rename n_obs() -> nsamples()

Author: alyst

src/StructuralEquationModels.jl

@@ -82,7 +82,6 @@ include("frontend/fit/fitmeasures/BIC.jl")
 include("frontend/fit/fitmeasures/chi2.jl")
 include("frontend/fit/fitmeasures/df.jl")
 include("frontend/fit/fitmeasures/minus2ll.jl")
-include("frontend/fit/fitmeasures/n_obs.jl")
 include("frontend/fit/fitmeasures/p.jl")
 include("frontend/fit/fitmeasures/RMSEA.jl")
 include("frontend/fit/fitmeasures/n_man.jl")
@@ -165,7 +164,7 @@ export AbstractSem,
     df,
     fit_measures,
     minus2ll,
-    n_obs,
+    nsamples,
     p_value,
     RMSEA,
     n_man,

src/frontend/common.jl

@@ -45,4 +45,13 @@ parind[:param_name]
 
 See also [`params`](@ref).
 """
-param_indices(semobj) = Dict(par => i for (i, par) in enumerate(params(semobj)))
+param_indices(semobj) = Dict(par => i for (i, par) in enumerate(params(semobj)))
+
+"""
+    nsamples(semobj)
+
+Return the number of samples (observed data points).
+
+For ensemble models, return the sum over all submodels.
+"""
+function nsamples end

src/frontend/fit/SemFit.jl

@@ -48,6 +48,7 @@ end
 
 params(fit::SemFit) = params(fit.model)
 nparams(fit::SemFit) = nparams(fit.model)
+nsamples(fit::SemFit) = nsamples(fit.model)
 
 # access fields
 minimum(sem_fit::SemFit) = sem_fit.minimum

src/frontend/fit/fitmeasures/BIC.jl

@@ -3,4 +3,4 @@
 
 Return the bayesian information criterion.
 """
-BIC(sem_fit::SemFit) = minus2ll(sem_fit) + log(n_obs(sem_fit)) * nparams(sem_fit)
+BIC(sem_fit::SemFit) = minus2ll(sem_fit) + log(nsamples(sem_fit)) * nparams(sem_fit)

src/frontend/fit/fitmeasures/RMSEA.jl

@@ -6,13 +6,13 @@ Return the RMSEA.
 function RMSEA end
 
 RMSEA(sem_fit::SemFit{Mi, So, St, Mo, O} where {Mi, So, St, Mo <: AbstractSemSingle, O}) =
-    RMSEA(df(sem_fit), χ²(sem_fit), n_obs(sem_fit))
+    RMSEA(df(sem_fit), χ²(sem_fit), nsamples(sem_fit))
 
 RMSEA(sem_fit::SemFit{Mi, So, St, Mo, O} where {Mi, So, St, Mo <: SemEnsemble, O}) =
-    sqrt(length(sem_fit.model.sems)) * RMSEA(df(sem_fit), χ²(sem_fit), n_obs(sem_fit))
+    sqrt(length(sem_fit.model.sems)) * RMSEA(df(sem_fit), χ²(sem_fit), nsamples(sem_fit))
 
-function RMSEA(df, chi2, n_obs)
-    rmsea = (chi2 - df) / (n_obs * df)
+function RMSEA(df, chi2, nsamples)
+    rmsea = (chi2 - df) / (nsamples * df)
     rmsea > 0 ? nothing : rmsea = 0
     return sqrt(rmsea)
 end

src/frontend/fit/fitmeasures/chi2.jl

@@ -20,11 +20,11 @@ function χ² end
 
 # RAM + SemML
 χ²(sem_fit::SemFit, observed, imp::Union{RAM, RAMSymbolic}, optimizer, loss_ml::SemML) =
-    (n_obs(sem_fit) - 1) * (sem_fit.minimum - logdet(observed.obs_cov) - observed.n_man)
+    (nsamples(sem_fit) - 1) * (sem_fit.minimum - logdet(observed.obs_cov) - observed.n_man)
 
 # bollen, p. 115, only correct for GLS weight matrix
 χ²(sem_fit::SemFit, observed, imp::Union{RAM, RAMSymbolic}, optimizer, loss_ml::SemWLS) =
-    (n_obs(sem_fit) - 1) * sem_fit.minimum
+    (nsamples(sem_fit) - 1) * sem_fit.minimum
 
