Calculating & Reporting Healthcare Statistics Second Edition Chapter 11 Presentation of Data.

Calculating & Reporting Healthcare Statistics

Second Edition

Chapter 11Presentation of Data

©2006 All rights reserved.

Types of Data - Categorical

• Four types or scales of measurement of categorical data

• Nominal• Ordinal• Ratio• Interval



• Nominal Data– Lowest level of measurement– “Nominal” means “pertaining to a name”– Observations are organized into categories

• There is no recognition of order within these categories

• For example – True/false– Male/female– Types of insurance carriers– Patient occupations



• Nominal Data– Numbers may be used to represent

categories• For example

– Males may be listed as 1, female as 2– Persons may be grouped according to blood type, where

1 represents type A; 2, type B; 3, type AB; and 4, type 0– The sequence of the values is not important. The

numbers simply serve as labels for the some piece of information



• Ordinal Data– Values are in ordered categories– “Ordinal” means “to put something in order” – On the ordinal scale, the order of the numbers

is meaningful, not the number itself• The intervals or distance between categories are

not necessarily equal• For example

– Head injuries may be classified according to level of severity, where 4 is fatal; 3, severe; 2, moderate; and 1, minor



• Ordinal Data– A natural order exists among the groupings

• The largest number representing the most serious level of injury

– The order could be revised– Intervals between ordered categories are not

assumed to be equal



• Interval Data– Include units of equal size– There is no zero point– For example

• Temperature in Fahrenheit degrees– The intervals between the values are the same

• The most important characteristic is that the intervals between values are equal



• Ratio Data – The highest level of measurement– There is a defined unit of measure– There is a real zero point– The intervals between successive values are

equal



• Ratio Data– May be displayed by units of equal size placed on a

scale starting with zero and thus can be manipulated mathematically, such as 0, 5, 10, 15, and 20

– For example• Age

– The difference between two years would be the same (the difference between age 1 and 2 is 1 year; the difference between age 55 and 56 is one year, and so on)

– There is a “zero point” in that zero would mean an absence of age or birth

– Someone who is 100 years old is twice as old as someone who is 50 years old


Types of Data

• Numerical Data– Two types of numerical statistical data– Discrete data– Continuous data


Types of Data – Numerical• Discrete data

– Discrete data are finite numbers– They can have only specified values– For example

• The number of children in a family– A family can have two or three children but cannot have 2.25 or 3.5

children– The numbers represent actual measurable quantities rather than

labels– Other examples

• The number of motor vehicle accidents in a particular community• The number of times a woman has given birth• The number of new cases of cancer cases in your state within the

past five years• The number of beds available in your hospital


Types of Data – Numerical

• Discrete Data– A natural order exists among the possible

data values– In the example of the number of times a

woman has given birth, a larger number indicates that she has had more children

• the difference between one and two births is the same as the difference between four and five

• the number of births is restricted to whole numbers (a woman cannot give birth 2.3 times)



• Continuous Data– A measure of quantity will usually be continuous– It can take on a fractional value– For example

• A patient’s temperature may be 102.6 º F• Height - One could say that someone is approximately 6 feet

tall, refine it to 5 feet 10 inches, and refine it still further to 5 feet 10 ½ inches

• Age - You may have been 20 years old on your last birthday, but your are 20 plus some part of another year



• Continuous Data– The only limiting factor for a continuous observation is

the degree of accuracy– For analysis, continuous data often are converted to a

range that acts as a category– For example

• Age can be categorized in ranges (0–20, 21–40, and so on)

– Measurements on the interval and ratio scales are can be grouped

• Interval and ratio variables are continuous


Data Display

• Data is generally presented in the forma of a table or graph and charts– Tables are used for summarizing data– Graphs can present data for quick

visualization of relationships


Data Display

• Advantages to using tables– More information can be presented– Exact values can be entered to retain

precision– Supportive details can be provided– Less work and fewer costs required in the

preparation– Flexibility is maintained without distortion of

data


Data Display

• Advantages to using graphs and charts– They get the audience’s attention– Easy to understand– Bring out hidden facts– Vividly display trends or comparison– A picture is worth a thousand words


Data Display

• Tables– An orderly arrangement of values that groups

data into rows and columns– Almost any type of quantitative information

can be grouped into tables– Columns allow you to read data up and down

while rows allow you to read data across• Columns and rows should be labeled


Data Display

• Tables - essential components– Title

• Must explain as simply as possible what is contained in the table

– Stub heading• The title or heading of the first column

– Column headings• The headings or titles for the columns

– Stubs• The categories (the left-hand column of a table)

– Cells• The information formed by intersecting columns and rows

– Source footnote• The source for any data should be identified in a footnote


Data Display

• Frequency Distribution Tables– Shows the values that a variable can take and

the number of observations associated with each value

– A variable is a characteristic or property that may take on different values

• For example– Third party payors– Discharge service– Admission day


Data Display

• Frequency Distribution Tables– Constructing A Frequency Distribution Table– For example

