We are interested in an association between response y and a predictor x. To this end a regression model (y ~ x) is fitted to the data.
Adding another predictor z into the regression model (y ~ x + z) may have a dramatic impact on the association between the response y and the predictor x.
An immunological variable y was measured on healthy controls (K) and on patients with a certain diagnosis (D).
We are interested in differences of the immunological variable y among healthy controls and patients.
We also have data on age of the participants of the study.
| Characteristic | K, N = 191 | D, N = 1781 |
|---|---|---|
| y | 10.6 (2.2) | 6.2 (2.4) |
| Age | 35 (9) | 74 (10) |
|
1
Mean (SD)
|
||
| contrast | estimate | SE | df | t.ratio | p.value |
|---|---|---|---|---|---|
| K - D | 4.4 | 0.6 | 195 | 7.5 | 0 |
| estimate | estimate1 | estimate2 | statistic | p.value | parameter | conf.low | conf.high | method | alternative |
|---|---|---|---|---|---|---|---|---|---|
| 4.4 | 10.6 | 6.2 | 8.3 | 0 | 23.1 | 3.3 | 5.5 | Student Two Sample t-test | two.sided |
NOTE: the linear hypothesis test based on the regression model,
and t test (w equal variance) give the same results.
| contrast | estimate | SE | df | t.ratio | p.value |
|---|---|---|---|---|---|
| K - D | -4.8 | 0.3 | 194 | -17.3 | 0 |
| Group | emmean | SE | df | lower.CL | upper.CL |
|---|---|---|---|---|---|
| K | 7.0 | 0.2 | 194 | 6.7 | 7.4 |
| D | 11.8 | 0.1 | 194 | 11.5 | 12.1 |
| Group | Age.trend | SE | df | lower.CL | upper.CL |
|---|---|---|---|---|---|
| K | -0.24 | 0.01 | 194 | -0.25 | -0.23 |
| D | -0.24 | 0.01 | 194 | -0.25 | -0.23 |
From the regression model M1 (y ~ Group), we have drawn the conclusion that the population mean of y in control group K (estimated to be 10.6) is statistically significantly higher (pval < 0.001) than the mean in patients subpopulation D (estimated to be 6.2). In other words, the difference of means, K minus D, was 4.4, and it was statistically significant.
When the new information on age of the subjects was added into regression, then the M2-based test of equality of the subpopulation means of y was the opposite: the mean difference between K and D is -4.8, and it is statistically significant. Hence, after taking into account the age of subjects, the mean of y in K turns out to be significantly lower than in D.
─ Session info ───────────────────────────────────────────────────────────────
setting value
version R version 4.0.5 (2021-03-31)
os CentOS Stream 8
system x86_64, linux-gnu
ui X11
language (EN)
collate en_US.UTF-8
ctype en_US.UTF-8
tz Europe/Bratislava
date 2024-02-23
pandoc 3.1.1 @ /usr/lib/rstudio/resources/app/bin/quarto/bin/tools/ (via rmarkdown)
─ Packages ───────────────────────────────────────────────────────────────────
package * version date (UTC) lib source
broom * 1.0.5 2023-06-09 [1] CRAN (R 4.0.5)
emmeans * 1.7.5 2022-06-22 [1] CRAN (R 4.0.5)
ggplot2 * 3.4.4 2023-10-12 [1] CRAN (R 4.0.5)
ggpubr * 0.4.0.999 2021-07-17 [1] Github (kassambara/ggpubr@ac5a01f)
gtsummary * 1.5.0 2021-10-16 [1] CRAN (R 4.0.5)
kableExtra * 1.3.4 2021-02-20 [1] CRAN (R 4.0.5)
MASS * 7.3-57 2022-04-22 [1] CRAN (R 4.0.5)
multcomp * 1.4-17 2021-04-29 [1] CRAN (R 4.0.5)
mvtnorm * 1.1-1 2020-06-09 [1] CRAN (R 4.0.5)
patchwork * 1.1.3 2023-08-14 [1] CRAN (R 4.0.5)
sjPlot * 2.8.12 2022-12-13 [1] Github (strengejacke/sjPlot@4058580)
survival * 3.5-7 2023-08-14 [1] CRAN (R 4.0.5)
TH.data * 1.0-10 2019-01-21 [1] CRAN (R 4.0.5)
[1] /home/mg/R/x86_64-pc-linux-gnu-library/4.0
[2] /opt/R/4.0.5/lib/R/library
──────────────────────────────────────────────────────────────────────────────