Scribd Logo
Upload

Welcome to Scribd!

  • 47 views

    Practice 01 Linear Regression

    Uploaded by

    Capung fly
    The document provides instructions for 6 practical exercises using linear regression techniques to analyze different datasets in SPSS. For each exercise, participants are asked to build regression models to predict a specified dependent variable from given independent variables, and compare the prediction accuracy and number of predictors from stepwise, backward, and forward regression methods. The goal is to identify the best regression model for predicting the outcome variable in each dataset.

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd

    Practice 01 Linear Regression

    Uploaded by

    Capung fly
    47 views3 pages
    The document provides instructions for 6 practical exercises using linear regression techniques to analyze different datasets in SPSS. For each exercise, participants are asked to build regression models to predict a specified dependent variable from given independent variables, and compare the prediction accuracy and number of predictors from stepwise, backward, and forward regression methods. The goal is to identify the best regression model for predicting the outcome variable in each dataset.

    Original Title

    Practice+01+linear+regression

    Copyright

    © © All Rights Reserved

    Available Formats

    PDF, TXT or read online from Scribd

    Did you find this document useful?

    Is this content inappropriate?

    The document provides instructions for 6 practical exercises using linear regression techniques to analyze different datasets in SPSS. For each exercise, participants are asked to build regression models to predict a specified dependent variable from given independent variables, and compare the prediction accuracy and number of predictors from stepwise, backward, and forward regression methods. The goal is to identify the best regression model for predicting the outcome variable in each dataset.

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd
    Download as pdf or txt
    47 views3 pages

    Practice 01 Linear Regression

    Uploaded by

    Capung fly
    The document provides instructions for 6 practical exercises using linear regression techniques to analyze different datasets in SPSS. For each exercise, participants are asked to build regression models to predict a specified dependent variable from given independent variables, and compare the prediction accuracy and number of predictors from stepwise, backward, and forward regression methods. The goal is to identify the best regression model for predicting the outcome variable in each dataset.

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd
    Download as pdf or txt
    of 3

    Practical Exercises

    Linear Regression Techniques

    N.B. For each exercise, the working SPSS data set is indicated. The download link for
    the data sets can be found in the section called “Download Your Resources Here”.

    1
    Data set: cpuperform.sav

    This data set contains technical information about 209 computers. Create regression
    models that predict the relative CPU performance (prp) based on the following
    variables: myct, mmin, mmax, cach, chmin, chmax. (Each variable is explained in its
    label.) Use all three stepwise regression methods available in SPSS – stepwise,
    backward and forward – and retain the model with the highest prediction accuracy.

    2
    Data set: winequality.sav

    This data set contains information about various types of wines. Your task is to find the
    best predictors for the wines quality (quality) from the following 11 variables: fixed
    acidity, volatile acidity, citric acid, residual sugar, chlorides, free sulfur dioxide, total
    sulfur dioxide, density, pH, sulphates and alcohol. (Each variable is explained in its
    label.) Use all three stepwise regression methods available in SPSS – stepwise,
    backward and forward. Which method gives the model with the greatest prediction
    accuracy? Which method gives the model with the smallest number of predictors?
    3
    Data set: housedata.sav

    This data set contains information about over 21,000 houses. You are supposed to find
    the best predictors for a house price (price) out of the following variables: bedrooms,
    bathrooms, sqft_living, sqft_lot, floors, grade, sqft_basement and old. (Each variable is
    explained in its label.) Use all three stepwise regression methods available in SPSS –
    stepwise, backward and forward – and retain the model that provides good prediction
    accuracy with the smallest number of predictors.

    4
    Data set: bostonhousing.sav

    This data set contains information about 506 houses in Boston, USA. You have to
    predict the median house value (medv) using the following variables: crim, zn, indus,
    nox, rm, age, dis, rad, tax, ptratio and lstat. (Each variable is explained in its label.)
    Identify the model with the highest prediction accuracy using these regression methods:
    stepwise, backward and forward.

    5
    Data set: cellular.sav

    This data set contains information about 250 customers of a cell phone company. You
    have to find the best predictors of the customers’ propensity to leave score (score). To
    that effect, build the following nested regression models:
    1. The first model uses as the following variables as predictors: minutes, bill
    2. The second model uses as the following variables as predictors: minutes, bill,
    business, los
    3. The third model uses as the following variables as predictors: minutes, bill,
    business, los, income
    Each variable is explained in its label.
    Which is the model with the greatest prediction accuracy? Which are the best predictors
    of the propensity to leave?

    6
    Data set: mallcost.sav

    This data set contains information about the cost of construction for 40 malls. You have
    to find the best predictors for this cost (variable cost) by creating three nested
    regression models:
    1. The first model uses as the following variable as predictors: sqft
    2. The second model uses as the following variables as predictors: sqft, inorout
    3. The third model uses as the following variables as predictors: sqft, inorout, yrext
    Each variable is explained in its label.

    Which is the model with the greatest prediction accuracy? What are the best predictors
    of the construction cost?

    You might also like