00
Correct
00
Incorrect
00 : 00 : 00
Session Time
00 : 00
Average Question Time ( Mins)
• #### Question 1 - If a study has a Type I error rate of <0.05 and a...

Correct

• If a study has a Type I error rate of <0.05 and a Type II error rate of 0.2, what is the power of the study?

Explanation:

A study’s ability to correctly detect a true effect of difference may be calculated as Power = 1 – Type II error rate. In the given scenario, the power can be calculated as Power = 1 – 0.2 = 0.8. Type I error refers to a false positive, while Type II error refers to a false negative.

• This question is part of the following fields:

• Research Methods, Statistics, Critical Review And Evidence-Based Practice
3.1
Seconds
• #### Question 2 - A new medication is being developed to treat hypertension in elderly patients. Several...

Correct

• A new medication is being developed to treat hypertension in elderly patients. Several different drugs are being considered for their efficacy in reducing blood pressure. Which study design would require the largest number of participants to achieve a significant outcome?

Explanation:

Since a superiority trial involves comparing a new drug with an already existing treatment that can also reduce HbA1c levels, a substantial sample size is necessary to establish a significant distinction.

Study Designs for New Drugs: Options and Considerations

When launching a new drug, there are various study design options available. One common approach is a placebo-controlled trial, which can provide strong evidence but may be deemed unethical if established treatments are available. Additionally, it does not allow for a comparison with standard treatments. Therefore, statisticians must decide whether the trial aims to demonstrate superiority, equivalence, of non-inferiority to an existing treatment.

Superiority trials may seem like the obvious choice, but they require a large sample size to show a significant benefit over an existing treatment. Equivalence trials define an equivalence margin on a specified outcome, and if the confidence interval of the difference between the two drugs falls within this margin, the drugs are assumed to have a similar effect. Non-inferiority trials are similar to equivalence trials, but only the lower confidence interval needs to fall within the equivalence margin. These trials require smaller sample sizes, and once a drug has been shown to be non-inferior, larger studies may be conducted to demonstrate superiority.

It is important to note that drug companies may not necessarily aim to show superiority over an existing product. If they can demonstrate that their product is equivalent of even non-inferior, they may compete on price of convenience. Overall, the choice of study design depends on various factors, including ethical considerations, sample size, and the desired outcome.

• This question is part of the following fields:

• Research Methods, Statistics, Critical Review And Evidence-Based Practice
1.6
Seconds
• #### Question 3 - What is the difference in the percentage of participants who reported using non-prescription...

Incorrect

• What is the difference in the percentage of participants who reported using non-prescription opioids at six months between the treatment group and the control group, and how much of this difference can be attributed to the use of buprenorphine?

Explanation:

Absolute Rate Reduction (ARR)

The Absolute Rate Reduction (ARR) is a measure of the difference in risk between the rates of adverse outcomes in the control and experimental groups. It is calculated by subtracting the experimental event rate (EER) from the control event rate (CER). For example, if the CER is 33% and the EER is 18%, the ARR would be 15% of 0.15. This measure is useful in evaluating the effectiveness of interventions of treatments in reducing the risk of adverse outcomes.

• This question is part of the following fields:

• Research Methods, Statistics, Critical Review And Evidence-Based Practice
38
Seconds
• #### Question 4 - Which statement accurately describes bar charts? ...

Correct

• Which statement accurately describes bar charts?

Your Answer: The height of the bar indicates the frequency

Explanation:

The frequency of each category of characteristic is displayed through the height of the bars in a bar chart. When dealing with discrete data, it is typically organized into distinct categories and presented in a bar chart. On the other hand, continuous data covers a range and the categories are not separate but rather blend into one another. This type of data is best represented through a histogram, which is similar to a bar chart but with bars that are connected.

Differences between Bar Charts and Histograms

Bar charts and histograms are both used to represent data, but they differ in their application and design. Bar charts are used to summarize nominal of ordinal data, while histograms are used for quantitative data. In a bar chart, the x-axis represents categories without a scale, and the y-axis represents frequencies. The columns are of equal width, and the height of the bar indicates the frequency. On the other hand, histograms have a scale on both axes, with the y-axis representing the relative frequency of frequency density. The width of the columns in a histogram can vary, and the area of the column indicates the true frequency. Overall, bar charts and histograms are useful tools for visualizing data, but their differences in design and application make them better suited for different types of data.

• This question is part of the following fields:

• Research Methods, Statistics, Critical Review And Evidence-Based Practice
13.7
Seconds
• #### Question 5 - What methods are most effective in determining interobserver agreement? ...

Correct

• What methods are most effective in determining interobserver agreement?

Explanation:

Kappa is used to assess the consistency of reliability between different raters.

