Advantages and Disadvantages of Primary Data

1
BUSINESS ANALYSIS

2
Contents
Introduction................................................................................................................................3
Question 1..................................................................................................................................3
Significance of population.........................................................................................................3
The significance of sampling techniques...................................................................................4
Question 2..................................................................................................................................5
Primary data...............................................................................................................................5
Secondary data...........................................................................................................................5
The main difference between primary and secondary data........................................................5
Advantages and disadvantages of primary data.........................................................................7
Advantages and disadvantages of Secondary data.....................................................................7
Question 3..................................................................................................................................8
Question 4..................................................................................................................................9
Conclusion................................................................................................................................11
Reference..................................................................................................................................13

3
Introduction
The business decisions are crucial as they can change the performance of the company in a
short time. Either the decision can increase the value of the company or it can result in a
blunder. Therefore, business managers use analysis techniques to assess the options before
making decisions. The objective of the paper is to demonstrate the business analysis
techniques used by the business managers by answering some of the questions related to the
topic. For the analysis of the paper, the organization of Google Inc has been selected. Google
Inc is one of the largest digital service providers in the world.
Question 1
Significance of population
The business managers first tend to collect data from various sources to get an insight from
the data points recorded in the previous periods. The survey is one of the methods of data
collection where respondents are asked simple questions related to the decision that the
company is going to undertake (Etikan and Babatope, 2019). In this case, the survey is done
for collecting the information on the view of the colleagues in Google Inc regarding the
possibility of a holiday pay scheme. The information collected from different colleagues
allows the business manager to understand the opinion of all the stakeholders of the business.
Now the population in the survey method of data collection is total people for which the
survey result will be inferred. However, it is not possible for the researcher to survey the total
population and hence a sample taken out from the population is used for the data collection.
The population and the sample play an important role in the accuracy of the data collection
and inference of the result. Guha and Chandra (2019) stated that, if the sample size is close to
the population size then the accuracy of the data collection is high. On the other hand, if the
sample size is smaller compared to the population size the accuracy reduces. In the case of
Google Inc, the number of colleagues is huge in number and hence the population is high.
Therefore, in this case, there is a chance of sampling error that can reduce the robustness of
the research result (Maerz, 2018). The size of the population determines the accuracy of the
result from the survey. If the size of the population is low, it is easier for the researcher to
draw the inference from the selected sample. In addition to that population also determines
the challenge of the researcher as well. In the case of a small population, the accuracy
remains high and hence their small challenges. On the other hand, if the population is high
the accuracy reduces and hence challenges to the researcher are very high.

4
In the case of all the employees of Google Inc, the total number of employees is 98125 as of
2019. This is a medium-sized population and hence the challenge for the researcher is also
moderate. Here the population is the total strength of the company and the objective of the
researcher is to pick samples out of the population in such a way that it represents the
population in the most accurate ways. Chauvet (2020) stated that the process of choosing or
picking the sample is called the sampling technique. This sampling technique further
influences the robustness of the study.
The significance of sampling techniques
The significance of sampling in the research design is very crucial. There are several choices
available to the researcher in terms of sampling technique which can influence the study
differently. First and foremost a sampling technique can either be probabilistic or not
probabilistic depending on how the samples are being selected by the researcher. If the
samples are selected randomly from the population it is called a probabilistic sampling
whereas, if the samples are purposely picked up from the population it is called
nonprobabilistic sampling (Shimizu and de Siqueira Bueno, 2019). While probabilistic
sampling avoids the biases of the researcher from the study, non-probabilistic sampling can
induce biases in the process. For example, in the case of Google Inc, if a non-probabilistic
sampling technique is used by the researcher, the choice of sample picked up from the
population can be done in such a way that it shows the desired result of the researcher.
Another difference between the probabilistic and non probabilistic sampling is that in
probabilistic sampling all the members of the population has the equal chance to get selected.
Non probabilistic sampling is useful when different types of people of sample need to be
collected from the population. Random sampling is an example of probabilistic sampling
while an example of non probabilistic sampling can be the purposive sampling.
Quota sampling is a type of sampling where different type of people from the population is
selected. For example, if employees of Google Inc who are travelers are given a specific
quota in the sampling there will be less chance of sampling error in the process (Symonds et
al. 2018). Random sampling is the most widely used sampling technique that can influence
the findings as well. In this sampling technique, each of the individuals of the population has
an equal chance of being chosen in the sample. Therefore, the bias of the researcher can be
avoided and participation of different types of employees will be equal in the sample. Pollet
et al. (2018) stated that, in the case of random sampling, individuals of having the same
preferences will not have any different probability of getting selected in the sample. Stratified

