We just had the same question, trying to create a very similar table using SPSS to report results of crosstab analyses. It’s too bad that the program doesn’t give you this as an output. I made a quick calculator in Excel using the standard error formula -- enter percentages as decimals on the left and it gives you upper and lower bounds for the 95% CI on the right. Sharing here in case it saves time for anyone else in the same situation!

Hi,

Confidence intervals provide a means of assessing and reporting the precision of a point estimate, such as a mortality or hospitalization rate or a frequency of reported behaviors. Confidence intervals account for the uncertainty that arises from the natural variation inherent in the world around us. In the special case of sample surveys, confidence intervals also account for the difference between a sample from a population and the population itself.

Confidence intervals do not account for several other sources of uncertainty in point estimates, including missing or incomplete data or other data errors, or bias resulting from non-response or poor data collection. When confidence intervals are used to describe health data such as incidence or mortality rates, confidence levels of 95% are generally used (although 90% or 99% confidence intervals are not uncommon). Confidence intervals are sometimes used as a test of significance.

SPSS didn't calculate the confidence interval for a proportion.  But, how it was easy to obtain this, giving me the textbook formula for the standard error of a proportion.  You can find the C.I from the software STATA.

In SPSS you can get the confidence intervals using the bootstrap option. 

go to frequency, click the bootstrap option , you will get the CI for proportions.

the calculation of a CI for one variable isn't my question. The relationships between two variable including their frequencies is unknown,

SE for proportions is: sqrt [ p(1 - p) / n ]; but for a more conservative interval you could do a logistic regression analysis. Your "dependent variable" is 0 or 1 and your "predictor" has three categories. In SPSS use regression->binary logistic, which will give you the Beta's and SE's, from those you can calculate the percentages and 95% CI-values using the logistic transformation (EXP(Beta) / (1+EXP(Beta))*100.

Hi odds ratio wanted to say? if so, is the number of times you are most likely an effect or result in a comparison. 

You can calculate  CI for proportion in SPSS and STATA. Otherwise the  excel can be the best software to compute CI using formula. Without number of success and total event, one cannot compute CI. 

Thanks dears, the calculation of OR isn't my question.

Bootstrap option or using SPSS complex samples could give you the CI.

There is also an option called "Ratio statistics" in the menu Analyze/Descriptive statistics. There you have the option "confidence interval" but i think you need one previous calculation

The simplest way in SPSS i think it is Regression/Binary Logistic. On the output look at exp(b) and its confidence interval. the only thing is to link OR=p/1-p as Andre Wiersma noted

No, SPSS does not give CI for a single proportion. 

I think you should split or sort casses according to their smoking status (DATA>Split cases), then run analyse>Descriptive statistics>explore. 

We just had the same question, trying to create a very similar table using SPSS to report results of crosstab analyses. It’s too bad that the program doesn’t give you this as an output. I made a quick calculator in Excel using the standard error formula -- enter percentages as decimals on the left and it gives you upper and lower bounds for the 95% CI on the right. Sharing here in case it saves time for anyone else in the same situation!

We faced the same challenge! Thank you, dear @Paul F Cook !

Thank you @Paul F Cook