Limits...
Epidemiological methods: about time.

Kraemer HC - Int J Environ Res Public Health (2009)

Bottom Line: Epidemiological studies often produce false positive results due to use of statistical approaches that either ignore or distort time.The three time-related issues of focus in this discussion are: (1) cross-sectional vs. cohort studies, (2) statistical significance vs. public health significance, and (3), how risk factors "work together" to impact public health significance.The issue of time should be central to all thinking in epidemiology research, affecting sampling, measurement, design, analysis and, perhaps most important, the interpretation of results that might influence clinical and public-health decision-making and subsequent clinical research.

View Article: PubMed Central - PubMed

Affiliation: Department of Psychiatry and Behavioral Sciences, Stanford University, 1116 Forest Avenue, Palo Alto, CA 94301, USA. hckhome@pacbell.net

ABSTRACT
Epidemiological studies often produce false positive results due to use of statistical approaches that either ignore or distort time. The three time-related issues of focus in this discussion are: (1) cross-sectional vs. cohort studies, (2) statistical significance vs. public health significance, and (3), how risk factors "work together" to impact public health significance. The issue of time should be central to all thinking in epidemiology research, affecting sampling, measurement, design, analysis and, perhaps most important, the interpretation of results that might influence clinical and public-health decision-making and subsequent clinical research.

Show MeSH

Related in: MedlinePlus

Equipotency curves comparing the locus of all points (p0, p1) with p1 > p0, the ROC plane with Odds Ratio = p1(1 − p0)/[(1 − p1)p0] and NNT = 1/(p1 − p0) = 3. (The Figure 3 here selected to be equal to (OR1/2 + 1)/(OR1/2 − 1)).
© Copyright Policy - open-access
Related In: Results  -  Collection

License 1 - License 2
getmorefigures.php?uid=PMC2819774&req=5

f3-ijerph-07-00029: Equipotency curves comparing the locus of all points (p0, p1) with p1 > p0, the ROC plane with Odds Ratio = p1(1 − p0)/[(1 − p1)p0] and NNT = 1/(p1 − p0) = 3. (The Figure 3 here selected to be equal to (OR1/2 + 1)/(OR1/2 − 1)).

Mentions: To demonstrate this and to understand why this is often so, it is necessary to put OR and SRD on comparable scales. In Figure 3 is shown the location of all pairs of probabilities (p1, p0) that would yield OR = 4 (OR = p1(1 − p0)/((1 − p1)p0)), and all pairs of probabilities that would yield SRD = 1/3 or NNT = 1/SRD = 3 (equipotency curves[43]). The same demonstration could be done for any fixed value of OR > 1, with SRD = (OR1/2 − 1)/(OR1/2 + 1) = Y (Yule’s Index).


Epidemiological methods: about time.

Kraemer HC - Int J Environ Res Public Health (2009)

Equipotency curves comparing the locus of all points (p0, p1) with p1 > p0, the ROC plane with Odds Ratio = p1(1 − p0)/[(1 − p1)p0] and NNT = 1/(p1 − p0) = 3. (The Figure 3 here selected to be equal to (OR1/2 + 1)/(OR1/2 − 1)).
© Copyright Policy - open-access
Related In: Results  -  Collection

License 1 - License 2
Show All Figures
getmorefigures.php?uid=PMC2819774&req=5

f3-ijerph-07-00029: Equipotency curves comparing the locus of all points (p0, p1) with p1 > p0, the ROC plane with Odds Ratio = p1(1 − p0)/[(1 − p1)p0] and NNT = 1/(p1 − p0) = 3. (The Figure 3 here selected to be equal to (OR1/2 + 1)/(OR1/2 − 1)).
Mentions: To demonstrate this and to understand why this is often so, it is necessary to put OR and SRD on comparable scales. In Figure 3 is shown the location of all pairs of probabilities (p1, p0) that would yield OR = 4 (OR = p1(1 − p0)/((1 − p1)p0)), and all pairs of probabilities that would yield SRD = 1/3 or NNT = 1/SRD = 3 (equipotency curves[43]). The same demonstration could be done for any fixed value of OR > 1, with SRD = (OR1/2 − 1)/(OR1/2 + 1) = Y (Yule’s Index).

Bottom Line: Epidemiological studies often produce false positive results due to use of statistical approaches that either ignore or distort time.The three time-related issues of focus in this discussion are: (1) cross-sectional vs. cohort studies, (2) statistical significance vs. public health significance, and (3), how risk factors "work together" to impact public health significance.The issue of time should be central to all thinking in epidemiology research, affecting sampling, measurement, design, analysis and, perhaps most important, the interpretation of results that might influence clinical and public-health decision-making and subsequent clinical research.

View Article: PubMed Central - PubMed

Affiliation: Department of Psychiatry and Behavioral Sciences, Stanford University, 1116 Forest Avenue, Palo Alto, CA 94301, USA. hckhome@pacbell.net

ABSTRACT
Epidemiological studies often produce false positive results due to use of statistical approaches that either ignore or distort time. The three time-related issues of focus in this discussion are: (1) cross-sectional vs. cohort studies, (2) statistical significance vs. public health significance, and (3), how risk factors "work together" to impact public health significance. The issue of time should be central to all thinking in epidemiology research, affecting sampling, measurement, design, analysis and, perhaps most important, the interpretation of results that might influence clinical and public-health decision-making and subsequent clinical research.

Show MeSH
Related in: MedlinePlus