Sie sind auf Seite 1von 5

Introduction Regression analysis is one of the statistical tools to determine the relationships between variables.

The researcher will seek to ascertain the causal effect of one variable upon another; such as the effect of increasing land price upon demand or effect of changes in the price of house upon the condition of panorama or scene of the construction site. To investigate such issues, the researcher needs to assemble data on the underlying variables of interest and use regression to estimate the quantitative effect of the causal variables upon the variable that they influence. Besides, the researcher also assesses the statistical significance of the estimated relationship, i.e. the degree of confidence, which is to determine whether the true relationship is close to the estimated relationship or not. Regression fits a linear function to a set of data. It needs a single dependent variable that we are trying to understand, explain and determine. The dependent variable must be a quantitative variable i.e. preferably measured on a continuous level. Regression approximates a set of coefficients that represent the effect of a single variable or a set of independent variables on the dependent variable. Independent variable can be measured into three types: qualitative level, continuous level or ordinal level.

Theoritical background and consideration Regression analysis with a single explanatory variable is termed as simple regression. However, multiple regression is a technique that allows additional factors to enter the analysis separately so that the effect of each can be estimated. It is useful to quantify the impact of various simultaneous influences upon a single dependent variable. For example, a study has been done to like to quantify and identify the factors that identify the factors that determine the wages in the labor market. There are lots of factors that are associated with variations in earnings among individuals; such as type of occupation, age, experience and educational attainment. For the time being let restrict attention to a single factor, for instance, experience. Hence, from the analysis, single regression can be done since it includes single explanatory variable. However,

multiple regression can be obtained when additional factors (independent variable) such as education level is introduced to the study.

Discussion and application Multiple regression will includes more than one independent variable, which allows including additional variables in the model and estimating their effects on the dependent variables as well. It is valuable for quantifying the impact of various simultaneous effects upon a single dependent variable. Relationships may be nonlinear, independent variables may be quantitative or qualitative, and one can examine the effects of a single variable or multiple variables with or without the effects of other variables taken into account. In multiple linear regression, there are p explanatory variables, and the relationship between the dependent variable and the explanatory variables is represented by the following equation: , where is the constant term, to are the coefficients

relating to the p explanatory variables to the variable of interest; and is the error term. Multiple linear regression can be explained as an extension of simple linear regression, where are p explanatory variables, or simple linear regression can be explained as a special case of multiple linear regression, where p = 1. The term linear is used so as to assume that y is directly related to a linear combination of the explanatory variables. The following example uses a data set for house sales by MN Company in east coast of Canada. Mostly buyers will ask the price of heating costs during winter. Three variables that are related to the heating costs during winter are (1) the mean temperature daily, (2) the number of inches of insulation in the attic and (3) the age of furnace. Hence to investigate, MN Companys research department selected a random sample of 5 recently sold homes. It also determined the cost to heat each home last December, as well. The data are as follow:

Home 1 2 3 4 5

Heating cost ($) 250 370 235 43 92

Mean outside temperature (oF) 35 29 32 40 60

Attic insulation (inch) 3 6 6 5 7

Age of furnace (years) 10 3 8 5 6

Assume that, based on the calculation has been done by Excel: Intercept Temperature Insulation Age Coefficients 427.194 4.583 14.831 6.101 Standard error 59.601 0.772 4.754 4.012

Hence, the multiple regression equation is Y = 427.194 4.583X1 14.831X2 + 6.10X3 From the multiple regression equation, the regression coefficient for mean outside temperature is 4.583. The coefficient is negative and shows an inverse relationship between heating cost and temperature. As the outside temperature increases, the cost to heat the home decreases. Besides, the attic insulation variable also shows an inverse relationship: the more insulation in the attic, the less the cost to heat the home. So the negative sign for this coefficient is logical. For each additional inch of insulation, we expect the cost to heat the home to decline $14.83 per month, regardless of the outside temperature or the age of the furnace. The age of the furnace variable shows a direct relationship. With an older furnace, the cost to heat the home increases. Specifically, for each additional year older the furnace is, we expect the cost to increase $6.10 per month. Hence, the heating cost of a house if the mean outside temperature is 30 oF, have 5 inch of insulation in the attic and the age of furnace is 10 years can be estimated by: Y = 427.194 4.583X1 14.831X2 + 6.10X3 = 427.194 4.583(30) 14.831(5) + 6.10(10) = 276.56

R is a measure of the correlation between the observed value and the predicted value of the criterion variable. From the calculation above, the correlation would be between the heating cost of a house and other levels predicted for them by the variable. R-square (R2) is the square of the measure of correlation and indicates the proportion of the variance in the criterion variable which is accounted by the model in my example the proportion of the variance in the heating cost of the house by our set of predicator variable (mean temperature daily, etc.). it will determine on how good a predication of the criterion variable that can be made by knowing the predicator variables. However R2 tends to somewhat over-estimate the success of the model. Adjusted R-square value is calculated which takes into account the number of variables in the model and number of observations in the model.

Conclusion Multiple regression involves having more than one independent variable in the model. This allows us to estimate more sophisticated models with many explanatory variables influencing a single dependent variable. Multiple regression also allows us to estimate the relationship of each independent variable to the dependent variable while controlling for the effects of the other independent variables in the model. Although the model is linear in its parameters, it can be used to model non-linear relationships by appropriately choosing the dependent and independent variables. It also allows the independent variables to be correlated. Multiple regression requires that the dependent variable is measured on a continuous level, but it has great flexibility for the independent variables.

References Granger, C. W. J. & Newbold, P. 1974. Spurious Regressions in Econometrics. Journal of Econometrics 2: 111-120 Imbens, G. W. & Lemieux, T. 2007. Regression discontinuity design; A guide to practice. Journal of Econometrics. doi 10/1016/j.jeconom.2007.05.001 Imbens, G., Van Der Klaauw, W., 1995. Evaluating the cost of conscription in The Netherlands. Journal of Business and Economic Statistics 13, 7280. Pagan, A., Ullah, A., 1999. Nonparametric Econometrics. Cambridge University Press, Cambridge. Hardle, W., 1990. Applied Nonparametric Regression. Cambridge University Press, Cambridge.

DEPARTMENT OF LAND MANAGEMENT FACULTY OF AGRICULTURE

AGR 5201 ADVANCED STASTICAL METHODS

ASSIGNMENT REGRESSION AND MULTIPLE REGRESSION ANALYSIS (ANALYSIS OF REGRESSION OF HOUSING ASPECT)

NAME MATRIC NO.

: CLAOSTON ANAK NARDON : GS30120

Das könnte Ihnen auch gefallen