Follow this link and read the article. http://fivethirtyeight.com/features/you-c
ID: 3452497 • Letter: F
Question
Follow this link and read the article.
http://fivethirtyeight.com/features/you-cant-trust-what-you-read-about-nutrition/
You Can’t Trust What You Read About Nutrition (Links to an external site.)Links to an external site.
We found a link between cabbage and innie bellybuttons, but that doesn’t mean it’s real.
By Christie Aschwanden (Links to an external site.)Links to an external site.
Jan 6, 2016 at 6:00 AM
QUESTIONS:
1.
"Developers of the surveys recognize that answers are imperfect, and they correct for this with validation studies that check FFQ results against those obtained via other methods, usually a 24-hour food recall or longer food diary. The results of such validation studies, Block said, allow researchers to account for variability in daily intake."
What would be the appropriate statistic to compare each participant’s estimated caloric intake via the FFQ results to each participant’s estimated caloric intake via recall of what they have eaten in the last day? SELECT ONE
A. t-test - because you have two groups and a continuous outcome measure.
B. correlation - because both variables are measured continuously.
C. Chi-square - because both variables are measured categorically.
D. ANOVA- because you have more than two groups and a continuous outcome measure.
2.
"Critics of FFQs, such as Edward Archer, a computational physiologist at the University of Alabama’s Nutrition Obesity Research Center in Birmingham, say that these validations are nothing more than circular reasoning. “You’re taking one type of subjective report and validating it with another form of subjective report,” he said."
What would be a less subjective report? SELECT ONE
A. Having the participants unobtrusively observed for one day
B. Asking the participants how confident they feel about their answers
C. Having the participants fast for one day
3.
"The problems with food questionnaires go even deeper. They aren’t just unreliable, they also produce huge data sets with many, many variables. The resulting cornucopia of possible variable combinations makes it easy to p-hack your way to sexy (and false) results, as we learned when we invited readers to take an FFQ and answer a few other questions about themselves. We ended up with 54 complete responses and then looked for associations — much as researchers look for links between foods and dreaded diseases. It was silly easy to find them.
Source: FFQ & FiveThirtyEight Supplement
The FFQ we used produced 1,066 variables, and the additional questions we asked sorted survey-takers according to 26 possible characteristics (left- or right-handed, for example). This vast data set allowed us to do 27,716 comparisons in just a few hours. With that many possibilities to examine, we were guaranteed to find some “statistically significant” correlations that aren’t real. Using a p-value of 0.05 or less as the metric for statistical significance (as is common) equates to an error rate of 5 percent. And with 27,716 comparisons, that means we should expect about 1,386 false positives.
How did they estimate that they would expect 1,386 false positives? SELECT ONE
A. It is .5% of 27,716
B. It is 5% of 27,716
C. It is .05% of 27,716
4.
This point is describing SELECT ONE
A. Construct validity
B. Internal Validity
C. Statistical Validity
D. External Validity
5.
“…our experiment found that people who trim the fat from their steaks were more likely to be atheists than those who ate the fat that god had provided for them. It’s possible that there’s a real correlation between cutting the fat from meat and being an atheist, Vieland said, but that doesn’t mean that it’s a causal one.”
Why can they not conclude that this is a causal relationship? SELECT ONE
A. Because they did not manipulate the predictor
B. None of these reasons are valid - they can conclude that this is a causal relationship
C. Because they did not start with two equal groups
D. Because they do not know which variable came first
E. All of these reasons are valid and contribute to this not being a causal relationship
6.
“For instance, a 2013 study found that people who ate three servings of nuts per week had a nearly 40 percent reduction in mortality risk . If nibbling nuts really cut the risk of dying by 40 percent, it would be revolutionary, but the figure is almost certainly an overstatement, Ioannidis told me. It’s also meaningless without context. Can a 90-year-old get the same benefits as a 60-year-old? How many days or years must you spend eating nuts for the benefits to kick in, and how long does the effect last? These are the questions that people really want answers to. But as our experiment demonstrated, it’s easy to use nutrition surveys to link foods to outcomes, yet it’s difficult to know what these connections mean.”
When we question what the connections mean, for example whether these findings would generalize to people of different ages, we are questioning the SELECT ONE
A. internal validity
B. statistical validity
C. construct validity
D. external validity
7.
“The tendency to report results as more precise and important than they are also explains why we get so many back-and-forth headlines about things like coffee. “Big data sets just confer spurious precision status to noise,” Ioannidis wrote in his 2013 analysis.”
What is an alternate way of phrasing “Big data sets just confer spurious precision status to noise? SELECT ONE
A. Making thousands of comparisons between variables means that relationships due to error will appear to be real
B. Making thousands of comparisons between variables means that you can detect relationships even if they have a very large effect size.
C. Making thousands of comparisons between variables means that relationships that are real will appear to be due to error.
D. Making thousands of comparisons between variables means that you can detect relationships even if they have a very small effect size.
Explanation / Answer
Note: This response is in UK English, please paste the response to MS Word and you should be able to spot discrepancies easily. You may elaborate the answer based on personal views or your classwork if necessary. Also, some of these options are not absolute answers but rather about choosing the best opinion. If you feel the answer might be different, you may change it.
(Answers) (1) – D – because the ANOVA test is used to determine statistically significant differences between 2 or more IVs.
(2) C – So that at least one element will not be subjective. In other words, there would be a “clean-slate” on one aspect of the study that would allow for a retest.
(3) B – 5% of 27716 is 1385.8 rounds up to 1386.
(4) A – Because this test lacks internal and external validity and construct validity is used to measure whether the construct is adequate.
(5) A – Because they cannot manipulate the predictor.
(6) D – Although this study has no validity at all, the sentences at the end of this question are directed towards the context of the variables and the study.
(7) D – it is closest to the headline.