5
sampling again has a different outcome if the researcher chooses it over any other sampling
technique. Stratified sampling allows the researcher to categorize between the samples based
on their importance on the topic of the research. For example, the research outcome will be
different if the researcher selects a different sample for different age groups of the employees.
Vu et al. (2019) stated that different age groups can have different preferences which can be
appropriate in some of the cases based on the topic of research. In this case, the preferences
of young employees for holiday will be more than the aged employees and hence to avoid
bias, stratified sampling can be a good option for the robust outcome of the paper.
Furthermore, systematic sampling is another technique where the samples are chosen based
on the order of the appearance of the sample. The biggest significance of this sampling is that
it does not allow any bias from the side of the researcher and hence the process is random
(Shukla and Sisodia, 2018). However, in this case of the holiday pay scheme, this sampling
technique can cause sample frame errors where the wrong sub-population is selected for the
study. This can hugely influence the result of the study. Apart from that, there can be a
chance of systematic error in the case of this sampling as well. According to the theory of
sampling technique, systematic error is when the result of the sample does not accurately
show the result of the population. Therefore systematic sampling in the case of Google Inc
can result in a bias in terms of result.
Question 2
Primary data
The primary data are the data that are collected directly from the respondents or the primary
sources such as individuals, machines, etc. Primary data collection requires effort from the
side of humans as well (Jennings et al. 2018). There are several techniques such as surveys,
interview, observation and experiment which are used in the collection of the primary data.
The choice of the primary data for the analysis depends on the nature of the project and the
objective of the study. In the case of the holiday pay scheme of Google Inc, primary data will
be the best as these unique data will not be available in any other secondary source.
Secondary data
Secondary data are data that are collected by other people who have researched the same
topic. Secondary data are collected from secondary sources that are used in journals, articles,
websites, etc. Secondary data collection is much more cost-effective compared to the primary
data (Slade et al. 2018). However, secondary data cannot be used in all the research projects

6
such as in this one. Any other researches will not be able to provide the specific preferences
of the colleagues working in Google Inc.
The main difference between primary and secondary data
One of the major differences between the primary and secondary data is the source. While
primary data is a firsthand data collected directly from the sources, secondary data is used
data by any other studies researching the same topic. In addition to that primary data is also
called the real-time data as data can be dynamic (Livingstone et al. 2019). In the case of
preference for the holiday pay scheme, the preferences of the employees of Google Inc can
change over time. Therefore primary data collection provides real-time updated data. This
can make the outcome of the paper more robust and credible. On the other hand, secondary
data are past data collected at a backdate before the date of the current research. Therefore,
the dynamic nature of the individual’s choices is not incorporated in the secondary data (Jekel
et al. 2019). For example, if the company had collected the data for the same reason 15 years
back and uses it for the analysis of the paper, it can be different from the real current
preferences of the employees of the company. In addition to that, the involvement of the
researcher is more in case of primary data collection compared to that of secondary data
collection.
The process of data collection of primary and secondary data is also different from each
other. While surveys, the interview is often used for the collection of primary data, secondary
data requires research of the government publication and journal that has already collected
data from the primary sources (Santhanam and Keller, 2018). This is also the reason for the
increased cost in the case of primary data collection as it requires manpower and involvement
in the overall process. Secondary data collection is cheaper compared to that of primary data
collection as it does not require the researcher to go to each of the respondents. In the case of
Google Inc, primary data collection is the only option and hence it will be costlier for the
researcher. Another important difference between the two data types is in terms of the cost of
acquiring the data. Primary data collection requires time as the researcher goes to each of the
respondents personally and jots down their data. Bilau et al. (2018) stated that primary data
also needs manipulation and analysis after the collection in its raw form as well. On the other
hand, secondary data are mostly easy to achieve from websites, journals, and articles. The
primary data are in its crude form which requires analysis from the side of the researcher
before it can be used for the synthesis. Secondary data are already analyzed by the researcher
who collected the data. Therefore it is easier and less complex to work with the secondary

