En primer logar, cargamos la base de datos, y la limitamos a las variables de interes:
df <- read_sav("bd_tesis_final.sav") %>% as_tibble() %>%
select(media_gohai, media_scgohai,
sexo,
edad_s1,
escola_v00,
fuma_s1,
escola_gohai,
valoraboca_gohai2,
periodontitisB,
numdientes_gohai2,
#clasifica_obtu,
dent5_prot
)
df## # A tibble: 100 x 11
## media_gohai media_scgohai sexo edad_s1 escola_v00 fuma_s1 escola_gohai
## <dbl> <dbl> <dbl> <dbl> <dbl+lbl> <dbl+l> <dbl>
## 1 4.17 4 2 64 1 5 1
## 2 3.5 6 1 67 3 2 2
## 3 4.17 3 1 70 4 5 3
## 4 4.75 0 1 65 2 4 1
## 5 4.25 3 2 64 3 1 2
## 6 4.33 3 1 58 4 5 3
## 7 4.08 3 1 70 4 4 3
## 8 3.83 5 1 56 3 4 2
## 9 3.08 7 1 59 4 4 3
## 10 3.25 7 2 64 3 4 2
## # ... with 90 more rows, and 4 more variables: valoraboca_gohai2 <dbl>,
## # periodontitisB <dbl>, numdientes_gohai2 <dbl>, dent5_prot <dbl>Veamos ahora una comparación entre los resultados del modelo crudo y del modelo ajustado para cada variable dependiente:
modelo1=lm(media_gohai ~
periodontitisB+
numdientes_gohai2+
dent5_prot, data=df
)
modelo2=lm(media_gohai ~ sexo+
edad_s1+
fuma_s1+
escola_gohai+
valoraboca_gohai2+
periodontitisB+
numdientes_gohai2+
dent5_prot, data=df
)
tab_model(modelo1,modelo2,show.se = TRUE) %>% return() %$%
knitr %>%
asis_output()| media gohai | media gohai | |||||||
|---|---|---|---|---|---|---|---|---|
| Predictors | Estimates | std. Error | CI | p | Estimates | std. Error | CI | p |
| (Intercept) | 3.27 | 0.28 | 2.73 – 3.81 | <0.001 | 3.66 | 0.85 | 2.00 – 5.32 | <0.001 |
| periodontitis B | 0.20 | 0.16 | -0.12 – 0.51 | 0.233 | 0.06 | 0.13 | -0.20 – 0.31 | 0.667 |
| numdientes gohai 2 | 0.51 | 0.26 | -0.00 – 1.02 | 0.054 | 0.64 | 0.20 | 0.25 – 1.04 | 0.002 |
| dent 5 prot | -0.28 | 0.19 | -0.65 – 0.09 | 0.138 | -0.05 | 0.16 | -0.36 – 0.26 | 0.766 |
| sexo | -0.37 | 0.13 | -0.63 – -0.12 | 0.005 | ||||
| Edad | 0.02 | 0.01 | -0.01 – 0.04 | 0.206 | ||||
|
¿Fuma usted cigarrillos actualmente? |
0.09 | 0.05 | -0.00 – 0.18 | 0.065 | ||||
| escola gohai | -0.28 | 0.08 | -0.43 – -0.12 | 0.001 | ||||
| valoraboca gohai 2 | -0.55 | 0.09 | -0.74 – -0.37 | <0.001 | ||||
| Observations | 89 | 89 | ||||||
| R2 / adjusted R2 | 0.179 / 0.150 | 0.542 / 0.496 | ||||||
modelo1=lm(media_scgohai ~
periodontitisB+
numdientes_gohai2+
dent5_prot, data=df
)
modelo2=lm(media_scgohai ~ sexo+
edad_s1+
fuma_s1+
escola_gohai+
valoraboca_gohai2+
periodontitisB+
numdientes_gohai2+
dent5_prot, data=df
)
tab_model(modelo1,modelo2,show.se = TRUE) %>% return() %$%
knitr %>%
asis_output()| media scgohai | media scgohai | |||||||
|---|---|---|---|---|---|---|---|---|
| Predictors | Estimates | std. Error | CI | p | Estimates | std. Error | CI | p |
| (Intercept) | 6.43 | 1.07 | 4.33 – 8.52 | <0.001 | 3.06 | 3.20 | -3.21 – 9.34 | 0.342 |
| periodontitis B | -0.84 | 0.63 | -2.08 – 0.39 | 0.186 | -0.19 | 0.50 | -1.16 – 0.79 | 0.705 |
| numdientes gohai 2 | -1.75 | 1.01 | -3.73 – 0.23 | 0.086 | -2.34 | 0.77 | -3.84 – -0.84 | 0.003 |
| dent 5 prot | 1.22 | 0.73 | -0.21 – 2.65 | 0.099 | 0.23 | 0.60 | -0.95 – 1.41 | 0.708 |
| sexo | 1.84 | 0.49 | 0.88 – 2.80 | <0.001 | ||||
| Edad | -0.05 | 0.05 | -0.15 – 0.05 | 0.345 | ||||
|
¿Fuma usted cigarrillos actualmente? |
-0.30 | 0.18 | -0.66 – 0.05 | 0.092 | ||||
| escola gohai | 1.09 | 0.30 | 0.50 – 1.67 | 0.001 | ||||
| valoraboca gohai 2 | 2.15 | 0.36 | 1.45 – 2.85 | <0.001 | ||||
| Observations | 89 | 89 | ||||||
| R2 / adjusted R2 | 0.180 / 0.151 | 0.565 / 0.521 | ||||||