Download as pptx, pdf, or txt
Download as pptx, pdf, or txt
You are on page 1of 12

3.2.

2 models based on summarization

• Many statistical concepts are used to measure


– Abstraction & Summarization
• Mean, Median, Mode, Std Deviation, Variance
• Frequency Distribution is mostly used
– Many Tech. are available to rep. structure of data
graphically
• Histogram
• Box Plot
– Each region is divided into Quartiles
• Scatter diagram
– 2 axis rep
Box Plot Eg
Scatter Diagram eg
3.2.3 Bayes Theorem
• Is a tech to estimate the likelihood of a property given
the set of data as evidence or input
– ie. Either hypothesis h1 / h2 can occur but not both
– x can be the observed event
3.2.4 Hypothesis Testing
• Attempts to find a model that explains the
observed data by first creating a hypothesis
and then testing that hypothesis against the
data
– Given : a Population
– Initial hypothesis to be tested is H0  null hypo
– Hypo causes another hypo is H1  alternate hypo
– Chi-squared statistics is used for hypo testing
3.2.5 Bivariate Regression & Correlation
• Reg  Used to predict future values
• Corr  used to examine the degree of two
values behave similarly
– Linear Reg : relationship b/w i/p and o/p data
– Y = c0 + c1x1 + ……..cnxn
(nPredictors/regressors, Y response)
• Correlation:
3.4 Decision Trees
• Predictive modeling tech
• Used for
– Classification
– Clustering
– prediction

You might also like