variable
any characteristics that can and does assume different values for different people, objects or events.
4 measurement scales for
... [Show More] variables
nominal, ordinal, interval ratio
nominal scale (categorizational)
numbers simply used as a code to represent characteristics such as ethnicity. no order to category, assignment of numbers to categories is arbitrary or random.
e.g. Male = 1 and Female = 2
these variables may be called categorical or qualitative
ordinal scale (rank ordering)
numbers represent categories that can be placed in meaningful numerical order e.g. lowest to highest. no information regarding size of the interval between the different values. sized of interval may be different between different categories. there is no true zero, they are subjective eg pain scale, satisfaction scale based on perception. almost all subjective scales are ordinal also military rank.
interval scale
numbers can be placed in meaningful order, intervals between are equal. possible to add and subtract across an interval scale. no true zero. ratios cannot be calculated. e.g. Fahrenheit temperature. cognitive exams. either continuous or discrete
ratio scale (numerical ordering)
numbers can be placed in meaningful order. intervals between numbers are equal. there is a true zero, determined by nature, which represents the absence of the phenomena. almost all biomedical measures are ratio scale. e.g. weight, age, number of minutes spent exercising, pulse rate, height cholesterol level. all mathematical operations are possible
displaying data
overall goal is to get feeling for distribution data. considerations are central tendency, dispersion, shape and skewness, outliers
central tendency
most frequently occurring values. e.g. mean, median, mode
dispersion
how are the values spread out
shape and skewness
symmetry (equal distribution on both sides) or asymmetry of the distribution of the values.
outliers
unusual values that do not fit the pattern of the data.
visual displays of data
frequency distribution table, graphical displays e.g. histogram and descriptive statistics' goal is to help in understanding four things about each variable 1 its central tendency, 2 dispersion, 3 shape and 4 outliers.
frequency distribution table
organize data in table form. show possible values of the variables, raw frequencies (# of cases with that value), relative frequency (%of cases with that value), cumulative frequency (total % having up to and including a given value of the variable).advantages condense data into a form that can make them easier to understand and show many details in summary fashion.
raw frequency
number of cases with that value
relative frequency
% of cases with that value
cumulative frequency
total percent having up to and including a given value of the variable.
histograms
visual depictions of frequency distributions. way of organizing the data in visual forms, data have to be at least ordinal in scale. rules for histogram construction= values of the variable being graphed are on the x-axis. class intervals (mutually exclusive, exhaustive and even widths) are used, bars must tough. used for ordinal, interval and ratio level variables. not nominal [Show Less]