Slides (see attached files)

Running head: BUSINESS DECISION 0

Business Decision Making Part II

Ailaine Grant

QNT275

July 03, 2017

University of Phoenix

Identify which types of descriptive statistics might be best for summarizing the data, if you were to collect a sample.

Data is the base of statistics and all related aspects to it. When data is collected a conclusion can be formed on the data with regards to how we use it. For instance, Descriptive statistics include the calculation of mean, median and mode, where the data is required and formulated accordingly. When the data is large, it is difficult to work with yet the calculations need to be done is only basic upon the equations formulated. The data of a given data set is termed as population. It cannot be used to reach any conclusions given in the dataset. They describe the distribution of variables based on the dataset that is given to ascertain the respective values. This will also include the range, quartiles, of the respective dataset. Variance and standard deviation are also calculated. It is in single term defined as measures of central tendency (Univariate analysis), measures of dispersion, and measures of spread.

The main type of descriptive statistics we ascertain at the first stage is measures of central tendency. There are separate ways describing groups of central tendency. Several ways are used to conclude on this central tendency. This is ascertained with the mean, median, and mode. The statistical performance, using the men, median and mode – several types of data can be analyzed. Mean of number, is normally calculated as the average of the population though the median and mode are also important.

Other types of descriptive statistics are measures of dispersion. It is used to measure and analyze how the data is dispersed. Suppose an example, several students in a class scored 70 percentiles than other classes. The difference of the measures of dispersion between highest and lowest spread is called the range. It is mainly easy to measure as well as calculate the largest number in a dataset. The data is thusly analyzed and measured with regards to the average, and from the maximum and minimum value - the range as well.

Analyze which types of inferential statistics might be best for analyzing the data, if you were to collect a sample.

With quantitative data, Unilever should analyze them and infer the results accordingly. Inferential statistics as its names states is the inferences on description of the data. Inferential statistics include comprises of measuring and inferring from the mean, median, mode, variance, standard deviation, quartiles, and percentiles etc. When we need to infer the statistics about the data we use for a study. Comparisons across time, groups, and expecting the data collected. Inferential statistics are used to move beyond the direct depiction. It will help in inferring conclusions about the data being used. Unlike the descriptive statistics, inferential statistics do not make mere descriptions but key inferences of larger population as based on the sample data. It will provide inference on the sample population accordingly rather than mere description of the characteristics as in descriptive statistics i.e. distribution, central tendency, dispersion).

T-tеѕtѕ: t test is a statistical test used to compare the means of different distributions. It has three divisions, i.e. types: оnе-ѕаmplе t-tеѕt, іndеpеndеnt-ѕаmplеѕ t-tеѕt, аnd pаіrеd-ѕаmplеѕ t-tеѕt. All the t tests, the difference is significantly considering the difference between means and then divide the ascertained difference through variation measures.

ANOVA – Analysis of Variance (ANOVA) is the statistical test that compares different means at a specific time. The difference between the t test and ANOVA is that t test will compare two means at a specific time and the ANOVA will compare several means of different observations at the same time. ANOVA also measures the numerous factors of the same measure. Yet sometimes, ANOVA can become complicated with the analysis as finished by a statistical expert. Analyze the role probability or trend analysis might play in helping address the business problem.

The analysis of the trend is very important in addressing the problem as faced by Unilever. Trend analysis explores through the comparison of the available business data. This will support in measuring the outcomes or trends of Unilever. It can then be further supported to respond to these trends building a method for the business goals and keeping them in line with the norms and standards formed. It supports the business with the expected practices and the current operations of Unilever. It will support in moving the business in the right way based on the future trends.

Analyze the role linear regression for trend analysis might play in helping address the business problem.

After the data collection, I will apply it with regression and analyze the relationship between variables. I can find support this by making sure the supplies that will be ordered every month. This will also pertain to framing the time duration and the supply order as required optimizing the production as well. Linear regression approach supports formulating relationship between scalable dependent and one or more explanatory variables to define the relationship between them.

Analyze the role a time series might play in helping address the business problem.

Time series shall be used by Unilever to measure the various methods through which the top management can be supported in business decision making in a much better and enhanced manner. This will also support towards solving problems related to the business. The management should analyze certain points such as creation of products as compared to the previous years and working along with the right path to grow further supporting the development of better products eliminating the total number of complaints from consumers as a whole.

When the operations are considered Unilever will accumulate all the data regarding the sales performance, profit, and the market information along with that of the customers. Also, they find the employees with strong statistical skills since the data insights measured gives the business with better choices related to the operations. The Linear regression has many uses in business. They can use to evaluate the trends as well as make forecasts about the same.

Linear regression can also be used for measuring and analyzing the need of pricing behavior and their impact in the measured variables. Suppose that Unilever makes a change into the cost during specific periods then each level of quantity offered by it can be recorded further linear regression can be performed with the data where the dependent variables it sales quantity and explanatory variable being the cost. The results can be thusly interpreted that the show the quantity purchase is likely to affect the use of their product with the increase in the cost helping in future pricing decisions. This will help Unilever in establishing the relationship between variables and formulate outputs and new decisions accordingly.

References

Caillier, J. G. (2016). Does satisfaction with family-friendly programs reduce turnover? A panel study conducted in US Federal Agencies. Public Personnel Management, 45(3), 284-307.

Hale, D., Ployhart, R. E., & Shepherd, W. (2016). A two-phase longitudinal model of a turnover event: Disruption, recovery rates, and moderators of collective performance. Academy of Management Journal, 59(3), 906-929.

Unilever. (2017). Unilever, Marketline, 1-40.

Wolberg, J. (2010). Designing quantitative experiments: prediction analysis. New York: Springer Science & Business Media.