 # FIML
 function χ²(sem_fit::SemFit, observed::SemObservedMissing, imp, optimizer, loss_ml::SemFIML)
@@ -45,7 +45,7 @@ end
 function χ²(sem_fit::SemFit, model::SemEnsemble, lossfun::L) where {L <: SemWLS}
     check_ensemble_length(model)
     check_lossfun_types(model, L)
-    return (sum(n_obs.(model.sems)) - 1) * sem_fit.minimum
+    return (nsamples(model) - 1) * sem_fit.minimum
 end
 
 function χ²(sem_fit::SemFit, model::SemEnsemble, lossfun::L) where {L <: SemML}
@@ -56,7 +56,7 @@ function χ²(sem_fit::SemFit, model::SemEnsemble, lossfun::L) where {L <: SemML
         w * (logdet(m.observed.obs_cov) + m.observed.n_man) for
         (w, m) in zip(model.weights, model.sems)
     ])
-    return (sum(n_obs.(model.sems)) - 1) * F_G
+    return (nsamples(model) - 1) * F_G
 end
 
 function χ²(sem_fit::SemFit, model::SemEnsemble, lossfun::L) where {L <: SemFIML}

src/frontend/fit/fitmeasures/minus2ll.jl

@@ -25,7 +25,7 @@ minus2ll(sem_fit::SemFit, obs, imp, optimizer, args...) =
 
 # SemML ------------------------------------------------------------------------------------
 minus2ll(minimum::Number, obs, imp::Union{RAM, RAMSymbolic}, optimizer, loss_ml::SemML) =
-    n_obs(obs) * (minimum + log(2π) * n_man(obs))
+    nsamples(obs) * (minimum + log(2π) * n_man(obs))
 
 # WLS --------------------------------------------------------------------------------------
 minus2ll(minimum::Number, obs, imp::Union{RAM, RAMSymbolic}, optimizer, loss_ml::SemWLS) =
@@ -41,8 +41,8 @@ function minus2ll(
     loss_ml::SemFIML,
 )
     F = minimum
-    F *= n_obs(observed)
-    F += sum(log(2π) * observed.pattern_n_obs .* observed.pattern_nvar_obs)
+    F *= nsamples(observed)
+    F += sum(log(2π) * observed.pattern_nsamples .* observed.pattern_nvar_obs)
     return F
 end
 
@@ -53,25 +53,25 @@ function minus2ll(observed::SemObservedMissing)
         minus2ll(
             observed.em_model.μ,
             observed.em_model.Σ,
-            observed.n_obs,
+            nsamples(observed),
             observed.rows,
             observed.patterns,
             observed.obs_mean,
             observed.obs_cov,
-            observed.pattern_n_obs,
+            observed.pattern_nsamples,
             observed.pattern_nvar_obs,
         )
     else
         em_mvn(observed)
         minus2ll(
             observed.em_model.μ,
             observed.em_model.Σ,
-            observed.n_obs,
+            nsamples(observed),
             observed.rows,
             observed.patterns,
             observed.obs_mean,
             observed.obs_cov,
-            observed.pattern_n_obs,
+            observed.pattern_nsamples,
             observed.pattern_nvar_obs,
         )
     end
@@ -85,13 +85,13 @@ function minus2ll(
     patterns,
     obs_mean,
     obs_cov,
-    pattern_n_obs,
+    pattern_nsamples,
     pattern_nvar_obs,
 )
     F = 0.0
 
     for i in 1:length(rows)
-        nᵢ = pattern_n_obs[i]
+        nᵢ = pattern_nsamples[i]
         # missing pattern
         pattern = patterns[i]
         # observed data
@@ -106,7 +106,7 @@ function minus2ll(
         F += F_one_pattern(meandiffᵢ, Σᵢ⁻¹, Sᵢ, ld, nᵢ)
     end
 
-    F += sum(log(2π) * pattern_n_obs .* pattern_nvar_obs)
+    F += sum(log(2π) * pattern_nsamples .* pattern_nvar_obs)
     #F *= N
 
     return F

src/frontend/fit/fitmeasures/n_obs.jl

@@ -46,13 +46,13 @@ end
 H_scaling(model::AbstractSemSingle) =
     H_scaling(model, model.observed, model.imply, model.optimizer, model.loss.functions...)
 
-H_scaling(model, obs, imp, optimizer, lossfun::SemML) = 2 / (n_obs(model) - 1)
+H_scaling(model, obs, imp, optimizer, lossfun::SemML) = 2 / (nsamples(model) - 1)
 
 function H_scaling(model, obs, imp, optimizer, lossfun::SemWLS)
     @warn "Standard errors for WLS are only correct if a GLS weight matrix (the default) is used."
-    return 2 / (n_obs(model) - 1)
+    return 2 / (nsamples(model) - 1)
 end
 
-H_scaling(model, obs, imp, optimizer, lossfun::SemFIML) = 2 / n_obs(model)
+H_scaling(model, obs, imp, optimizer, lossfun::SemFIML) = 2 / nsamples(model)
 
-H_scaling(model::SemEnsemble) = 2 / n_obs(model)
+H_scaling(model::SemEnsemble) = 2 / nsamples(model)

src/frontend/fit/standard_errors/hessian.jl

@@ -17,7 +17,7 @@ function sem_summary(
     println("No. iterations/evaluations:  $(n_iterations(sem_fit))")
     print("\n")
     println("Number of parameters:        $(nparams(sem_fit))")
-    println("Number of observations:      $(n_obs(sem_fit))")
+    println("Number of data samples:      $(nsamples(sem_fit))")
     print("\n")
     printstyled(
         "----------------------------------- Model ----------------------------------- \n";