Understanding the Kappa Statistic for Measuring Interobserver Variation

The kappa statistic, also known as Cohen’s kappa coefficient, is a useful tool for quantifying the level of agreement between independent observers. This measure can be applied in any situation where multiple observers are evaluating the same thing, such as in medical diagnoses of research studies. The kappa coefficient ranges from 0 to 1, with 0 indicating complete disagreement and 1 indicating perfect agreement. By using the kappa statistic, researchers and practitioners can gain insight into the level of interobserver variation present in their data, which can help to improve the accuracy and reliability of their findings. Overall, the kappa statistic is a valuable tool for understanding and measuring interobserver variation in a variety of contexts.

• This question is part of the following fields:

• Research Methods, Statistics, Critical Review And Evidence-Based Practice
1.4
Seconds
• #### Question 6 - What is the significance of the cut off of 5 on the MDQ...

Correct

• What is the significance of the cut off of 5 on the MDQ in diagnosing depression?

Explanation:

The threshold score that results in the lowest misclassification rate, achieved by minimizing both false positive and false negative rates, is known as the optimal threshold. Based on the findings of the previous study, the ideal cut off for identifying caseness on the MDQ is five, making it the optimal threshold.

• This question is part of the following fields:

• Research Methods, Statistics, Critical Review And Evidence-Based Practice
2.4
Seconds
• #### Question 7 - A psychologist aims to conduct a qualitative study to explore the experiences of...

Correct

• A psychologist aims to conduct a qualitative study to explore the experiences of elderly patients referred to the outpatient clinic. To obtain a sample, the psychologist asks the receptionist to hand an invitation to participate in the study to all follow-up patients who attend for an appointment. The recruitment phase continues until a total of 30 elderly individuals agree to be in the study.

How is this sampling method best described?

Explanation:

Qualitative research is a method of inquiry that seeks to understand the meaning and experience dimensions of human lives and social worlds. There are different approaches to qualitative research, such as ethnography, phenomenology, and grounded theory, each with its own purpose, role of the researcher, stages of research, and method of data analysis. The most common methods used in healthcare research are interviews and focus groups. Sampling techniques include convenience sampling, purposive sampling, quota sampling, snowball sampling, and case study sampling. Sample size can be determined by data saturation, which occurs when new categories, themes, of explanations stop emerging from the data. Validity can be assessed through triangulation, respondent validation, bracketing, and reflexivity. Analytical approaches include content analysis and constant comparison.

• This question is part of the following fields:

• Research Methods, Statistics, Critical Review And Evidence-Based Practice
4.4
Seconds
• #### Question 8 - How would you rephrase the question to refer to the test's capacity to...

Correct

• How would you rephrase the question to refer to the test's capacity to identify a person with a disease as positive?

Explanation:

Clinical tests are used to determine the presence of absence of a disease of condition. To interpret test results, it is important to have a working knowledge of statistics used to describe them. Two by two tables are commonly used to calculate test statistics such as sensitivity and specificity. Sensitivity refers to the proportion of people with a condition that the test correctly identifies, while specificity refers to the proportion of people without a condition that the test correctly identifies. Accuracy tells us how closely a test measures to its true value, while predictive values help us understand the likelihood of having a disease based on a positive of negative test result. Likelihood ratios combine sensitivity and specificity into a single figure that can refine our estimation of the probability of a disease being present. Pre and post-test odds and probabilities can also be calculated to better understand the likelihood of having a disease before and after a test is carried out. Fagan’s nomogram is a useful tool for calculating post-test probabilities.

• This question is part of the following fields:

• Research Methods, Statistics, Critical Review And Evidence-Based Practice
7.7
Seconds
• #### Question 9 - By implementing a double-blinded randomised controlled trial to evaluate the efficacy of a...

Correct

• By implementing a double-blinded randomised controlled trial to evaluate the efficacy of a new medication for Lewy Body Dementia, what type of bias can be prevented by ensuring that both the patient and doctor are blinded?

Explanation:

Types of Bias in Statistics

Bias is a systematic error that can lead to incorrect conclusions. Confounding factors are variables that are associated with both the outcome and the exposure but have no causative role. Confounding can be addressed in the design and analysis stage of a study. The main method of controlling confounding in the analysis phase is stratification analysis. The main methods used in the design stage are matching, randomization, and restriction of participants.

There are two main types of bias: selection bias and information bias. Selection bias occurs when the selected sample is not a representative sample of the reference population. Disease spectrum bias, self-selection bias, participation bias, incidence-prevalence bias, exclusion bias, publication of dissemination bias, citation bias, and Berkson’s bias are all subtypes of selection bias. Information bias occurs when gathered information about exposure, outcome, of both is not correct and there was an error in measurement. Detection bias, recall bias, lead time bias, interviewer/observer bias, verification and work-up bias, Hawthorne effect, and ecological fallacy are all subtypes of information bias.

