Suppose that we take a data set, divide it into equally-sized training and test sets, and then try out two different classification procedures. First we use logistic regression and get an error rate of 20% on the training data and 30% on the test data. Next we use 1-nearest neighbors (i.e. K = 1) and get an average error rate (averaged over both test and training data sets) of 18%. Based on these results, which method should we prefer to use for classification of new observations? Why?

Suppose that we take a data set, divide it into equally-sized training and test sets, and then try out two different classification procedures. First we use logistic regression and get an error rate of 20% on the training data and 30% on the test data. Next we use 1-nearest neighbors (i.e. K = 1) and get an average error rate (averaged over both test and training data sets) of 18%. Based on these results, which method should we prefer to use for classification of new observations? Why?

MATLAB: An Introduction with Applications

6th Edition

ISBN:9781119256830

Author:Amos Gilat

Publisher:Amos Gilat

Chapter1: Starting With Matlab

Section: Chapter Questions

Problem 1P

See similar textbooks

Similar questions

In many fast food restaurants, there is a strong correlation between a menu item's fat content (measured in grams) and its calorie content. We want to investigate this relationship. Using all of the food menu items at a well-known fast food restaurant, the fat content and calorie content were measured. We decide to fit the least-squares regression line to the data, with fat content ( x) as the explanatory variable and calorie content ( y) as the response variable. A scatterplot of the data (with regression line included) and a summary of the data are provided. One of the menu items is a hamburger with 117 grams of fat and 1520 calories. r = 0.979 (correlation between x and y) = 40.35 grams (mean of the values of x) = 662.88 calories (mean of the values of y) = 27.99 grams (standard deviation of the values of x) = 324.90 calories (standard deviation of the values of y) Refer to the example data point (117 grams, 1520 calories). What is the residual corresponding to this…
Suppose that a kitchen cabinet warehouse company would like to be able to predict the area of a customer’s kitchen using the number of cabinets and the kitchen ceiling height. To do so data is collected on the following variables from a random sample of customers: Area – area of the kitchen in square feet Height – ceiling height in the kitchen (from floor to ceiling) in inches Cabinets – number of cabinets in the kitchen Suppose that a multiple linear regression model was fit to the data and that the following output resulted: Coefficients: (Intercept)HeightCabinets Estimate-57.98771.2760.3393 Std. Error8.63820.26430.1302 t value -6.7134.8282.607 Pr(>|t|)2.75e-074.44e-050.0145 What is the predicted area of a kitchen with a height of 96 inches and 10 cabinets? Report your answer to 1 decimal place. square feet
Suppose you want to estimate the effect of access to public transportation on house prices. You write down the following regression model: Price; = Bo + B₁ Distance; + B₂ Schoolį + Ui where Price; is the average house price in a community, in dollars per square foot, Distance; is the distance in miles from the community to the nearest subway station, and School; is the number of schools in the neighborhood. Your estimation yields ₁ = 1327. Suppose two communities differ in their distance to the nearest subway stops by 0.5 miles but have identical characteristics otherwise. What is the expected difference in the average house price between the two communities? 663.5 Not enough information given to answer the question 1327 2652
The relationship between number of beers consumed (x) and blood alcohol content (y) was studied in 16 male college students by using least squares regression. The following regression equation was obtained from this study: y = -0.0127 + 0.0180x. Suppose that the legal limit to drive is a blood alcohol content of 0.08. If Ricky consumed 5 beers the model would predict that he would be:
The average gestational age (time from conception to birth) of a newborn infant is about 40 weeks. The following data presents the gestational age in weeks and corresponding mean birth weight in pounds for female infants born in Canada. Find the least-squares regression line for predicting the birth weight from the gestational age. You should be able to grab the data in the table, copy it, and paste it in Excel. You would then select the data in Excel, Insert a Scatter Chart and then under Trendline, check the two boxes at the bottom to display the equation and the R-squared. Gestational Age Birth Weight 36 6.1 37 6.6 38 7.0 39 7.4 40 7.7 41 7.9 42 8.0 43 8.1 A. y= 3.2787x + 15.402 B. y= 15.402x + 3.2787 C. y= 0.2857x - 3.9357 D. Y= 3.9357X + 0.2857