7
data than primary data. Primary data is collected due to the special need of the report and
hence it’s specific to the needs of the researcher and the topic chosen by the researcher. On
the other hand, secondary data are not always specific to the needs of the researcher and
hence require operation for the best use (Zhao et al. 2018). Lastly, in the case of primary
data, the researcher can personally choose the respondents based on the appropriateness
according to the paper. In the case of secondary data, the researcher can only know what
types of sampling techniques have been used for the collection of the data. Therefore,
accuracy and the credibility of the primary data is more than that of the secondary data.
Advantages and disadvantages of primary data
Due to the differences in the characteristics of the two data types, there are different pros and
cons of each of the data types.
The advantages of primary data are that it can be collected specifically for the needs of the
project. The primary data can be collected based on the objective of the research that can
further increase the robustness of the paper. In this case of Google Inc, the primary data needs
to be collected that will provide the live preferences of the employees of the company
regarding the new holiday pay scheme. In addition to that primary data also provides better
accuracy that estimates the characteristics of the population in a better way. For example, if
the researcher's hand-collected secondary data for the study of the employees of Google, it
would not have provided the best result (Ketchen et al. 2019). Lastly, the primary data also
provides great control to the research in terms of the approach and design of the research as
well. However, the biggest disadvantage of using primary data is that it is costly for any
researcher. The collection of primary data requires manual effort and hence can be hectic as
well. The time taken to collect the primary data and transform it into a usable database is also
much time-consuming. Therefore if the research needs to be undertaken in a short time
primary data collection is not the correct option (O’Halloran et al. 2018). Furthermore,
primary data collection also can be impossible to carry out in some of the cases.
Advantages and disadvantages of Secondary data
The biggest advantage of using secondary data is that it saves the time of the researcher as the
collection of secondary data is very easy. In addition to that, the accessibility of secondary
data is also more than the primary data as it is freely available in the journals and articles.
However, there are some of the sources of secondary data that require subscription and
unique access (Phakiti et al. 2018). Therefore the collection of secondary data also saves

8
costs for the researcher as well. Therefore, the researches which are low in the budget can
easily use secondary data (Sheard and Marsh, 2019). Another advantage of secondary data is
that it is readily available in most of the sources and hence does not require the researcher to
run operations on them. However, secondary data has the biggest disadvantage of being
generic. The secondary data collected from the secondary sources may not be suitable for the
project into consideration. For example, in the case of Google Inc, the secondary data will fail
to provide the real preferences of the employees working in the company. In addition to that,
the researcher can't understand whether there is a bias in the data collected by the other paper
(Summers, 2019). This bias can influence the study of the project in hand and reduce the
robustness of the paper. Lastly, the secondary data are not updated versions of the dynamic
preferences of the respondents that provide a wrong inference of the population.
Question 3
The chosen organization is Google Inc, and the chosen financial measurement is the profit of
the company. The data has been collected from the official website of the company for the
year 2001 to 2018. The calculations and the table have been presented below:
Year
Revenue in Billion
USD
2014 59.62
2015 67.39
2016 79.38
2017 95.38
2018 116.32
Mean 83.618
Mode #N/A
Standard
Deviation 20.32229357
Table 1: The calculations of statistical measures
(Source: Developed by the learner)
(a) The mean of the profit of the company is 83.61 (Approx) billion USD for the total
period chosen. The means of the profit of this company is more than any other global
companies in the world. It also needs to be noted that due to the increase in the growth
of profit over the years, the mean has increased as well.

