How to carry out disordered multi-classification logistic regression analysis

Today, I will talk to you about how to carry out disordered multi-classification logistic regression analysis. Many people may not know much about it. In order to let you know more, Xiaobian summarized the following contents for you. I hope you can gain something according to this article.

disordered polytaxic logistic

Disordered multiple logistic regression analysis is a multiple regression analysis method used to study independent variables X and dependent variables Y (categorical variables). Independent variable X can be categorical variable or continuous variable, dependent variable Y is disordered multi-categorical variable, that is, the rank information among dependent variables is not considered, for example, occupation can be divided into doctor, teacher, engineer, worker, etc.

case analysis

To see if adult access to health knowledge differs between communities and genders, researchers surveyed 314 adults in two communities. (Data source: Medical Statistics 4th Edition, click "Read Original" to get data + password: adgm)

Variable assignment

Community (X1)

Community 1=0, Community 2 = 1

Gender (X2)

M =0, F = 1

Access to health knowledge (Y)

Traditional Mass Communication = 1, Internet = 2, Community Advocacy = 3

data view

variables view

Problem analysis: The data types of this case are all categorical variables, and the dependent variable Y has three levels (traditional mass media = 1, network = 2, community propaganda = 3) and disorder, so disordered multi-categorical logistic regression analysis is adopted.

teach you

[1] Weighting processing, weighting the frequency "freq"

[II] Click Analysis, Regression, Multinomial logistic (M)

[III] The dialog box shown below pops up.

[IV] Select "variable Y" into "dependent variable," and variables "community"(X1)"and" gender (X2)"into" factor,"(if it is a continuous variable, put it into" covariate ")

Other options can be selected according to specific needs

result analysis

① Summary of case handling

② Model fitting information

Likelihood ratio test of the model, P