AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |
Back to Blog
![]() These findings indicate that both age and gender have an impact on BMI, because the older group has higher BMIs than the younger group, while males consistently have higher BMIs than the females. The investigator suspected that gender might also be a confounding factor, and when she identified males and females, the graph looked like this: She first identifies which subjects who are older than 20 years old, and it turns out that the younger subjects and older subjects are clustered in the scatter plot, as shown in the figure below. While this is discouraging, the investigator considers that it is possible that confounding by age and/or gender is masking the true relationship between "diet score" and BMI. The graph below shows the relationship between the new "diet score" and BMI, and it suggests that the "diet score" is not a very good predictor, (i.e., there is little if any association between the two. Information is collected from a small sample of subjects in order to compute their "diet score," and the weight and height of each subject is measured in order to compute their BMI. The investigator wanted to test this new "diet score" to determine how closely it was associated with actual measurements of BMI. Suppose an investigator had developed a scoring system that enabled her to predict an individual's body mass index (BMI) based on information about what they ate and how much. To provide an intuitive understanding of how multiple linear regression does this, consider the following hypothetical example. This is a very useful procedure for identifying and adjusting for confounding. However, if there were other factors (independent variables) that influenced body weight besides height (e.g., age, calorie intake, and exercise level), we might expect that the points for individual subjects would be more loosely scattered around the line, since we are only taking height into account. If height were the only determinant of body weight, we would expect that the points for individual subjects would lie close to the line. In this simple linear regression, we are examining the impact of one independent variable on the outcome. In this example, if an individual was 70 inches tall, we would predict his weight to be: ![]() We could use the equation to predict weight if we knew an individual's height. We could also describe this relationship with the equation for a line, Y = a + b(x), where 'a' is the Y-intercept and 'b' is the slope of the line. If we were to plot height (the independent or 'predictor' variable) as a function of body weight (the dependent or 'outcome' variable), we might see a very linear relationship, as illustrated below. For example, suppose that height was the only determinant of body weight. Regression analysis makes use of mathematical models to describe relationships. LaMorte, MD, PhD, MPH, Professor of Epidemiologyīoston University School of Public Health Lastly, one can compute correlations between the sensors parameter estimates to gain insight.Lisa Sullivan, Professor of Biostatistics In addition, there is a theoretical foundation for combining estimates based on their variances, while not clear if such a clear standing exists for the previously proposed method. Also, one can delete an input from a poor sensor and not blindly incorporate it. Examination of single regression suggests if more data sampling is required and for what sensor. To the extent that the expected precision produced by another sensor is very poor, either gather more observations or remove it from your list.ĮDIT: This approach has a few advantages, in addition to fast and easy, over what has been proposed. In essence for correlated sensors, we do want to combine data, but without collinearity associated issues. So weight all the results for each parameter by the inverse of its variance to the sum of 1/variance for each separate estimate obtained. ![]() Per least-squares theory, there is an associated variance on each of your estimated parameters. Run each of the six regressions separately, repeat experiment if needed to get more observations.
0 Comments
Read More
Leave a Reply. |