9
(b) The mode is the value of the variable that has the highest frequency. In this case, all
the values of profit for the company are unique and unequal to each other. Therefore
the mode of the selected data does not exist.
(c) The standard deviation measures the deviation of the values of the variable from the
mean value. In this case, the standard deviation is 20.30 which are moderately low
given the size of the data set. Therefore the values of the variable are only slightly
scattered about the mean of the variable.
Question 4
Decision making is very crucial in the case of modern business operations. A slight change in
the decision can change the outcome enjoyed by any company in the market. Therefore
nowadays, companies are careful about making decisions right away (Boddy et al. 2018). A
management information system is a collection of hardware and software which stores data
regarding the operation of the company and helps in the process of these data so that
appropriate decision can be taken by the management of the company. The management
information system in the wake of the digital revolution has become more pivotal for the
success of the organizations. One of the biggest contributions of the management information
system in decision making is that it provides updated data and analysis that helps in the
process of decision making (Guha and Kumar, 2018). An effective information system can
transform the data into a suitable format so that it matches the requirement of the company.
In addition to that, it also can structure the available data from the company information and
record into the report so that enough insight about the company is present to the decision-
maker.
The management information system records operational data of the company in a useful
format. The effectiveness of the management information system allows the company to
access data and information of the company which is not influenced by any external manual
output. Management information system records the finances, expenses, labor-related data
and the investment of the company. Therefore any decision that is taken based on the
information provided by the management information system it is just analysing the historical
data of the company. Yamamoto et al. (2018) stated that one of the biggest advantages of the
management information system in the context of decision making is that it only uses the
workforce data and hence there is no scope for the bias of the company. Therefore, effective
management information system can be a good tool for the decision making of the company.
For example, if a company wants to decide something that depends on the past level of

10
profits earned by the company then management information system is going to do that for
the management (Msallam et al. 2018). In the case of Google Inc and the decision making,
the management information system can provide the preferences of the employees provided
in some back dates. Therefore the management information system collects the data to be
used and processed in the future so that the decision makers of the company can base their
decision on the past data.
In addition to that running scenarios is an important tool to undertake decisions of a
company. An effective management information system needs to have this feature inbuilt.
The running scenario tool of the business decision making is a process where some
assumptions are made for the future activities of the company. In other words the running
scenario is a feature of the management information system that presents a probable scenario
in front of the decision maker (Mayer et al. 2019). The running scenario provides a clear
vision to the decision maker of the company that further allows them to place the operation of
the company as per the aims and the objective. Furthermore, the management information
system also allows the decision maker to conceive of alternative events that can happen in the
real time. Therefore it allows the management of the company to prepare for contingency
plans as well. Kobayashi (2018) stated that management information system analyses the data
for the company and combines the data with the running scenario tool in order to provide data
and information regarding the alternative course of action undertaken by the management of
the company. It is important for the management to regulate the number of workers working
in the company in order to maximise the profit. The management information system
provides the impacts of cutting the labour force before the management actually takes the
decision.
The change in the decision of the company reflects in the organisational performance and
hence the goals of the organisation. For example, if the holiday pay scheme is implemented
by the management of Google, it needs to alter the financial planning and the goals of the
company set for the long term. The contribution of the management information system in
this case is that it provides the necessary data and information to change the company goals
and the objective corresponding to the change in the labour force as well. Therefore
management information system provides a comprehensive support to the decision makers of
the company. Little (2018) stated that management information system also provides the
support for carrying out trend analysis on the data of the company as well. There are many
companies in the market that that base their decision on the trend of the company. The

11
management information system stores the trend in a meaningful pattern that the management
of the company can access in any point for the purpose of decision making. Furthermore, the
management information system becomes crucial for the projections as well. Usenko et al.
(2018) stated that it is important for the businesses to have projections for all the financial
measurements. The management information system uses the data from the operation of the
company and provides it to the decision maker that is further used for the investment decision
making process of the company. If the decision makers are aware about the future
performances of the company then the decisions made by the company would be more
effective. In the case of Google Inc, if the management of the company has the management
information system then it will have ideas about the future preferences of the employees in
terms of the holiday pay scheme. Therefore the management can also match the result of the
research with the information provided by the management information system.
Furthermore, an effective management information system also provides the decision makers
to have a good monitoring after the implementation of the policy. That means if the holiday
pay scheme is implemented by the management of the company, it can use the recorded data
of the management information system to track whether the policy implemented by the
company is in line with the objective of the company (Kurbanova et al. 2018). In that case
the managers develop a model using the past data provided by the system and then collect
real time data from the respondents and match them in order to understand whether the
policies of the company are going to meet the objective. In addition to that the management
information system also provides the data for corrective actions that needs to be taken by the
management in order to increase the effectiveness of the policy. Avison et al. (2018) stated
that corrective actions are very important as the effectiveness of policies are not understood if
it is not implemented already. Correction actions also allow the company to become more
responsive to the problems as well. The emulation of the business during the operation
becomes very tough for the management of any company. The management information
system has a feature that allows the mangers to emulate the operation of the company based
on which needs are manually developed by the decision makers.
Conclusion
Therefore, business analytics is an important tool for the decision making processes of
corporate organisations. Due to the low margin of error in the decision making process, an
accurate decision making makes a huge difference in the outcome. The decision making of a
company and the analysis of the business starts with the data collection and the sampling

