Data Presentation Esra Akdeniz February 12th, 2016
HOW TO DO RESEARCH? Question. Literature research. Hypothesis. Collect data. Analyze data. Interpret and present results.
HOW TO DO RESEARCH? Analyze data.
WHAT IS DATA? Data is a collection of facts, such as values or measurements. It can be numbers, words, measurements, observations or even just descriptions of things.
AIDS Patients Suffering from Kaposi s Sarcoma Generated by CamScanner from intsig.com
Types of Numerical Data Qualitative data Nominal data Ordinal data Quantitative data Discrete data Continuous data
Qualitative data Nominal data: Unordered categories or classes. Ordinal data: The order of the categories are important. Arithmetic operations make no sense, because magnitude of numbers is not the main interest.
Example A clinical trial is an experimental study involving human subjects with the purpose of (usually) comparing treatments for a certain type of disease.
Quantitative data Discrete data: Both ordering and magnitude are important. Cannot be fractions. Ex: number of tuberculosis patients in a hospital. Continuous data: Can take real values, not limited to integers. Can be fractions. Ex: time, temperature.
Types of Numerical Data Nominal Ordinal Discrete Continuous Each data type requires a specific way to describe it.
Examples The length of time that a cancer patient survives after diagnosis. The number of miscarriages a woman had. My top five favourite tv channels. Gas prices in Turkey.
Tables Frequency Distribution. Relative Frequency.
Frequency Distribution Kaposi s Number Sarcoma of Individuals Yes 246 No 2314 Year Number of Cigarettes 1900 54 1910 151 1920 665 1930 1485 1940 1976 1950 3522 1960 4171 1970 3985 1980 3851 1990 2828
Frequency Distribution (Cont d) Can we use frequency distributions for discrete or continuous data?
Frequency Distribution (Cont d) Can we use frequency distributions for discrete or continuous data? Yes, by breaking data into distinct intervals.
Frequency Distribution (Cont d) Can we use frequency distributions for discrete or continuous data? Yes, by breaking data into distinct intervals.
Frequency Distribution (Cont d) Can we use frequency distributions for discrete or continuous data? Yes, by breaking data into distinct intervals. Cholesterol Number Level of Men 80-119 13 120-159 150 160-199 442..
Relative Frequency The relative frequency for an interval is the proportion of the total number of observations that appear in that interval. Useful for data sets with unequal number of observations in each interval. The cumulative relative frequency for an interval is the percentage of the total number of observations that have a value less than or equal to the upper limit of the interval.
Graphs Bar Charts: Representation of frequency distribution for either nominal or ordinal data. Generated by CamScanner from intsig.com
Histogram Representation of frequency distribution for either discrete or continuous data.
Histogram Representation of frequency distribution for either discrete or continuous data. Absolute frequency versus Relative frequency.
Histogram Representation of frequency distribution for either discrete or continuous data. Absolute frequency versus Relative frequency. Generated by CamScanner from intsig.com
Scatter Plot Used to depict the relationship between two different continuous measurements: nonlinear, linear, positive, negative, no relationship. Each point in the plot represents a pair of values.
Scatter Plot Used to depict the relationship between two different continuous measurements: nonlinear, linear, positive, negative, no relationship. Each point in the plot represents a pair of values.
Scatter Plot (Cont d)
Scatter Plot (Cont d)
Line Graphs Similar to scatter plots, instead of points, we have lines. Difference: Each value on x-axis has a single corresponding measurement on the y-axis.
Line Graphs Similar to scatter plots, instead of points, we have lines. Difference: Each value on x-axis has a single corresponding measurement on the y-axis.