❑Partial and Multiple Correlation
❑Multiple Regression.
Types of Correlation
❖ Positive Linear Correlation:
There is a positive linear correlation when the variable on the x-axis increases as the
variable on the y-axis increases. This is shown by an upwards sloping straight regression line.
❖ Negative Linear Correlation:
There is a negative linear correlation when the variable on the x-axis increases as the
variable on the y-axis decreases. This is shown by an downwards sloping straight regression
line.
❖ Non-linear Correlation (known as curvilinear correlation):
There is a non-linear correlation when there is a relationship between variables but the
relationship is not linear (straight).
❖ No Correlation:
There is no correlation when there is no pattern that can be detected between the variables.
There are three types based upon the number of variables studied as
❑ Simple Correlation
❑ Multiple Correlation
❑ Partial Correlation
Simple Correlation:
If only two variables are taken for study then it is said to be simple correlation.
Ex. Y= a + bX
Example: The relationship between the daily temperature (in degrees Fahrenheit) and
daily ice cream sales (in dollars) in a particular city
Multiple Correlations:
❑ Multiple correlation is the study of combined influence of two or
more variables on a single variable.
❑ If three or more than three variables are studied simultaneously,
then it is termed as multiple correlation.
Example:
Prediction of a student's final exam score (dependent variable) based on multiple
independent variables, such as hours spent studying per week, attendance in class, and the
number of practice quizzes taken.
The Multiple R can be calculated for two predictor variables is
Example:
Find the correlation between academic achievement and the linear
combination of intelligence and anxiety
Partial Correlation:
If there are more than two variables but only two variables are considered keeping the
other variables constant, then the correlation is said to be Partial Correlation.
Example:
The relationship between diet (in terms of daily calorie intake) and weight loss (in
pounds) while accounting for the influence of exercise (in hours per week). The partial
correlation between diet and weight loss while controlling for exercise.
Example:
Find the partial correlation between the
two variables, academic achievement
and anxiety controlled for intelligence
Solution:
Other formula for coefficient of correlation:
r=
∑ ( x − x )( y − y ) =
∑ XY
2 2 2 2
∑ ( x − x ) ∑ (y − y ) ∑ X ∑Y
Find the Karl Pearson’s coefficient of correlation for the following data
Marks in accounts 48 35 17 23 47
Marks in stats 45 20 40 25 45
Rank Correlation:
Type1: when ranks are given/
not given:
Type 3: when the data is repeated
RANK CORRELATION
❖ It is studied when no assumption about the parameters of the population is made.
❖ This method is based on ranks.
❖ It is useful to study the qualitative measure of attributes like honesty, colour, beauty,
intelligence, character, morality etc.
❖ The individuals in the group can be arranged in order and there on, obtaining for each
individual a number showing his/her rank in the group. This method was developed
by Edward Spearman in 1904.
❖ It is defined as
Type1: when ranks are given:
Type 2: When the ranks are not given
Regression Analysis- Simple Linear Regression
Simple linear regression is a model that assesses the relationship between a
dependent variable and an independent variable. The simple linear model is
expressed using the following equation:
Y=a+bX+Ɛ
where
Y- Dependent variable
X- Independent variable
a- Intercept
b-slop
Ɛ- Residual
Lines of Regression:
A line of regression is the line which that the best estimate of one variable for any given
value of the other variable.
Regression lines are of two types:
1) Regression line of X on Y
2) Regression line of Y on X
∑ XY − ∑ X ∑Y
σX N
Where bXY = r = 2
σY
2 (∑ )
Y
∑Y −
N
Regression Equation of Y on X:
This line can also be expressed as
σy
y-y=r (x-x)
σx
∑ X ∑Y
σy ∑ XY − N
Where b YX =r = 2
σx (∑ X )
2
X
∑ − N
here x and y are means of x and y series respectively
and is known as the regression coefficient of y on x
𝑦
𝑥
𝑏
1. From the following data, find
(i) The two regression equation
(ii) The coefficient of correlation between the marks in Economic and Statistics.
(iii) The most likely marks in statistics when marks in Economic are 30.
Regression equations through least square method:
The regression line of Y on X:
The regression line of X on Y:
Properties of Regression Coefficient:
1. Correlation coefficient is the geometric mean between the regression coefficient
2. One of the regression coefficient is grater than unity , the other must be less than
unity.
3. If r= 0, then the regression line are perpendicular to each other
if r= ±1 then regression lines are coincide.
NOTE:
• Regression analysis Problems
1. From the following data calculate regression equations
x 6 2 10 4 8
y 9 11 5 8 7
2. Height of the father and sons are given below. Find the height of the son when
the height of the father is 70 inches
Father 71 68 66 67 70 71 70 73 72 65 66
Son 69 64 65 63 65 62 65 64 66 59 62
3. From the data given below find the two regression equations
X 25 28 35 32 31 36 29 38 34 32
Y 43 46 49 41 36 32 31 30 33 39
1. From the following data obtain the two regression equations using least square
method x 6 2 10 4 8
y 9 11 5 8 7
2. For certain X and Y series which are correlated , the two
lines of regressions are
5 x − 6 y + 90 = 0
15 x − 8 y − 130 = 0
Find the mean of two series and the correlation coefficient.
3.
Multiple Regression
As the number of children in a dual-career household increases by one, the husband’s
hours of housework per week increases on average by 0.65 hours (about 39 minutes),
controlling for husband’s education
As the husband’s years of education increases by one year, the number of
hours of housework per week decreases on average by 0.07 (about 4
minutes), controlling for the number of children
With zero children in the family and a husband with zero years of education,
that husband is predicted to complete 2.5 hours of housework per week on
average