• This question is part of the following fields:

• Research Methods, Statistics, Critical Review And Evidence-Based Practice
28.7
Seconds
• #### Question 10 - What is the meaning of the C in the PICO model utilized in...

Correct

• What is the meaning of the C in the PICO model utilized in evidence-based medicine?

Explanation:

Evidence-based medicine involves four basic steps: developing a focused clinical question, searching for the best evidence, critically appraising the evidence, and applying the evidence and evaluating the outcome. When developing a question, it is important to understand the difference between background and foreground questions. Background questions are general questions about conditions, illnesses, syndromes, and pathophysiology, while foreground questions are more often about issues of care. The PICO system is often used to define the components of a foreground question: patient group of interest, intervention of interest, comparison, and primary outcome.

When searching for evidence, it is important to have a basic understanding of the types of evidence and sources of information. Scientific literature is divided into two basic categories: primary (empirical research) and secondary (interpretation and analysis of primary sources). Unfiltered sources are large databases of articles that have not been pre-screened for quality, while filtered resources summarize and appraise evidence from several studies.

There are several databases and search engines that can be used to search for evidence, including Medline and PubMed, Embase, the Cochrane Library, PsycINFO, CINAHL, and OpenGrey. Boolean logic can be used to combine search terms in PubMed, and phrase searching and truncation can also be used. Medical Subject Headings (MeSH) are used by indexers to describe articles for MEDLINE records, and the MeSH Database is like a thesaurus that enables exploration of this vocabulary.

• This question is part of the following fields:

• Research Methods, Statistics, Critical Review And Evidence-Based Practice
15.6
Seconds
• #### Question 11 - What does a smaller p-value indicate in terms of the strength of evidence?...

Incorrect

• What does a smaller p-value indicate in terms of the strength of evidence?

Correct Answer: The alternative hypothesis

Explanation:

A p-value represents the likelihood of rejecting a null hypothesis that is actually true. A smaller p-value indicates a lower chance of mistakenly rejecting the null hypothesis, providing evidence in favor of the alternative hypothesis.

Understanding Hypothesis Testing in Statistics

In statistics, it is not feasible to investigate hypotheses on entire populations. Therefore, researchers take samples and use them to make estimates about the population they are drawn from. However, this leads to uncertainty as there is no guarantee that the sample taken will be truly representative of the population, resulting in potential errors. Statistical hypothesis testing is the process used to determine if claims from samples to populations can be made and with what certainty.

The null hypothesis (Ho) is the claim that there is no real difference between two groups, while the alternative hypothesis (H1 of Ha) suggests that any difference is due to some non-random chance. The alternative hypothesis can be one-tailed of two-tailed, depending on whether it seeks to establish a difference of a change in one direction.

Two types of errors may occur when testing the null hypothesis: Type I and Type II errors. Type I error occurs when the null hypothesis is rejected when it is true, while Type II error occurs when the null hypothesis is accepted when it is false. The power of a study is the probability of correctly rejecting the null hypothesis when it is false, and it can be increased by increasing the sample size.

P-values provide information on statistical significance and help researchers decide if study results have occurred due to chance. The p-value is the probability of obtaining a result that is as large of larger when in reality there is no difference between two groups. The cutoff for the p-value is called the significance level (alpha level), typically set at 0.05. If the p-value is less than the cutoff, the null hypothesis is rejected, and if it is greater or equal to the cut off, the null hypothesis is not rejected. However, the p-value does not indicate clinical significance, which may be too small to be meaningful.

• This question is part of the following fields:

• Research Methods, Statistics, Critical Review And Evidence-Based Practice
36.5
Seconds
• #### Question 12 - Which of the following can be used to represent the overall number of...

Correct

• Which of the following can be used to represent the overall number of individuals affected by a disease during a specific period?

Explanation:

Measures of Disease Frequency: Incidence and Prevalence

Incidence and prevalence are two important measures of disease frequency. Incidence measures the speed at which new cases of a disease are emerging, while prevalence measures the burden of disease within a population. Cumulative incidence and incidence rate are two types of incidence measures, while point prevalence and period prevalence are two types of prevalence measures.

Cumulative incidence is the average risk of getting a disease over a certain period of time, while incidence rate is a measure of the speed at which new cases are emerging. Prevalence is a proportion and is a measure of the burden of disease within a population. Point prevalence measures the number of cases in a defined population at a specific point in time, while period prevalence measures the number of identified cases during a specified period of time.

