Dear Allstat =
1. I am now reposting a shortened and sharpened version of my May enquiry in the hope that it will attract a response this time. It is posed from the perspective of a researcher who is using a sample to test hypotheses about population parameters and it excludes many other possible reasons for sampling eg exploratory.
2. In particular, I would welcome List members' advice on the likely external validity of hypotheses test results derived from `unadjusted' samples whose sampling units (firms) are, in each case, drawn from a range of industrial sectors with key characteristics that differ substantially from one another (eg glove-making and motor car manufacturing, where eg capital intensitivity and R & D levels are likely to differ greatly).
3. By `unadjusted' I mean that (in the studies I am assessing) no steps have been taken, by means of weighting or otherwise, to bring the disparate sampling units within each sample onto a common, or near common basis. While some of these studies split their overall (often random) samples into different firm-size groups, all of their sampling units are treated (usually implicitly) as equivalents. There is no separate analysis by sector subgroups, nor is any such distinction made in the reporting of the studies' findings, which most of these authors tend to claim can be generalised. One appreciates of course that, other things being equal, the ability to generalise may be enhanced by drawing the sample from more than one sector. (But a pre-condition for this might be that inter-sectoral variability/ hetereogeneity is explicitly recognised and minimised).
4. At least when survey samples are used to test population parameters, it seems
likely that, without suitable weightings or other appropriate adjustments, the apples and pears nature of sampling units in a multi-sector sample will have negative implications for external validity. I would much welcome Listers advice on this issue. It would also be useful to have some scholarly references.
With advance thanks =