Question

The below provides information about the dataset.

Input variables (based on physicochemical tests)
Fixed acidity	Numeric
Volatile acidity	Numeric
Citric acid	Numeric
Residual sugar	Numeric
Chlorides	Numeric
Free sulfur dioxide	Numeric
Total sulfur dioxide	Numeric
Density	Numeric
pH	Numeric
Sulphates	Numeric
Alcohol	Numeric (%)
Wine Type	red or white
Output variable (based on sensory data)
Quality	Score between 0 and 10 in ordinal

Data set

fixed acidity	volatile acidity	citric acid	residual sugar	chlorides	free sulfur dioxide	total sulfur dioxide	density	pH	sulphates	alcohol	winetype	quality
7.4	0.7	0	1.9	0.076	11	34	0.9978	3.51	0.56	9.4	red	5
7.8	0.88	0	2.6	0.098	25	67	0.9968	3.2	0.68	9.8	red	5
7.8	0.76	0.04	2.3	0.092	15	54	0.997	3.26	0.65	9.8	red	5
11.2	0.28	0.56	1.9	0.075	17	60	0.998	3.16	0.58	9.8	red	6
7.4	0.7	0	1.9	0.076	11	34	0.9978	3.51	0.56	9.4	red	5
7.4	0.66	0	1.8	0.075	13	40	0.9978	3.51	0.56	9.4	red	5
7.9	0.6	0.06	1.6	0.069	15	59	0.9964	3.3	0.46	9.4	red	5
7.3	0.65	0	1.2	0.065	15	21	0.9946	3.39	0.47	10	red	7
7.8	0.58	0.02	2	0.073	9	18	0.9968	3.36	0.57	9.5	red	7
7.5	0.5	0.36	6.1	0.071	17	102	0.9978	3.35	0.8	10.5	red	5

Using R, build a linear regression model, logistic regression and classification model for wine quality prediction and no data partition is needed.

Which approach is best, regression or classification models? Why?

Answer 1

After entering the data in Excel we can do the analysis in R

R code along with output is attached herewith.

Here from the summary statistics both the model looks to be fine but the response variable is a ordinal varaiable so it is more appropriate to fit a classification model i.e., Logistic regression model.

Because in linear regression model many response values may be greater than 7 or less than 5

and we cannot interpret them on the other hand if they are categorical then it will be classified to one of the classes.