It is important to note that prevalence is equal to incidence multiplied by the duration of the condition. In chronic diseases, the prevalence is much greater than the incidence. The incidence rate is stated in units of person-time, while cumulative incidence is always a proportion. When describing cumulative incidence, it is necessary to give the follow-up period over which the risk is estimated. In acute diseases, the prevalence and incidence may be similar, while for conditions such as the common cold, the incidence may be greater than the prevalence.

Incidence is a useful measure to study disease etiology and risk factors, while prevalence is useful for health resource planning. Understanding these measures of disease frequency is important for public health professionals and researchers in order to effectively monitor and address the burden of disease within populations.

• This question is part of the following fields:

• Research Methods, Statistics, Critical Review And Evidence-Based Practice
33.4
Seconds
• #### Question 13 - Which statement about disease rates is incorrect? ...

Correct

• Which statement about disease rates is incorrect?

Your Answer: The odds ratio is synonymous with the risk ratio

Explanation:

Disease Rates and Their Interpretation

Disease rates are a measure of the occurrence of a disease in a population. They are used to establish causation, monitor interventions, and measure the impact of exposure on disease rates. The attributable risk is the difference in the rate of disease between the exposed and unexposed groups. It tells us what proportion of deaths in the exposed group were due to the exposure. The relative risk is the risk of an event relative to exposure. It is calculated by dividing the rate of disease in the exposed group by the rate of disease in the unexposed group. A relative risk of 1 means there is no difference between the two groups. A relative risk of <1 means that the event is less likely to occur in the exposed group, while a relative risk of >1 means that the event is more likely to occur in the exposed group. The population attributable risk is the reduction in incidence that would be observed if the population were entirely unexposed. It can be calculated by multiplying the attributable risk by the prevalence of exposure in the population. The attributable proportion is the proportion of the disease that would be eliminated in a population if its disease rate were reduced to that of the unexposed group.

• This question is part of the following fields:

• Research Methods, Statistics, Critical Review And Evidence-Based Practice
72.1
Seconds
• #### Question 14 - What is the middle value in the given data set? ...

Incorrect

• What is the middle value in the given data set?

Explanation:

Measures of Central Tendency

Measures of central tendency are used in descriptive statistics to summarize the middle of typical value of a data set. There are three common measures of central tendency: the mean, median, and mode.

The median is the middle value in a data set that has been arranged in numerical order. It is not affected by outliers and is used for ordinal data. The mode is the most frequent value in a data set and is used for categorical data. The mean is calculated by adding all the values in a data set and dividing by the number of values. It is sensitive to outliers and is used for interval and ratio data.

The appropriate measure of central tendency depends on the measurement scale of the data. For nominal and categorical data, the mode is used. For ordinal data, the median of mode is used. For interval data with a normal distribution, the mean is preferable, but the median of mode can also be used. For interval data with skewed distribution, the median is used. For ratio data, the mean is preferable, but the median of mode can also be used for skewed data.

In addition to measures of central tendency, the range is also used to describe the spread of a data set. It is calculated by subtracting the smallest value from the largest value.

• This question is part of the following fields:

• Research Methods, Statistics, Critical Review And Evidence-Based Practice
45.4
Seconds
• #### Question 15 - The regional Health Authority has requested your expertise in determining whether to establish...

Incorrect

• The regional Health Authority has requested your expertise in determining whether to establish a new 12 bed pediatric ward of a six bed adolescent psychiatric unit. Your task is to conduct an economic analysis that evaluates the financial advantages and disadvantages of both proposals.

Correct Answer: Cost benefit analysis

Explanation:

A cost benefit analysis is a method of evaluating whether the benefits of an intervention outweigh its costs, using monetary units as the common measurement. Typically, this type of analysis is employed by funding bodies to make decisions about financing, such as whether to allocate resources for a new delivery suite of electroconvulsive therapy suite.

• This question is part of the following fields:

• Research Methods, Statistics, Critical Review And Evidence-Based Practice
26.9
Seconds
• #### Question 16 - What statement accurately describes percentiles? ...

Correct

• What statement accurately describes percentiles?

Your Answer: Q1 is the 25th percentile

Explanation:

Measures of dispersion are used to indicate the variation of spread of a data set, often in conjunction with a measure of central tendency such as the mean of median. The range, which is the difference between the largest and smallest value, is the simplest measure of dispersion. The interquartile range, which is the difference between the 3rd and 1st quartiles, is another useful measure. Quartiles divide a data set into quarters, and the interquartile range can provide additional information about the spread of the data. However, to get a more representative idea of spread, measures such as the variance and standard deviation are needed. The variance gives an indication of how much the items in the data set vary from the mean, while the standard deviation reflects the distribution of individual scores around their mean. The standard deviation is expressed in the same units as the data set and can be used to indicate how confident we are that data points lie within a particular range. The standard error of the mean is an inferential statistic used to estimate the population mean and is a measure of the spread expected for the mean of the observations. Confidence intervals are often presented alongside sample results such as the mean value, indicating a range that is likely to contain the true value.