12
process. The paper shows the sampling technique plays an important role in the robustness of
the outcome. The paper then goes on to discuss the differences between the primary and the
secondary data. It has also analysed the profit data of the company over the span of 2000-
2018. Lastly the paper discusses the importance of the management information system in the
decision making of the company. It finds out that an effective management information
system supports the decision maker with the quantitative historical data collection from the
past operation of the company.

13
Reference
Avison, D.E., Davison, R.M. and Malaurent, J., 2018. Information systems action research:
Debunking myths and overcoming barriers. Information & Management, 55(2), pp.177-187.
Bilau, A.A., Witt, E. and Lill, I., 2018. Research methodology for the development of a
framework for managing post-disaster housing reconstruction. Procedia engineering, 212,
pp.598-605.
Boddy, D., McCalman, J. and Buchanan, D.A., 2018. The new management challenge:
information systems for improved performance. Routledge.
Cardot, H., De Moliner, A. and Goga, C., 2019. Estimation of total electricity consumption
curves by sampling in a finite population when some trajectories are partially
unobserved. Canadian Journal of Statistics, 47(1), pp.65-89.
Chauvet, G., 2020. Introduction to Sampling Techniques. In Sampling Techniques for
Supervised or Unsupervised Tasks (pp. 1-21). Springer, Cham..
Etikan, I. and Babatope, O., 2019. A Basic Approach in Sampling Methodology and Sample
Size Calculation. Med Life Clin, 1(1), p.1006.
Guha, S. and Chandra, H., 2019. Improved chain-ratio type estimator for population total in
double sampling. Mathematical Population Studies, pp.1-16.
Guha, S. and Kumar, S., 2018. Emergence of big data research in operations management,
information systems, and healthcare: Past contributions and future roadmap. Production and
Operations Management, 27(9), pp.1724-1735.
Jekel, M., Glöckner, A., Fiedler, S., Allstadt Torras, R., Dorrough, A., Mischkowski, D.,
Franke, N., Goltermann, J. and Miketta, S., 2019. The Impact of Open Science Practices on
Research Methodology: A Case Study for Research in Judgment and Decision Making. Open
Science 2019, Trier, Germany.
Jennings, H., Slade, M., Bates, P., Munday, E. and Toney, R., 2018. Best practice framework
for Patient and Public Involvement (PPI) in collaborative data analysis of qualitative mental
health research: methodology development and refinement. BMC psychiatry, 18(1), p.213.

14
Ketchen, D.J., Bergh, D.D. and Boyd, B.K., 2019. The Research Design Canvas: A Tool for
Creating Better Studies', Standing on the Shoulders of Giants (Research Methodology in
Strategy and Management, Volume 11).
Kobayashi, Y., 2018. Disaster information management apparatus, disaster information
system, disaster information management method, disaster information management
program, portable terminal, control method of portable terminal, and control program of
controlling operation of portable terminal. U.S. Patent 10,154,390.
Kurbanova, E., Korableva, O. and Kalimullina, O., 2018, January. Enhancing the
effectiveness of asset management through development of license management system on
the basis of SCCM 2012 program by microsoft company. In 20th International Conference on
Enterprise Information Systems, ICEIS 2018 (pp. 171-178). SciTePress.
Little, M.C., 2018. Using status inquiry and status response messages to exchange
management information. U.S. Patent Application 10/027,563.
Livingstone, S., Stoilova, M. and Nandagiri, R., 2019. Talking to children about data and
privacy online: research methodology.
Maerz, N.H., 2018. Image sampling techniques and requirements for automated image
analysis. Measurement of Blast Fragmentation, p.115.
Mayer, N., Aubert, J., Grandry, E., Feltus, C., Goettelmann, E. and Wieringa, R., 2019. An
integrated conceptual model for information system security risk management supported by
enterprise architecture management. Software & Systems Modeling, 18(3), pp.2285-2312.
Mayer, N., Aubert, J., Grandry, E., Feltus, C., Goettelmann, E. and Wieringa, R., 2019. An
integrated conceptual model for information system security risk management supported by
enterprise architecture management. Software & Systems Modeling, 18(3), pp.2285-2312.
Msallam, A.A., Al-Hila, A.A., Al-Habil, W.A., Abu-Naser, S.S. and AL Shobaki, M., 2018.
The Reality of Computerized Management Information Systems in the Palestinian Cellular
Communications Company-Jawwal. The Reality of Computerized Management Information
Systems in the Palestinian Cellular Communications Company-Jawwal, 2.
O’Halloran, K.L., Tan, S., Pham, D.S., Bateman, J. and Vande Moere, A., 2018. A digital
mixed methods research design: Integrating multimodal analysis with data mining and

