एक सामान्य वितरण की पीडीएफ है
fμ,σ(x)=12π−−√σe−(x−μ)22σ2dx
लेकिन के मामले में यह हैτ=1/σ2
gμ,τ(x)=τ−−√2π−−√e−τ(x−μ)22dx.
एक गामा वितरण की पीडीएफ है
hα,β(τ)=1Γ(α)e−τβτ−1+αβ−αdτ.
उनका उत्पाद, आसान बीजगणित के साथ थोड़ा सरल है, इसलिए
fμ,α,β(x,τ)=1βαΓ(α)2π−−√e−τ((x−μ)22+1β)τ−1/2+αdτdx.
Its inner part evidently has the form exp(−constant1×τ)×τconstant2dτ, making it a multiple of a Gamma function when integrated over the full range τ=0 to τ=∞. That integral therefore is immediate (obtained by knowing the integral of a Gamma distribution is unity), giving the marginal distribution
fμ,α,β(x)=β−−√Γ(α+12)2π−−√Γ(α)1(β2(x−μ)2+1)α+12.
Trying to match the pattern provided for the t distribution shows there is an error in the question: the PDF for the Student t distribution actually is proportional to
1k−−√s⎛⎝⎜⎜11+k−1(x−ls)2⎞⎠⎟⎟k+12
(the power of (x−l)/s is 2, not 1). Matching the terms indicates k=2α, l=μ, and s=1/αβ−−−√.
Notice that no Calculus was needed for this derivation: everything was a matter of looking up the formulas of the Normal and Gamma PDFs, carrying out some trivial algebraic manipulations involving products and powers, and matching patterns in algebraic expressions (in that order).