Scribd
Upload
7 views

Methods of Data Analysis

Uploaded by

kdiana
Copyright
© © All Rights Reserved
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
7 views

Methods of Data Analysis

Uploaded by

kdiana
Copyright
© © All Rights Reserved
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
You are on page 1/ 3

Methods of Data Analysis

 Methods of data analysis

o Visual analysis

 We use visual analysis

 Most common method of data analysis in single subject research

 Can be somewhat subjective

 Examination of level and trend

o Statistical analysis

o Qualitative analysis

 Researchers also analyze

o The number of data points in each phase

 In clinical settings we look at this

o Arithmetic means across phases

o Variability of performance

o Level of performance

o Direction of trend

o Overlaps in data points

 Before visual analysis can be done

o Legends, axes, and phases must be labeled

o All data points must be connected appropriately

 Can’t connect data points over phase change lines

o Scaling of the Y axis must be appropriate


 changes in performance appear commensurate with clinical significance

 don’t shrink or resize your graph to make it look like a bigger effect

o Must know if data predict the performance of an individual or a group

 How many data points per phases?

o Should be sufficient to make reasonable determination of whether the data path

accurately represents performance on the dependent variable

o The greater number of data points the more confident the determination

o May be less if it’s clear that the dependent variable is not likely to change without

phase change

 Variability

o Less data points are needed in a phase if the performance is showing little

variability

 Flat data path at a given level

 Stead data path with a clear trend

 Data points and phases

o The more repeat phases the fewer data points are needed in each phase

o Ethical decisions with reversals and prolonged baselines may make phases wit

few data points acceptable

o Level of behavior refers to performance of the DV as it is viewed vertically on the

graph

 Trend

o Trend refers to the direction of the data path (stable, etc)

o We are concerned whether the data path is


 Flat

 Stable

 Ascending

 Descending

 Variable

o The more likely trends are similar between phases the less likely there is a

functional relationship

 Immediate change in level

o Immediate change in trend or level between phases is a good indictor of the

effects of your intervention

 Identify the last data point in the first phase and the first data point in the

subsequence phase

 Subtract the

You might also like