En primer lugar, cargamos la base de datos, y la limitamos a las variables de interes:

df <- read.spss("bd_tesis_final.sav") %>% as_tibble() %>% 
  select(media_gohai, media_scgohai, add_gohai, sc_gohai,
sexo_s1,
edad_s1,
escola_v00,
fuma_s1,
escola_gohai,
valoraboca_gohai2,
periodontitisB,
numdientes_gohai2,
everything())

Tablas 6 y 7 según las instrucciones del 21 de junio de 2019

Tabla 6

tabla=df %>% finalfit(
dependent =  "add_gohai", 
explanatory= c("sexo_s1", "edad_s1", "est_civilgohai", "escola_gohai", "fuma_gohai3", "valoraboca_gohai2", "numdientes_gohai2", "periodontitisB"
),metrics = TRUE)
knitr::kable(tabla[[1]], row.names=FALSE)
Dependent: NULL Mean (sd) Coefficient (univariable) Coefficient (multivariable)
sexo_s1 Hombre 45.6 (9.4)
Mujer 40.9 (9.8) -4.66 (-8.52 to -0.80, p=0.019) -5.68 (-9.05 to -2.32, p=0.001)
edad_s1 [55,74] 43.6 (9.8) 0.07 (-0.34 to 0.48, p=0.734) 0.15 (-0.15 to 0.45, p=0.313)
est_civilgohai Soltero 36.8 (10.9)
Casado 44.8 (9.2) 8.02 (0.92 to 15.12, p=0.027) 2.83 (-2.78 to 8.44, p=0.319)
Divorciado y otros 41.9 (10.8) 5.19 (-2.99 to 13.37, p=0.211) 6.67 (0.30 to 13.04, p=0.040)
escola_gohai Titulacion superior o técnico 46.3 (11.4)
Escuela 2° 45.1 (8.2) -1.22 (-6.53 to 4.09, p=0.650) -3.51 (-7.35 to 0.34, p=0.073)
Escuela 1° o ninguno 41.2 (10.0) -5.11 (-10.29 to 0.07, p=0.053) -6.89 (-10.65 to -3.14, p<0.001)
fuma_gohai3 Sí 38.4 (12.5)
Exfumador de 0 a 1 año 43.0 (7.2) 4.60 (-6.26 to 15.46, p=0.403) -0.60 (-9.00 to 7.80, p=0.887)
Exfumador de 1 a 5 años 47.0 (13.0) 8.60 (-3.61 to 20.81, p=0.165) 7.49 (-1.40 to 16.38, p=0.097)
Exfumador > 5 años 44.8 (8.6) 6.43 (0.58 to 12.27, p=0.031) 4.91 (0.27 to 9.56, p=0.038)
Nunca fumador/DI 44.3 (9.6) 5.89 (0.00 to 11.77, p=0.050) 4.82 (-0.07 to 9.70, p=0.053)
valoraboca_gohai2 Excelente-muy buena 56.1 (3.3)
Buena 47.2 (7.8) -8.95 (-15.38 to -2.52, p=0.007) -9.05 (-14.63 to -3.47, p=0.002)
Justa-pobre 39.6 (8.4) -16.58 (-22.94 to -10.23, p<0.001) -14.91 (-20.33 to -9.49, p<0.001)
numdientes_gohai2 Pocos dientes (0-12) 34.7 (10.1)
Muchos dientes (13-32) 46.2 (8.1) 11.50 (7.38 to 15.61, p<0.001) 8.95 (4.68 to 13.23, p<0.001)
periodontitisB Sin pt 41.2 (10.8)
Con pt 46.4 (8.3) 5.16 (1.17 to 9.15, p=0.012) 0.05 (-3.17 to 3.27, p=0.976)
x
Number in dataframe = 100, Number in model = 91, Missing = 9, Log-likelihood = -289.14, R-squared = 0.58, Adjusted r-squared = 0.5 
tabla=df %>% finalfit(
dependent =  "sc_gohai", 
explanatory= c("sexo_s1", "edad_s1", "est_civilgohai", "escola_gohai", "fuma_gohai3", "valoraboca_gohai2", "numdientes_gohai2", "periodontitisB"
),metrics = TRUE)
knitr::kable(tabla[[1]], row.names=FALSE)
Dependent: NULL Mean (sd) Coefficient (univariable) Coefficient (multivariable)
sexo_s1 Hombre 4.3 (2.8)
Mujer 6.3 (3.0) 1.95 (0.79 to 3.11, p=0.001) 2.40 (1.37 to 3.44, p<0.001)
edad_s1 [55,74] 5.1 (3.0) 0.01 (-0.12 to 0.14, p=0.881) -0.04 (-0.13 to 0.05, p=0.422)
est_civilgohai Soltero 6.8 (3.3)
Casado 4.8 (2.9) -1.91 (-4.12 to 0.30, p=0.090) -0.65 (-2.37 to 1.08, p=0.457)
Divorciado y otros 5.6 (3.1) -1.16 (-3.71 to 1.39, p=0.368) -2.25 (-4.20 to -0.29, p=0.025)
escola_gohai Titulacion superior o técnico 4.1 (3.4)
Escuela 2° 4.7 (2.7) 0.63 (-1.00 to 2.26, p=0.445) 1.40 (0.21 to 2.58, p=0.021)
Escuela 1° o ninguno 5.9 (3.0) 1.83 (0.24 to 3.42, p=0.024) 2.37 (1.21 to 3.53, p<0.001)
fuma_gohai3 Sí 6.3 (3.3)
Exfumador de 0 a 1 año 6.0 (3.3) -0.27 (-3.64 to 3.11, p=0.876) 1.47 (-1.11 to 4.05, p=0.261)
Exfumador de 1 a 5 años 4.0 (4.0) -2.27 (-6.06 to 1.53, p=0.239) -2.63 (-5.36 to 0.10, p=0.059)
Exfumador > 5 años 4.7 (2.7) -1.59 (-3.41 to 0.23, p=0.085) -1.37 (-2.80 to 0.06, p=0.060)
Nunca fumador/DI 5.1 (3.2) -1.14 (-2.96 to 0.69, p=0.221) -1.38 (-2.88 to 0.12, p=0.071)
valoraboca_gohai2 Excelente-muy buena 1.3 (1.4)
Buena 4.0 (2.6) 2.67 (0.64 to 4.69, p=0.010) 2.68 (0.97 to 4.40, p=0.003)
Justa-pobre 6.5 (2.5) 5.21 (3.21 to 7.22, p<0.001) 4.75 (3.08 to 6.41, p<0.001)
numdientes_gohai2 Pocos dientes (0-12) 7.7 (2.7)
Muchos dientes (13-32) 4.4 (2.7) -3.34 (-4.63 to -2.05, p<0.001) -2.83 (-4.14 to -1.51, p<0.001)
periodontitisB Sin pt 5.9 (3.2)
Con pt 4.3 (2.7) -1.62 (-2.86 to -0.37, p=0.011) 0.07 (-0.92 to 1.06, p=0.893)
x
Number in dataframe = 100, Number in model = 91, Missing = 9, Log-likelihood = -181.84, R-squared = 0.62, Adjusted r-squared = 0.55

Tabla 7

tabla=df %>% finalfit(
dependent =  "add_gohai", 
explanatory= c("sexo_s1", "edad_s1", "est_civilgohai", "escola_gohai", "fuma_gohai2", "valoraboca_gohai2", "numdientes_gohai2", "periodontitisB"
),metrics = TRUE)
knitr::kable(tabla[[1]], row.names=FALSE)
Dependent: NULL Mean (sd) Coefficient (univariable) Coefficient (multivariable)
sexo_s1 Hombre 45.6 (9.4)
Mujer 40.9 (9.8) -4.66 (-8.52 to -0.80, p=0.019) -5.08 (-8.33 to -1.82, p=0.003)
edad_s1 [55,74] 43.6 (9.8) 0.07 (-0.34 to 0.48, p=0.734) 0.14 (-0.16 to 0.44, p=0.346)
est_civilgohai Soltero 36.8 (10.9)
Casado 44.8 (9.2) 8.02 (0.92 to 15.12, p=0.027) 2.87 (-2.73 to 8.47, p=0.311)
Divorciado y otros 41.9 (10.8) 5.19 (-2.99 to 13.37, p=0.211) 6.35 (0.07 to 12.62, p=0.047)
escola_gohai Titulacion superior o técnico 46.3 (11.4)
Escuela 2° 45.1 (8.2) -1.22 (-6.53 to 4.09, p=0.650) -3.19 (-7.00 to 0.62, p=0.099)
Escuela 1° o ninguno 41.2 (10.0) -5.11 (-10.29 to 0.07, p=0.053) -6.58 (-10.33 to -2.84, p=0.001)
fuma_gohai2 Fumador NA (NA)
Ex fumador 38.4 (12.5)
Nunca ha fumado /DI 44.8 (8.6) 6.41 (0.74 to 12.08, p=0.027) 4.53 (-0.02 to 9.09, p=0.051)
3 44.3 (9.6) 5.89 (0.06 to 11.72, p=0.048) 4.51 (-0.36 to 9.39, p=0.069)
valoraboca_gohai2 Excelente-muy buena 56.1 (3.3)
Buena 47.2 (7.8) -8.95 (-15.38 to -2.52, p=0.007) -9.42 (-14.93 to -3.90, p=0.001)
Justa-pobre 39.6 (8.4) -16.58 (-22.94 to -10.23, p<0.001) -15.34 (-20.72 to -9.96, p<0.001)
numdientes_gohai2 Pocos dientes (0-12) 34.7 (10.1)
Muchos dientes (13-32) 46.2 (8.1) 11.50 (7.38 to 15.61, p<0.001) 8.49 (4.25 to 12.73, p<0.001)
periodontitisB Sin pt 41.2 (10.8)
Con pt 46.4 (8.3) 5.16 (1.17 to 9.15, p=0.012) 0.45 (-2.73 to 3.62, p=0.780)
x
Number in dataframe = 100, Number in model = 91, Missing = 9, Log-likelihood = -290.58, R-squared = 0.57, Adjusted r-squared = 0.5 
tabla=df %>% finalfit(
dependent =  "sc_gohai", 
explanatory= c("sexo_s1", "edad_s1", "est_civilgohai", "escola_gohai", "fuma_gohai2", "valoraboca_gohai2", "numdientes_gohai2", "periodontitisB"
),metrics = TRUE)
knitr::kable(tabla[[1]], row.names=FALSE)
Dependent: NULL Mean (sd) Coefficient (univariable) Coefficient (multivariable)
sexo_s1 Hombre 4.3 (2.8)
Mujer 6.3 (3.0) 1.95 (0.79 to 3.11, p=0.001) 2.10 (1.07 to 3.12, p<0.001)
edad_s1 [55,74] 5.1 (3.0) 0.01 (-0.12 to 0.14, p=0.881) -0.03 (-0.13 to 0.06, p=0.500)
est_civilgohai Soltero 6.8 (3.3)
Casado 4.8 (2.9) -1.91 (-4.12 to 0.30, p=0.090) -0.66 (-2.43 to 1.11, p=0.457)
Divorciado y otros 5.6 (3.1) -1.16 (-3.71 to 1.39, p=0.368) -2.07 (-4.06 to -0.09, p=0.041)
escola_gohai Titulacion superior o técnico 4.1 (3.4)
Escuela 2° 4.7 (2.7) 0.63 (-1.00 to 2.26, p=0.445) 1.24 (0.04 to 2.44, p=0.044)
Escuela 1° o ninguno 5.9 (3.0) 1.83 (0.24 to 3.42, p=0.024) 2.21 (1.03 to 3.39, p<0.001)
fuma_gohai2 Fumador NA (NA)
Ex fumador 6.3 (3.3)
Nunca ha fumado /DI 4.7 (2.8) -1.52 (-3.29 to 0.25, p=0.091) -1.17 (-2.61 to 0.27, p=0.110)
3 5.1 (3.2) -1.14 (-2.95 to 0.68, p=0.219) -1.23 (-2.77 to 0.31, p=0.117)
valoraboca_gohai2 Excelente-muy buena 1.3 (1.4)
Buena 4.0 (2.6) 2.67 (0.64 to 4.69, p=0.010) 2.86 (1.12 to 4.61, p=0.002)
Justa-pobre 6.5 (2.5) 5.21 (3.21 to 7.22, p<0.001) 4.96 (3.26 to 6.66, p<0.001)
numdientes_gohai2 Pocos dientes (0-12) 7.7 (2.7)
Muchos dientes (13-32) 4.4 (2.7) -3.34 (-4.63 to -2.05, p<0.001) -2.59 (-3.93 to -1.25, p<0.001)
periodontitisB Sin pt 5.9 (3.2)
Con pt 4.3 (2.7) -1.62 (-2.86 to -0.37, p=0.011) -0.13 (-1.13 to 0.87, p=0.792)
x
Number in dataframe = 100, Number in model = 91, Missing = 9, Log-likelihood = -185.7, R-squared = 0.59, Adjusted r-squared = 0.52

