Use the StatTool software The data describe information on 1436 different Toyota Corolla cars. Your goals
Use the StatTool software
The data describe information on 1436 different Toyota Corolla cars. Your goals are to explore these data, and to decide on a model that predicts the offer price in Euros (PRICE) for an unlisted car based on information such as KM, HP and Age. The variables in the data are as follow.
There are 39 variables on which observations have been gathered. They are:
|
Re: The goal of exploring the data
- Select 3 variables and examine the Histograms of the data values for them. Describe which of these variables will likely have the most impact on another variable, and why it will do so?
- Select 3 pairs of variables, and examine their scatterplots. Describe which of these pairs of variables will most likely have a strong relationship based on these plots, and justify your choice?
- Compute the correlation table for all the variables’ values, except for the variable – (Price) offer prices in Euros. Comment on your results.
- Describe and justify what you think was the sampling technique used to gather the data for each of three variables in your dataset?
- Select 3 variables. What inferences can you make about the true average values for these variables if the data for all cars could have been collected?
Re: The goal of predicting offer prices in Euros(Price)
- Use the linear regression technique to identify the ‘best" simple linear regression model for predicting offer prices in Euros? [Be sure to include a couple of the models you tried to determine which one is "best."]
- Perform a multiple regression for "Price" with at least 3 predictors, and try to maximize your R-squared value? [ show a couple of the models you tried]
- Identify which variables could be dropped from your model above, and not impact the R-squared value in your model by a significant amount?
- Discuss whether the coefficients in your model from the previous question are all statistically significant?
- Discuss the final result of your multiple regression model. [Your discussion should focus on how reasonable your model seems in theory and for practice].
Price: $23.39
Solution: The downloadable solution consists of 15 pages, 839 words and 6 charts.
Deliverable: Word Document
Deliverable: Word Document
