Investigate the Impact of Various Factors on Companies Sales - Essay Example

Finance and Accounting of Institute] Finance and Accounting Introduction There have many quantitative studies to investigate the impact of various factors on companies’ sales. These studies are not limited to a single set of factors but in fact there are based on a wide range of variables that are affecting businesses at a particular time. It would be an interesting study to investigate certain factors and how they affect sales of Dutch fashion stores. For this purpose, data of 400 Dutch fashions collected in the year 1990 is used. A statistical report consists of a complete data of the different variables that have been determined. Various statistical tools like correlation and regression of the data are conducted and complete analysis of the data is provided in the report. Correlation Analysis The chart below shows the results of correlation coefficient between sales per square meter and each of the other variables.   sales sales 1 nfull 0.237185 npart 0.050085 hoursw 0.262997 ssize -0.29379 Correlation between Sales per square meter (sales) and Number of full timers (nfull) The coefficient correlation between the two variables sales per square meter and number of full timers depicts the result that there is a weak positive relationship as the value is 0.2371. As observed there is not much increase in the sales with an increase in number of full timers. The dependent variable of sales per square meter will increase by 23.71 % if the number of full timers increases by 1 employee. It is a very minimal change as the increase in the number of full timers will not be very beneficial because it will not generate higher sales (Miller & Rodgers, 2008). Scatter Plot From the scatter plot it is observed that there is a weak positive correlation because the point on the scatter plot is dispersed from the trend line. The trend line shows a positive association between sales per square meter and number of full timers. Correlation between Sales per square meter (sales) and Number of part timers (npart) The result of correlation coefficient between the two variables per square meter and number of part timers is 0.0500, which means that there is a weak positive relationship between them. As observed there is not much increase in the sales with an increase in number of part timers. The dependent variable of sales per square meter will increase by 5% if the number of part timers increases by 1 employee. It is a very minimal change as the sales generated from the increase in the number of part timers will not high and beneficial (Miller & Rodgers, 2008). Scatter Plot From the scatter plot it is observed that there is a weak positive correlation because the point on the scatter plot is dispersed from the trend line. The trend line shows a positive association between the two variables as the line is moving in an upward direction. Correlation between Sales per square meter (sales) and Total number of hours worked (hoursw) The correlation coefficient between the two variables sales per square meter and total number of hours worked depicts the result that there is a weak positive relationship as the value is 0.2629. As observed there is not much increase in the sales with an increase in number of full timers. The dependent variable of sales per square meter will increase by 26.29 % with an increase in total number of hours worked. It is a very minimal change as the increase in the total number of hours worked will not be very beneficial because it will not generate higher sales (Miller & Rodgers, 2008). Scatter Plot From the scatter plot it is observed that there is a weak positive correlation because the points on the scatter plot are dispersed from the trend line. The trend line shows a positive association between the two variables as the line is upward sloping. Correlation between Sales per square meter (sales) and Sales floor space of the store (ssize) The correlation coefficient between the dependent variable sales per square meter and the independent variable sales floor space of the floor illustrates that there is a weak negative relationship as the value is - 0.2937. A decrease in the sales is observed with an increase in sales floor space of the store. The dependent variable sales per square meter will decrease by 29.37% with an increase in sales floor space of the store. It is illustrated that increase in the floor space of the store will not be a favourable decision (Miller & Rodgers, 2008). Scatter Plot From the scatter plot, it is observed that there is a weak negative correlation because the points on the scatter plot are dispersed from the trend line. The trend line shows a negative association between the two variables as the trend line is downward sloping (Miller & Rodgers, 2008). Regression Analysis Regression analysis is performed to determine the impact of different variables on the sales of Dutch stores. The relationship between sales per square meter and total number of hours worked and sales floor space of the store is identified. It is observed that the two independent variables ‘total number of hours worked’ and ‘sales floor space of the store’ are considered and ‘sales per square meter’ is the only dependent variable highlighted. A regression equation between the three variables is developed and is useful to make predictions regarding to the sales. It is usually observed that the increase in the values of independent variable will increase the value of the dependent variable. If the value of both or one of the variables is negative then the impact on the outcome of sales can be negative as well. The linear regression model consists