Tablas 6 y 7 según las instrucciones del 28 de mayo de 2019

Tabla 6

Tengo que quitar “periodontitisB”, pues está demasiado relacionada con otras que ya están ahí presentes, como sangra_gohai

tabla=df %>% finalfit(
dependent =  "add_gohai", 
explanatory= c("valoraboca_gohai2", "numdientes_gohai2", "obtu_gohai2", "caries_gohai2", "dent1_protesis",  "sangra_gohai"
),metrics = TRUE)
knitr::kable(tabla[[1]], row.names=FALSE)
Dependent: NULL Mean (sd) Coefficient (univariable) Coefficient (multivariable)
valoraboca_gohai2 Excelente-muy buena 56.1 (3.3)
Buena 47.2 (7.8) -8.95 (-15.38 to -2.52, p=0.007) -9.59 (-15.21 to -3.97, p=0.001)
Justa-pobre 39.6 (8.4) -16.58 (-22.94 to -10.23, p<0.001) -16.27 (-21.84 to -10.69, p<0.001)
numdientes_gohai2 Pocos dientes (0-12) 34.7 (10.1)
Muchos dientes (13-32) 46.2 (8.1) 11.50 (7.38 to 15.61, p<0.001) 8.13 (3.89 to 12.36, p<0.001)
obtu_gohai2 Sin obt 29.0 (NA)
Con obt 44.1 (9.2) 15.12 (-3.28 to 33.53, p=0.106) 3.66 (-10.24 to 17.57, p=0.602)
caries_gohai2 No 43.2 (10.5)
Sí 44.9 (8.1) 1.67 (-2.06 to 5.39, p=0.377) 0.43 (-2.47 to 3.34, p=0.768)
dent1_protesis No 47.0 (8.8)
Si 40.4 (8.7) -6.67 (-10.19 to -3.15, p<0.001) -1.63 (-4.96 to 1.71, p=0.336)
sangra_gohai No 44.1 (9.5)
Sí 42.9 (8.0) -1.19 (-7.12 to 4.74, p=0.691) -0.20 (-4.68 to 4.27, p=0.928)
x
Number in dataframe = 100, Number in model = 97, Missing = 3, Log-likelihood = -319.23, R-squared = 0.5, Adjusted r-squared = 0.46 
tabla=df %>% finalfit(
dependent =  "sc_gohai", 
explanatory= c("valoraboca_gohai2", "numdientes_gohai2", "obtu_gohai2", "caries_gohai2", "dent1_protesis", "sangra_gohai"
),metrics = TRUE)
knitr::kable(tabla[[1]], row.names=FALSE)
Dependent: NULL Mean (sd) Coefficient (univariable) Coefficient (multivariable)
valoraboca_gohai2 Excelente-muy buena 1.3 (1.4)
Buena 4.0 (2.6) 2.67 (0.64 to 4.69, p=0.010) 2.85 (1.03 to 4.66, p=0.002)
Justa-pobre 6.5 (2.5) 5.21 (3.21 to 7.22, p<0.001) 5.05 (3.24 to 6.85, p<0.001)
numdientes_gohai2 Pocos dientes (0-12) 7.7 (2.7)
Muchos dientes (13-32) 4.4 (2.7) -3.34 (-4.63 to -2.05, p<0.001) -2.45 (-3.82 to -1.08, p=0.001)
obtu_gohai2 Sin obt 10.0 (NA)
Con obt 5.0 (2.9) -5.00 (-10.84 to 0.84, p=0.092) -1.57 (-6.07 to 2.93, p=0.489)
caries_gohai2 No 5.2 (3.3)
Sí 4.9 (2.6) -0.31 (-1.50 to 0.88, p=0.605) 0.00 (-0.93 to 0.94, p=0.993)
dent1_protesis No 4.1 (2.9)
Si 6.2 (2.7) 2.04 (0.91 to 3.16, p=0.001) 0.49 (-0.59 to 1.57, p=0.374)
sangra_gohai No 5.0 (3.0)
Sí 5.8 (2.7) 0.86 (-1.01 to 2.74, p=0.363) 0.48 (-0.97 to 1.93, p=0.511)
x
Number in dataframe = 100, Number in model = 97, Missing = 3, Log-likelihood = -209.73, R-squared = 0.49, Adjusted r-squared = 0.45

Tabla 7

tabla=df %>% finalfit(
dependent =  "add_gohai", 
explanatory= c("sexo_s1", "edad_s1","fuma_gohai2","escola_gohai", "cepilla_gohai2"
),metrics = TRUE)
knitr::kable(tabla[[1]], row.names=FALSE)
Dependent: NULL Mean (sd) Coefficient (univariable) Coefficient (multivariable)
sexo_s1 Hombre 45.6 (9.4)
Mujer 40.9 (9.8) -4.66 (-8.52 to -0.80, p=0.019) -7.52 (-11.33 to -3.70, p<0.001)
edad_s1 [55,74] 43.6 (9.8) 0.07 (-0.34 to 0.48, p=0.734) 0.07 (-0.29 to 0.43, p=0.710)
fuma_gohai2 Fumador NA (NA)
Ex fumador 38.4 (12.5)
Nunca ha fumado /DI 44.8 (8.6) 6.41 (0.74 to 12.08, p=0.027) 6.59 (1.38 to 11.79, p=0.014)
3 44.3 (9.6) 5.89 (0.06 to 11.72, p=0.048) 9.03 (3.37 to 14.69, p=0.002)
escola_gohai Titulacion superior o técnico 46.3 (11.4)
Escuela 2° 45.1 (8.2) -1.22 (-6.53 to 4.09, p=0.650) -4.00 (-8.68 to 0.68, p=0.093)
Escuela 1° o ninguno 41.2 (10.0) -5.11 (-10.29 to 0.07, p=0.053) -8.72 (-13.34 to -4.10, p<0.001)
cepilla_gohai2 No cepilla 41.7 (9.4)
Cepilla 44.2 (9.3) 2.52 (-3.39 to 8.44, p=0.399) 4.77 (-0.63 to 10.16, p=0.083)
x
Number in dataframe = 100, Number in model = 99, Missing = 1, Log-likelihood = -345.03, R-squared = 0.27, Adjusted r-squared = 0.22 
tabla=df %>% finalfit(
dependent =  "sc_gohai", 
explanatory= c("sexo_s1", "edad_s1", "fuma_gohai2","escola_gohai", "cepilla_gohai2"
),metrics = TRUE)
knitr::kable(tabla[[1]], row.names=FALSE)
Dependent: NULL Mean (sd) Coefficient (univariable) Coefficient (multivariable)
sexo_s1 Hombre 4.3 (2.8)
Mujer 6.3 (3.0) 1.95 (0.79 to 3.11, p=0.001) 2.69 (1.49 to 3.89, p<0.001)
edad_s1 [55,74] 5.1 (3.0) 0.01 (-0.12 to 0.14, p=0.881) -0.01 (-0.12 to 0.10, p=0.871)
fuma_gohai2 Fumador NA (NA)
Ex fumador 6.3 (3.3)
Nunca ha fumado /DI 4.7 (2.8) -1.52 (-3.29 to 0.25, p=0.091) -1.78 (-3.42 to -0.15, p=0.033)
3 5.1 (3.2) -1.14 (-2.95 to 0.68, p=0.219) -2.50 (-4.28 to -0.72, p=0.006)
escola_gohai Titulacion superior o técnico 4.1 (3.4)
Escuela 2° 4.7 (2.7) 0.63 (-1.00 to 2.26, p=0.445) 1.34 (-0.13 to 2.81, p=0.074)
Escuela 1° o ninguno 5.9 (3.0) 1.83 (0.24 to 3.42, p=0.024) 2.73 (1.27 to 4.18, p<0.001)
cepilla_gohai2 No cepilla 5.5 (2.8)
Cepilla 5.0 (3.0) -0.45 (-2.34 to 1.43, p=0.633) -1.28 (-2.98 to 0.42, p=0.137)
x
Number in dataframe = 100, Number in model = 99, Missing = 1, Log-likelihood = -230.48, R-squared = 0.29, Adjusted r-squared = 0.23