15
information visualization for big data analytics. Journal of Mixed Methods Research, 12(1),
pp.11-30.
Phakiti, A., De Costa, P., Plonsky, L. and Starfield, S., 2018. Applied Linguistics Research:
Current Issues, Methods, and Trends. In The Palgrave Handbook of Applied Linguistics
Research Methodology (pp. 5-29). Palgrave Macmillan, London.
Pollet, L., Prokof'ev, N.V. and Svistunov, B.V., 2018. Stochastic lists: Sampling
multivariable functions with population methods. Physical Review B, 98(8), p.085102.
Santhanam, A. and Keller, C., 2018. Using Design Science Research Methodology for
Making Data Centers Environmentally Sustainable. In 13th International Conference on
Design Science Research in Information Systems and Technology DESRIST 2018.
Sheard, L. and Marsh, C., 2019. How to analyse longitudinal data from multiple sources in
qualitative health research: the pen portrait analytic technique. BMC medical research
methodology, 19(1), pp.1-10.
Shimizu, R.M. and de Siqueira Bueno, S.L., 2019. 10 ChaPtER Sampling and Data analysis
for Population Studies on the Life history of Aegla spp. Aeglidae: Life History and
Conservation Status of Unique Freshwater Anomuran Decapods, 19, p.257.
Shukla, D. and Sisodia, B.V.S., 2018. Double sampling regression estimator of population
mean subsequent to preliminary test of significance in finite population survey
sampling. Journal of Statistical Theory and Practice, 12(2), pp.325-335.
Slade, M., Bates, P. and Toney, R., 2018. Best-practice framework for Patient and Public
Involvement (PPI) in collaborative data analysis of qualitative mental health research:
Methodology development and refinement.
Summers, J.O., 2019. Guidelines for conducting research and publishing in marketing: From
conceptualization through the review process. In How to Get Published in the Best Marketing
Journals. Edward Elgar Publishing.
Symonds, C., Kattirtzi, J.A. and Shalashilin, D.V., 2018. The effect of sampling techniques
used in the multiconfigurational Ehrenfest method. The Journal of chemical physics, 148(18),
p.184113.

16
Usenko, L.N., Bogataya, I.N., Bukhov, N.V., Kuvaldina, T.B. and Pavlyuk, A.V., 2018.
Formation of an integrated accounting and analytical management system for value analysis
purposes.
Vu, L.T., Vu, L.T., Nguyen, N.T., Do, P.T.T. and Dao, D.P., 2019. Feature selection methods
and sampling techniques to financial distress prediction for Vietnamese listed
companies. Investment Management & Financial Innovations, 16(1), p.276.
Yamamoto, A. and Yamamoto, T., Hitachi Ltd, 2018. Information system, management
program, and program exchange method of information system. U.S. Patent 10,152,260.
Zhao, D., Valdes-Vasquez, R., Simmons, D.R. and Parrish, K., 2018, January. Assessing the
Graduate Education in Research Methodology on Sustainability. In Construction Research
Congress 2018: Sustainable Design and Construction and Education, CRC 2018 (pp. 108-
117). American Society of Civil Engineers (ASCE).