Number of Observations in Logistic Regression in VA

[znhnm]

Hi,

I am using a visual logistic regression model in VA. When the model is built, I have "Observations: 1215 of 10675" statement. When I apply a filter in the dataset, the statement changes to be "Observations: 1215 of 5475". Then, I update the filter and now I have "Observations: 924 of 2767". My questions are: 

What does this "Observations: XXX of YYY" mean?
Why there is a drop in the number of observations when I apply a filter?

[PaigeMiller]

It means that some (actually most) observations can't be used because they contain missing values. You might want to consider imputing values for these missings.

When you apply a filter (you didn't say what filter, so I am guessing), there are fewer observations that can be used.