Professional Documents
Culture Documents
BMB-308
TUTORIAL
REPORT AND PRESENTATION
TOPICS:REGRESSION ANALYSIS
Group-6 presented by
1.M.D.Jahirul Islam(1039)
2.A.Z.M.Ariful Islam(1050)
3.M.D.Gulzar Hossain(1043)
4.M.D.Mostafizur Rahman(1220)
What is statistics?
Statistics is a field of study concerned with
1.Collection,organization,summarization and
analysis of data.
2.Drawing of inference about a body of data.
What is biostatistics?
When tools of statistics are employed in analyze of
data derived from biological science and medicine
Term needed to understand regression analysis
Variable: Observed characteristics have different value in different
person, places or things
The purpose of correlation is to determine if two variables are linearly related to each
other
The correlation coefficient tells us:
the strength of the relation
the direction of the relation (direct or indirect)
The correlation coefficient, however, does not tell us how the variables are related
I.e., it does not tell us how to predict the value of one variable given the value of the
other
ASSUMPTION UNDERLYING SIMPLE LINEAR REGRESSION:
In the simple linear regression model two variables, X and Y. The
variable X is usually referred to as the independent variable. Values
of X is selected by the investigator and corresponding to each
preselected value of X, one or more values of Y are obtained. Y is
called the dependent variable
1.Values of the independent variable X are said to be fixed, this
means that values of X are preselected by the investigator . X is
also referred to as a nonrandom variable and mathematical
variable.
2.The variable X is measured without error.
3.For each value of X there is a subpopulation of Y values, these
subpopulation must be normally distributed.
4.The variances of the subpopulations of Y are all equal.
5.The means of the subpopulations of Y all line in the same straight
line . This is known as the assumption of linearity . This assumption
may be expressed as µ y/x=α+βx. Where μ y/x is the mean of
the subpopulation of the Y values for particular X value,α and β are
called population regression coefficients.α and β represent the y
intercept and slope.
6.The Y values are statistically independent, the X values are
dependent.
The regression model is y=α + βx + e. Where e is the error term.
e=y-(α+βx)
The scattered diagram of two variables, lipid peroxide
and bilirubin show that they are correlated
So we can do regression analysis procedure within this
variable.
20 number of observation
The average amount of L.P.O. for each individual is 1.5121
The average amount of bilirubin for each individual is
0.2281
Standard Deviation in case of L.P.O.is 0.7165
Standard Deviation in case of bilirubin is 0.7165
Correlation coefficient:
between LPO and bilirubin is 0.708 is very close to 1. that means
they are highly correlated.
Coefficient of determination:
r2=0.502
*50% variation in regression variable Y can be explained by the total
variation in X.
So the regression model moderately fits the sample data.
(the regression co-efficient is moderate when the value of r2 lies
between 0.50 to 0.70,
the regression co-efficient is good when the value of r2 lies
between 0.70 to 1.0, the regression co-efficient is poor when the
value of r2 is less then 0.50)
Adjusted r square gibes more accurate value
ANOVA : There is a significant effect of the independent
variable on the dependent variable . So, β have significant
effect on regression model.
COEFFICIENT : When there is no amount of bilirubin in
the individual body yet at least 0.367 amount of LPO exist
in his body.
If we increase 1 unit of bilirubin than LPO. Is increased
5.018 per unit.
T statistics : The result is .226>level of significance α.Do
not reject nul hypothesis at 5% level of significance.