Tablas 6 y 7 según las instrucciones del 24 de mayo de 2019

Tabla 6

tabla=df %>% finalfit(
dependent =  "add_gohai", 
explanatory= c("valoraboca_gohai2", "numdientes_gohai2", "obtu_gohai", "caries_gohai", "periodontitisB", "dent5_prot"
),metrics = TRUE)
knitr::kable(tabla[[1]], row.names=FALSE)
Dependent: NULL Mean (sd) Coefficient (univariable) Coefficient (multivariable)
valoraboca_gohai2 Excelente-muy buena 56.1 (3.3)
Buena 47.2 (7.8) -8.95 (-15.38 to -2.52, p=0.007) -9.38 (-15.37 to -3.39, p=0.003)
Justa-pobre 39.6 (8.4) -16.58 (-22.94 to -10.23, p<0.001) -15.86 (-21.73 to -9.98, p<0.001)
numdientes_gohai2 Pocos dientes (0-12) 34.7 (10.1)
Muchos dientes (13-32) 46.2 (8.1) 11.50 (7.38 to 15.61, p<0.001) 7.91 (2.02 to 13.79, p=0.009)
obtu_gohai < 1 obtu 39.7 (9.3)
2-6 obtu 44.3 (8.1) 4.55 (-0.59 to 9.70, p=0.082) -0.59 (-5.25 to 4.06, p=0.801)
>7 obtu 46.8 (8.8) 7.04 (3.07 to 11.01, p=0.001) 0.19 (-3.90 to 4.28, p=0.926)
caries_gohai 0-1 caries 44.0 (9.8)
2-4 caries 43.5 (10.1) -0.45 (-5.22 to 4.32, p=0.852) -1.73 (-5.50 to 2.05, p=0.365)
5 o más 45.2 (6.1) 1.17 (-3.80 to 6.13, p=0.642) -0.74 (-4.72 to 3.25, p=0.713)
periodontitisB Sin pt 41.2 (10.8)
Con pt 46.4 (8.3) 5.16 (1.17 to 9.15, p=0.012) 2.41 (-0.94 to 5.76, p=0.155)
dent5_prot No 47.1 (8.4)
Si 39.4 (8.9) -7.71 (-11.25 to -4.17, p<0.001) -0.67 (-4.69 to 3.35, p=0.740)
x
Number in dataframe = 100, Number in model = 88, Missing = 12, Log-likelihood = -289.21, R-squared = 0.47, Adjusted r-squared = 0.41 
tabla=df %>% finalfit(
dependent =  "add_gohai", 
explanatory= c("sexo_s1", "edad_s1","fuma_gohai2","escola_gohai", "cepilla_gohai", "visita_gohai"
),metrics = TRUE)
knitr::kable(tabla[[1]], row.names=FALSE)
Dependent: NULL Mean (sd) Coefficient (univariable) Coefficient (multivariable)
sexo_s1 Hombre 45.6 (9.4)
Mujer 40.9 (9.8) -4.66 (-8.52 to -0.80, p=0.019) -7.90 (-12.04 to -3.75, p<0.001)
edad_s1 [55,74] 43.6 (9.8) 0.07 (-0.34 to 0.48, p=0.734) 0.13 (-0.27 to 0.52, p=0.527)
fuma_gohai2 Fumador NA (NA)
Ex fumador 38.4 (12.5)
Nunca ha fumado /DI 44.8 (8.6) 6.41 (0.74 to 12.08, p=0.027) 6.31 (0.03 to 12.59, p=0.049)
3 44.3 (9.6) 5.89 (0.06 to 11.72, p=0.048) 8.81 (2.14 to 15.49, p=0.010)
escola_gohai Titulacion superior o técnico 46.3 (11.4)
Escuela 2° 45.1 (8.2) -1.22 (-6.53 to 4.09, p=0.650) -4.99 (-10.06 to 0.08, p=0.053)
Escuela 1° o ninguno 41.2 (10.0) -5.11 (-10.29 to 0.07, p=0.053) -9.19 (-14.30 to -4.08, p=0.001)
cepilla_gohai 0-1 vez 41.7 (9.4)
2 veces 45.3 (8.1) 3.53 (-2.98 to 10.04, p=0.284) 5.43 (-1.13 to 11.99, p=0.103)
3 o mas 43.7 (9.9) 1.97 (-4.13 to 8.08, p=0.522) 4.50 (-1.82 to 10.81, p=0.160)
visita_gohai Nunca visita 40.8 (11.0)
1 visita 45.6 (8.2) 4.75 (0.05 to 9.44, p=0.048) 3.25 (-1.28 to 7.78, p=0.157)
2 o mas visitas 44.5 (8.5) 3.63 (-1.62 to 8.89, p=0.173) 0.46 (-4.66 to 5.57, p=0.860)
x
Number in dataframe = 100, Number in model = 86, Missing = 14, Log-likelihood = -297.31, R-squared = 0.32, Adjusted r-squared = 0.23

Tabla 7

tabla=df %>% finalfit(
dependent =  "sc_gohai", 
explanatory= c("sexo_s1", "edad_s1", " fuma_gohai2","escola_gohai", "cepilla_gohai", "visita_gohai"
),metrics = TRUE)
knitr::kable(tabla[[1]], row.names=FALSE)
Dependent: NULL Mean (sd) Coefficient (univariable) Coefficient (multivariable)
sexo_s1 Hombre 4.3 (2.8)
Mujer 6.3 (3.0) 1.95 (0.79 to 3.11, p=0.001) 2.84 (1.52 to 4.15, p<0.001)
edad_s1 [55,74] 5.1 (3.0) 0.01 (-0.12 to 0.14, p=0.881) -0.02 (-0.15 to 0.10, p=0.737)
fuma_gohai2 Fumador NA (NA)
Ex fumador 6.3 (3.3)
Nunca ha fumado /DI 4.7 (2.8) -1.52 (-3.29 to 0.25, p=0.091) -1.44 (-3.43 to 0.55, p=0.154)
3 5.1 (3.2) -1.14 (-2.95 to 0.68, p=0.219) -2.28 (-4.39 to -0.16, p=0.035)
escola_gohai Titulacion superior o técnico 4.1 (3.4)
Escuela 2° 4.7 (2.7) 0.63 (-1.00 to 2.26, p=0.445) 1.54 (-0.07 to 3.14, p=0.060)
Escuela 1° o ninguno 5.9 (3.0) 1.83 (0.24 to 3.42, p=0.024) 2.65 (1.03 to 4.27, p=0.002)
cepilla_gohai 0-1 vez 5.5 (2.8)
2 veces 4.9 (2.9) -0.58 (-2.66 to 1.49, p=0.578) -1.28 (-3.36 to 0.79, p=0.222)
3 o mas 5.1 (3.0) -0.38 (-2.33 to 1.56, p=0.696) -1.35 (-3.35 to 0.65, p=0.182)
visita_gohai Nunca visita 5.8 (3.1)
1 visita 4.7 (2.7) -1.17 (-2.66 to 0.31, p=0.121) -0.85 (-2.29 to 0.58, p=0.239)
2 o mas visitas 4.9 (3.0) -0.98 (-2.64 to 0.68, p=0.245) -0.15 (-1.77 to 1.47, p=0.854)
x
Number in dataframe = 100, Number in model = 86, Missing = 14, Log-likelihood = -198.41, R-squared = 0.3, Adjusted r-squared = 0.21

Desde aquí en adelante son todos análisis anteriores.

Análisis que corresponde a la tabla 6 tal como aparece en el borrador

tabla=df %>% finalfit(

dependent =  "add_gohai", 
explanatory= c("sexo_s1", "edad_s1","fuma_s1","escola_gohai", 
                         "valoraboca_gohai2", "periodontitisB", "numdientes_gohai2", "dent5_prot",  "dent5_dmft" 
),metrics = TRUE)


knitr::kable(tabla[[1]], row.names=FALSE)
Dependent: NULL Mean (sd) Coefficient (univariable) Coefficient (multivariable)
sexo_s1 Hombre 45.6 (9.4)
Mujer 40.9 (9.8) -4.66 (-8.52 to -0.80, p=0.019) -4.56 (-7.99 to -1.13, p=0.010)
edad_s1 [55,74] 43.6 (9.8) 0.07 (-0.34 to 0.48, p=0.734) 0.18 (-0.14 to 0.50, p=0.260)
fuma_s1 Sí 38.4 (12.5)
Exfumador de 0 a 1 año 43.0 (7.2) 4.60 (-6.26 to 15.46, p=0.403) 0.44 (-8.11 to 8.98, p=0.919)
Exfumador de 1 a 5 años 47.0 (13.0) 8.60 (-3.61 to 20.81, p=0.165) 7.78 (-1.19 to 16.76, p=0.088)
Exfumador > 5 años 44.8 (8.6) 6.43 (0.58 to 12.27, p=0.031) 5.22 (0.55 to 9.88, p=0.029)
Nunca fumador 44.3 (9.6) 5.89 (0.00 to 11.77, p=0.050) 4.28 (-0.52 to 9.08, p=0.080)
Datos insuficientes NA (NA)
escola_gohai Titulacion superior o técnico 46.3 (11.4)
Escuela 2° 45.1 (8.2) -1.22 (-6.53 to 4.09, p=0.650) -3.97 (-7.96 to 0.02, p=0.051)
Escuela 1° o ninguno 41.2 (10.0) -5.11 (-10.29 to 0.07, p=0.053) -6.98 (-10.96 to -3.00, p=0.001)
valoraboca_gohai2 Excelente-muy buena 56.1 (3.3)
Buena 47.2 (7.8) -8.95 (-15.38 to -2.52, p=0.007) -8.05 (-13.75 to -2.35, p=0.006)
Justa-pobre 39.6 (8.4) -16.58 (-22.94 to -10.23, p<0.001) -14.26 (-19.75 to -8.77, p<0.001)
periodontitisB Sin pt 41.2 (10.8)
Con pt 46.4 (8.3) 5.16 (1.17 to 9.15, p=0.012) -0.20 (-3.51 to 3.10, p=0.903)
numdientes_gohai2 Pocos dientes (0-12) 34.7 (10.1)
Muchos dientes (13-32) 46.2 (8.1) 11.50 (7.38 to 15.61, p<0.001) 7.93 (2.58 to 13.28, p=0.004)
dent5_prot No 47.1 (8.4)
Si 39.4 (8.9) -7.71 (-11.25 to -4.17, p<0.001) 1.06 (-3.19 to 5.31, p=0.621)
dent5_dmft [3,33] 44.0 (9.3) -0.40 (-0.62 to -0.19, p<0.001) -0.18 (-0.43 to 0.06, p=0.144)
x
Number in dataframe = 100, Number in model = 89, Missing = 11, Log-likelihood = -283.84, R-squared = 0.58, Adjusted r-squared = 0.5 
tabla=df %>% finalfit(

dependent =  "sc_gohai", 
explanatory= c("sexo_s1", "edad_s1","fuma_s1","escola_gohai", 
                         "valoraboca_gohai2", "periodontitisB", "numdientes_gohai2", "dent5_prot",  "dent5_dmft" 
),metrics = TRUE)


