Show me the data
A type of categorical variable that is named with an order/superiority. For example, for NEC, stage III is worse than stage II, stage II is worse than stage I
What is an ordinal variable?
Also known as Gaussian distribution, and refers to a symmetric bell-shaped frequency distribution, in which mean, median and mode all have the same value/
What is a normal distribution?
A simple commonly used parametric test to compare two groups of continuous variables that are normally distributed. It can be paired, unpaired, one-tailed or two-tailed.
What is a t-test?
It is calculated as true positives divided by (true positives + false negatives).
What is the sensitivity of a test?
Sensitivity of a test is defined as the proportion of subjects with the disease in whom the test gives the correct answer. A highly sensitive test has a low false-negative rate and is good as a screening test, and a negative test almost rules out the disease.
These two types of variables are continuous, and can have an infinite number of possible values. Examples of these variables are body temperature in Fahrenheit, and volume of NG aspirate quantified in mL per day.
What are interval and ratio variables?
Interval: Equal interval between values but no meaningful zero point (ex. the difference between 98.4F and 97.4F is the same as the difference between 99.4 and 98.4F, but 0F does not mean there is no temperature)
Ratio: Equal intervals with a meaningful zero point and all mathematical operations are functional. Ex 15ml NG output is 3x higher than 5ml
The area under this curve is a useful summary of the overall accuracy of a test, or the capability of the test. For example, for a diagnostic test, the area under this curve ranges from a diagonal from lower left to upper right corner (and a useless to test) to a curve along the left and upper borders (for a perfect test).
What is the receiver operating characteristic curve?
The chi squared test is a common test used to compare categorical data. Data are first entered into a 2x2 contingency table, where nominal or ordinal variables are compared. Significance is calculated by analyzing the square of observed values and expected values. If the numbers are small, (expected value is </=5), THIS alternative test is used.
What is a Fisher's exact test?
It is calculated by true positives divided by (true positives + false positives).
What is the positive predictive value?
The PPV of a test is the proportion of the subjects with positive tests who have the disease.
This is a measure of central tendency, and is defined as the most frequently occurring observation.
What is the mode?
When the distribution of data is skewed, the direction of the skew refers to the direction of the tail. Therefore a curve is skewed in this direction if it has a positive skew.
What is skewed right?
For data with skewed distributions, the appropriate statistic test is a non-parametric test, such as Wilcoxon or Mann-Whitney Test. Data are usually represented as median, inter-quartile range (IQR).
This value represents the PROBABILITY of the null hypothesis being true by chance alone. For example, if the value is 0.05, there is at least a 95% chance that two samples represent different populations.
What is the p value?
It is calculated as true negatives divided by (false positives + true negatives).
What is specificity?
Specificity is the proportion of subjects without the disease in whom the test gives the right answer. A highly specific test has a low false positive rate.
The square root of variance and is the most common measure of dispersion used for normally distributed data. For a normal distribution, if the mean and this value are known, the percentage of the sample included in a given range of values can be calculated.
What is the standard deviation?
Mean +/- 1 SD: 68.2% of the sample is included
Mean +/- 2 SDs: 95.4% of sample is included
Mean +/-3 SDs: 99.8% of sample is included
In survival analysis, this commonly used method is also called the product limit method. This nonparametric technique uses the exact survival time for each subject in a sample.
What is the Kaplan Meier Method?
Absolute risk reduction is the measure of association that describes the absolute effect of exposure of excess risk of disease in those exposed compared to those who were not exposed (ex, risk of developing NEC when exposed to formula vs breastmilk). THIS NUMBER is the reciprocal of the absolute risk reduction.
What is the number needed to treat? NNT
The effect of increased prevalence on positive predictive value.
What is increased PPV?
Increased prevalence of disease will increase PPV and decrease NPV.
This hypothesis proposes that there is no difference between the groups being compared.
What is the null hypothesis?
These 3 Measures of central tendency all start with an M and have the same values when the distribution of data is normal.
What are mean, median and mode?
Mean is the average value for the data. Median is the middle value when data are sequentially ordered from lowest to highest or highest to lowest. Mode is the most frequently occurring observation.
Confidence intervals (typically at 95%) for relative risk and OR indicate that the investigator can be 95% confident that the real relative risk of OR in the population lies within this range of values. If the 95% confidence interval crosses THIS NUMBER, the association is not significant.
What is 1?
This is an algorithm that combines several predicts, including the presence or absence of various symptoms, signs and lab tests, to estimate the probability of a particular disease or outcome.
What is the clinical prediction rule?