Quiz 3 Flashcards
Internal validity is defined as: the extent to which the results of a study reflect the ‘true situation’ in the study sample.
a) True
b) False
a) True
More: review the material and resources from weeks 2-4 for a more detailed understanding of internal validity. This is a key concept to understand.
Q2 while reviewing a research paper you ask questions about the ability of the research findings to applied to other people other than those included in the study. These questions are exploring the concept of:
a) internal validity
b) external validity
c) statistical significance
d) clinical significance
b) external validity
More: these questions relate to external validity (generisability) of the study results. Review your lecture notes and resources from weeks 2-3 for more on this concept. This is a key concept to understand.
Low participant response rates and losing participants during the follow up period are both examples of:
a) systematic selection bias
b) random selection bias
c) systematic measurement bias
d) random measurement bias
a) systematic selection bias
More: there were two key components required to be understood when answering this question. Firstly there is a systematic issue as the problem is NOT due to chance. Secondly, it is a selection bias/error as it is to do with the participants included in the study. The week 2-3 resources have more information on this topic.
you are performing a study that requires the blood pressure of every patient to be taken. While reviewing the data from the study you identify a potential error and test the BP cuff used and technique used to acquire the BP.
a) it will most likely result in low precision
b) it will most likely result in low accuracy
b) it will most likely result in low accuracy
More: This will most likely cause an issue with low accuracy. That is, there is a systematic error, but little random error.
Q5 confounding is a significant issue required to be considered and managed when performing health research. Write a sentence to describe what a confounder is and give 2 examples of potential confounders.
More: confounding is a mixing or muddling of the results that can occur when the relationship we are interested in is confused by the effects of something else – the confounder. A confounder must be associated with both the exposure and the outcome, but independent of both. Some examples include: age, socioeconomic status, gender, education level, ethnicity etc.
In your own words, define what a 95% confidence interval is.
More: your response should include a number of the following components: it is a range that is placed around a point estimate (i.e. odds ratio, mean height etc) in which the true result is likely to lie and a way of quantifying the amount of random error (or precision) of the result. Interpretation: with 95% confidence, the true value is between the lower and upper limits of the confidence interval. OR there is a 95% probability that the confidence interval contains the true value.
You are involved in a study that is exploring if “medication A” will improve the ability of blood to clot, compared to “medication B”. Develop a null hypothesis.
More: your statement (null hypothesis) should highlight that there is no difference between the two drugs. For example: the bleeding time (outcome) of patients taking drug A (experimental drug) will be no different to those patients taking drug B / or a placebo (control group). Your response does not need to be identical, the key point is that you have written a statement indicating that there is NO difference between the two medications.
From the answers below, select the odds ratio results that is statistically significant.
a) OR 1.070 (95% CI 0.81 - 1.42)
b) OR 0.12 (95% CI 0.01 - 17.66)
c) OR 1.20 (95% CI 0.82 - 1.75)
d) OR 2.59 (95% CI 1.09 - 6.14)
d) OR 2.59 (95% CI 1.09 - 6.14)
More: with an Odds Ratio (OR) if the confidence interval includes 1, it is considered to be not statistically significant. Review the resources from week 3 for more information on this topic.
Following the completion of an observational study the researcher rejects the null hypothesis when it is actually true. What type of error is this?
a) type II error
b) type I error
b) type I error
More: this is actually a type I error. Review the lecture notes and resources from week 3 for more information.