knitr::kable(tabla[[1]], row.names=FALSE)
Dependent: NULL Mean (sd) Coefficient (univariable) Coefficient (multivariable)
sexo_s1 Hombre 4.3 (2.8)
Mujer 6.3 (3.0) 1.95 (0.79 to 3.11, p=0.001) 2.00 (0.94 to 3.07, p<0.001)
edad_s1 [55,74] 5.1 (3.0) 0.01 (-0.12 to 0.14, p=0.881) -0.05 (-0.15 to 0.05, p=0.365)
fuma_s1 Sí 6.3 (3.3)
Exfumador de 0 a 1 año 6.0 (3.3) -0.27 (-3.64 to 3.11, p=0.876) 1.20 (-1.46 to 3.86, p=0.371)
Exfumador de 1 a 5 años 4.0 (4.0) -2.27 (-6.06 to 1.53, p=0.239) -2.63 (-5.42 to 0.16, p=0.065)
Exfumador > 5 años 4.7 (2.7) -1.59 (-3.41 to 0.23, p=0.085) -1.32 (-2.77 to 0.13, p=0.075)
Nunca fumador 5.1 (3.2) -1.14 (-2.96 to 0.69, p=0.221) -1.11 (-2.60 to 0.38, p=0.143)
Datos insuficientes NA (NA)
escola_gohai Titulacion superior o técnico 4.1 (3.4)
Escuela 2° 4.7 (2.7) 0.63 (-1.00 to 2.26, p=0.445) 1.46 (0.22 to 2.71, p=0.022)
Escuela 1° o ninguno 5.9 (3.0) 1.83 (0.24 to 3.42, p=0.024) 2.33 (1.09 to 3.56, p<0.001)
valoraboca_gohai2 Excelente-muy buena 1.3 (1.4)
Buena 4.0 (2.6) 2.67 (0.64 to 4.69, p=0.010) 2.30 (0.53 to 4.08, p=0.012)
Justa-pobre 6.5 (2.5) 5.21 (3.21 to 7.22, p<0.001) 4.45 (2.74 to 6.16, p<0.001)
periodontitisB Sin pt 5.9 (3.2)
Con pt 4.3 (2.7) -1.62 (-2.86 to -0.37, p=0.011) 0.10 (-0.93 to 1.12, p=0.854)
numdientes_gohai2 Pocos dientes (0-12) 7.7 (2.7)
Muchos dientes (13-32) 4.4 (2.7) -3.34 (-4.63 to -2.05, p<0.001) -2.49 (-4.15 to -0.82, p=0.004)
dent5_prot No 4.1 (2.8)
Si 6.5 (2.6) 2.44 (1.32 to 3.57, p<0.001) -0.42 (-1.74 to 0.91, p=0.534)
dent5_dmft [3,33] 5.1 (3.0) 0.12 (0.06 to 0.19, p<0.001) 0.06 (-0.02 to 0.14, p=0.134)
x
Number in dataframe = 100, Number in model = 89, Missing = 11, Log-likelihood = -179.95, R-squared = 0.61, Adjusted r-squared = 0.53
Otros análisis parecidos.

Cuando te interesa mucho una variable, como periodontitis, ajustada solo por sociodemográficas, y no tal vez el resto de variables, se puede limitar el estudio a justo lo que te interesa, como esto:

tabla=df %>% finalfit(

dependent =  "add_gohai", 
explanatory= c("sexo_s1", "edad_s1","fuma_s1","escola_gohai", 
                         "valoraboca_gohai2", "periodontitisB") 
,metrics = TRUE)


knitr::kable(tabla[[1]], row.names=FALSE)
Dependent: NULL Mean (sd) Coefficient (univariable) Coefficient (multivariable)
sexo_s1 Hombre 45.6 (9.4)
Mujer 40.9 (9.8) -4.66 (-8.52 to -0.80, p=0.019) -4.70 (-8.39 to -1.01, p=0.013)
edad_s1 [55,74] 43.6 (9.8) 0.07 (-0.34 to 0.48, p=0.734) 0.15 (-0.19 to 0.48, p=0.382)
fuma_s1 Sí 38.4 (12.5)
Exfumador de 0 a 1 año 43.0 (7.2) 4.60 (-6.26 to 15.46, p=0.403) 1.45 (-7.85 to 10.75, p=0.757)
Exfumador de 1 a 5 años 47.0 (13.0) 8.60 (-3.61 to 20.81, p=0.165) 6.17 (-3.58 to 15.92, p=0.212)
Exfumador > 5 años 44.8 (8.6) 6.43 (0.58 to 12.27, p=0.031) 3.67 (-1.27 to 8.61, p=0.143)
Nunca fumador 44.3 (9.6) 5.89 (0.00 to 11.77, p=0.050) 4.99 (-0.25 to 10.23, p=0.062)
Datos insuficientes NA (NA)
escola_gohai Titulacion superior o técnico 46.3 (11.4)
Escuela 2° 45.1 (8.2) -1.22 (-6.53 to 4.09, p=0.650) -4.11 (-8.26 to 0.04, p=0.052)
Escuela 1° o ninguno 41.2 (10.0) -5.11 (-10.29 to 0.07, p=0.053) -6.56 (-10.72 to -2.40, p=0.002)
valoraboca_gohai2 Excelente-muy buena 56.1 (3.3)
Buena 47.2 (7.8) -8.95 (-15.38 to -2.52, p=0.007) -6.40 (-12.46 to -0.33, p=0.039)
Justa-pobre 39.6 (8.4) -16.58 (-22.94 to -10.23, p<0.001) -13.44 (-19.39 to -7.50, p<0.001)
periodontitisB Sin pt 41.2 (10.8)
Con pt 46.4 (8.3) 5.16 (1.17 to 9.15, p=0.012) 2.52 (-0.84 to 5.87, p=0.139)
x
Number in dataframe = 100, Number in model = 91, Missing = 9, Log-likelihood = -301.22, R-squared = 0.45, Adjusted r-squared = 0.37 
tabla=df %>% finalfit(

dependent =  "sc_gohai", 
explanatory= c("sexo_s1", "edad_s1","fuma_s1","escola_gohai", 
                         "valoraboca_gohai2", "periodontitisB") 
,metrics = TRUE)


knitr::kable(tabla[[1]], row.names=FALSE)
Dependent: NULL Mean (sd) Coefficient (univariable) Coefficient (multivariable)
sexo_s1 Hombre 4.3 (2.8)
Mujer 6.3 (3.0) 1.95 (0.79 to 3.11, p=0.001) 2.03 (0.88 to 3.18, p=0.001)
edad_s1 [55,74] 5.1 (3.0) 0.01 (-0.12 to 0.14, p=0.881) -0.04 (-0.14 to 0.07, p=0.494)
fuma_s1 Sí 6.3 (3.3)
Exfumador de 0 a 1 año 6.0 (3.3) -0.27 (-3.64 to 3.11, p=0.876) 0.86 (-2.04 to 3.76, p=0.555)
Exfumador de 1 a 5 años 4.0 (4.0) -2.27 (-6.06 to 1.53, p=0.239) -2.12 (-5.16 to 0.92, p=0.169)
Exfumador > 5 años 4.7 (2.7) -1.59 (-3.41 to 0.23, p=0.085) -0.83 (-2.37 to 0.71, p=0.284)
Nunca fumador 5.1 (3.2) -1.14 (-2.96 to 0.69, p=0.221) -1.32 (-2.95 to 0.32, p=0.113)
Datos insuficientes NA (NA)
escola_gohai Titulacion superior o técnico 4.1 (3.4)
Escuela 2° 4.7 (2.7) 0.63 (-1.00 to 2.26, p=0.445) 1.52 (0.23 to 2.82, p=0.022)
Escuela 1° o ninguno 5.9 (3.0) 1.83 (0.24 to 3.42, p=0.024) 2.21 (0.91 to 3.51, p=0.001)
valoraboca_gohai2 Excelente-muy buena 1.3 (1.4)
Buena 4.0 (2.6) 2.67 (0.64 to 4.69, p=0.010) 1.80 (-0.10 to 3.69, p=0.063)
Justa-pobre 6.5 (2.5) 5.21 (3.21 to 7.22, p<0.001) 4.19 (2.34 to 6.04, p<0.001)
periodontitisB Sin pt 5.9 (3.2)
Con pt 4.3 (2.7) -1.62 (-2.86 to -0.37, p=0.011) -0.73 (-1.78 to 0.31, p=0.167)
x
Number in dataframe = 100, Number in model = 91, Missing = 9, Log-likelihood = -195.18, R-squared = 0.49, Adjusted r-squared = 0.42

Nuevos análisis

Tiro diag_perio3. Si una variable no tiene datos no debe usarse. Para los cálculos y pero no se sabe por qué.

tabla=df %>% finalfit(

dependent =  "add_gohai", 
explanatory= c("sexo_s1", "edad_s1","fuma_s1","escola_gohai", 
                         "valoraboca_gohai2", "periodontitisB", "numdientes_gohai2", "dent5_prot", "clasifica_obtu", "Clasifica_cpi", "perinsermedia", "perinsermax", "profsondmax", "necesita_tto", "dent1_cepilla", "dent5_dmft" 
),metrics = TRUE)


