The following is an interesting summary of a study done on errors in research design: Empirical Evidence of Prevalence of Methodological Problems in Published Reports of Randomized Trials (Altman, 2002).

Failing to specify eligibility criteria

                25% of 364 reports in surgery journals

Not reporting an adequate method for generating random numbers

                68% of 206 reports in OB/GYN journals; 52% of 80 reports in general medicine journals

Not reporting the mechanism used to allocate interventions

89% of 196 reports in rheumatoid arthritis journals, 48% of 206 reports in OB/GYN Journals;  44% of 80 reports in general medicine journals

Failing to state whether blinding was used

51% of 506 in cystic fibrosis journals, 33% of 196 reports in rheumatoid arthritis journals; 38% of 68 reports in dermatology journals

Incorrect analysis of multiple observations

                63% of 196 reports in rheumatoid arthritis journals

Inadequate information on harmful consequences of interventions

                61% of 192 reports in 7 medical areas

Incorrect method of comparison of subgroups

                58% of 50 reports in general journals

References:

Altman, G. (2002, June). Poor quality medical research.  JAMA. 287(21). 2765-2767