In: Statistics and Probability
Overview
Most doctors would probably agree that a Mediterranean diet, rich
in vegetables, fruits, and grains, is healthier than a
high-saturated fat diet. Indeed, previous research has found that
the diet can lower risk of heart disease. However, there is still
considerable uncertainty about whether the Mediterranean diet is
superior to a low-fat diet recommended by the American Heart
Association. This study is the first to compare these two
diets.
The subjects, 605 survivors of a heart attack, were randomly
assigned follow either (1) a diet close to the "prudent diet step
1" of the American Heart Association (control group) or (2) a
Mediterranean-type diet consisting of more bread and cereals, more
fresh fruit and vegetables, more grains, more fish, fewer
delicatessen foods, less meat. An experimental canola-oil-based
margarine was used instead of butter or cream. The oils recommended
for salad and food preparation were canola and olive oils
exclusively. Moderate red wine consumption was allowed.
Over a four-year period, patients in the experimental condition
were initially seen by the dietician, two months later, and then
once a year. Compliance with the dietary intervention was checked
by a dietary survey and analyses of plasma fatty acids. Patients in
the control group were expected to follow the dietary advice given
by their physician.
The researchers collected information on number of deaths from cardiovascular causes e.g., heart attack, strokes, as well as number of nonfatal heart-related episodes. The occurrence of malignant and nonmalignant tumors was also carefully monitored.
Question to Answer
Is the Mediterranean diet superior to a low-fat diet recommended by
the American Heart Association?
Design Issues
The strength of the design is that subjects were randomly assigned
to conditions. A possible weakness is that compliance rates
depended on reports rather than observation since observation is
impractical in this type of research.
Descriptions of Variables
Variable | Description |
Type of diet | AHA or Mediterranean |
Various outcome measures of health and disease |
does the patient have cancer, etc.? |
Data Frequencies
Cancers | Deaths | Nonfatal illness | Healthy | Total | |
AHA |
15 | 24 | 25 | 239 | 303 |
Mediterranean |
7 | 14 | 8 | 273 | 302 |
Total |
22 | 38 | 33 | 512 | 605 |
Assignment
The following questions are to be answered on the Chapter 11 Quiz.
The percentage of people on the AHA diet had some sort of illness or death = (24 + 25)/303 =
The percentage of people on the Mediterranean diet had some sort of illness or death = (14 + 8)/302 =
The hypothesis being tested is:
H0: There is no relationship between diet and outcome
Ha: There is a relationship between diet and outcome
Col 1 | Col 2 | Col 3 | Col 4 | Total | ||
Row 1 | Observed | 15 | 24 | 25 | 239 | 303 |
Expected | 11.02 | 19.03 | 16.53 | 256.42 | 303.00 | |
O - E | 3.98 | 4.97 | 8.47 | -17.42 | 0.00 | |
(O - E)² / E | 1.44 | 1.30 | 4.34 | 1.18 | 8.26 | |
Row 2 | Observed | 7 | 14 | 8 | 273 | 302 |
Expected | 10.98 | 18.97 | 16.47 | 255.58 | 302.00 | |
O - E | -3.98 | -4.97 | -8.47 | 17.42 | 0.00 | |
(O - E)² / E | 1.44 | 1.30 | 4.36 | 1.19 | 8.29 | |
Total | Observed | 22 | 38 | 33 | 512 | 605 |
Expected | 22.00 | 38.00 | 33.00 | 512.00 | 605.00 | |
O - E | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | |
(O - E)² / E | 2.88 | 2.60 | 8.70 | 2.37 | 16.55 | |
16.55 | chi-square | |||||
3 | df | |||||
.0009 | p-value |
The test statistic is 16.55.
The p-value is 0.0009.
Since the p-value (0.0009) is less than the significance level (0.05), we can reject the null hypothesis.
Therefore, we can conclude that there is a relationship between diet and outcome.