• This question is part of the following fields:

• Research Methods, Statistics, Critical Review And Evidence-Based Practice
60.7
Seconds
• #### Question 17 - What is a correct statement about funnel plots? ...

Incorrect

• What is a correct statement about funnel plots?

Your Answer: The standard error is plotted on the x-axis

Correct Answer: Studies with a smaller standard error are located towards the top of the funnel

Explanation:

Funnel plots are utilized in meta-analyses to visually display the potential presence of publication bias. However, it is important to note that an asymmetric funnel plot does not necessarily confirm the existence of publication bias, as other factors may contribute to its formation.

Stats Publication Bias

Publication bias refers to the tendency for studies with positive findings to be published more than studies with negative findings, leading to incomplete data sets in meta-analyses and erroneous conclusions. Graphical methods such as funnel plots, Galbraith plots, ordered forest plots, and normal quantile plots can be used to detect publication bias. Funnel plots are the most commonly used and offer an easy visual way to ensure that published literature is evenly weighted. The x-axis represents the effect size, and the y-axis represents the study size. A symmetrical, inverted funnel shape indicates that publication bias is unlikely, while an asymmetrical funnel indicates a relationship between treatment effect and study size, indicating either publication bias of small study effects.

• This question is part of the following fields:

• Research Methods, Statistics, Critical Review And Evidence-Based Practice
21.8
Seconds
• #### Question 18 - Which of the following is an example of primary evidence? ...

Correct

• Which of the following is an example of primary evidence?

Your Answer: A case-series of chronic leukocytosis associated with clozapine

Explanation:

Evidence-based medicine involves four basic steps: developing a focused clinical question, searching for the best evidence, critically appraising the evidence, and applying the evidence and evaluating the outcome. When developing a question, it is important to understand the difference between background and foreground questions. Background questions are general questions about conditions, illnesses, syndromes, and pathophysiology, while foreground questions are more often about issues of care. The PICO system is often used to define the components of a foreground question: patient group of interest, intervention of interest, comparison, and primary outcome.

When searching for evidence, it is important to have a basic understanding of the types of evidence and sources of information. Scientific literature is divided into two basic categories: primary (empirical research) and secondary (interpretation and analysis of primary sources). Unfiltered sources are large databases of articles that have not been pre-screened for quality, while filtered resources summarize and appraise evidence from several studies.

There are several databases and search engines that can be used to search for evidence, including Medline and PubMed, Embase, the Cochrane Library, PsycINFO, CINAHL, and OpenGrey. Boolean logic can be used to combine search terms in PubMed, and phrase searching and truncation can also be used. Medical Subject Headings (MeSH) are used by indexers to describe articles for MEDLINE records, and the MeSH Database is like a thesaurus that enables exploration of this vocabulary.

• This question is part of the following fields:

• Research Methods, Statistics, Critical Review And Evidence-Based Practice
15.1
Seconds
• #### Question 19 - Which of the options below does not demonstrate selection bias? ...

Incorrect

• Which of the options below does not demonstrate selection bias?

Correct Answer: Recall bias

Explanation:

Types of Bias in Statistics

Bias is a systematic error that can lead to incorrect conclusions. Confounding factors are variables that are associated with both the outcome and the exposure but have no causative role. Confounding can be addressed in the design and analysis stage of a study. The main method of controlling confounding in the analysis phase is stratification analysis. The main methods used in the design stage are matching, randomization, and restriction of participants.

There are two main types of bias: selection bias and information bias. Selection bias occurs when the selected sample is not a representative sample of the reference population. Disease spectrum bias, self-selection bias, participation bias, incidence-prevalence bias, exclusion bias, publication of dissemination bias, citation bias, and Berkson’s bias are all subtypes of selection bias. Information bias occurs when gathered information about exposure, outcome, of both is not correct and there was an error in measurement. Detection bias, recall bias, lead time bias, interviewer/observer bias, verification and work-up bias, Hawthorne effect, and ecological fallacy are all subtypes of information bias.

• This question is part of the following fields:

• Research Methods, Statistics, Critical Review And Evidence-Based Practice
97.6
Seconds
• #### Question 20 - A new test is developed to screen for dementia in elderly patients. Trials...

Incorrect

• A new test is developed to screen for dementia in elderly patients. Trials have shown it has a sensitivity for detecting clinically significant dementia of 80% but a specificity of 60%. What is the likelihood ratio for a positive test result?

