, age range, and background

 After categorizing our respondents, we should give them the questionnaire forms to be filled for them to provide the required information. A sample questionnaire form which can be used to collect the required data.After the design, the researchers should implement the research. In the implementation, the researchers begin by giving the questionnaire forms to the already identified respondents. In our research, we are going to give the questionnaire forms to five thousand (5000) respondents in different places within Australia. A sample size of five thousand will help us to obtain good results which can be used to estimate the overall results of the whole country.

2.4.2 Analysis of the number of respondents who took place in the research

After deciding on the sample size to be used, we can formulate some hypothetical numbers according to our expectations to represent the numbers of the respondents who took part in the research. We shall break down the numbers of the respondents according to their gender, age range and background for easier analysis. The analysis will be done using some special mathematical tools such as scientific calculators and some special computer software such as Ms. Excel. A table to represent the numbers of respondents who participated in the research is shown below.

Table 5: A table showing the numbers of the respondents who participated in the research

2.4.3 Representation of the numbers of the respondents who took part in the research using graphs

We can draw bar graphs and pie charts to represent the numbers of the respondents who took part in the research. The graphs and pie charts will be drawn according to the categorization of the respondents of by their gender, age range, and background. These graphs and pie charts will help to improve the visualization of the data of the numbers of respondents (Janert, 2010).After carrying out the research, we obtained the results shown in the table below:

Table 6: A table showing the summary of the results of the research

 The results estimation

Before we conduct any research, it is good to have a rough idea of the results we expect to get in our research. The expected results help the researchers to run their research smoothly, and they will easily identify any abnormalities which they come across during the research or experiment (MacLean, et al., 2010, pp.966-968).

In our research, we expect the number of customers using the social media and the internet to purchase their products and services to be very high, about 90%. Due to the increased levels of technology, most businesses have incorporated E-commerce services in their transactions, and this has motivated many people to use the internet on the purchase of different products and services. We also expect the number of the youths using the social media and the internet to purchase goods and services to be higher than that of the old people since the use of modern technology has been adopted by more youths than adults (Zhang, 2013).

3.2 The summary of the results

From our research, we obtained the following summarized results:

85.5% of the total number of respondents use the social media or the internet to purchase their products or services.

57.36% of the total number of customers who use the social media and the internet to purchase their products and services were male customers.

42.64% of the total number of customers who use the social media and the internet to purchase their products and services were female customers.

83.88% of the total number of respondents purchase their products or services in malls which offer E-commerce services.

84.32% of the total number of respondents purchase their products or services in businesses which offer E-commerce services.

The use of E-commerce in businesses has helped to increase the number of customers which has helped to increase the profits made by the businesses (Traver and Laudon, 2013).

References

MacLean, D. M. T. N. S. M. C. G. L. F. B. F. R. K. D. L. T. D. C. L. M. J. M., 2010. Skyline: an open source document editor for creating and analyzing targeted proteomics experiments. Bioinformatics, 26(7), pp. 966-968.

Delen, D. L. O. a. D., 2008. Advanced Data Mining Techniques. Berlin: Springer.

Mancini, B. M. a. S. P., 2012. Design and implementation of a flexible beamline for fs electron diffraction experiments. Nuclear Instruments and Methods in Physics, Volume 691, pp. 113-122.

Janert, P., 2010. Gnuplot in action: understanding data with graphs, s.l.: Manning.

Taylor, R. J. S. a. G. A. M., 2012. An Overview of CMIP5 and the Experiment Design. BAMS, Volume 93.

Dallachiesa, A. E. a. A. E., 2013. NADEEF: a commodity data cleaning system. ACM, Volume 41, pp. 541-552 .

Sullivan-Bolyai, S. B. a. C. S., 2014. Data-collection methods. Nursing Research in Canada-E-Book: Methods, Critical Appraisal, and Utilization, Volume 2, pp. 10-27.

Scott, J., 2007. Data storage: Multiferroic memories. Nature Materials, Volume 6, pp. 256-257.

Tashakkori, C. a., 2007. Exploring the Nature of Research Questions in Mixed Methods Research. Journal of Mixed Methods Research, 1(3), pp. 2-5.

Traver, C. G. L. a. K. C. a., 2013. E-commerce 2012: Business. Technology, Society, Volume 4.

Yamada, M. W. a. N., 2007. Phase-change materials for rewriteable data storage. Nature Materials, 6(11), pp. 824-832.

Zhang, W., 2013. Redefining youth activism through digital technology. International Communication Gazette, 75(3).