100 k

Total Downloads

1.82 m

Views

Downlaod PDF

Statistic for Management

Part A

Statistics

Statistics can be explained as science which deals with the collection, analysis, interpretation as well as representation of data (Ayyub and McCuen, 2016).

Key characteristics of Statistics

Effected by many causes:

Statistics is associated with data as well as it is stated that it should be based on certain logical facts.

Numerically expressed:

According to Zhang (2016), it can be stated that investigating the effects of one factor by neglecting the effects of other factors is not easy. Here, the effects of all factors must be examined individually and in combination as their effects may change with the change of location, time or situation.

Numerically expressed:

Data, called statistics, must be expressed in the number form to measure data. This means that data must appear in quantitative form.

Enumerated or estimated accurately:

Statements must be accurate and concise. The enquiry should not be very large for reasonable accuracy. Even if the data is infinite or very large, it is not even possible to count the data and may not reach a reasonable level of accuracy (Zhang, 2016).

Collected in a systematic manner:

Another characteristic of statistics is that data should be collected systematically. Randomly collected data leads to difficulties and inaccurate conclusions in the analysis process. In order to collect statistical data, researchers must develop an appropriate plan to collect as well as analyse the data (Rees, 2018). If this is not the case, the reliability of the data will decrease. Therefore, the data must be collected correctly to get the correct results.

Collected for a predetermined purpose:

Before collecting data, it is essential for the researcher to understand that why they are collecting data and what they are gathering (Rees, 2018). Collecting data without any specified information regarding the goal the researcher cannot gather sufficient and reliable details.

Capable of being placed in relation to each other:

Normally, data is collected for comparison. If the numbers collected cannot be compared, they will lose much of their meaning.

Overview of methods

There are different methods that can be used to collect the most suitable and reliable information regarding a certain research objective. Different types of methods are as follows;

Primary methods

The primary method of data collection can be explained as the researchers collect data by themselves, such as by observations and conducting surveys. Additionally, researchers can gather both qualitative and quantitative data by the help of primary research technique (Sen and Singer, 2017).

Secondary methods

The secondary research method of data collection can be explained as retrieving data from online research engine or already published data on the official website (Sen and Singer, 2017).

Sources and types of data and information businesses can access:

Quantitative method

It enables researchers to get the most reliable and relevant information quickly. The significance of using questionnaire survey can be given as it enables the researchers to complete the research anonymously; it is inexpensive, enables the researchers to analyse as well as compare information easily (Bell et al., 2018). However, there are certain challenges that are associated with the questionnaire survey such as researchers may not get reliable responses, can get biased information and it does not enable the researcher to get a complete story regarding a certain research phenomenon.

Qualitative methods

Interviews are frequently used in the research where the researchers aim to view the perspective of others regarding a certain research phenomenon. It enables the researchers to understand the experiences of others. The interview method is preferred because it enables the researchers to get in-depth and details information. However, data collection with this technique requires a lot of time as well as it is quite difficult to compare and analyse the information obtained by the interviews (Bell et al., 2018). In addition, qualitative research methods also include the collection of data from already published articles and journals available it enables the researchers to access comprehensive as well as historical information regarding research phenomenon.

Difference between a sample and a population

The population can be explained as a set of data which involves all elements while the sample comprises one or more observations of the population. Moreover, based on the sampling methods, it can be stated that the sample comprises on few numbers of observations as compared to the population. Parameters of the population are mean and standard deviation, while the measurable characteristic of the sample is known as a statistic (Maronna et al., 2019).

Value of employing statistical methods when meeting business objectives and achieving competitive advantage

Lei et al., (2017, p.59) stated that statistical methods play an important role in business management to achieve competitive advantage. One of the functions of statistics in business organisations is to inform the manager about the performance as well as the productivity of employees and managers within the organisation.  The manager collects data on employee productivity, such as the number of jobs done or the number of units produced. Business organisations must analyse the data to find ways that can be used by the employee to maximise productivity. Many companies also collect data and analyse it with statistical techniques on the commitment of employees at work, which can be monitored to reduce the rate of employee turnover.

Difference between descriptive and inferential statistics

Statistical techniques of descriptive statistics, as well as inferential statistics, are frequently used in the business researches to analyse the gathered data.  The statistical technique of descriptive statistics is used to summarise a large set of data and to get meaningful information. Descriptive statistics enables business organisations to understand a specific set of data. Descriptive statistics describe a sample as well as there is no uncertainty because it only describes data (Lei et al., 2017, p.59). However, inferential statistical enables the researchers to analyse data and make effective decisions. The goal of using inferential statistics is to draw a conclusion based on the collected facts and figures.