Explanation:

The likelihood ratio for a positive test result is 2, which means that the probability of a positive test result in a person with the condition is twice as high as the probability of a positive test result in a person without the condition.

Clinical tests are used to determine the presence of absence of a disease of condition. To interpret test results, it is important to have a working knowledge of statistics used to describe them. Two by two tables are commonly used to calculate test statistics such as sensitivity and specificity. Sensitivity refers to the proportion of people with a condition that the test correctly identifies, while specificity refers to the proportion of people without a condition that the test correctly identifies. Accuracy tells us how closely a test measures to its true value, while predictive values help us understand the likelihood of having a disease based on a positive of negative test result. Likelihood ratios combine sensitivity and specificity into a single figure that can refine our estimation of the probability of a disease being present. Pre and post-test odds and probabilities can also be calculated to better understand the likelihood of having a disease before and after a test is carried out. Fagan’s nomogram is a useful tool for calculating post-test probabilities.

• This question is part of the following fields:

• Research Methods, Statistics, Critical Review And Evidence-Based Practice
58.8
Seconds
• #### Question 21 - What is the mathematical operation used to determine the value of the square...

Incorrect

• What is the mathematical operation used to determine the value of the square root of the variance?

Correct Answer: Standard deviation

Explanation:

Measures of dispersion are used to indicate the variation of spread of a data set, often in conjunction with a measure of central tendency such as the mean of median. The range, which is the difference between the largest and smallest value, is the simplest measure of dispersion. The interquartile range, which is the difference between the 3rd and 1st quartiles, is another useful measure. Quartiles divide a data set into quarters, and the interquartile range can provide additional information about the spread of the data. However, to get a more representative idea of spread, measures such as the variance and standard deviation are needed. The variance gives an indication of how much the items in the data set vary from the mean, while the standard deviation reflects the distribution of individual scores around their mean. The standard deviation is expressed in the same units as the data set and can be used to indicate how confident we are that data points lie within a particular range. The standard error of the mean is an inferential statistic used to estimate the population mean and is a measure of the spread expected for the mean of the observations. Confidence intervals are often presented alongside sample results such as the mean value, indicating a range that is likely to contain the true value.

• This question is part of the following fields:

• Research Methods, Statistics, Critical Review And Evidence-Based Practice
23.8
Seconds
• #### Question 22 - What hierarchical language does NLM utilize to enhance search strategies and index articles?...

Incorrect

• What hierarchical language does NLM utilize to enhance search strategies and index articles?

Explanation:

NLM’s hierarchical vocabulary, known as MeSH (Medical Subject Heading), is utilized for the purpose of indexing articles in PubMed.

Evidence-based medicine involves four basic steps: developing a focused clinical question, searching for the best evidence, critically appraising the evidence, and applying the evidence and evaluating the outcome. When developing a question, it is important to understand the difference between background and foreground questions. Background questions are general questions about conditions, illnesses, syndromes, and pathophysiology, while foreground questions are more often about issues of care. The PICO system is often used to define the components of a foreground question: patient group of interest, intervention of interest, comparison, and primary outcome.

When searching for evidence, it is important to have a basic understanding of the types of evidence and sources of information. Scientific literature is divided into two basic categories: primary (empirical research) and secondary (interpretation and analysis of primary sources). Unfiltered sources are large databases of articles that have not been pre-screened for quality, while filtered resources summarize and appraise evidence from several studies.

There are several databases and search engines that can be used to search for evidence, including Medline and PubMed, Embase, the Cochrane Library, PsycINFO, CINAHL, and OpenGrey. Boolean logic can be used to combine search terms in PubMed, and phrase searching and truncation can also be used. Medical Subject Headings (MeSH) are used by indexers to describe articles for MEDLINE records, and the MeSH Database is like a thesaurus that enables exploration of this vocabulary.

• This question is part of the following fields:

• Research Methods, Statistics, Critical Review And Evidence-Based Practice
26.5
Seconds
• #### Question 23 - What does the term external validity in a study refer to? ...

Incorrect

• What does the term external validity in a study refer to?

Your Answer: The extent to which an experiment, test, of any measuring procedure yields the same result on repeated trials

Correct Answer: The degree to which the conclusions in a study would hold for other persons in other places and at other times

Explanation:

Validity in statistics refers to how accurately something measures what it claims to measure. There are two main types of validity: internal and external. Internal validity refers to the confidence we have in the cause and effect relationship in a study, while external validity refers to the degree to which the conclusions of a study can be applied to other people, places, and times. There are various threats to both internal and external validity, such as sampling, measurement instrument obtrusiveness, and reactive effects of setting. Additionally, there are several subtypes of validity, including face validity, content validity, criterion validity, and construct validity. Each subtype has its own specific focus and methods for testing validity.

