The family of statistical tools that I will use to perform my analysis are ANOVA (analysis of variance) and a regression analysis for the future prediction. ANOVA is an analysis tool used in statistics that splits the aggregate variability found inside a data set into two parts: systematic factors and random factors (Analysis of Variance – ANOVA, 2017). I chose these tools since the transformers required are in dependent on the sale of fridges. I’ll use the regression analysis to determine how much the sale of the fridges affect the number of transformers required. The category of the data provided belongs to time series since the sales figures are increasing over the years, which shows a time trend. Since the next year data correlates to the previous year data, time series analysis is the category of choice. I chose time series data because the data provided if a sequence of numerical data points in successive order (Time Series, 2006). Using ANOVA to test the independence or dependence of the transformer requirements on the sales of fridges and a regression analysis to establish the relationship between sales fridges and transformer required.I chose to use ANOVA and the regression analysis because A-CAT is both under and overstocking their transformers which is either delaying delivery or hindering needed money. The two methods could prove whether or not the sales of fridges influence the number of transformer required and if the transformer required is dependent or independent on the sales of the fridges themselves. This is not an experiment since the data provided is from previous years and includes the actual number of transformers used over that past period of time. Since there are no guesses needed to be made because we have the actual data we can be sure the data is reliable and analysis will be accurate. The process we’re going to implement are the collection of data make sure to rid the data of outliers. Next, is to analyze the date, third is gather the analysis output and finally to describe the output. Following the outline process is important because should we go astray of our original methods this can cause inaccurate results regardless of it not being an experiment and having actual data. First perform the test of independence then the regression analysis. H_o: sales of fridges and transformers are independentH_a: sales of fridges and transformers are not independentp-value =. 0.00.3202 (06-08)p-value 1.73969 x10-6Since P-values are less than an alpha 0.05 and 0.01, rejecting the null hypothesis and accept alternative hypothesis, meaning the sales of fridges and transformers are not independent. Now that independences is shown, next is to perform the regression analysis to show predictions in the future. To show how predicting the number of required transformers over time, make the regression equation show how the “y” variable, which is transformers required changes the sales of fridges “x” increases by one. The sale of fridges affects the transformers. Regress the sales of fridges against the transformer requirements.As sales of fridges increases by 1 the number of transformers increases by 0.31. R2 = 85.74% meaning variation in the number of transformers required correlates with the variation in sales of fridges, resulting in the conclusion that the number of transformers is heavily impacted by the number of fridges sold. The mean number of transformers required has increased from 06′-10′. We can use the regression output to predict the needed transformers requirements and the mount of parts needed. Now that A-CAT knows how to predict the needed transformers, it will eliminate the under/overstocking problem that happened. In turn, with this solution they will rid their habit of overages and shortages and revenue will be maximized. Summing up the analysis plan, we began with breaking down the data provided data, then checking to see if the variables had a relationship, it was imperative to find out whether or not transformers were dependent on sales of fridges. If in fact the relationship did exist then using the regression analysis was the next step. A-CAT had a classic under/overstocking problem at hand. We needed to look at past data to predict future needs. Seeing that mean increased between o6’and 10′, using the regression analysis helped show the relationship between variables to provide better forecasting. Using the regression method was best, because its uses one independent variable to explain/predict the outcome of the dependent variable, while multiple regression uses two or more independent variables to predict the outcome (Regression, 2015). With these changes implement, stakeholders can look forward to seeing their investment flourish since deliveries are now more efficient and timely and the factory store has a decreased waiting time for inventory replenishment.