Statistics Flashcards
Standard Error of Mean is always … than the SD. If SEM … than SD then it’s always due to inappropriate calculation.
SEM always smaller than SD
If it’s larger, then calculation error.
CI in normal distribution:
68% of sample fall between …
95% …
99.7% …
- /+ 1 SD
- /+ 2 SD
- /+ 3 SD
Mode is …
Most frequently occurring value
Median is …
Middle most value
Null hypothesis is …
No difference or no chance
An alpha value of 0.05 means …
The null hypothesis is true in 95% of the time and the chance of it being wrong is 5% (5% chance of type 1 error)
Type 1 error means …
Accepting as statistically significant difference in the data when actually there is no difference (false positive).
Type 2 error means … and factors affecting it …
Failure to reject null hypothesis when it is false.
Small sample size
Variability in the population
Small alpha value
Power of study =
1-beta (fentanyl is false negative rate)
Power increases when sample size increases.
Continues variables
The one has mean
Ht, wt, labs, BP
Catacorigal variables
Has no mean
Color, age, gender, Yes/No, stages of cancer
Tests for catacorigal
If small sample size (<30) -> Fischer exact test
Chi-squared rest -> > 30
A statistical method which allows the clinician to compare 2 different measurement techniques (continues variables)
Bland-Altman analysis
Compares with a reference which may or may not be a gold standard
Bland-Altman plot
Pearson correlation coefficient
It is a measure of correlation (relationship) or linear dependence btw the continues variables.
Zero = no correlation 1= perfect correlation >0.8 = high degree of correlation