• This question is part of the following fields:

• Research Methods, Statistics, Critical Review And Evidence-Based Practice
7
Seconds
• #### Question 24 - How would you rephrase the question Which of the following refers to the...

Incorrect

• How would you rephrase the question Which of the following refers to the proportion of people scoring positive on a test that actually have the condition?

Correct Answer: Positive predictive value

Explanation:

Clinical tests are used to determine the presence of absence of a disease of condition. To interpret test results, it is important to have a working knowledge of statistics used to describe them. Two by two tables are commonly used to calculate test statistics such as sensitivity and specificity. Sensitivity refers to the proportion of people with a condition that the test correctly identifies, while specificity refers to the proportion of people without a condition that the test correctly identifies. Accuracy tells us how closely a test measures to its true value, while predictive values help us understand the likelihood of having a disease based on a positive of negative test result. Likelihood ratios combine sensitivity and specificity into a single figure that can refine our estimation of the probability of a disease being present. Pre and post-test odds and probabilities can also be calculated to better understand the likelihood of having a disease before and after a test is carried out. Fagan’s nomogram is a useful tool for calculating post-test probabilities.

• This question is part of the following fields:

• Research Methods, Statistics, Critical Review And Evidence-Based Practice
19.2
Seconds
• #### Question 25 - Which of the following is an example of a non-random sampling method? ...

Incorrect

• Which of the following is an example of a non-random sampling method?

Correct Answer: Quota sampling

Explanation:

Sampling Methods in Statistics

When collecting data from a population, it is often impractical and unnecessary to gather information from every single member. Instead, taking a sample is preferred. However, it is crucial that the sample accurately represents the population from which it is drawn. There are two main types of sampling methods: probability (random) sampling and non-probability (non-random) sampling.

Non-probability sampling methods, also known as judgement samples, are based on human choice rather than random selection. These samples are convenient and cheaper than probability sampling methods. Examples of non-probability sampling methods include voluntary sampling, convenience sampling, snowball sampling, and quota sampling.

Probability sampling methods give a more representative sample of the population than non-probability sampling. In each probability sampling technique, each population element has a known (non-zero) chance of being selected for the sample. Examples of probability sampling methods include simple random sampling, systematic sampling, cluster sampling, stratified sampling, and multistage sampling.

Simple random sampling is a sample in which every member of the population has an equal chance of being chosen. Systematic sampling involves selecting every kth member of the population. Cluster sampling involves dividing a population into separate groups (called clusters) and selecting a random sample of clusters. Stratified sampling involves dividing a population into groups (strata) and taking a random sample from each strata. Multistage sampling is a more complex method that involves several stages and combines two of more sampling methods.

Overall, probability sampling methods give a more representative sample of the population, but non-probability sampling methods are often more convenient and cheaper. It is important to choose the appropriate sampling method based on the research question and available resources.

• This question is part of the following fields:

• Research Methods, Statistics, Critical Review And Evidence-Based Practice
6.7
Seconds
• #### Question 26 - Which odds ratio suggests that there is no significant variation in the odds...

Incorrect

• Which odds ratio suggests that there is no significant variation in the odds between two groups?

Explanation:

Measures of Effect in Clinical Studies

When conducting clinical studies, we often want to know the effect of treatments of exposures on health outcomes. Measures of effect are used in randomized controlled trials (RCTs) and include the odds ratio (of), risk ratio (RR), risk difference (RD), and number needed to treat (NNT). Dichotomous (binary) outcome data are common in clinical trials, where the outcome for each participant is one of two possibilities, such as dead of alive, of clinical improvement of no improvement.

To understand the difference between of and RR, it’s important to know the difference between risks and odds. Risk is a proportion that describes the probability of a health outcome occurring, while odds is a ratio that compares the probability of an event occurring to the probability of it not occurring. Absolute risk is the basic risk, while risk difference is the difference between the absolute risk of an event in the intervention group and the absolute risk in the control group. Relative risk is the ratio of risk in the intervention group to the risk in the control group.

The number needed to treat (NNT) is the number of patients who need to be treated for one to benefit. Odds are calculated by dividing the number of times an event happens by the number of times it does not happen. The odds ratio is the odds of an outcome given a particular exposure versus the odds of an outcome in the absence of the exposure. It is commonly used in case-control studies and can also be used in cross-sectional and cohort study designs. An odds ratio of 1 indicates no difference in risk between the two groups, while an odds ratio >1 indicates an increased risk and an odds ratio <1 indicates a reduced risk.

