In the mid 1970's, some researchers decided to do a study on the effects of smoking cessation as well as other "healthy behaviors". They sought to avoid the flaws that had plagued other epidemiological studies and, to that end, they sought to study groups that were not self selected, but rather were selected, at least in part, on a random basis. The study group was called the "Multiple Risk Factor Intervention Trial (MRFIT) Research Group".
12,866 high risk men, aged 35 to 57 years, were randomly assigned to one of two groups. One group was treated to a special intervention program, consisting of drug-care treatment for hypertension, counseling to stop cigarette smoking, and dietary advice for lowering blood cholesterol (I will call this the "special intervention" or"SI group"). The other group, which I will call the "control group", was left to smoke, eat, and have high blood pressure, without intervention.
The MRFIT Research Group rendered its first report in 1982, reflecting an average follow-up time of 7 years. To the disappointment of the researchers, there was no statistically significant difference between the mortality in the SI group, from that in the control group - despite the fact that, as a result of the nagging, the participants in the SI group significantly "improved" their health habits, i.e., stopped smoking, and lowered their blood pressure and cholesterol levels. {Multiple risk factor intervention trial, JAMA, 248, 1465-77 (1982). }
In 1990, the MRFIT group produced another report, reflecting 10.5 years of research, using the same two groups. This time, the results appeared to show a statistically significant reduction in coronary heart disease (CHD) in the intervention group, but this was attributed not to smoking cessation, but rather to reduction in hypertension 41 . It turned out that there were more deaths from ischemic heart disease in the SI group than in the control group (96 vs. 86 deaths). Moreover, there were more deaths from cancer of the respiratory and intrathoracic organs in the SI group than in the control group (66 vs. 55) {Mortality rates after 10-15 years for participants in the Multiple Risk Factors Intervention Trial, JAMA, 263, 1795-1801 (1990).}
And here are some comments on methodologies used in many of the studies that link smoking to health problems:

"As a general rule of thumb, we are looking for a relative risk of 3 or more before accepting a paper for publication." - Marcia Angell, editor of the New England Journal of Medicine"
"My basic rule is if the relative risk isn't at least 3 or 4, forget it." - Robert Temple, director of drug evaluation at the Food and Drug Administration.
In 1993 the EPA issued a report which claimed that Environmental Tobacco Smoke (ETS) caused 3,000 deaths per year. The first step in a meta analysis is identifying all of the relevant studies. The EPA located 33 studies that compared ETS exposure to lung cancer rates. The EPA selected 31 of the 33 studies. Later they rejected one of their chosen studies, bringing the total to 30. On page 3-46 of the report the EPA estimates, based on nicotine measurements in non-smokers blood, "this would translate to the equivalent of about one-fifth of a cigarette per day." {from second hand smoke} Studies that measured actual exposure by having non-smokers wear monitors indicate even this low estimate is exaggerated. Actual exposure (for people who live and/or work in smoky environments) is about six cigarettes per year. (See also the study by Oak Ridge National Laboratories.)
In 1995 The Congressional Research Service (CRS) released a review of the EPA report. The CRS pointed out that "from a group of 30 studies. . six found a statistically significant (but small) effect, 24 found no statistically significant effect and six of the 24 found a passive smoking effect opposite to the expected relationship." The EPA based their numbers on a meta analysis of just 11 studies. The analysis showed no increase in risk at the 95% confidence level. Even after excluding most of the studies, the EPA couldn't come up with 3,000 deaths, but they had already announced the results. So they doubled their margin of error. Let me repeat that, because it may seem hard to believe: After failing to achieve their pre-announced results by ignoring half of the data, they doubled their margin of error!
After juggling the numbers, The EPA came up with an RR (Relative Risk) of ETS causing lung cancer 1.19. A RR of less than 2.0 is usually written off as and insignificant result, most likely to be due to error or bias. An RR of 3.0 or higher is considered desirable. Although the EPA declared ETS was a Class A carcinogen with an RR of 1.19, in analysis of other agents they found relative risks of 2.6 and 3.0 insufficient to justify a Group A classification.

In 1998 Judge William Osteen vacated the study - declaring it null and void after extensively commentating on the shoddy way it was conducted. His decision was 92 pages long. Osteen used the term "cherry-picking" to describe he way the EPA selected their data. "First, there is evidence in the record supporting the accusation that EPA "cherry picked" its data. Without criteria for pooling studies into a meta- analysis, the court cannot determine whether the exclusion of studies likely to disprove EPA's a priori hypothesis was coincidence or intentional. Second, EPA's excluding nearly half of the available studies directly conflicts with EPA's purported purpose for analyzing the epidemiological studies and conflicts with EPA's Risk Assessment Guidelines." Osteen found other deep flaws in the the EPA's methodology. In his judgment he stated: "The record and EPA's explanations to the court make it clear that using standard methodology, EPA could not produce statistically significant results with its selected studies. Analysis conducted with a .05 significance level and 95% confidence level included relative risks of 1. Accordingly, these results did not confirm EPA's controversial a priori hypothesis. In order to confirm its hypothesis, EPA maintained its standard significance level but lowered the confidence interval to 90%. This allowed EPA to confirm its hypothesis by finding a relative risk of 1.19, albeit a very weak association. EPA's conduct raises several concerns besides whether a relative risk of 1.19 is credible evidence supporting a Group A classification. First, with such a weak showing, if even a fraction of Plaintiffs' allegations regarding study selection or methodology is true, EPA cannot show a statistically significant association between ETS and lung cancer." The following is another direct quote from Judge Osteen's decision: "In this case, EPA publicly committed to a conclusion before research had begun; excluded industry by violating the Act's procedural requirements; adjusted established procedure and scientific norms to validate the Agency's public conclusion, and aggressively utilized the Act's authority to disseminate findings to establish a de facto regulatory scheme intended to restrict Plaintiffs, products and to influence public opinion. In conducting the ETS Risk Assessment, disregarded information and made findings on selective information; did not disseminate significant epidemiologic information; deviated from its Risk Assessment Guidelines; failed to disclose important findings and reasoning; and left significant questions without answers. EPA's conduct left substantial holes in the administrative record. While so doing, produced limited evidence, then claimed the weight of the Agency's research evidence demonstrated ETS causes cancer. Gathering all relevant information, researching, and disseminating findings were subordinate to EPA's demonstrating ETS a Group A carcinogen."
[QUOTE]The World Health Organization conducted a study of Environmental Tobacco Smoke (ETS) and lung cancer in Europe. ETS is commonly referred to as Second Hand Smoke (SHS). The two terms are interchangeable.
This was a case control study using a large sample size. The purpose of the study was to provide a more precise estimate of risk, to discover any differences between different sources of ETS, and the effect of ETS exposure on different types of lung cancer. The study was conducted from twelve centers in seven European countries over a period of seven years. The participants consisted of 650 patients with lung cancer and 1542 control subjects. Patients with smoking related diseases were excluded from the control group. None of the subjects in either group had smoked more than 400 cigarettes in their lifetime. The study found no statistically significant risk existed for non-smokers who either lived or worked with smokers. The only statistically significant number was a decrease in the risk of lung cancer among the children of smokers. The study found a Relative Risk (RR) for spousal exposure of 1.16, with a Confidence Interval (CI) of .93 - 1.44. The 1.16 number is not statistically significant.