The accompanying data file contains 40 observations on the response variable y along with the predictor variables x₁ and x₂. Use the holdout method to compare the predictability of the linear model with the exponential model using the first 30 observations for training and the remaining 10 observations for validation.

a-1. Use the training set to estimate Models 1 and 2. (Negative values should be indicated by a minus sign. Round your answers to 2 decimal places.) a-2. Calculate the RMSE of the two models in the validation set. (Do not round intermediate calculations and round final answers to 2 decimal places.) a-3. Which model is better for making predictions?

y	x1	x2
533.86	20	30
104.84	15	20
64.89	20	23
159.61	16	21
43.06	13	16
4.27	13	13
736.56	15	30
64.89	20	23
10.64	20	22
76.90	18	20
4.89	11	13
80.90	11	16
135.00	12	19
45.75	16	25
8.13	17	17
319.97	13	30
48.61	19	25
564.67	12	27
111.87	11	25
152.39	13	24
13.34	18	14
28.80	15	22
37.56	13	15
105.62	17	26
135.00	18	21
451.65	17	28
10.34	18	21
32.70	12	13
19.21	14	12
14.02	15	16
2.45	16	12
2.48	20	15
50.34	17	21
29.31	17	20
33.75	16	12
196.28	17	29
943.12	13	30
7.25	10	12
89.73	15	25
32.91	12	18