• This question is part of the following fields:

• Research Methods, Statistics, Critical Review And Evidence-Based Practice
13.1
Seconds
• #### Question 27 - What is a criterion used to evaluate the quality of meta-analysis reporting? ...

Incorrect

• What is a criterion used to evaluate the quality of meta-analysis reporting?

Explanation:

As an AI language model, I do not have personal opinions of beliefs. However, I can provide information and guidance on the standards of reporting for different types of research studies. The guidelines mentioned above are essential for ensuring that research studies are reported accurately and transparently, which is crucial for the scientific community to evaluate and replicate the findings. It is important for researchers to be familiar with these standards and follow them when reporting their studies to ensure the quality and integrity of their research.

• This question is part of the following fields:

• Research Methods, Statistics, Critical Review And Evidence-Based Practice
40.2
Seconds
• #### Question 28 - As the occurrence of a condition decreases, what increases? ...

Incorrect

• As the occurrence of a condition decreases, what increases?

Correct Answer: Negative predictive value

Explanation:

The prevalence of a condition has an impact on both the PPV and NPV. When the prevalence decreases, the PPV also decreases while the NPV increases.

Clinical tests are used to determine the presence of absence of a disease of condition. To interpret test results, it is important to have a working knowledge of statistics used to describe them. Two by two tables are commonly used to calculate test statistics such as sensitivity and specificity. Sensitivity refers to the proportion of people with a condition that the test correctly identifies, while specificity refers to the proportion of people without a condition that the test correctly identifies. Accuracy tells us how closely a test measures to its true value, while predictive values help us understand the likelihood of having a disease based on a positive of negative test result. Likelihood ratios combine sensitivity and specificity into a single figure that can refine our estimation of the probability of a disease being present. Pre and post-test odds and probabilities can also be calculated to better understand the likelihood of having a disease before and after a test is carried out. Fagan’s nomogram is a useful tool for calculating post-test probabilities.

• This question is part of the following fields:

• Research Methods, Statistics, Critical Review And Evidence-Based Practice
30.6
Seconds
• #### Question 29 - Which of the following statements accurately describes relative risk? ...

Correct

• Which of the following statements accurately describes relative risk?

Your Answer: It is the usual outcome measure of cohort studies

Explanation:

The relative risk is the typical measure of outcome in cohort studies. It is important to distinguish between risk and odds. For example, if 20 individuals out of 100 who take an overdose die, the risk of dying is 0.2, while the odds are 0.25 (20/80).

Measures of Effect in Clinical Studies

When conducting clinical studies, we often want to know the effect of treatments of exposures on health outcomes. Measures of effect are used in randomized controlled trials (RCTs) and include the odds ratio (of), risk ratio (RR), risk difference (RD), and number needed to treat (NNT). Dichotomous (binary) outcome data are common in clinical trials, where the outcome for each participant is one of two possibilities, such as dead of alive, of clinical improvement of no improvement.

To understand the difference between of and RR, it’s important to know the difference between risks and odds. Risk is a proportion that describes the probability of a health outcome occurring, while odds is a ratio that compares the probability of an event occurring to the probability of it not occurring. Absolute risk is the basic risk, while risk difference is the difference between the absolute risk of an event in the intervention group and the absolute risk in the control group. Relative risk is the ratio of risk in the intervention group to the risk in the control group.

The number needed to treat (NNT) is the number of patients who need to be treated for one to benefit. Odds are calculated by dividing the number of times an event happens by the number of times it does not happen. The odds ratio is the odds of an outcome given a particular exposure versus the odds of an outcome in the absence of the exposure. It is commonly used in case-control studies and can also be used in cross-sectional and cohort study designs. An odds ratio of 1 indicates no difference in risk between the two groups, while an odds ratio >1 indicates an increased risk and an odds ratio <1 indicates a reduced risk.

• This question is part of the following fields:

• Research Methods, Statistics, Critical Review And Evidence-Based Practice
13.2
Seconds
• #### Question 30 - What is the optimal number needed to treat (NNT)? ...

Incorrect

• What is the optimal number needed to treat (NNT)?

Explanation:

The effectiveness of a healthcare intervention, usually a medication, is measured by the number needed to treat (NNT). This represents the average number of patients who must receive treatment to prevent one additional negative outcome. An NNT of 1 would indicate that all treated patients improved while none of the control patients did, which is the ideal scenario. The NNT can be calculated by taking the inverse of the absolute risk reduction. A higher NNT indicates a less effective treatment, with the range of NNT being from 1 to infinity.

• This question is part of the following fields:

• Research Methods, Statistics, Critical Review And Evidence-Based Practice
0
Seconds

### SESSION STATS - PERFORMANCE PER SPECIALTY

Research Methods, Statistics, Critical Review And Evidence-Based Practice (21/29) 72%