Project A: Super mart Sales predictionResults from the multiple regression analysis:In the first step the data was loaded into the statistical software and the sample from the dataframe is shown in the table below:## 'data.frame': 150 obs. of 14 variables:## $ Store.No. : int 1 2 3 4 5 6 7 8 9 10 ...## $ Sales..m : num 12.5 14.5 19 18.2 7.6 18.5 13.1 14.9 17.1 9.2 ...## $ Wages..m : num 2.3 2.7 3.1 2.6 2 2.7 2.4 2.5 2.7 2.1 ...## $ No..Staff : int 60 69 79 66 51 62 61 59 65 55 ...## $ Age..Yrs. : int 10 8 7 7 15 6 7 6 8 16 ...## $ GrossProfit..m: num 0.712 0.091 1.72 1.372 0.935 ...## $ Adv...000 : int 171 213 255 287 112 238 124 214 215 154 ...## $ Competitors : int 3 4 1 1 3 0 2 2 2 5 ...## $ HrsTrading : int 110 134 98 85 72 77 100 95 112 75 ...## $ SundayD : int 0 0 1 1 0 1 1 0 1 0 ...## $ Mng.GenderD : int 1 1 1 1 1 1 1 1 1 0 ...## $ Mng.Age : int 33 33 40 29 36 32 52 41 31 42 ...## $ Mng.Exp : int 12 16 13 10 4 15 15 4 12 13 ...## $ Car.Spaces : int 46 73 64 66 29 40 69 45 42 34 ...After loading the data, the nest step is to check for the missing values in the data. It was foundthat there are no missing values in the data set. Also there are 150 observations in the data setwith 13 different variables.Questions:a)Which independent variables have the strongest linear relationship with sales?Results from the multiple regression analysis shows that advertisement & promotionalexpenses have the strongest linear relationship with sales. b)Is your multiple regression models overall significant?
c)Call:d)## lm(formula = sales_data$Sales..m ~ Adv...000 + Wages..m + Mng.Exp + e)## Mng.Age + Competitors + HrsTrading + SundayD, data = sales_data)f)## g)## Residuals:h)## Min 1Q Median 3Q Max i)## -4.9523 -0.8091 -0.1140 0.9140 3.4853 j)## k)## Coefficients:l)## Estimate Std. Error t value Pr(>|t|) m)## (Intercept) 3.339111 0.982191 3.400 0.000876 ***n)## Adv...000 0.021164 0.002863 7.392 1.14e-11 ***o)## Wages..m 2.055372 0.336267 6.112 8.97e-09 ***p)## Mng.Exp 0.184404 0.031292 5.893 2.63e-08 ***q)## Mng.Age -0.064327 0.015781 -4.076 7.58e-05 ***r)## Competitors -0.402110 0.099351 -4.047 8.48e-05 ***s)## HrsTrading 0.017513 0.007007 2.499 0.013581 * t)## SundayD 0.589674 0.263707 2.236 0.026905 * u)## ---v)## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1w)## x)## Residual standard error: 1.356 on 142 degrees of freedomy)## Multiple R-squared: 0.8625, Adjusted R-squared: 0.8558 z)## F-statistic: 127.3 on 7 and 142 DF, p-value: < 2.2e-16As the results shown in the above table F statistics is significant at 5 % significance level as the pvalue for F statistics is less than 0.05 so the overall model is significant.c) If so, which variables do not help you in modeling the dependent measure?
End of preview
Want to access all the pages? Upload your documents or become a member.
Related Documents
Development of a Multiple Regression Model for Sales Estimationlg...
|12
|1908
|297
Analysis of Sales and Customerslg...
|3
|779
|416
Data Analysis and Linear Programminglg...
|7
|838
|160
Time Series Analysis for Ozone Layer Thicknesslg...
|19
|1811
|401
Management Analytics: Regression Analysis on Gender and Salarylg...