I hope someone can help me, Im trying to analyse a sample in which the dependent variable is death and the independent belonging to a category (Disease Type A, B,C etc.). All individuals were assigned a probability to die (calculated beforehand and independently) and I want to adjust for the differing baseline risk of individual samples to die. Eventually getting an OR to die comparing individual disease groups to another.
1 - is present of variable
0 - absence of variable
Can someone please help me in figuring out how this work in SPSS ? I have tried asking several people for help but never got a sufficient answer.
The Data would look similar to this (file: simple data)
At first, put two categories of death "yes=0" and "no=0". Then anlyze binary logistic regression.
#Steps of Logistic regression in SPSS
1. The data is entered in a between-subjects fashion.
2. Click Analyze.
3. Drag the cursor over the Regression drop-down menu.
4. Click Binary Logistic.
5. Click on the dichotomous categorical outcome variable to highlight it.
6. Click on the arrow to move the variable into the Dependent: box.
7. Click on the polychotomous categorical predictor variable to highlight it.
8. Click on the arrow to move the variable into the Covariates: box.
9. Click on the Categorical button.
10. Click on the predictor variable in the Covariates: box to highlight it.
11. Click on the arrow to move the variable into the Categorical Covariates: box.
12. Click on the Reference Category: First marker to select it.
13. Click on the Change button.
14. Click Continue.
15. Click on the Options button.
16. Click on the CI for exp(B): box to select it.
17. Click Continue.
18. Click OK.
#The steps for interpreting the SPSS output for an unadjusted odds ratio
1. Scroll all the way down to the bottom of the output, until the Variables in the Equation table.
2. Look under the first column of the table to find the name of the predictor variable. In the second row, the name will have a (1) beside it. This is the independent group or level of the categorical variable that is one unit more than what has been codified as the reference category.
This is why it is important to codify the reference category as "0." The SPSS outputs assign these values to multivariate analyses and interpretation can become cumbersome when one is not aware of this formatting issue. For example, if researchers designate the reference category as "1," then the variable in the second row of the table with a (1) in the name is not Group 1, but Group 2. The variable in the third row with a (2) is not Group 2, but Group 3. So, just to make things easier, please codify reference category as "0." It is SO much easier to interpret!
3. In the Exp(B) column, interpret the unadjusted odds ratios for each group or independent level when compared to the reference category.
4. Under the 95% C.I. for EXP(B) column heading, one can find the Lower and Upper limits of the 95% confidence interval for each unadjusted odds ratio.
5. There is no need to report a p-value with this type of statistic. The 95% confidence interval of the odds ratio is the primary inferential statistic for interpretation.
Thank you so much Md. Saiful Islam for your time and answer.
I don't understand why I should change my binary coding of death=1 and alive=0 to 0 and 0 as you suggested.
Also the way you explain the procedure im not really accounting for the individual baseline risk, as you are not adding risk dying anywhere in your calculation.
Maybe I have expressed my self wrongly before, but I want to add the individual baseline risk for everyone in this equation.
Have a look at the answers to this (contemporaneous) question
https://www.researchgate.net/post/How_to_calculate_unadjusted_odds_ratio_in_SPSS_Another_question_is_when_we_calculate_adjusted_and_unadjusted_odds_ratio
- Badges
- Science topic
- Similar topics
- Filing