Evaluate the model fit residuals and comment on their randomness using autocorrelation functions (ACFs), histogram and a normality plot (Use a four-in-one graph set along with residual ACFs).ĩ.
Rerun the model and evaluate the fit again including error measures, R adjusted square, F value, slope coefficient significance, DW and VIF.Ĩ. Determine the best remedies for any of the problems identified in 5 above and make the appropriate changes to the regression model if required. Evaluate model fit with 2 error measures (RMSE and MAPE).Ħ. Multicollinearity with the VIF statisticħ. Heteroscedasticity with a residuals versus order plot (look for a megaphone effect)Ĭ. Autocorrelation (Serial correlation) with the DW statisticī. Investigate the best model using appropriate statistics or graphs to comment on possible:Ī. Rule– if the coefficient is not significant then you may not use the model to forecast.ĥ. Note the significance of each slope term in the model. Use R square and F as primary determinants of the best model. Note that is any seasonal dummy variables are used all of the seasonal dummy variables must be used. Use regression to evaluate the variable combinations to determine the best regression model. Use either Decomposition centered moving average of Y (CMA) for Y and seasonal indices (SI) to seasonally adjust the Y variable or use dummy X variables in regression.Ĥ. for Y variable seasonality or significant events) and include a table of the dummy variable values for regression analysis. Determine if the model requires dummy variables (e.g. Create a table for the Y, X and X transformed values.ģ. If they do, calculate the transformed values and create a scatter plot with a regression line and run a correlation with Y for each transformed X. Determine if any of the variables require transformation. Note any seasonality in the Y data with ACF (autocorrelation analysis of Y).Ģ. Be sure to complete each part and write the responses supported by Minitab/excel work.īe sure to comment on each of the 10 points below.ġ. But, as an overall software, the few improvements that would be necessary are nothing compared to the changes and improvements that Minitab has made over the past 13+ years that I've used the product since it's Quality Companion days.Evaluate the forecast error measures- Microeconomicsĭevelop a good regression model with X variables in the regression equation. There is some individual tool functionality that can be improved, such as the Prioritization of Inputs (X's) taken from a Process Map. This has all of the soft skill templates, forms and project flow in one place. A common headache is the need for many programs.
#MINITAB ENGAGE SOFTWARE#
It is phenomenal.Ĭompanion/Workspace by Minitab is a very intuitively-designed software program for Continuous Improvement specialists to manage projects all in one place. I teach LSS Black Belts and Master Black Belts as dozens of companies and I wouldn't recommend any other software for them to manage their projects. There is nothing that makes things as simple as these programs. I don't believe there is anything close to competing with Companion by Minitab or Workspace for those in business and industry that are managing many projects that may use a plethora of different tools and applications.
0 kommentar(er)