knitr::kable(tabla[[1]], row.names=FALSE)
Dependent: NULL Mean (sd) Coefficient (univariable) Coefficient (multivariable)
sexo_s1 Hombre 45.6 (9.4)
Mujer 40.9 (9.8) -4.66 (-8.52 to -0.80, p=0.019) -5.05 (-8.63 to -1.47, p=0.006)
edad_s1 [55,74] 43.6 (9.8) 0.07 (-0.34 to 0.48, p=0.734) 0.23 (-0.10 to 0.57, p=0.172)
fuma_s1 Sí 38.4 (12.5)
Exfumador de 0 a 1 año 43.0 (7.2) 4.60 (-6.26 to 15.46, p=0.403) 2.26 (-6.54 to 11.06, p=0.610)
Exfumador de 1 a 5 años 47.0 (13.0) 8.60 (-3.61 to 20.81, p=0.165) 8.19 (-1.09 to 17.47, p=0.083)
Exfumador > 5 años 44.8 (8.6) 6.43 (0.58 to 12.27, p=0.031) 5.80 (0.79 to 10.81, p=0.024)
Nunca fumador 44.3 (9.6) 5.89 (0.00 to 11.77, p=0.050) 5.03 (-0.24 to 10.30, p=0.061)
Datos insuficientes NA (NA)
escola_gohai Titulacion superior o técnico 46.3 (11.4)
Escuela 2° 45.1 (8.2) -1.22 (-6.53 to 4.09, p=0.650) -4.14 (-8.22 to -0.06, p=0.047)
Escuela 1° o ninguno 41.2 (10.0) -5.11 (-10.29 to 0.07, p=0.053) -7.34 (-11.40 to -3.29, p=0.001)
valoraboca_gohai2 Excelente-muy buena 56.1 (3.3)
Buena 47.2 (7.8) -8.95 (-15.38 to -2.52, p=0.007) -7.65 (-13.51 to -1.79, p=0.011)
Justa-pobre 39.6 (8.4) -16.58 (-22.94 to -10.23, p<0.001) -13.35 (-19.06 to -7.63, p<0.001)
periodontitisB Sin pt 41.2 (10.8)
Con pt 46.4 (8.3) 5.16 (1.17 to 9.15, p=0.012) -0.64 (-5.31 to 4.03, p=0.786)
numdientes_gohai2 Pocos dientes (0-12) 34.7 (10.1)
Muchos dientes (13-32) 46.2 (8.1) 11.50 (7.38 to 15.61, p<0.001) 9.21 (2.51 to 15.92, p=0.008)
dent5_prot No 47.1 (8.4)
Si 39.4 (8.9) -7.71 (-11.25 to -4.17, p<0.001) 0.20 (-4.20 to 4.60, p=0.929)
clasifica_obtu 0 obturadas 39.9 (10.1)
> 1 pieza obturada 45.5 (8.6) 5.66 (1.63 to 9.69, p=0.006) 1.05 (-3.08 to 5.18, p=0.614)
Clasifica_cpi cpi 0 al 4 43.2 (9.9)
cpi 5 46.6 (8.8) 3.38 (-0.69 to 7.45, p=0.102) -4.49 (-9.27 to 0.30, p=0.065)
perinsermedia [0.267,6.33] 44.5 (9.6) -1.35 (-2.90 to 0.21, p=0.088) 0.84 (-1.57 to 3.25, p=0.489)
perinsermax [2,12] 44.5 (9.6) -0.33 (-1.37 to 0.72, p=0.535) -0.44 (-1.88 to 0.99, p=0.538)
profsondmax [3,11] 44.5 (9.6) 1.29 (0.08 to 2.51, p=0.037) 1.42 (-0.47 to 3.31, p=0.139)
necesita_tto no necesita tto 39.8 (12.7)
necesita tto 44.4 (9.0) 4.61 (-0.51 to 9.73, p=0.077) -3.85 (-9.37 to 1.68, p=0.169)
dent1_cepilla [0,5] 44.0 (9.3) 0.81 (-1.22 to 2.85, p=0.431) 1.33 (-0.43 to 3.08, p=0.136)
dent5_dmft [3,33] 44.0 (9.3) -0.40 (-0.62 to -0.19, p<0.001) -0.18 (-0.45 to 0.10, p=0.197)
```
x
Number in dataframe = 100, Number in model = 89, Missing = 11, Log-likelihood = -277.99, R-squared = 0.63, Adjusted r-squared = 0.51 
tabla=df %>% finalfit(

dependent =  "sc_gohai", 
explanatory= c("sexo_s1", "edad_s1","fuma_s1","escola_gohai", 
                         "valoraboca_gohai2", "periodontitisB", "numdientes_gohai2", "dent5_prot", "clasifica_obtu", "Clasifica_cpi", "perinsermedia", "perinsermax", "profsondmax", "necesita_tto", "dent1_cepilla", "dent5_dmft" 
),metrics = TRUE)


knitr::kable(tabla[[1]], row.names=FALSE)
Dependent: NULL Mean (sd) Coefficient (univariable) Coefficient (multivariable)
sexo_s1 Hombre 4.3 (2.8)
Mujer 6.3 (3.0) 1.95 (0.79 to 3.11, p=0.001) 2.16 (1.02 to 3.31, p<0.001)
edad_s1 [55,74] 5.1 (3.0) 0.01 (-0.12 to 0.14, p=0.881) -0.05 (-0.16 to 0.06, p=0.368)
fuma_s1 Sí 6.3 (3.3)
Exfumador de 0 a 1 año 6.0 (3.3) -0.27 (-3.64 to 3.11, p=0.876) 0.92 (-1.89 to 3.74, p=0.515)
Exfumador de 1 a 5 años 4.0 (4.0) -2.27 (-6.06 to 1.53, p=0.239) -2.59 (-5.56 to 0.37, p=0.086)
Exfumador > 5 años 4.7 (2.7) -1.59 (-3.41 to 0.23, p=0.085) -1.45 (-3.05 to 0.15, p=0.075)
Nunca fumador 5.1 (3.2) -1.14 (-2.96 to 0.69, p=0.221) -1.40 (-3.08 to 0.29, p=0.103)
Datos insuficientes NA (NA)
escola_gohai Titulacion superior o técnico 4.1 (3.4)
Escuela 2° 4.7 (2.7) 0.63 (-1.00 to 2.26, p=0.445) 1.47 (0.17 to 2.78, p=0.028)
Escuela 1° o ninguno 5.9 (3.0) 1.83 (0.24 to 3.42, p=0.024) 2.30 (1.01 to 3.60, p=0.001)
valoraboca_gohai2 Excelente-muy buena 1.3 (1.4)
Buena 4.0 (2.6) 2.67 (0.64 to 4.69, p=0.010) 2.19 (0.31 to 4.06, p=0.023)
Justa-pobre 6.5 (2.5) 5.21 (3.21 to 7.22, p<0.001) 4.20 (2.37 to 6.03, p<0.001)
periodontitisB Sin pt 5.9 (3.2)
Con pt 4.3 (2.7) -1.62 (-2.86 to -0.37, p=0.011) 0.15 (-1.34 to 1.64, p=0.841)
numdientes_gohai2 Pocos dientes (0-12) 7.7 (2.7)
Muchos dientes (13-32) 4.4 (2.7) -3.34 (-4.63 to -2.05, p<0.001) -2.92 (-5.06 to -0.77, p=0.008)
dent5_prot No 4.1 (2.8)
Si 6.5 (2.6) 2.44 (1.32 to 3.57, p<0.001) -0.21 (-1.62 to 1.20, p=0.765)
clasifica_obtu 0 obturadas 6.2 (3.0)
> 1 pieza obturada 4.6 (2.8) -1.56 (-2.85 to -0.27, p=0.018) -0.41 (-1.73 to 0.91, p=0.539)
Clasifica_cpi cpi 0 al 4 5.3 (3.1)
cpi 5 4.1 (2.8) -1.23 (-2.49 to 0.04, p=0.057) 0.83 (-0.70 to 2.36, p=0.283)
perinsermedia [0.267,6.33] 4.9 (3.0) 0.38 (-0.11 to 0.87, p=0.124) -0.43 (-1.20 to 0.34, p=0.270)
perinsermax [2,12] 4.9 (3.0) 0.12 (-0.20 to 0.45, p=0.463) 0.24 (-0.21 to 0.70, p=0.292)
profsondmax [3,11] 4.9 (3.0) -0.40 (-0.78 to -0.02, p=0.041) -0.29 (-0.90 to 0.31, p=0.336)
necesita_tto no necesita tto 6.1 (3.7)
necesita tto 4.9 (2.8) -1.20 (-2.79 to 0.38, p=0.136) 0.76 (-1.01 to 2.53, p=0.394)
dent1_cepilla [0,5] 5.1 (3.0) -0.17 (-0.81 to 0.48, p=0.614) -0.32 (-0.88 to 0.24, p=0.255)
dent5_dmft [3,33] 5.1 (3.0) 0.12 (0.06 to 0.19, p<0.001) 0.06 (-0.03 to 0.15, p=0.188)
x
Number in dataframe = 100, Number in model = 89, Missing = 11, Log-likelihood = -176.55, R-squared = 0.64, Adjusted r-squared = 0.52

Tablas recientes con add_gohai

Estás son las últimas tablas. Primero con ADD_GOHAI

tabla=df %>% finalfit(dependent = "add_gohai", 
                      explanatory=c("sexo_s1", "edad_s1","fuma_s1","escola_gohai", 
                                    "valoraboca_gohai2", "periodontitisB", "numdientes_gohai2", "dent5_prot"),metrics = TRUE)  

knitr::kable(tabla[[1]], row.names=FALSE)
Dependent: NULL Mean (sd) Coefficient (univariable) Coefficient (multivariable)
sexo_s1 Hombre 45.6 (9.4)
Mujer 40.9 (9.8) -4.66 (-8.52 to -0.80, p=0.019) -4.51 (-7.97 to -1.05, p=0.011)
edad_s1 [55,74] 43.6 (9.8) 0.07 (-0.34 to 0.48, p=0.734) 0.17 (-0.16 to 0.49, p=0.308)
fuma_s1 Sí 38.4 (12.5)
Exfumador de 0 a 1 año 43.0 (7.2) 4.60 (-6.26 to 15.46, p=0.403) 0.25 (-8.36 to 8.85, p=0.954)
Exfumador de 1 a 5 años 47.0 (13.0) 8.60 (-3.61 to 20.81, p=0.165) 8.04 (-0.99 to 17.08, p=0.080)
Exfumador > 5 años 44.8 (8.6) 6.43 (0.58 to 12.27, p=0.031) 4.48 (-0.11 to 9.07, p=0.056)
Nunca fumador 44.3 (9.6) 5.89 (0.00 to 11.77, p=0.050) 4.50 (-0.33 to 9.33, p=0.067)
Datos insuficientes NA (NA)
escola_gohai Titulacion superior o técnico 46.3 (11.4)
Escuela 2° 45.1 (8.2) -1.22 (-6.53 to 4.09, p=0.650) -4.47 (-8.43 to -0.51, p=0.028)
Escuela 1° o ninguno 41.2 (10.0) -5.11 (-10.29 to 0.07, p=0.053) -7.34 (-11.32 to -3.36, p<0.001)
valoraboca_gohai2 Excelente-muy buena 56.1 (3.3)
Buena 47.2 (7.8) -8.95 (-15.38 to -2.52, p=0.007) -8.74 (-14.41 to -3.08, p=0.003)
Justa-pobre 39.6 (8.4) -16.58 (-22.94 to -10.23, p<0.001) -14.49 (-20.01 to -8.96, p<0.001)
periodontitisB Sin pt 41.2 (10.8)
Con pt 46.4 (8.3) 5.16 (1.17 to 9.15, p=0.012) -0.26 (-3.59 to 3.07, p=0.875)
numdientes_gohai2 Pocos dientes (0-12) 34.7 (10.1)
