We test both the unconditional and conditional Mean Variance Efficienc
y of the UK stockmarket, paying particular attention to choosing a sui
table set of instruments for the conditional version of the model. By
considering more carefully than previous authors the pricing of econom
ic risk within the mean-variance framework we show that certain instru
ments can enhance the basic model structure. Given the tendency for fi
nancial market data to display non-constancy in variance and non-norma
lity we employ the GMM procedure described in Hansen (1982), which req
uires much weaker distributional assumptions than the more traditional
OLS techniques. We discuss forming portfolios of stocks using both si
ze and dividend yield as a criterion to achieve a suitable spread of r
isk and return, acid find that our conclusions are sensitive both to t
he method of portfolio formation and to the choice of estimator. This
is an important finding given the problem of thin trading associated w
ith the size ordering of UK stocks. We find some support for both the
unconditional and conditional version of the CAPM, though we are cauti
ous about our conclusions given the instability of the parameter estim
ates.