ex3ab09 - name (required) _ Data Presentation 1. (6pts)....

Info iconThis preview shows pages 1–3. Sign up to view the full content.

View Full Document Right Arrow Icon
name (required) ___________________________ 11 Nov 2009 - 1 – of 7 Bio301D Exam 3 Data Presentation 1. (6pts). Which of the following points about the data presentation lecture and chapter are true? MTF A) A major point in this chapter/lecture is that different ways of presenting the same data can have a large influence on how people interpret or respond to the data. B) We said in class that, for example, a 50% reduction in mortality could be same as saving only 1 life per 1000 individuals. C) If an HIV test is 98% accurate, a person with a positive result normally has a 2% chance that it is a false positive. D) Lecture and the book showed that use of a log scale on a graph inflates (increases) the appearance of differences. Language of evaluation (is science logical?) 2. (6pts) The following options pertain to the concept of model falsifiability. Which are true? MTF A) We discussed a newspaper article on pet psychics. It was suggested that many of the claims of a pet psychic (about how the pet feels) are not falsifiable. B) When data are irrelevant to a model, it means the model is not falsifiable. C) If a model is not falsifiable, no data can possibly be gathered that might refute the model. D) After watching a video, we concluded that psychic phenomena applied to humans (e.g., horoscopes, palm reading) are not falsifiable. E) When doing a coin flip in class, we expected that the Probability of Heads was 0.5, even before we looked at the data. This Pr[H] = 0.5 is an example of a null model. 3 ( 6 pts ) The following points pertain to the book and lecture on ‘language’. Which statements are true? MTF A) In testing the model that smokers have at least 5-fold (5X) the lung cancer rates of non-smokers, data showing that smokers have 7 lung cancers per 1000 per year and non-smokers have 2 lung cancers per 1000 per year would be inconsistent with the model. (Ignore the possibility of sampling error.) B) In testing the model that smokers have at least 5-fold (5X) the lung cancer rates of non-smokers, data showing that heavy drinkers have 7 lung cancers per 1000 per year and non-drinkers have 2 lung cancers per 1000 per year would be inconsistent with the model. (Ignore the possibility of sampling error.) C) In science and in many aspects of society, the scientific method dictates that we adopt strict thresholds for acceptance of a model (typically rejecting the model if the probability of observing the data is less than 0.05). A model slightly below the acceptance threshold is considered just as refuted as one far below the threshold. D) If data support a model, then they are also consistent with it. E) A null model is part of every properly designed study. A study lacking a null model is not properly designed.
Background image of page 1

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
name ____________________ 11 Nov 2009 Page 2 of 6 Bio 301D exam 2 4. (8 pts) Which of the following statements describe a (non-zero) correlation? Do not choose any option that describes a zero correlation, for which a correlation is undefined, or which describes causation without
Background image of page 2
Image of page 3
This is the end of the preview. Sign up to access the rest of the document.

Page1 / 6

ex3ab09 - name (required) _ Data Presentation 1. (6pts)....

This preview shows document pages 1 - 3. Sign up to view the full document.

View Full Document Right Arrow Icon
Ask a homework question - tutors are online