Implications of Statistics for business intelligence

Statistical techniques in business intelligence enable to analyse past performance, predict future business prospects, and manage the business effectively. Statistics can describe markets which can help business organisations to announce advertising, set prices and respond to changes in consumer demand. A descriptive analysis examines what happened and helps explain why (Laursen and Thorlund, 2016). Using historical data, managers can analyse past performance and mistakes. Also known as "cause and effect analysis". Common applications for descriptive analysis include sales, marketing, finance and operations. The forecasting techniques use a variety of statistical methods (such as calculation models and mining) to predict the likelihood and future development based on past or historical data. The best possible assessment of what is happening is going over the records of what happened (Laursen and Thorlund, 2016).  

Examples of analysis of given sample sets

Different statistical techniques can be used by the business organisations to analyse the gathered data such as for the descriptive statistics and summary of data researchers can calculate mean, median, mode, standard deviation, variance and range of data which can help the researchers to determine the rate of fluctuations in their productivity based on the gathered data. In addition, the technique of graphical representation can also be used by the researchers to visualise the fluctuation as well as the trend of the data. Based on the analysis researcher can demonstrate that either a certain strategy which is being used in the organisation is efficient or productive, or they need to change their strategies (Mertler and Reinhart, 2016. As an illustration, an organisation can gather the data of employee performance and productivity before implementing a certain strategy and analyse the trend of the overall productivity which can help the management to decide either to change a certain strategy to enhance the productivity or the implemented strategy is already helping the organisation to achieve the specified goals.

Cta 1 How “Dissertation Proposal” Can Help You!

Our top dissertation writing experts are waiting 24/7 to assist you with your university project, from critical literature reviews to a complete masters dissertation.

Find Out More

Part B

Statistical application for business data

The data for monthly adjusted shared price for Apple, Microsoft, Amazon and Netflix for the last five years and for analysis of the data Apple and Microsoft have been selected. The provided data has been analysed with the help of inferential and descriptive statistics.

Descriptive statistics:

As discussed above, descriptive statistics are used to summarise data and get meaningful values from a large set of data. From table 1, it can be observed that average adjusted price for the Apple is 133.72632 with a standard deviation of 38.58 and Microsoft is 66393 with a standard deviation of 25.99 and average NASDAQ-IXIC is 5844.1046 with the standard deviation of 1178.917. standard deviation enables the researchers to determine how much data is far from the central values, and high standard deviation indicates high fluctuation in the data.

Table 1: Descriptive Statistics

Apple

 

Microsoft

 

NASDAQ-IXIC

 

Mean

133.7262

Mean

66.39398102

Mean

5844.588

Standard Error

4.97412

Standard Error

3.355728871

Standard Error

152.1046

Median

117.294

Median

57.145624

Median

5317.84

Mode

#N/A

Mode

#N/A

Mode

#N/A

Standard Deviation

38.52937

Standard Deviation

25.99336407

Standard Deviation

1178.197

Sample Variance

1484.512

Sample Variance

675.6549755

Sample Variance

1388149

Kurtosis

-0.53538

Kurtosis

-0.892740606

Kurtosis

-1.24886

Skewness

0.681033

Skewness

0.685135537

Skewness

0.478652

Range

145.1161

Range

87.339714

Range

3866.92

Minimum

79.96438

Minimum

36.420288

Minimum

4242.62

Maximum

225.0804

Maximum

123.760002

Maximum

8109.54

Sum

8023.575

Sum

3983.638861

Sum

350675.3

Count

60

Count

60

Count

60

With the help of descriptive statistics, the data can be just summaries; however, the trend and fluctuations in the shared price for Apple, Microsoft can be visualised with the help of a line graph. There are different types of graphical representations such as histogram, line graph and scatter plot histogram enables the researchers to visualise the frequency distribution, line graph enables the researchers to determine the fluctuations within the data set over a period of time while scatter plot enables the researchers to determine the existence  of different data points around the mean (Mertler and Reinhart, 2016). The data which has been used in the study is time-series data such as shared price in last five years for every month therefore, in order to visualise the fluctuations in the data set line graph has been used. 

Figure 1, determines the trend for the shared price of Apple for last five years and it can be visualised that the shared price of Apple indicates a continuous fluctuating trend which indicates uncertainty in the data set. Additionally, it can be visualised that the fluctuations with the shared price of Apple are in increasing pattern as well as a significant increase, then decline can be observed during 2108. 


Figure 1: share price trend of Apple

From figure 2, the shared price of Microsoft can be observed and it is clear that from the last five years, the shared price for Microsoft is continuously increasing. Moreover, it can be observed that eh standard deviation for the shared rice of Microsoft is also small indicating a low rate of fluctuation in the data.


Figure 2: the share price of Microsoft

Correlation:

Correlation can be explained as an inferential statistic that is frequently used to demonstrate the strength of association between two or more variables. Additionally, according to the range of correlation is-1 to +1 as well as the value less than 0.5 enables the researchers to state that there is weak association between variables while if ha value is greater than 0.5 than the researchers can state that there is a strong association between the variables (Stephens, 2017, p. 195). In this report eh association of the shared price with the NASDAQ-IXIC has been analysed and the results are mentioned in table 2. Table2 indicates that shared price of Apple, as well as Microsoft, has a positive as well as a strong association between shared price and NASDAQ-IXIC.