Muchos dientes (13-32) 46.2 (8.1) 11.50 (7.38 to 15.61, p<0.001) 9.07 (3.91 to 14.24, p=0.001)
dent5_prot No 47.1 (8.4)
Si 39.4 (8.9) -7.71 (-11.25 to -4.17, p<0.001) -0.21 (-4.13 to 3.71, p=0.917)
x
Number in dataframe = 100, Number in model = 89, Missing = 11, Log-likelihood = -285.14, R-squared = 0.56, Adjusted r-squared = 0.49 
tabla=df %>% finalfit(dependent = "add_gohai", 
                      explanatory=c("periodontitis", "periodontitisB", "PeriodontitisC", "piezas_presentes", "numdientes_gohai2", "dent5_prot",
                                    "valoraboca_gohai2","Frec_dentista", "Frec_cepillado", "sitios_periodontitis"),metrics = TRUE)  


knitr::kable(tabla[[1]], row.names=FALSE)
Dependent: NULL Mean (sd) Coefficient (univariable) Coefficient (multivariable)
periodontitis Sin pt (Profsondmedia<3 mm) 44.8 (9.6)
Con pt (profsondajemedia<=3mm) 42.6 (9.5) -2.22 (-7.76 to 3.31, p=0.427) -2.68 (-8.22 to 2.86, p=0.339)
periodontitisB Sin pt 41.2 (10.8)
Con pt 46.4 (8.3) 5.16 (1.17 to 9.15, p=0.012) 1.61 (-2.85 to 6.06, p=0.475)
PeriodontitisC Sin pt-pt leve 48.6 (6.3)
Pt mod 43.6 (10.5) -5.01 (-11.64 to 1.62, p=0.137) -1.27 (-7.59 to 5.05, p=0.690)
Pt severa 44.4 (9.0) -4.18 (-10.98 to 2.61, p=0.224) -1.43 (-9.13 to 6.28, p=0.713)
piezas_presentes [0,32] 43.6 (9.8) 0.55 (0.37 to 0.73, p<0.001) -0.10 (-0.58 to 0.38, p=0.684)
numdientes_gohai2 Pocos dientes (0-12) 34.7 (10.1)
Muchos dientes (13-32) 46.2 (8.1) 11.50 (7.38 to 15.61, p<0.001) 7.99 (-0.96 to 16.93, p=0.079)
dent5_prot No 47.1 (8.4)
Si 39.4 (8.9) -7.71 (-11.25 to -4.17, p<0.001) -1.43 (-6.62 to 3.77, p=0.586)
valoraboca_gohai2 Excelente-muy buena 56.1 (3.3)
Buena 47.2 (7.8) -8.95 (-15.38 to -2.52, p=0.007) -9.03 (-15.75 to -2.31, p=0.009)
Justa-pobre 39.6 (8.4) -16.58 (-22.94 to -10.23, p<0.001) -15.18 (-21.98 to -8.39, p<0.001)
Frec_dentista Nunca ha ido 41.8 (10.7)
1 vez 45.6 (8.2) 3.82 (-0.41 to 8.05, p=0.076) 0.42 (-3.41 to 4.24, p=0.828)
2 o + veces 44.2 (8.6) 2.42 (-2.56 to 7.40, p=0.337) 0.17 (-4.49 to 4.82, p=0.943)
Frec_cepillado 0 al dia 43.3 (8.2)
2 al dia 43.1 (10.2) -0.15 (-4.30 to 4.00, p=0.942) -1.06 (-5.06 to 2.95, p=0.600)
3 o + al dia 47.0 (9.1) 3.78 (-1.33 to 8.89, p=0.145) 2.12 (-2.50 to 6.73, p=0.363)
sitios_periodontitis [0,70] 44.5 (9.6) 0.06 (-0.05 to 0.17, p=0.298) 0.08 (-0.08 to 0.23, p=0.339)
x
Number in dataframe = 100, Number in model = 88, Missing = 12, Log-likelihood = -292.56, R-squared = 0.45, Adjusted r-squared = 0.34

Ahora con sc_gohai

tabla=df %>% finalfit(dependent = "sc_gohai", 
                      explanatory=c("sexo_s1", "edad_s1","fuma_s1","escola_gohai", 
                                    "valoraboca_gohai2", "periodontitisB", "numdientes_gohai2", "dent5_prot"),metrics = TRUE)  

knitr::kable(tabla[[1]], row.names=FALSE)
Dependent: NULL Mean (sd) Coefficient (univariable) Coefficient (multivariable)
sexo_s1 Hombre 4.3 (2.8)
Mujer 6.3 (3.0) 1.95 (0.79 to 3.11, p=0.001) 1.99 (0.91 to 3.07, p<0.001)
edad_s1 [55,74] 5.1 (3.0) 0.01 (-0.12 to 0.14, p=0.881) -0.04 (-0.14 to 0.06, p=0.427)
fuma_s1 Sí 6.3 (3.3)
Exfumador de 0 a 1 año 6.0 (3.3) -0.27 (-3.64 to 3.11, p=0.876) 1.26 (-1.42 to 3.94, p=0.351)
Exfumador de 1 a 5 años 4.0 (4.0) -2.27 (-6.06 to 1.53, p=0.239) -2.71 (-5.53 to 0.10, p=0.059)
Exfumador > 5 años 4.7 (2.7) -1.59 (-3.41 to 0.23, p=0.085) -1.08 (-2.51 to 0.35, p=0.136)
Nunca fumador 5.1 (3.2) -1.14 (-2.96 to 0.69, p=0.221) -1.18 (-2.68 to 0.32, p=0.123)
Datos insuficientes NA (NA)
escola_gohai Titulacion superior o técnico 4.1 (3.4)
Escuela 2° 4.7 (2.7) 0.63 (-1.00 to 2.26, p=0.445) 1.62 (0.39 to 2.86, p=0.011)
Escuela 1° o ninguno 5.9 (3.0) 1.83 (0.24 to 3.42, p=0.024) 2.44 (1.20 to 3.68, p<0.001)
valoraboca_gohai2 Excelente-muy buena 1.3 (1.4)
Buena 4.0 (2.6) 2.67 (0.64 to 4.69, p=0.010) 2.53 (0.76 to 4.29, p=0.006)
Justa-pobre 6.5 (2.5) 5.21 (3.21 to 7.22, p<0.001) 4.53 (2.80 to 6.25, p<0.001)
periodontitisB Sin pt 5.9 (3.2)
Con pt 4.3 (2.7) -1.62 (-2.86 to -0.37, p=0.011) 0.12 (-0.92 to 1.15, p=0.826)
numdientes_gohai2 Pocos dientes (0-12) 7.7 (2.7)
Muchos dientes (13-32) 4.4 (2.7) -3.34 (-4.63 to -2.05, p<0.001) -2.85 (-4.46 to -1.24, p=0.001)
dent5_prot No 4.1 (2.8)
Si 6.5 (2.6) 2.44 (1.32 to 3.57, p<0.001) -0.01 (-1.23 to 1.21, p=0.986)
x
Number in dataframe = 100, Number in model = 89, Missing = 11, Log-likelihood = -181.32, R-squared = 0.59, Adjusted r-squared = 0.52 
tabla=df %>% finalfit(dependent = "sc_gohai", 
                      explanatory=c("periodontitis", "periodontitisB", "PeriodontitisC", "piezas_presentes", "numdientes_gohai2", "dent5_prot",
                                    "valoraboca_gohai2","Frec_dentista", "Frec_cepillado", "sitios_periodontitis"),metrics = TRUE)  


knitr::kable(tabla[[1]], row.names=FALSE)
Dependent: NULL Mean (sd) Coefficient (univariable) Coefficient (multivariable)
periodontitis Sin pt (Profsondmedia<3 mm) 4.8 (3.1)
Con pt (profsondajemedia<=3mm) 5.4 (2.6) 0.55 (-1.18 to 2.28, p=0.530) 0.49 (-1.30 to 2.28, p=0.585)
periodontitisB Sin pt 5.9 (3.2)
Con pt 4.3 (2.7) -1.62 (-2.86 to -0.37, p=0.011) -0.68 (-2.12 to 0.76, p=0.348)
PeriodontitisC Sin pt-pt leve 3.4 (2.0)
Pt mod 5.3 (3.2) 1.86 (-0.20 to 3.92, p=0.076) 0.58 (-1.45 to 2.62, p=0.569)
Pt severa 4.8 (2.9) 1.43 (-0.68 to 3.54, p=0.181) 0.30 (-2.18 to 2.79, p=0.809)
piezas_presentes [0,32] 5.1 (3.0) -0.17 (-0.22 to -0.11, p<0.001) 0.01 (-0.15 to 0.16, p=0.916)
numdientes_gohai2 Pocos dientes (0-12) 7.7 (2.7)
Muchos dientes (13-32) 4.4 (2.7) -3.34 (-4.63 to -2.05, p<0.001) -2.15 (-5.04 to 0.74, p=0.142)
dent5_prot No 4.1 (2.8)
Si 6.5 (2.6) 2.44 (1.32 to 3.57, p<0.001) 0.43 (-1.25 to 2.10, p=0.614)
valoraboca_gohai2 Excelente-muy buena 1.3 (1.4)
Buena 4.0 (2.6) 2.67 (0.64 to 4.69, p=0.010) 2.59 (0.42 to 4.76, p=0.020)
Justa-pobre 6.5 (2.5) 5.21 (3.21 to 7.22, p<0.001) 4.74 (2.54 to 6.93, p<0.001)
Frec_dentista Nunca ha ido 5.6 (3.1)
1 vez 4.7 (2.8) -0.91 (-2.26 to 0.45, p=0.186) 0.13 (-1.10 to 1.37, p=0.832)
2 o + veces 4.9 (3.0) -0.67 (-2.27 to 0.92, p=0.403) 0.12 (-1.38 to 1.62, p=0.875)
Frec_cepillado 0 al dia 5.1 (2.5)
2 al dia 5.4 (3.3) 0.29 (-1.02 to 1.61, p=0.659) 0.65 (-0.64 to 1.94, p=0.319)
3 o + al dia 4.1 (3.0) -1.04 (-2.66 to 0.59, p=0.208) -0.40 (-1.89 to 1.09, p=0.597)
sitios_periodontitis [0,70] 4.9 (3.0) -0.01 (-0.05 to 0.02, p=0.432) -0.01 (-0.06 to 0.04, p=0.707)
x
Number in dataframe = 100, Number in model = 88, Missing = 12, Log-likelihood = -193.06, R-squared = 0.45, Adjusted r-squared = 0.35

Veamos ahora una comparación entre los resultados del modelo crudo y del modelo ajustado para cada variable dependiente:

#Variable dependiente: media_gohai

Primero estudiamos como variable dependiente media_gohai

tabla=df %>% finalfit(dependent = "media_gohai", 
                      explanatory=c("sexo_s1", "edad_s1","fuma_s1","escola_gohai", 
                                    "valoraboca_gohai2", "periodontitisB", "numdientes_gohai2", "dent5_prot"),metrics = TRUE)  

knitr::kable(tabla[[1]], row.names=FALSE)
Dependent: NULL Mean (sd) Coefficient (univariable) Coefficient (multivariable)
sexo_s1 Hombre 3.8 (0.8)
