Statistics Flashcards
What is the basic idea behind using statistics in health and fitness assessments?
Statistics help us make sense of data and find patterns, allowing us to predict things like someone’s fitness level or health risks.
Why is statistics important?
Statistics are important because they have predictive utility and allow us to understand and interpret data
How can statistics be used to make predictions?
Statistics can reveal linear relationships that allow us to predict values, such as VO2 max from heart rate using the Fick equation.
What does ‘variability’ mean when we’re talking about data?
Variability refers to how spread out the data is. It tells us if the values are tightly clustered or scattered widely
What is the ‘mean’ and how is it calculated?
The mean is the average of a set of numbers. You find it by adding all the numbers together and then dividing by how many numbers there are
What does ‘standard deviation’ (SD) tell us about a group of data?
The standard deviation measures the variability within a specific group of people being assessed. A higher SD means the data is more spread out
If you have a standard deviation, what percentage of the data will be within 2 SDs?
Approximately 95% of the data will fall within a range of two standard deviations from the mean
What is ‘standard error’ (SE) and how is it different from SD?
Standard error measures the accuracy of the true mean for a population, whereas SD is the variability within the sample. SE is used when we want to generalize results to a larger group
How is standard error affected by sample size?
The standard error depends on both the standard deviation and the sample size. As the sample size gets bigger, the standard error decreases
What is the Coefficient of Variation (CV) and why do we use it?
The CV, also known as relative standard deviation, standardizes the SD, allowing for comparison of variability when means are different. It accounts for the fact that SD depends on the mean.
How do you calculate the Coefficient of Variation?
CV = (Standard Deviation / Mean) * 100
What are some factors that can influence variability in data?
Variability can come from biological factors (like mood), technical issues (precision of tools), testing methods, and even the environment.
What’s the difference between ‘validity’ and ‘reliability’?
- Validity is about accuracy or correctness. It asks, “does the test measure what it should?”
- Reliability is about precision and repeatability. It asks, “can the test be trusted to give the same results?”
Why is validity important in fitness testing?
Validity is important because it ensures that the tests we use are actually measuring what we intend them to measure
What are the main types of validity?
The main types of validity are content-related, criterion-related, face, concurrent, construct, and predictive validity
What is ‘face validity’?
Face validity is about whether a test appears to measure what it’s supposed to measure.
* For example, a balance test looks like it measures balance, but is the weakest form of validity and does not have statistical verification
What is ‘construct validity’?
Construct validity assesses whether a test captures the information about the underlying concept it’s trying to measure.
- An example is cardiorespiratory fitness assessed by peak aerobic power
What is ‘concurrent validity’?
Concurrent validity checks if a test gives similar results to a test that has already been proven to be valid.
- An example would be comparing the results of a 2000m rowing race on a machine to an actual on-water race
What is ‘predictive validity’?
Predictive validity assesses whether a test can predict a future outcome or another variable of interest
ex: using skinfold measurements to predict body fat.
Why is reliability important in testing?
Reliability is important because it indicates how consistent the test results are. We need to know if we can trust a measurement to be repeatable
What is ‘systematic error’?
Systematic error is a consistent type of error that causes measurements to change in one direction on repeated tests, such as from learning or fatigue
What is ‘random error’?
Random error is variability that can increase or decrease test scores unpredictably on repeated tests.
What is ‘inter-rater reliability’?
Inter-rater reliability compares measurements taken by two or more different testers
What is ‘intra-rater reliability’?
Intra-rater reliability compares measurements taken by the same tester at different times
intra-rater reliability is also known as test-retest relability
What is ‘test-retest reliability’?
Test-retest reliability measures how consistent the results are when the same test is done on two or more occasions. It measures the reliability of a technique
test-restest is also known as intra-rater reliability
What does ‘Intra-Class Correlation’ (ICC) tell us?
ICC measures the repeatability of a measurement
How do you interpret ICC values?
ICC values are interpreted as follows: less than 0.40 is poor, 0.40 to 0.59 is fair, 0.60 to 0.74 is good, and 0.75 to 1.00 is excellent
What does ‘correlation’ measure?
Correlation measures the strength of the relationship between two variables, but does not mean one causes the other
Does correlation mean causation?
No, correlation does NOT mean causation.
What is the difference between correlation and regression?
Correlation describes the strength of a relationship between two variables, while regression describes the numerical relationship and the pattern.
What is ‘regression’ used for?
Regression is used to describe the numerical relationship between variables and can show the pattern of that relationship using a line of best fit
Can relationships be non-linear in regression?
Yes, regression models can be non-linear to fit more complex patterns
Can multiple factors influence the relationship between variables?
Yes, multiple factors can influence the relationship between variables
What is ‘Bland-Altman’ analysis used for?
Bland-Altman analysis is used to compare a new measurement technique to a gold standard, showing how well they agree.
Why is Bland-Altman analysis important?
It helps determine if a new test is accurate enough to replace a more complex or expensive “gold standard” test
What is the purpose of Risk and Odds Ratios?
Risk Ratios (RR) and Odds Ratios (OR) are used to represent the effect of an intervention on a particular outcome, often used in medicine to normalize results compared to a control group
What is an ‘odds ratio’ (OR)?
An odds ratio tells us the odds of an event happening with a particular exposure compared to a control
How is an odds ratio calculated?
OR = (a/b)/(c/d) = (ad) / (bc)
- where ‘a’ and ‘c’ are the exposed and unexposed groups, respectively, who had the event and ‘b’ and ‘d’ are the exposed and unexposed groups, respectively, who did not have the event.
What does an odds ratio of 1 mean?
An OR of 1 indicates that the odds of the event are the same in the exposed and unexposed groups
What is a ‘risk ratio’ (RR)?
A risk ratio identifies the probability of an outcome with a specific exposure or intervention
How is a risk ratio calculated?
RR = [a/(a+b)] / [c/(c+d)]
- where ‘a’ and ‘c’ are the number in the exposed and unexposed groups, respectively, who had the event and ‘b’ and ‘d’ are the number in the exposed and unexposed groups, respectively, who did not have the event. This number can be multiplied by 100 to get a percentage
What are meta-analyses used for?
Meta-analyses combine data from multiple studies to create a larger sample size and to increase the statistical power to interpret variability and determine validity
Why are meta-analyses important?
Meta-analyses are highly regarded for interpreting variability and controversy in data and they are the basis for many clinical practice guidelines
How do meta-analyses contribute to evidence-based practice?
Meta-analyses help determine the validity of outcomes across different studies, leading to more reliable clinical guidelines
What is the key concept in “Representing Data”?
The key concept is understanding how data is presented and interpreted using tools like mean, standard deviation, and standard error
How does understanding these statistics help in health and fitness?
By knowing about variability, validity, reliability, and risk assessment, we can make better decisions, design better tests, and interpret data more effectively
What are the two content-related validity?
Face and Construct validity
What are the two criterion-related validity?
Concurrent and predictice validity