of two predictors, first predictor is number of hours worked and the second predictor is sales floor space of the store. The regression equation is mentioned below. Sale per square meter = 5133.590282 + 37.52841616 * hoursw - 22.14457144 * ssize From the equation, it is determined that slight change in the two independent variables total number of hours worked and sales floor space of the store can cause a change in the dependent variable sales per square meter. If the value of total number of hours worked is more than the value of sales floor space of the store then sales per square meter will increase but it is not necessary that if the sales floor space of the store has a greater value than total number of hours worked, the sales will decrease. There is a possibility that the sales may increase but not with a faster pace as it did in the latter condition. If the value of total number of hours worked is in negative then there is a possibility that the there is a negative impact on the sales of the industry. The values of the two variables are very important to predict the sales per square meter as from the coefficients it is observed that β1 is 37.52841616 and β2 is - 22.14457144 and because of the positive and negative value it cannot be assured the changes in the independent variable will always increase the dependent variable (Miller & Rodgers, 2008). Interpretation of Coefficients     Coefficients Standard Error t Stat P-value hoursw B1 37.52841616 2.83722 13.22718 0.00 ssize B2 -22.14457144 1.625067 -13.6269 0.00 Coefficient table consists of the values of the independent variables. On calculating the coefficients, it is observed that for total number of hours worked, β1 is 37.52841616 and for sales floor space of the store, β2 is - 22.14457144. The standard error, t-stats and p value are also identified in the coefficient table. Total number of hours worked The coefficient value calculated of total number of hours worked is β1 37.52841616. With the help of this value the change in the value of the dependent variable can be calculated. From the value of β1, it is determined that value of dependent variable will increase by 37.52841616. By the addition of 1 unit of total number of hours worked the sales per square meter will increase by 37.52841616. The p- value is used for the determination of the statistical significance of the variable. If the p-value of the variable is less than 0.05 then the relationship between the variable is statistically significant. From the above results, it is observed that the value of the variable (total numbers of hours worked) is less than 0.05, which means that the statistical relationship between both variables is significant (Miller & Rodgers, 2008). Economically, it is justified that the increase in the independent variable will increase the value of the dependent variable as by increasing the total number of hours worked, the production will increase. The increased production will reduce the cost of the product and will increase the sales. As more units of hours worked are utilized the more sales will increase (Miller & Rodgers, 2008). Sales floor space of the store The coefficient value calculated of sales floor space of the store is β2 - 22.14457144. Based on this this value, the change in the value of the dependent variable can be calculated. From the value of β2 it is determined that value of dependent variable (sales per square meter) will decrease by 22.145 by the addition of 1 unit of sales floor space. The p-value is used to determine the statistical significance of the variables. If the value of p-value is below 0.05 (i.e. the confident interval level) then the variable is statistically significant. From the above chart, it is analysed that the p-value of the variable is 0.00 that implies that the relationship between the variable of sales floor space of the store is statistically significant. From the economics point of view, the negative value of β2 will have a negative impact on the sales as the variable (sales floor space of the store) will decrease the value of the sales per square meter because an increase in sales floor space of the store will only lower the cost of the sales and it cannot be considered as an investment. From the data of 400 Dutch fashion stores, it is observed that the sales per square meter did not have any direct relation with sales floor space of the store (Miller & Rodgers, 2008). Inclusion of other Variables in the Model If the other two independent variables, numbers of full timers and number of part timers are included in the regression model then the regression model is expected to improve the predictability of the dependent variable. Before inclusion of these two variables, the value of R-squared was .3658 that implied that the regression model without these two additional variables was able to only predict 36.58% of the total variations observed in the value of the dependent variable. After including two additional independent variables that are full timers and number of part timers in the analysis, the value of R-squared improved to .40218. It implies that the regression model is able to explain 40.218 of the total variations observed in the value of the dependent variable using the data of 400 Dutch companies. Both independent variables, number of full timers and number of part timers have a positive relationship with the dependent variable that implies that a positive change in their values will have a positive impact on the value of the dependent variable i.e. sales will increase. Moreover, these two independent variables, numbers of full timers and number of part timers have a significant relationship (p-value Read More