Mujer 3.4 (0.8) -0.39 (-0.71 to -0.07, p=0.019) -0.38 (-0.66 to -0.09, p=0.011)
edad_s1 [55,74] 3.6 (0.8) 0.01 (-0.03 to 0.04, p=0.734) 0.01 (-0.01 to 0.04, p=0.308)
fuma_s1 Sí 3.2 (1.0)
Exfumador de 0 a 1 año 3.6 (0.6) 0.38 (-0.52 to 1.29, p=0.403) 0.02 (-0.70 to 0.74, p=0.954)
Exfumador de 1 a 5 años 3.9 (1.1) 0.72 (-0.30 to 1.73, p=0.165) 0.67 (-0.08 to 1.42, p=0.080)
Exfumador > 5 años 3.7 (0.7) 0.54 (0.05 to 1.02, p=0.031) 0.37 (-0.01 to 0.76, p=0.056)
Nunca fumador 3.7 (0.8) 0.49 (0.00 to 0.98, p=0.050) 0.37 (-0.03 to 0.78, p=0.067)
Datos insuficientes NA (NA)
escola_gohai Titulacion superior o técnico 3.9 (0.9)
Escuela 2° 3.8 (0.7) -0.10 (-0.54 to 0.34, p=0.650) -0.37 (-0.70 to -0.04, p=0.028)
Escuela 1° o ninguno 3.4 (0.8) -0.43 (-0.86 to 0.01, p=0.053) -0.61 (-0.94 to -0.28, p<0.001)
valoraboca_gohai2 Excelente-muy buena 4.7 (0.3)
Buena 3.9 (0.7) -0.75 (-1.28 to -0.21, p=0.007) -0.73 (-1.20 to -0.26, p=0.003)
Justa-pobre 3.3 (0.7) -1.38 (-1.91 to -0.85, p<0.001) -1.21 (-1.67 to -0.75, p<0.001)
periodontitisB Sin pt 3.4 (0.9)
Con pt 3.9 (0.7) 0.43 (0.10 to 0.76, p=0.012) -0.02 (-0.30 to 0.26, p=0.875)
numdientes_gohai2 Pocos dientes (0-12) 2.9 (0.8)
Muchos dientes (13-32) 3.8 (0.7) 0.96 (0.62 to 1.30, p<0.001) 0.76 (0.33 to 1.19, p=0.001)
dent5_prot No 3.9 (0.7)
Si 3.3 (0.7) -0.64 (-0.94 to -0.35, p<0.001) -0.02 (-0.34 to 0.31, p=0.917)
x
Number in dataframe = 100, Number in model = 89, Missing = 11, Log-likelihood = -63.98, R-squared = 0.56, Adjusted r-squared = 0.49

Otros modelos alternativos son estos: dejo fuera “diag_perio3”, que no tiene datos y “dent1_saludBoca” que parece estar muy asociada a otra variable que ya está dentro. también va fuera dent5_dfmt que no tiene datos

tabla=df %>% finalfit(dependent = "media_gohai", 
                      explanatory=c("periodontitis", "periodontitisB", "PeriodontitisC", "piezas_presentes", "numdientes_gohai2", "dent5_prot",
                                      "valoraboca_gohai2","Frec_dentista", "Frec_cepillado", "sitios_periodontitis"),metrics = TRUE)  


knitr::kable(tabla[[1]], row.names=FALSE)
Dependent: NULL Mean (sd) Coefficient (univariable) Coefficient (multivariable)
periodontitis Sin pt (Profsondmedia<3 mm) 3.7 (0.8)
Con pt (profsondajemedia<=3mm) 3.5 (0.8) -0.19 (-0.65 to 0.28, p=0.427) -0.22 (-0.69 to 0.24, p=0.339)
periodontitisB Sin pt 3.4 (0.9)
Con pt 3.9 (0.7) 0.43 (0.10 to 0.76, p=0.012) 0.13 (-0.24 to 0.51, p=0.475)
PeriodontitisC Sin pt-pt leve 4.0 (0.5)
Pt mod 3.6 (0.9) -0.42 (-0.97 to 0.13, p=0.137) -0.11 (-0.63 to 0.42, p=0.690)
Pt severa 3.7 (0.7) -0.35 (-0.91 to 0.22, p=0.224) -0.12 (-0.76 to 0.52, p=0.713)
piezas_presentes [0,32] 3.6 (0.8) 0.05 (0.03 to 0.06, p<0.001) -0.01 (-0.05 to 0.03, p=0.684)
numdientes_gohai2 Pocos dientes (0-12) 2.9 (0.8)
Muchos dientes (13-32) 3.8 (0.7) 0.96 (0.62 to 1.30, p<0.001) 0.67 (-0.08 to 1.41, p=0.079)
dent5_prot No 3.9 (0.7)
Si 3.3 (0.7) -0.64 (-0.94 to -0.35, p<0.001) -0.12 (-0.55 to 0.31, p=0.586)
valoraboca_gohai2 Excelente-muy buena 4.7 (0.3)
Buena 3.9 (0.7) -0.75 (-1.28 to -0.21, p=0.007) -0.75 (-1.31 to -0.19, p=0.009)
Justa-pobre 3.3 (0.7) -1.38 (-1.91 to -0.85, p<0.001) -1.27 (-1.83 to -0.70, p<0.001)
Frec_dentista Nunca ha ido 3.5 (0.9)
1 vez 3.8 (0.7) 0.32 (-0.03 to 0.67, p=0.076) 0.03 (-0.28 to 0.35, p=0.828)
2 o + veces 3.7 (0.7) 0.20 (-0.21 to 0.62, p=0.337) 0.01 (-0.37 to 0.40, p=0.943)
Frec_cepillado 0 al dia 3.6 (0.7)
2 al dia 3.6 (0.8) -0.01 (-0.36 to 0.33, p=0.942) -0.09 (-0.42 to 0.25, p=0.600)
3 o + al dia 3.9 (0.8) 0.31 (-0.11 to 0.74, p=0.145) 0.18 (-0.21 to 0.56, p=0.363)
sitios_periodontitis [0,70] 3.7 (0.8) 0.00 (-0.00 to 0.01, p=0.298) 0.01 (-0.01 to 0.02, p=0.339)
x
Number in dataframe = 100, Number in model = 88, Missing = 12, Log-likelihood = -73.89, R-squared = 0.45, Adjusted r-squared = 0.34

Hay otro modelo más a estudiar:

tabla=df %>% finalfit(dependent = "media_gohai", 
                      explanatory=c("sexo_s1", "edad_s1","fuma_s1","escola_gohai", 
                                     "periodontitis",  "periodontitisB", "PeriodontitisC",
                                     "piezas_presentes", "numdientes_gohai2", "dent5_prot",
                                      "valoraboca_gohai2", "Frec_dentista", "Frec_cepillado", "sitios_periodontitis"), metrics = TRUE)  

knitr::kable(tabla[[1]], row.names=FALSE)
Dependent: NULL Mean (sd) Coefficient (univariable) Coefficient (multivariable)
sexo_s1 Hombre 3.8 (0.8)
Mujer 3.4 (0.8) -0.39 (-0.71 to -0.07, p=0.019) -0.41 (-0.73 to -0.08, p=0.015)
edad_s1 [55,74] 3.6 (0.8) 0.01 (-0.03 to 0.04, p=0.734) 0.01 (-0.02 to 0.04, p=0.389)
fuma_s1 Sí 3.2 (1.0)
Exfumador de 0 a 1 año 3.6 (0.6) 0.38 (-0.52 to 1.29, p=0.403) 0.11 (-0.66 to 0.89, p=0.774)
Exfumador de 1 a 5 años 3.9 (1.1) 0.72 (-0.30 to 1.73, p=0.165) 0.92 (0.02 to 1.82, p=0.045)
Exfumador > 5 años 3.7 (0.7) 0.54 (0.05 to 1.02, p=0.031) 0.49 (0.06 to 0.93, p=0.027)
Nunca fumador 3.7 (0.8) 0.49 (0.00 to 0.98, p=0.050) 0.51 (0.05 to 0.96, p=0.029)
Datos insuficientes NA (NA)
escola_gohai Titulacion superior o técnico 3.9 (0.9)
Escuela 2° 3.8 (0.7) -0.10 (-0.54 to 0.34, p=0.650) -0.43 (-0.80 to -0.05, p=0.026)
Escuela 1° o ninguno 3.4 (0.8) -0.43 (-0.86 to 0.01, p=0.053) -0.65 (-1.02 to -0.27, p=0.001)
periodontitis Sin pt (Profsondmedia<3 mm) 3.7 (0.8)
Con pt (profsondajemedia<=3mm) 3.5 (0.8) -0.19 (-0.65 to 0.28, p=0.427) -0.19 (-0.65 to 0.27, p=0.408)
periodontitisB Sin pt 3.4 (0.9)
Con pt 3.9 (0.7) 0.43 (0.10 to 0.76, p=0.012) -0.12 (-0.49 to 0.24, p=0.497)
PeriodontitisC Sin pt-pt leve 4.0 (0.5)
Pt mod 3.6 (0.9) -0.42 (-0.97 to 0.13, p=0.137) 0.02 (-0.48 to 0.53, p=0.923)
Pt severa 3.7 (0.7) -0.35 (-0.91 to 0.22, p=0.224) 0.08 (-0.54 to 0.70, p=0.801)
piezas_presentes [0,32] 3.6 (0.8) 0.05 (0.03 to 0.06, p<0.001) -0.00 (-0.04 to 0.04, p=0.897)
numdientes_gohai2 Pocos dientes (0-12) 2.9 (0.8)
Muchos dientes (13-32) 3.8 (0.7) 0.96 (0.62 to 1.30, p<0.001) 0.82 (0.09 to 1.56, p=0.029)
dent5_prot No 3.9 (0.7)
Si 3.3 (0.7) -0.64 (-0.94 to -0.35, p<0.001) 0.01 (-0.40 to 0.42, p=0.969)
valoraboca_gohai2 Excelente-muy buena 4.7 (0.3)
Buena 3.9 (0.7) -0.75 (-1.28 to -0.21, p=0.007) -0.64 (-1.16 to -0.12, p=0.016)
Justa-pobre 3.3 (0.7) -1.38 (-1.91 to -0.85, p<0.001) -1.17 (-1.70 to -0.64, p<0.001)
Frec_dentista Nunca ha ido 3.5 (0.9)
1 vez 3.8 (0.7) 0.32 (-0.03 to 0.67, p=0.076) -0.11 (-0.43 to 0.22, p=0.522)
2 o + veces 3.7 (0.7) 0.20 (-0.21 to 0.62, p=0.337) -0.17 (-0.54 to 0.21, p=0.378)
Frec_cepillado 0 al dia 3.6 (0.7)
2 al dia 3.6 (0.8) -0.01 (-0.36 to 0.33, p=0.942) 0.13 (-0.21 to 0.46, p=0.451)
3 o + al dia 3.9 (0.8) 0.31 (-0.11 to 0.74, p=0.145) 0.26 (-0.11 to 0.63, p=0.166)
sitios_periodontitis [0,70] 3.7 (0.8) 0.00 (-0.00 to 0.01, p=0.298) 0.01 (-0.01 to 0.02, p=0.399)
x
Number in dataframe = 100, Number in model = 88, Missing = 12, Log-likelihood = -60.53, R-squared = 0.59, Adjusted r-squared = 0.45

#Variable dependiente: media_scgohai

tabla=df %>% finalfit(dependent = "media_scgohai", 
                      explanatory=c("sexo_s1", "edad_s1","fuma_s1","escola_gohai", 
