# Qso 510 Final Paper - A-Cat Corporation

Autor: Rachel • March 13, 2018 • 2,766 Words (12 Pages) • 2 Views

**Page 1 of 12**

...

No statistical test or method can forecast or predict future performance perfectly; however, statistical tests provide valuable quantitative data from which a business can make relatively accurate future inferences. Quantitative data is information that can be measured or written down with numbers. Shmoop, Qualitative vs Quantitative Data, (Last Visited, Feb 5,2016) In A-Cat Corp’s case, the quantitative data includes mean number of transformers that are required to produce voltage regulators and sales of refrigerators. Based on the quantitative data, Mr. Ratnaparkhi and Vice President Mittra can determine trends in sales and transformers needs. By conducting inferential statistics tests, Mr. Ratnaparkhi can determine mean number of transformers required to produce voltage regulators and future transformer inventory.

The first inferential test that Mr. Ratnaparkhi should conduct is the T- hypothesis test. A t-test is commonly used to determine whether the mean of a population significantly differs from a specific value or from the mean of another population. Minitab Blog, What is a T-Test, (Last Visited, Feb 2, 2016). The reason why Mr. Ratnaparkhi should use the T-test is because the population standard deviation is unknown and the sample size is less than 30. The sample size for this test will be 12 and the degrees of freedom will equal 11.The t-test will determine whether the mean number of transformers required exceeds 1000 transformers as the operations manager predicts. First, to test this hypothesis, the null and alternative hypothesis have to be stated. The null hypothesis will be that the mean number of transformers required is less than 1000 transformers. The alternative hypothesis will be that the number of transformers required exceeds 1000 transformers. Next, significance level has to be selected. For this problem, A-Cat Corp should select the 0.05 significance level. After both null and alternative hypothesis are stated and significance level is selected, Mr. Ratnaparkhi can perform the T-Test. Once the t and p values are calculated, Mr. Ratnaparkhi can determine whether there is a statistically significant difference between hypothesized means. If the statistical differences proves to be significant, the test will confirm operation manager’s predictions.

The second inferential test that Mr. Ratnaparkhi should conduct is the one-way ANOVA analysis. The one-way ANOVA compares the means between the groups you are interested in and determines whether any of those means are significantly different from each other. Laerd Statistics, One Way ANOVA, (Last Visited, Feb 2, 2016) The ANOVA analysis will test the mean number of transformers required to produce voltage regulators from years 2006-2010. The previous analysis of the 2006-2008 data suggested that the mean number of transformers has changed. To determine if there is a change in the mean number of transformers in the years 2009 and 2010, ANOVA analysis should be conducted for those years. The reason why Mr. Ratnaparkhi should use ANOVA analysis is that this hypothesis test will determine if there is a significant difference in the means of transformers from year to year.

The final statistical method Mr. Ratnaparkhi should utilize is the correlation and regression analysis. Correlation and regression analysis will be extremely helpful in forecasting future transformer needs. Correlation is a measure of association between two variables. Mr. Ratnaparkhi should use correlation analysis to determine if there is a relationship between refrigerator sales and transformer requirements. If a strong correlation exists between sales and transformers requirements, A-Cat Corp can then use regression equation to predict future transformer requirements. Mr. Ratnaparkhi should pay close attention to the R-squared coefficient because this statistics measures how close the data is fitted to the regression line. The higher percentage value of the R-square coefficient the better the model fits the data. Minitab Blog, Regression Analysis, (Last Visited, Feb 3, 2016). Once regression equation is calculated, future inventory forecasting will be more accurate.

After Mr. Ratnaparkhi conducts all of the above-mentioned statistical test, he will possess accurate information about A-Cat Corp problems. From the T-test Mr. Ratnaparkhi can conclude that the mean number of transformers required to produce voltage regulators exceeds 1000 transformers and thus confirming operation manager’s prediction. The p-value of .0135 was less than the significance level of .05 and this resulted in the rejection of the null hypothesis. The ANOVA analysis results confirmed operation manager’s suspicions that mean number of transformers required to produce voltage regulators has increased over the five-year period. The large difference in the F and F critical values indicates that the null hypothesis of the mean number of transformers remaining the same through the years has to be rejected. This conclusion is strengthen by the low p-value of .000000174, which indicates that there is strong evidence that the null hypothesis is invalid. From both inferential tests, Mr. Ratnaparkhi can conclude that mean number of transformers required to produce voltage regulators changes from year to year. Due to that discovery, Mr. Ratnaparkhi should recommend that A-Cat Corp adjust its mean number of transformers required to produce voltage regulators on a yearly basis.

Developing a model for forecasting transformer requirements based on sales of refrigerators can be accomplished by using correlation and regression analysis. From the correlation analysis, Mr. Ratnaparkhi can determine that there is a strong relationship between refrigerator sales and transformers requirements. The correlation coefficient of .926 indicates very strong relationship between two variables. Once strength of the relationship has been determined, Mr. Ratnaparkhi can use the regression equation to predict future transformer requirements. The regression equation is y = .3149x + 1233.5. Y is the transformer requirements and x is the refrigerator sales. The R2 score is .8574 which means that 85% of the total variation in y can be explained by the linear relationship between x and y. Statistics 2, Correlation Coefficient, (Last Visited, Feb 3, 2016). The 15 percent of variation that the regression line cannot explain can be worrisome for A-Cat Corp; however, R2 score is still very strong and A-Cat Corp should use the regression model for future forecasts.

Statistical Report Analysis and Recommendations

The statistical analysis performed by Mr. Ratnaparkhi uncovered two issues that hindered A-Cat Corp business performance. First, the analysis provided sufficient evidence that using estimation to determine mean number of

...