Assignment 2 – Statistical Report

Susan Quinn

Setting -I studied a group of 50 people in an exercise class. The class has a fairly even distribution of genders and ages from 20 to 60. All the people participated in the class for 30 weeks, and they may have lost weight in the process. I measured their weight at the beginning of the program and at the end of 30 weeks.

Hypotheses -1. Is age correlated with change in weight? I hypothesize that the younger a person is the greater will be his/her weight loss. 2. Is gender is associated with weight loss? I hypothesize that the women will have lost, on the average, more weight than the men.

Correlation - 1. Describe your subjective impressions from the overall mean weight loss, scatter plot, and regression line.

Overall the average weight loss of the group was about 5.8 pounds. The regression line is slightly negative and the data points are widely scattered. Age appears to be a determining factor in weight loss.
2. What is the correlation value? The correlation value is - .36.What standard are you using to decide if it is significant? I am using the .05 level of probability as my standard. A significant correlation at the .05 level of probability is .288 (This value is from Table 1, Chapter 8, The Whole Art of Deduction, using 45 degrees of freedom. The degrees of freedom are 48, but 45 is the next smaller increment on the table).Does it indicate a significant correlation? Since the obtained value (-.36) is greater than my criterion value (.288), I conclude that the correlation is significant. There is a slight relationship between age and weight loss.If the correlation is significant, is the relationship weak, strong or very strong? Since the correlation was only slightly significant, then there was a weak relationship present.3. What is your conclusion about the hypothesis and research question? Are they supported or not? I conclude that the hypothesis is supported. Since the correlation is small, and negative, then the hypothesis is supported. In regard to the research question, given that my hypothesis was supported, I conclude that there appears to be a weak relationship between age and weight loss.t-Test -1. Describe your subjective impressions from the means for men and women, the bar chart and error bars. The men lost on the average 5.1 pounds and the women lost 6.5 pounds. The bar charts show women with greater weight loss than men, but the men have a larger standard deviation as indicated by the error bars.2. What is the t-value and its associated probability? The t-value is 1.95 and the probability is .057.What standard are you using to decide if it is significant? I am using the .05 level of probability as my standard. Does it indicate a significant difference between the means for women vs. men on weight loss? Since the obtained probability (.057) is larger than my standard (.05), I conclude that the t-value does not indicate that there is a significant difference present between the means. Although the 1.4 pound difference appears large, due to the amount of variability in the data, that difference is not statstically significant. If the t-test is significant, which group lost the most weight? Since the t-value was not significant, then there was no difference between the means. The group that lost the most weight were the women.3. What is your conclusion about the hypothesis and research question? Are they supported or not? I conclude that the hypothesis was not supported. The group of women did lose more weight than the men but not significantly large enough to support the hypothesis..Since the t-test did not indicate significant differences, and the mean weight loss was not significantly larger for the women, the hypothesis was not supported. Had the results of the t-test indicated a significant difference, and the mean weight loss was larger for the women, then the hypothesis would have been supported. In regard to the research question, given that my hypothesis was not supported, I conclude that it does not appear that weight loss is a factor related to gender.
 
Copyright © 2003
  
 
Susan Quinn