Add documentation

src/HypothesisTests.jl

@@ -68,6 +68,13 @@ If `tail` is `:both` (default), then the p-value for the two-sided test is retur
 """
 function pvalue end
 
+"""
+    stderror(test::HypothesisTest)
+
+Compute the standard error for the point estimate of interest for a test. 
+"""
+function stderror end
+
 # Basic function for finding a p-value given a distribution and tail
 pvalue(dist::ContinuousUnivariateDistribution, x::Number; tail=:both) =
     if tail == :both

src/binomial.jl

@@ -45,7 +45,7 @@ probability is not equal to `p`.
 
 Computed confidence intervals ([`confint`](@ref)) by default are Clopper-Pearson intervals.
 
-Implements: [`pvalue`](@ref), [`confint(::BinomialTest)`](@ref)
+Implements: [`pvalue`](@ref), [`confint(::BinomialTest)`](@ref), [`stderror`](@ref)
 """
 BinomialTest(x::AbstractVector{Bool}, p=0.5) =
     BinomialTest(sum(x), length(x), p)

src/correlation.jl

@@ -11,7 +11,7 @@ export CorrelationTest
 Perform a t-test for the hypothesis that ``\\text{Cor}(x,y|Z=z) = 0``, i.e. the partial
 correlation of vectors `x` and `y` given the matrix `Z` is zero.
 
-Implements `pvalue` for the t-test.
+Implements `pvalue` for the t-test, as well as `stderror`. 
 Implements `confint` using an approximate confidence interval based on Fisher's
 ``z``-transform.
 

src/t.jl

@@ -79,7 +79,7 @@ Perform a one sample t-test of the null hypothesis that `n` values with mean `xb
 sample standard deviation `stddev`  come from a distribution with mean `μ0` against the
 alternative hypothesis that the distribution does not have mean `μ0`.
 
-Implements: [`pvalue`](@ref), [`confint`](@ref)
+Implements: [`pvalue`](@ref), [`confint`](@ref), [`stderror`](@ref)
 """
 function OneSampleTTest(xbar::Real, stddev::Real, n::Int, μ0::Real=0)
     stderr = stddev/sqrt(n)
@@ -95,7 +95,7 @@ Perform a one sample t-test of the null hypothesis that the data in vector `v` c
 a distribution with mean `μ0` against the alternative hypothesis that the distribution
 does not have mean `μ0`.
 
-Implements: [`pvalue`](@ref), [`confint`](@ref)
+Implements: [`pvalue`](@ref), [`confint`](@ref), [`stderror`](@ref)
 """
 OneSampleTTest(v::AbstractVector{T}, μ0::Real=0) where {T<:Real} = OneSampleTTest(mean(v), std(v), length(v), μ0)
 
@@ -106,7 +106,7 @@ Perform a paired sample t-test of the null hypothesis that the differences betwe
 values in vectors `x` and `y` come from a distribution with mean `μ0` against the
 alternative hypothesis that the distribution does not have mean `μ0`.
 
-Implements: [`pvalue`](@ref), [`confint`](@ref)
+Implements: [`pvalue`](@ref), [`confint`](@ref), [`stderror`](@ref)
 """
 function OneSampleTTest(x::AbstractVector{T}, y::AbstractVector{S}, μ0::Real=0) where {T<:Real, S<:Real}
     check_same_length(x, y)
@@ -144,7 +144,7 @@ Perform a two-sample t-test of the null hypothesis that `x` and `y` come from di
 with equal means and variances against the alternative hypothesis that the distributions
 have different means but equal variances.
 
-Implements: [`pvalue`](@ref), [`confint`](@ref)
+Implements: [`pvalue`](@ref), [`confint`](@ref), [`stderror`](@ref)
 """
 function EqualVarianceTTest(x::AbstractVector{T}, y::AbstractVector{S}, μ0::Real=0) where {T<:Real,S<:Real}
     nx, ny = length(x), length(y)
@@ -186,7 +186,7 @@ equation:
         \\frac{(k_i s_i^2)^2}{ν_i}}
 ```
 
-Implements: [`pvalue`](@ref), [`confint`](@ref)
+Implements: [`pvalue`](@ref), [`confint`](@ref), [`stderror`](@ref)
 """
 function UnequalVarianceTTest(x::AbstractVector{T}, y::AbstractVector{S}, μ0::Real=0) where {T<:Real,S<:Real}
     nx, ny = length(x), length(y)

src/z.jl

@@ -77,7 +77,7 @@ Perform a one sample z-test of the null hypothesis that `n` values with mean `xb
 population standard deviation `stddev`  come from a distribution with mean `μ0` against the
 alternative hypothesis that the distribution does not have mean `μ0`.
 
-Implements: [`pvalue`](@ref), [`confint`](@ref)
+Implements: [`pvalue`](@ref), [`confint`](@ref), [`stderror`](@ref)
 """
 function OneSampleZTest(xbar::Real, stddev::Real, n::Int, μ0::Real=0)
     stderr = stddev/sqrt(n)
@@ -92,7 +92,7 @@ Perform a one sample z-test of the null hypothesis that the data in vector `v` c
 a distribution with mean `μ0` against the alternative hypothesis that the distribution
 does not have mean `μ0`.
 
-Implements: [`pvalue`](@ref), [`confint`](@ref)
+Implements: [`pvalue`](@ref), [`confint`](@ref), [`stderror`](@ref)
 """
 OneSampleZTest(v::AbstractVector{T}, μ0::Real=0) where {T<:Real} = OneSampleZTest(mean(v), std(v), length(v), μ0)
 
@@ -103,7 +103,7 @@ Perform a paired sample z-test of the null hypothesis that the differences betwe
 values in vectors `x` and `y` come from a distribution with mean `μ0` against the
 alternative hypothesis that the distribution does not have mean `μ0`.
 
-Implements: [`pvalue`](@ref), [`confint`](@ref)
+Implements: [`pvalue`](@ref), [`confint`](@ref), [`stderror`](@ref)
 """
 function OneSampleZTest(x::AbstractVector{T}, y::AbstractVector{S}, μ0::Real=0) where {T<:Real, S<:Real}
     check_same_length(x, y)
@@ -139,7 +139,7 @@ Perform a two-sample z-test of the null hypothesis that `x` and `y` come from di
 with equal means and variances against the alternative hypothesis that the distributions
 have different means but equal variances.
 
-Implements: [`pvalue`](@ref), [`confint`](@ref)
+Implements: [`pvalue`](@ref), [`confint`](@ref), [`stderror`](@ref)
 """
 function EqualVarianceZTest(x::AbstractVector{T}, y::AbstractVector{S}, μ0::Real=0) where {T<:Real,S<:Real}
     nx, ny = length(x), length(y)
@@ -171,7 +171,7 @@ Perform an unequal variance two-sample z-test of the null hypothesis that `x` an
 from distributions with equal means against the alternative hypothesis that the
 distributions have different means.
 
-Implements: [`pvalue`](@ref), [`confint`](@ref)
+Implements: [`pvalue`](@ref), [`confint`](@ref), [`stderror`](@ref)
 """
 function UnequalVarianceZTest(x::AbstractVector{T}, y::AbstractVector{S}, μ0::Real=0) where {T<:Real,S<:Real}
     nx, ny = length(x), length(y)