Suppose the following data were collected from a sample of 5 car manufacturers relating monthly car sales to the number of dealerships and the quarter of the year. Use statistical software to find the following regression equation: SALESi= b0 + b1DEALERSHIPSi + b2 QUARTER1i+ b3QUARTER2i + b4QUARTER3i+ ei Is there enough evidence to support the claim that on average, car sales are higher in the 4th quarter than in the 2nd quarter at the 0.01 level of significance? If yes, write the regression equation in the spaces provided, rounded to two decimal places. Else, select "There is not enough evidence." Monthly Sales Number of Dealerships 1st Quarter (1 if Jan.-Mar., 0 otherwise) 2nd Quarter (1 if Apr.-Jun., 0 otherwise) 3rd Quarter (1 if Jul.-Sep., 0 otherwise) 4th Quarter (1 if Oct.-Dec., 0 otherwise) 85482 4 1 0 0 0 101319 9 1 0 0 0 121389 12 1 0 0 0 133677 18 1 0 0 0 194588 22 1 0 0 0 82128 4 0 1 0 0 150407 9 0 1 0 0 242714 12 0…
Please help with unanswered questions. Thank you!
Retail price data for n = 60 hard disk drives were recently reported in a computer magazine. Three variables were recorded for each hard disk drive: y = Retail PRICE (measured in dollars) X1 = Microprocessor SPEED (measured in megahertz) (Values in sample range from 10 to 40) x 2 = CHIP size (measured in computer processing units) (Values in sample range from 286 to 486) A first-order regression model. was fit to the data. Part of the printout follows: Parameter Estimates T FOR 0 ERROR PARAMETER = 0 PROB>ITI PARAMETER STANDARD VARIABLE DF ESTIMATE INTERCEPT 1 -373.526392 1258.1243396 -0.297 0.7676 SPEED 1 104.838940 22.36298195 4 688 0.0001 сHP 1 3.571850 3.89422935 0.917 0.3629 Identify and interpret the estimate of B2-
Suppose the following data were collected from a sample of 1515 CEOs relating annual salary to years of experience and the economic sector their company belongs to. Use statistical software to find the following regression equation: SALARYi=b0+b1EXPERIENCEi+b2SERVICEi+b3INDUSTRIALi+eiSALARY�=�0+�1EXPERIENCE�+�2SERVICE�+�3INDUSTRIAL�+��. Is there enough evidence to support the claim that on average, CEOs in the industrial sector have lower salaries than CEOs in the financial sector at the 0.010.01 level of significance? If yes, write the regression equation in the spaces provided with answers rounded to two decimal places. Else, select "There is not enough evidence." Copy Data CEO Salaries Salary Experience Service (1 if service sector, 0 otherwise) Industrial (1 if industrial sector, 0 otherwise) Financial (1 if financial sector, 0 otherwise) 155200155200 2020 11 00 00 179715179715 1818 00 00 11 171750171750 3131 11 00 00 187075187075 2121 00 00 11 151550151550…
A medical experiment on tumor growth gives the following data table. X: 65, 70, 86, 100, 222. Y: 33, 35, 45, 52, 70. The least squares regression line was found. Using technology, it is determined that the total sum of squares (SST) was 898 and the sum of squares of regression (SSR) was 806.2. Calculate R2, rounded to three decimal places
David's Landscaping has collected data on home values (in thousands of $) and expenditures (in thousands of $) on landscaping with the hope of developing a predictive model to help marketing to potential new clients. Data for 14 households may be found in the file Landscape. Click on the datafile logo to reference the data. (NEED ANSWERS FOR C, D, and E) c. Use the least squares method to develop the estimated regression equation (to 5 decimals). d. For every additional $1000 in home value, estimate how much additional will be spent on landscaping (to 2 decimals). e. Use the equation estimated in part (c) to predict the landscaping expenditures for a home valued at $575,000 (to the nearest whole number).
The owners of a chain of ice cream stores have the business objective of improving the forecast of daily sales so that staffing shortages can be minimized during the summer season. As a starting point, the owners decide to develop a simple linear regression model to predict daily sales based on atmospheric temperature. They select a sample of 15 consecutive days. The results are shown in the accompanying table. Complete parts (a) through (f) below. Click the icon to view the data table. E Click the icon to view a table of critical values of the Durbin-Watson statistic. a. Assuming a linear relationship, use the least-squares method to compute the regression coefficients b, and b,. b, = - 2.7630 (Round to four decimal places as needed.) %3D Ice cream sales b, = (Round to four decimal places as needed.) %3D Day Sales ($1,000) Temperature (°F) 63 1 2 1.52 1.68 71 75 3 1.92 1.79 74 76 4 2.02 2.36 6. 81 2.16 2.69 81 8 84 2.91 88 10 3.17 90 11 12 3.02 3.27 90 93 99 13 3.42 2.84 88 83 14 15…