In: Statistics and Probability
Statistics paper on the topic.
The title will be:
The Relationship between African American, Caucasian, and Graduates of a Bachelor Degree: A Case of New York
Need help or a sample of :
a. Introduction
b. Background of the Study
c. Purpose of the Study
d. Theoretical Framework (including independent and dependent variables).
e. Research Questions and Hypotheses.
f. Definition of variables.
g. Summary
f. Conclusion
First we know about LINEAR MODEL.These we can understood by rgression analysis.Qoustion in our mind what is linear model & regression analysis.
REGRESSION ANALYSIS:
Regression analysis is also usedto understand which among the independent variables are related to the dependent variable. what pattern draw when we use independent variable means that how figure is draw just like linear or curve.
eg: The Relationship between African American, Caucasian, and Graduates of a Bachelor Degree: A Case of New York
In above example we find what relation are found between each other.
Regression analysis are two type
1) Simple regression analysis(In which only one independent variable)
Yi=0+1X1+i
2)Multiple regression analysis(in which more than one independent variable)
Yi=0+iXi+j
What is dependent & independent variable:
In above model Xi are independent variable & Yi are dependent varible.
Independent variable are those variable which does't depend on any other variable & Dependent variable are those variable which depend on any other variable.
I Example 1.2 A real estate appraiser uses the square footage of houses to derive individual appraisal values on each house. The sales values and size of 100 houses are available. The least squares results by EXCEL are shown in the output overleaf. The results show that the estimated equation is determined as
VALUE \ = ?50034.607 + 72.82SIZE
Definition of Variable:
In programming, a variable is a value that can change, depending on conditions or on information passed to the program. Typically, a program consists of instruction s that tell the computer what to do and data that the program uses when it is running.
Testing of hypothesis:
The full model. Again, the full model is the model containing all of the possible predictors:
yi=(?0+?1xi1+?2xi2+?3xi3)+?iyi=(?0+?1xi1+?2xi2+?3xi3)+?i
The error sum of squares for the full model, SSE(F), is just the usual error sum of squares, SSE. Alternatively, because the three predictors in the model are x1, x2, and x3, we can denote the error sum of squares as SSE(x1, x2, x3). Again, because there are 4 parameters in the model, the number of error degrees of freedom associated with the full model is dfF = n - 4.
The reduced model. Null hypothesis sets the first slope parameter, ?1, equal to 0, the reduced model is:
yi=(?0+?2xi2+?3xi3)+?iyi=(?0+?2xi2+?3xi3)+?i
Because the two predictors in the model are x2 and x3, we denote the error sum of squares as SSE(x2, x3). Because there are 3 parameters in the model, the number of error degrees of freedom associated with the reduced model is dfR = n - 3.
The test. The general linear statistic:
F?=[SSE(R)?SSE(F)]/(dfR?dfF)÷SSE(F)dfF
F?=[SSE(R)?SSE(F)]/(dfR?dfF)÷SSE(F)/dfF
simplifies to:
F?=SSR(x1|x2,x3)1÷SSE(x1,x2,x3)n?4=MSR(x1|x2,x3)MSE(x1,x2,x3)
F calculated is less than F tabulated then the variable are significant otherwise not significant if Fcalculated >Ftabulated.