Statistics Flashcards
What are the 2 main variable types?
Categorical and quantitative
What two sub categories can categorical data be divided into?
Nominal and ordinal
Why are the characteristics of nominal data?
Unordered, labelled characteristics
Binary - variable has just 2 categories
E.g. Blood group (a/ab/o/b)
What are the characteristics of ordinal data?
Small set of ordered (ranked) categories
May be labels, numbers or both
Eg disease severity - none/ mild/ moderate/ severe
What are the characteristics of quantitative data?
Values have quantitative meaning
Higher number = more there is of it
E.g. Age in years or weight in kg
What type of data is marital status? (Binary, nominal, ordinal or quantitative)
Nominal
What type of data is body temp? (Binary, nominal, ordinal or quantitative)
Quantitative
What type of data is age in year intervals? (Binary, nominal, ordinal or quantitative)
Ordinal
What type of data is hypertension status (yes or no)? (Binary, nominal, ordinal or quantitative)
Binary
Define standard deviation
Average difference between scores and the mean
What percentage of the data does the interquartile range span?
The middle 50% of scores
What is the symmetry of a data set?
For each person that has a score below the median, there is someone with a score above it
Give 3 ways you could graphically summarise quantitative data, and what characteristic of these data does this asses?
Histogram, dotplot and box & whisker
Assesses if it’s parametric/ non parametric (the normal distribution)
If a box and whisker plot is positively skewed, how would the graph look different to that representing a normal distribution?
Top box thicker than the bottom box
Top whisker would be longer
If the data is symmetrical (normally distributed) what values do you report?
Mean (average) and standard deviation (variation)
If the data is asymmetrical (not normally distributed) what values do you report?
Median (average) and interquartile range (variation)
Inferential statistics use sample data to make inferences about characteristics in the whole population.
Name three types of values used in inferential statistics
Standard errors, confidence intervals, p values
What does standard error indicate?
How far on average the sample estimate is expected to be from the true population parameter value
Does standard error quantify accuracy or precision of the estimate?
Precision
What does a smaller standard error value show?
The closer the sample estimate is likely to be to the true value within the population
Does standard deviation measure sensitivity or variability of observations within the sample?
Variability
Define confidence interval
A range of values within which we can be certain with some degree of confidence that the true population parameter lies
What does the 95% confidence interval summarise in comparison to the 95% range?
95% confidence = Precision of the estimate
95% range = variability of observations within a sample