                                    "valoraboca_gohai2", "periodontitisB", "numdientes_gohai2", "dent5_prot"),metrics = TRUE)  

knitr::kable(tabla[[1]], row.names=FALSE)
Dependent: NULL Mean (sd) Coefficient (univariable) Coefficient (multivariable)
sexo_s1 Hombre 4.3 (2.8)
Mujer 6.3 (3.0) 1.95 (0.79 to 3.11, p=0.001) 1.99 (0.91 to 3.07, p<0.001)
edad_s1 [55,74] 5.1 (3.0) 0.01 (-0.12 to 0.14, p=0.881) -0.04 (-0.14 to 0.06, p=0.427)
fuma_s1 Sí 6.3 (3.3)
Exfumador de 0 a 1 año 6.0 (3.3) -0.27 (-3.64 to 3.11, p=0.876) 1.26 (-1.42 to 3.94, p=0.351)
Exfumador de 1 a 5 años 4.0 (4.0) -2.27 (-6.06 to 1.53, p=0.239) -2.71 (-5.53 to 0.10, p=0.059)
Exfumador > 5 años 4.7 (2.7) -1.59 (-3.41 to 0.23, p=0.085) -1.08 (-2.51 to 0.35, p=0.136)
Nunca fumador 5.1 (3.2) -1.14 (-2.96 to 0.69, p=0.221) -1.18 (-2.68 to 0.32, p=0.123)
Datos insuficientes NA (NA)
escola_gohai Titulacion superior o técnico 4.1 (3.4)
Escuela 2° 4.7 (2.7) 0.63 (-1.00 to 2.26, p=0.445) 1.62 (0.39 to 2.86, p=0.011)
Escuela 1° o ninguno 5.9 (3.0) 1.83 (0.24 to 3.42, p=0.024) 2.44 (1.20 to 3.68, p<0.001)
valoraboca_gohai2 Excelente-muy buena 1.3 (1.4)
Buena 4.0 (2.6) 2.67 (0.64 to 4.69, p=0.010) 2.53 (0.76 to 4.29, p=0.006)
Justa-pobre 6.5 (2.5) 5.21 (3.21 to 7.22, p<0.001) 4.53 (2.80 to 6.25, p<0.001)
periodontitisB Sin pt 5.9 (3.2)
Con pt 4.3 (2.7) -1.62 (-2.86 to -0.37, p=0.011) 0.12 (-0.92 to 1.15, p=0.826)
numdientes_gohai2 Pocos dientes (0-12) 7.7 (2.7)
Muchos dientes (13-32) 4.4 (2.7) -3.34 (-4.63 to -2.05, p<0.001) -2.85 (-4.46 to -1.24, p=0.001)
dent5_prot No 4.1 (2.8)
Si 6.5 (2.6) 2.44 (1.32 to 3.57, p<0.001) -0.01 (-1.23 to 1.21, p=0.986)
x
Number in dataframe = 100, Number in model = 89, Missing = 11, Log-likelihood = -181.32, R-squared = 0.59, Adjusted r-squared = 0.52

Otros modelos alternativos son estos: dejo fuera “diag_perio3”, que no tiene datos y “dent1_saludBoca” que parece estar muy asociada a otra variable que ya está dentro. también va fuera dent5_dfmt que no tiene datos

tabla=df %>% finalfit(dependent = "media_scgohai", 
                      explanatory=c("periodontitis", "periodontitisB", "PeriodontitisC", "piezas_presentes", "numdientes_gohai2", "dent5_prot",
                                    "valoraboca_gohai2","Frec_dentista", "Frec_cepillado", "sitios_periodontitis"),metrics = TRUE)  


knitr::kable(tabla[[1]], row.names=FALSE)
Dependent: NULL Mean (sd) Coefficient (univariable) Coefficient (multivariable)
periodontitis Sin pt (Profsondmedia<3 mm) 4.8 (3.1)
Con pt (profsondajemedia<=3mm) 5.4 (2.6) 0.55 (-1.18 to 2.28, p=0.530) 0.49 (-1.30 to 2.28, p=0.585)
periodontitisB Sin pt 5.9 (3.2)
Con pt 4.3 (2.7) -1.62 (-2.86 to -0.37, p=0.011) -0.68 (-2.12 to 0.76, p=0.348)
PeriodontitisC Sin pt-pt leve 3.4 (2.0)
Pt mod 5.3 (3.2) 1.86 (-0.20 to 3.92, p=0.076) 0.58 (-1.45 to 2.62, p=0.569)
Pt severa 4.8 (2.9) 1.43 (-0.68 to 3.54, p=0.181) 0.30 (-2.18 to 2.79, p=0.809)
piezas_presentes [0,32] 5.1 (3.0) -0.17 (-0.22 to -0.11, p<0.001) 0.01 (-0.15 to 0.16, p=0.916)
numdientes_gohai2 Pocos dientes (0-12) 7.7 (2.7)
Muchos dientes (13-32) 4.4 (2.7) -3.34 (-4.63 to -2.05, p<0.001) -2.15 (-5.04 to 0.74, p=0.142)
dent5_prot No 4.1 (2.8)
Si 6.5 (2.6) 2.44 (1.32 to 3.57, p<0.001) 0.43 (-1.25 to 2.10, p=0.614)
valoraboca_gohai2 Excelente-muy buena 1.3 (1.4)
Buena 4.0 (2.6) 2.67 (0.64 to 4.69, p=0.010) 2.59 (0.42 to 4.76, p=0.020)
Justa-pobre 6.5 (2.5) 5.21 (3.21 to 7.22, p<0.001) 4.74 (2.54 to 6.93, p<0.001)
Frec_dentista Nunca ha ido 5.6 (3.1)
1 vez 4.7 (2.8) -0.91 (-2.26 to 0.45, p=0.186) 0.13 (-1.10 to 1.37, p=0.832)
2 o + veces 4.9 (3.0) -0.67 (-2.27 to 0.92, p=0.403) 0.12 (-1.38 to 1.62, p=0.875)
Frec_cepillado 0 al dia 5.1 (2.5)
2 al dia 5.4 (3.3) 0.29 (-1.02 to 1.61, p=0.659) 0.65 (-0.64 to 1.94, p=0.319)
3 o + al dia 4.1 (3.0) -1.04 (-2.66 to 0.59, p=0.208) -0.40 (-1.89 to 1.09, p=0.597)
sitios_periodontitis [0,70] 4.9 (3.0) -0.01 (-0.05 to 0.02, p=0.432) -0.01 (-0.06 to 0.04, p=0.707)
x
Number in dataframe = 100, Number in model = 88, Missing = 12, Log-likelihood = -193.06, R-squared = 0.45, Adjusted r-squared = 0.35

Hay otro modelo más a estudiar:

tabla=df %>% finalfit(dependent = "media_scgohai", 
                      explanatory=c("sexo_s1", "edad_s1","fuma_s1","escola_gohai", 
                                    "periodontitis",  "periodontitisB", "PeriodontitisC",
                                    "piezas_presentes", "numdientes_gohai2", "dent5_prot",
                                    "valoraboca_gohai2", "Frec_dentista", "Frec_cepillado", "sitios_periodontitis"), metrics = TRUE)  

knitr::kable(tabla[[1]], row.names=FALSE)
Dependent: NULL Mean (sd) Coefficient (univariable) Coefficient (multivariable)
sexo_s1 Hombre 4.3 (2.8)
Mujer 6.3 (3.0) 1.95 (0.79 to 3.11, p=0.001) 1.99 (0.77 to 3.22, p=0.002)
edad_s1 [55,74] 5.1 (3.0) 0.01 (-0.12 to 0.14, p=0.881) -0.03 (-0.15 to 0.08, p=0.544)
fuma_s1 Sí 6.3 (3.3)
Exfumador de 0 a 1 año 6.0 (3.3) -0.27 (-3.64 to 3.11, p=0.876) 0.94 (-1.97 to 3.85, p=0.522)
Exfumador de 1 a 5 años 4.0 (4.0) -2.27 (-6.06 to 1.53, p=0.239) -3.53 (-6.91 to -0.16, p=0.041)
Exfumador > 5 años 4.7 (2.7) -1.59 (-3.41 to 0.23, p=0.085) -1.53 (-3.17 to 0.11, p=0.066)
Nunca fumador 5.1 (3.2) -1.14 (-2.96 to 0.69, p=0.221) -1.72 (-3.43 to -0.01, p=0.049)
Datos insuficientes NA (NA)
escola_gohai Titulacion superior o técnico 4.1 (3.4)
Escuela 2° 4.7 (2.7) 0.63 (-1.00 to 2.26, p=0.445) 1.83 (0.42 to 3.23, p=0.011)
Escuela 1° o ninguno 5.9 (3.0) 1.83 (0.24 to 3.42, p=0.024) 2.65 (1.24 to 4.05, p<0.001)
periodontitis Sin pt (Profsondmedia<3 mm) 4.8 (3.1)
Con pt (profsondajemedia<=3mm) 5.4 (2.6) 0.55 (-1.18 to 2.28, p=0.530) 0.18 (-1.54 to 1.90, p=0.836)
periodontitisB Sin pt 5.9 (3.2)
Con pt 4.3 (2.7) -1.62 (-2.86 to -0.37, p=0.011) 0.40 (-0.97 to 1.76, p=0.565)
PeriodontitisC Sin pt-pt leve 3.4 (2.0)
Pt mod 5.3 (3.2) 1.86 (-0.20 to 3.92, p=0.076) 0.07 (-1.82 to 1.96, p=0.942)
Pt severa 4.8 (2.9) 1.43 (-0.68 to 3.54, p=0.181) -0.30 (-2.62 to 2.02, p=0.795)
piezas_presentes [0,32] 5.1 (3.0) -0.17 (-0.22 to -0.11, p<0.001) 0.00 (-0.14 to 0.15, p=0.985)
numdientes_gohai2 Pocos dientes (0-12) 7.7 (2.7)
Muchos dientes (13-32) 4.4 (2.7) -3.34 (-4.63 to -2.05, p<0.001) -3.13 (-5.89 to -0.37, p=0.027)
dent5_prot No 4.1 (2.8)
Si 6.5 (2.6) 2.44 (1.32 to 3.57, p<0.001) -0.17 (-1.71 to 1.37, p=0.823)
valoraboca_gohai2 Excelente-muy buena 1.3 (1.4)
Buena 4.0 (2.6) 2.67 (0.64 to 4.69, p=0.010) 2.21 (0.25 to 4.16, p=0.028)
Justa-pobre 6.5 (2.5) 5.21 (3.21 to 7.22, p<0.001) 4.43 (2.44 to 6.42, p<0.001)
Frec_dentista Nunca ha ido 5.6 (3.1)
1 vez 4.7 (2.8) -0.91 (-2.26 to 0.45, p=0.186) 0.59 (-0.64 to 1.83, p=0.339)
2 o + veces 4.9 (3.0) -0.67 (-2.27 to 0.92, p=0.403) 0.73 (-0.69 to 2.14, p=0.309)
Frec_cepillado 0 al dia 5.1 (2.5)
2 al dia 5.4 (3.3) 0.29 (-1.02 to 1.61, p=0.659) -0.27 (-1.52 to 0.98, p=0.670)
3 o + al dia 4.1 (3.0) -1.04 (-2.66 to 0.59, p=0.208) -0.82 (-2.21 to 0.58, p=0.246)
sitios_periodontitis [0,70] 4.9 (3.0) -0.01 (-0.05 to 0.02, p=0.432) -0.01 (-0.05 to 0.04, p=0.765)
x
Number in dataframe = 100, Number in model = 88, Missing = 12, Log-likelihood = -176.96, R-squared = 0.62, Adjusted r-squared = 0.49