Table : Correlation

 

Apple

Microsoft

NASDAQ-IXIC

Apple

1

Microsoft

0.929817

1

NASDAQ-IXIC

0.967538

0.972825

1


In addition, regression analyses can also be used for the inferential statistics such as to demonstrate that either NASDAQ-IXIC has a significant impact on the shared price of Apple and Microsoft or not regression analysis can be used. Table 3, indicates that there is a strong relationship between the shared price of organisation and NASDAQ-IXIC as value for eh coefficient of correlation is obtained as 0.98 as well as value for the coefficient of determination is obtained as 0.97 indicating that model is fine fitted. 

Table 3: Regression

Regression Statistics

Multiple R

0.987766

R Square

0.975682

Adjusted R Square

0.974829

Standard Error

186.9265

Observations

60


ANOVA enables the researchers to make inference such as either to accept a certain hypothesis or not. According to Stephens, (2017, p. 195) null hypothesis of the study can be accepted if p-value would be greater than 005 as well as if the value of f-statistics calculated would be less than the value of F-statistics tabulated. From table 4, it is evident that the P-value is less than 0.05 which leads the researchers to state that there is a significant impact of NASDAQ-IXIC on shared price. 

Table 4: ANOVA

ANOVA

 

df

SS

MS

F

Significance F

Regression

2

79909128

39954564

1143.469

9.98E-47

Residual

57

1991667

34941.53

Total

59

81900796

 

 

 


Forecasting

Forecasting is used by the researchers to make an inference that either with the help of current strategies, they would be able to increase their productivity or not. Exponential smoothing is a statistical technique that is used by the researchers for forecasting. It enables the researchers to determine the expected future trend based on the previously available data (Kong et al., 2017, p.897).  In this study, exponential smoothing has been used to forecast the shared price of Apple and it can be observed from the figure that if the organisation will work on the similar strategies and will not look for innovation than there is a possibility that the share price of organisation would be decreased. 


Figure 3: exponential smoothing for Apple

Figure 4, indicates forecasting for the shared price of the Microsoft and based on the results it can be stated that the if the organization will continue working with similar strategies then there is a possibility that the shared price of Microsoft will decrease.


Figure 4: exponential smoothing

Cta 2 How “Dissertation Proposal” Can Help You!

Our top dissertation writing experts are waiting 24/7 to assist you with your university project, from critical literature reviews to a complete masters dissertation.

Find Out More

Conclusion:

This assignment was aimed to explore the effectiveness of the statistical technique for business management. Based on the discussion it can be concluded that with the help of descriptive statistics organisations can  get meaningful values from a large set of data, while with the help of graphical representation researchers can visualise the trend of data however with the help of inference statistics researchers can make inference regarding certain area of interest such as productivity of  organisation based on current strategies.

 

References

Ayyub, B.M. and McCuen, R.H., 2016. Probability, statistics, and reliability for engineers and scientists. CRC press.

Bell, E., Bryman, A. and Harley, B., 2018. Business research methods. Oxford university press.

Kong, Y., Li, D., Fan, Y. and Lv, J., 2017. Interaction pursuit in high-dimensional multi-response regression via distance correlation. The Annals of Statistics, 45(2), pp.897-922.

Laursen, G.H. and Thorlund, J., 2016. Business analytics for managers: taking business intelligence beyond reporting. John Wiley & Sons.

Lei, H., Ganjeizadeh, F., Jayachandran, P.K. and Ozcan, P., 2017. A statistical analysis of the effects of Scrum and Kanban on software development projects. Robotics and Computer-Integrated Manufacturing, 43, pp.59-67.

Maronna, R.A., Martin, R.D., Yohai, V.J. and Salibián-Barrera, M., 2019. Robust statistics: theory and methods (with R). John Wiley & Sons.

Mertler, C.A. and Reinhart, R.V., 2016. Advanced and multivariate statistical methods: Practical application and interpretation. Routledge.

Rees, D.G., 2018. Essential statistics. Chapman and Hall/CRC.

Sen, P.K. and Singer, J.M., 2017. Large Sample Methods in Statistics (1994): An Introduction with Applications. CRC press.

Stephens, M.A., 2017. Tests based on regression and correlation. In Goodness-of-Fit-Techniques (pp. 195-234). Routledge.

Zhang, Z., 2016. Univariate description and bivariate statistical inference: the first step delving into data. Annals of translational medicine, 4(5).

Ace Your Grades
Without Overspending

Why pay more for the same quality? Choose our cheap assignment writing services today and witness the difference yourself. Click now to get started!

  • 24/7 Customer Support
  • Team of Academic Experts
  • Guaranteed Results