• A study for our Utilization Review Committee• They would be interested in knowing the admission

days for patients• List the days of the week, Sunday through

Saturday• Then enter the observations, or number of patients

admitted on the corresponding day of the week


Data Display

• Graphs– Graphs of various types are the best means

for presenting data for quick visualization of relationships

– They often supply a lesser degree of detail than tables

– Data presented in a graph can be helpful in displaying statistics in a concise manner


Data Display

• Graphs– Should be easy to read– Simple in content– Correctly labeled


Data Display

• Graphs – guidelines for creating graphs– Title

• Must relate what the graph shows as simply as possible

– Legend or key• Use when including two or more variables on the same

graph

– Categories• Should be natural

– The vertical axis should always start with zero

– The scale of values for the x-axis reads from the lowest value on the left to the highest on the right

– The scale of values for the y-axis extends from the lowest value at the bottom of the graph to the highest at the top


Data Display

• Graphs – guidelines for creating graphs– Scale captions

• Placed on both axes to identify the values clearly– These are simply titles placed on each axis to identify the

values

– Graphs should emphasize the horizontal• It is easier for the eye to read along the horizontal axis from

left to right– Graphs should be greater in length than height

• A guideline is to follow the three-quarter-high rule– This rule states that the height (y-axis) of the graph should be

three-fourths the length (x-axis) of the graph

– Source footnote– The exact reference to an outside source should be given


Data Display

• Bar Graphs– Also called bar charts– Appropriate for displaying categorical data– Simplest bar graph is a one-variable bar graph

• The various categories of observations are presented along a horizontal, or x-axis

• The vertical, or y-axis, displays the frequency of the data• Data representing frequencies, proportions, or percentages

of categories are often displayed using bar graphs

– A grouped bar chart is used to display information from tables containing two or three variables


Data Display

• Pie Charts– A method of displaying data as component parts of a

whole– A circle is divided into sections, like wedges or slices– These represent percentages of the total

(100 percent)– Data must be converted into percentages – Pie chart wedges may be shaded or colored to help

differentiate the sections– Additionally, they can be cut out of the pie to help

emphasize a percentage


Data Display

• Line Graphs• Used to show data over time• For example

– Days, weeks, months, or years

• The x-axis shows the time period • The y-axis show the values of the variables• Consists of a line connecting a series of points

on an arithmetic scale• Also allow for several variables to be plotted


Data Display

• Histograms– A representation that is used to display

frequency distributions for continuous numerical data (interval or ratio data)

– Difference from bar graphs• Bar graphs display data that fall into categories• Histograms illustrate frequency distribution of

continuous variables

– Histograms are created from frequency tables


Data Display• Frequency Polygon

– May be used instead of a histogram– It is similar to a histogram in that it is a graph depicting

frequency of continuous data, but, a frequency polygon is in line form instead of bar form

– An advantage is that several can be placed on the same graph to make comparisons

– Uses the same axes as the histogram, that is the x-axis displays the scale of the variable and the y-axis displays the frequency

– A dot is placed at the midpoint of the class interval or frequency– These dots are then connected by a line that is drawn from one

point to the next– Because the x-axis represents the entire frequency distribution,

the line starts at zero cases and is drawn from the last frequency to the y-axis to end with zero


Data Display

• Pictogram– An attractive alternative type of bar graph in

that it uses pictures to show the frequency of the data

– For example– If you wanted to show the number of

individuals you can use stick people– Can be very entertaining– Can catch the attention of your audience


Data Display

• Scatter Diagram– Also called scattergram, or scatter plot– The relationship between two numerical

variables is shown graphically– Used to determine if there is a correlation, or

a relationship, between two characteristics


Data Display

• Scatter Diagram– Correlation implies that as one variable changes, the

other also changes• This does not always mean that there is a cause and effect

relationship between two variables since there may be other variables that could cause the change

• If the two characteristics are somehow related, the pattern of points will show tight clustering in a certain direction

• The closer the points look like a line in appearance, the more the two characteristics are likely to be correlated


Data Display

• Scatter Diagram• The slope of the line can be positive or negative

– Positive = Small values of the x-axis correspond to small values of the y-axis and large values of the x-axis correspond to large values of the y-axis

– There is said to be a positive linear relationship– Negative = Small values of the x-axis correspond to large

values of the y-axis and large values of the x-axis correspond to small values of the y-axis

– There is said to be a negative linear relationship


Data Display

• Before deciding to use a table or graph decide who will be reading the material

• What detail is needed?

• You may decide to create tables, graphs as well as narrative discussion to report to help people under the data


Data Display

• When preparing reports– Be objective

• Report positive and negative points

– Use bias-free language– Be concise and strive for clarity– Proofread your document

• Review your grammatical skills

– Write in the style of your workplace

Calculating & Reporting Healthcare Statistics Second Edition Chapter 11 Presentation of Data.

Documents

Transcript of Calculating & Reporting Healthcare Statistics Second Edition Chapter 11 Presentation of Data.