These are outputs of multinomial regression for Arthritis vs. sex(gender) Please

Question

These are outputs of multinomial regression for Arthritis vs. sex(gender)

Please interpret the output data between arthritis and sex (gender) and make a final conclusion.

Males (labeled number 1)

Females (Labeled number 2)

Case Processing Summary Marginal Percentage 1571 2943 TOLD HAVE ARTHRITIS YES 34.6% 64.8% Dont Know Refused Male Female 0.0% 41.5% 58.5 % 1 00.0% RESPONDENTS SEX 1886 Valid Missing 4540 4540 Subpopulation Likelihood Ratio Tests Model Fitting Criteria Likelihood Ratio Tests Likelihood of Reduced Model Intercept SEX 28.552 78.077 49.524 The chi-square statistic is the difference in -2 log- likelihoods between the final model and a reduced model. The reduced model is formed by omitting an effect from the inal model. The null hypothesis is that all parameters of that etfect are 0. a. This reduced model is equivalent to the final model because omitting the effect doesnot increase the degrees of freedom Parameter Estimates 95% Confidence Interval for Exp Std.Error Wald Sig. Exp(B) Lower Bound Upper Bound Intercept 1000 48.026 633 1.415 200 1 655 531 Intercept 1.000 54.489 189 1415018 1894 828 3.249 Dont Know Intercept 2833 029 7.581006 -887 1.44358 1550 12 SEX=2] a. The reference category is: Refused. b. This parameter is set to zero because it is redundant.

Explanation / Answer

Solution:

Hypothesis:

H0: All parametres effect are zero.

H1: At least two parameter effect not zero.

From the above table, we observe that

The resut of likelihood ratio test is significant i.e p-value<0.05. Hence, null hypothesis is rejected and conclude that parameters effect in this model is not zero.

We can see in the parameter estimate table:

All parameter estimates of "Yes", "No" and "Don't Know" are significant.

Related Questions

Navigate

• Browse (All)
• Browse T
• Subjects

---

---

Integrity-first tutoring: explanations and feedback only — we do not complete graded work. Learn more.