Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Logistic regression: improve existing documentation issue #371 #381

Merged
merged 2 commits into from
Feb 27, 2025
Merged

Logistic regression: improve existing documentation issue #371 #381

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
745c2a1
Updated SAS page to align to R page and with no R vs SAS comparisons
DrLynTaylor Feb 26, 2025
34da128
add detail on comparison SAS vs R to align
DrLynTaylor Feb 26, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
10 changes: 7 additions & 3 deletions Comp/r-sas_logistic-regr.qmd
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -42,9 +42,13 @@ Below are summary of findings from a numerical comparison using example data, wh
::: {.callout-note appearance="minimal" collapse="false"}
### Logistic regression

Exact match (at 0.001 level) can be obtained using `glm` in R vs `PROC LOGISTIC` procedure (without Firth option) in SAS.
Maximum Likelihood Estimates and p-values for the Model Parameters have an exact match (at 0.001 level) using `glm` in R vs `PROC LOGISTIC` procedure (without Firth option) in SAS.

NOTE: Although a 100% match is obtained for the Odds ratios, the default methods for calculating 95% CIs in SAS and R are different. SAS Proc Logistic outputs Wald CI's as default whereas in R, following use of the glm() function, the confint() function calculates CI's using the profile likelihood method.
When using GLM parameterization (see [SAS page](https://psiaims.github.io/CAMIS/SAS/logistic-regr.html) for explanation of parameterization types), the parameters estimates (and 95% CIs) can be exponentiated to provide odds ratios and 95% CIs for odds ratios.

An exact match (at 0.001 level) is obtained for the Odds ratios and CIs when the same method is used, however SAS Proc Logistic can only calculate Wald CI's. Profile likelihood CIs are not available.

R using glm() function, can use the confint() function to calculate CI's using the profile likelihood method or the confint.default() function to calculate CIs using the Wald method.
:::

::: {.callout-note appearance="minimal" collapse="false"}
Expand Down Expand Up @@ -104,7 +108,7 @@ trial01 <- trial01 %>% filter(!is.na(aval)) ## remove missing data i.e complete
# write.csv(trial01, file = "data/trial01.csv", na = ".")
```

# Logisitic Regression
# Logistic Regression

## Parameterisation Comparison

Expand Down
Loading