I used a multinomial logistic regression to predict whether people have confidence on a certain issue. The dependent variable has four categories 1 (1)not confident 2 (2)neutral 3 (3)confident 4 (4) unknown Independent variables include Identities, age, gender, education attainment, employment status, born in a certain place or not, community (urban or rural) and interaction terms.   Following are the outcomes of the model:     Model Fit Statistics Criterion Intercept Only Intercept and Covariates AIC 11678.775 11421.602 SC 11698.052 12019.195 -2 Log L 11672.775 11235.602     Testing Global Null Hypothesis: BETA=0 Test Chi-Square DF Pr > ChiSq Likelihood Ratio 437.1734 90 <.0001 Score 456.9761 90 <.0001 Wald 396.1174 90 <.0001   Deviance and Pearson Goodness-of-Fit Statistics Criterion Value DF Value/DF Pr > ChiSq Deviance 4083.7242 4359 0.9368 0.9987 Pearson 4494.1027 4359 1.0310 0.0750   The Deviance and Pearson Goodness-of-Fit Statistics show that P-value for Deviance is high. However, the P-value for Pearson statistics is low, even it greater than 0.05. Can I draw a conclusion that the model fits the data well? ... View more

I am trying to allocate a no-response category to other categories for a  age variable. The frequencies of age shown below Table 1. age_2 age_2 Frequency Percent Cumulative Frequency Cumulative Percent 1.     18-24 150 7.43 150 7.43 2.     25-34 301 14.91 451 22.34 3.     35-44 308 15.26 759 37.59 4.     45-54 400 19.81 1159 57.40 5.     55-64 426 21.10 1585 78.50 6.     65 and up 416 20.60 2001 99.11 9. no respond (NB) 18 0.89 2019 100.00 I used following code to redistribute no-response to other 1 to 6 categories in the data step (result shown in Table 2). From the table (Table 1) above, one can see that there are more older people (45 years old+) in the data set. Is there a method I can use to distribute more cases of “NB” to the age group 4 to 6?  Or there is method that I can use to allocate the cases of NB to other categories (1-6) according the distribution of the age group (see Table 1)?   Data set1; Set set1   call streaminit(0); if age_2=9 then age_2=ceil(ranuni(0)*5+1); run; Table 2. age_2 age_2 Frequency Percent Cumulative Frequency Cumulative Percent 1.     18-24 150 7.43 150 7.43 2.     25-34 305 15.11 455 22.54 3.     35-44 312 15.45 767 37.99 4.     45-54 404 20.01 1171 58.00 5.     55-64 431 21.35 1602 79.35 6.     65 and up 417 20.65 2019 100.00   ... View more

I have a dataset from a survey. The question about gender is: What is your gender?                    1    Male                          2    Female                3    Transgender      99    Prefer not to answer  The frequency (cell-count) for option 3 (transgender ) is less than 10. I would like to assign value of option 3 (transgender) to option 1 or 2 randomly. Any one has suggestions on how to randomly assigning a small category to other categories? Thanks for your help in advance! ... View more