Scribd
Upload
199 views2 pages

Logistics Regression Exercise

This logistic regression analyzes factors that impact TV viewing hours using data from the General Social Survey. It finds: 1) The logistic regression model is statistically significant in predicting TV viewing addiction. 2) Age, education levels, and paternal education are significant explanatory variables, with more of each associated with lower odds of TV addiction. 3) The model fits the data moderately well according to the Hosmer-Lemeshow test.

Uploaded by

Lakshmi Nair
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
199 views2 pages

Logistics Regression Exercise

This logistic regression analyzes factors that impact TV viewing hours using data from the General Social Survey. It finds: 1) The logistic regression model is statistically significant in predicting TV viewing addiction. 2) Age, education levels, and paternal education are significant explanatory variables, with more of each associated with lower odds of TV addiction. 3) The model fits the data moderately well according to the Hosmer-Lemeshow test.

Uploaded by

Lakshmi Nair
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
You are on page 1/ 2

Logistics Regression Exercise

Q.1 The General Social Survey is a large, national probability sample of adults (18 years and older) living
in the United States conducted by the National Opinion Research Center (NORC) at the University of
Chicago. Following is an analysis that was conducted on a few variables from that data set to identify the
factors that impact the TV viewing hours of a person.

TVhours_binary : Is a binary variable coded from the data about no of hours a person watches TV in a
day. Its value can be

0 : When no of TV viewing hours are great than 3, which means he is addicted to watching
Television

1 : When no of TV viewing hours are less than or equal to 3, which means he is not addicted to
watching Television

D1_age : His age in years

D4_educ : No of years of education he had

D24_educ : No of years of education his Father had

Study the following SAS output and answer the questions that follow.

Response Profile
Ordered Total
Value Tvhours_binary Frequency
1 0 515
2 1 2023

Probability modeled is Tvhours_binary='0'.

Testing Global Null Hypothesis: BETA=0


Test Chi-Square DF Pr > ChiSq
Likelihood Ratio 66.1376 3 <.0001
Score 63.1994 3 <.0001
Wald 64.7548 3 <.0001
Analysis of Maximum Likelihood Estimates
Parameter DF Estimate Standard Wald Pr > ChiSq
Error Chi-Square
Intercept 1 -1.0415 0.2745 14.3954 0.0001
d24_paeduc 1 0.00297 0.00128 A 0.0208
d1_age 1 0.0145 0.0028 B <.0001
d4_educ 1 -0.0866 0.0162 C <.0001

Odds Ratio Estimates


95% Wald
Effect Point Estimate Confidence Limits
d24_paeduc D 1 1.005
d1_age E 1.009 1.02
d4_educ F 0.888 0.947

Hosmer and Lemeshow Goodness-of-Fit


Test
Chi-Square DF Pr > ChiSq
16.9935 8 0.0302

Questions

a. Identify dependent and explanatory variable. Write the model for logistic regression
b. Is the model Significant?? Explain
c. Calculate the Wald Chi-square for parameter Estimates
d. Do all the explanatory variables have significant effect on outcome variable? Explain with
suitable hypothesis and their tests.
e. Calculate the odds ratio for each of the parameter estimate.
f. Comment on Goodness of Fit of the model.
g. If a person is of 57 years of age, with 12 years of education and 5 years of paternal education,
what are the chances of him not being addicted to TV.

You might also like