Entering of Data into SPSS:
Determining the appropriate Statistical Test:
In order to analyse our data, it is important to determine the appropriate statistical test that is being used. The type of statistical test chosen depends on:
1. Type of research question
"Is a person's BMI related to his height?"
As seen from above, our research topic falls under as a correlation question.
2. Type of measurement of variables
With regards to our independent (height) and dependent (BMI) variables, both variables are scale type of measurements.
Therefore, having considering these in mind first, we have decided to use the Pearson’s r test.
Pearson's r is a symmetric measure of association for interval level variables. Pearson's correlation coefficient ranges from -1.0 (perfect negative relationship) to +1.0 (perfect positive relationship).
When using Pearson's r, it is important to take note of four assumptions:
Assumption 1: All observations must be independent of each other
Assumption 2: The dependent variable should be normally distributed at each value of the independent variable
Assumption 3: The dependent variable should have the same variability at each value of the independent variable
Assumption 4: The relationship between the dependent and independent variables should be linear
As these assumptions are fulfilled in our data, we are able to use Pearson’s r as our statistical test.
***
Data Analysis 1:
Research hypothesis H1: There is a relationship between a person’s BMI and his height.
Null hypothesis H0: There is no relationship between a person’s BMI and his height.
So firstly, we have generated a scatter plot in the diagram shown above. The scatter plot appears to follow a general positive linear trend, although it shows the relationship is very weak. However, there is no violation of the linearity assumption.
Following that, we can compute Pearson's r.
From the table above,
Pearson's r value is 0.199 → This shows that there is a positive but very weak relationship between BMI and height.
However, the p value shows 0.218 (> 0.05). When p > 0.05, we accept the null hypothesis (H0).
In conclusion, there is no relationship between a person’s BMI and his/her height.
***
Data Analysis 2:
From our literature review, we found out that there is a difference in the relationship between height and weight for males and females. Therefore, we would like to find out if gender do make a difference in the BMI-height relationship.
(For females)
Research question: Is a female's BMI related to her height?
Research hypothesis H1: There is a relationship between a female’s BMI and her height.
Null hypothesis H0: There is no relationship between a female’s BMI and her height.
From the table above,
Pearson's r value is 0.046 → This shows that there is a positive but very weak relationship between BMI and height for females.
The p value is 0.848 (> 0.05). When p > 0.05, we accept the null hypothesis (H0).
Therefore, there is no relationship between females's BMI and his height.
(For males)
Research question: Is a male's BMI related to his height?
Research hypothesis H1: There is a relationship between a male’s BMI and his height.
Null hypothesis H0: There is no relationship between a male’s BMI and his height.
From the table above,
Pearson's r value is -2.24 → This shows that there is a negative relationship between BMI and height for males.
The p value is 0.343 (> 0.05). When p > 0.05, we accept the null hypothesis (H0).
Therefore, there is no relationship between males's BMI and his height.
***
Data Analysis 3:
With the results we found as mentioned previously, our group wanted to explore a little further if a person's BMI is related to his weight instead.
Research question: Is a person's BMI related to his weight?
Research hypothesis H1: There is a relationship between a person’s BMI and his weight.
Null hypothesis H0: There is no relationship between a person’s BMI and his weight.
A scatter plot was generated and it appears to follow a positive linear trend with a strong relationship.
Next, the pearson's r value was computed.
From the table above,
Pearson's r value is 0.866 → This shows that there is a strong positive relationship between BMI and weight for both males and females
The p value is 0.000 (< 0.05). When p < 0.05, we reject the null hypothesis (H0). Therefore, there is relationship between a person’s BMI and his/her weight.
Determining the appropriate Statistical Test:
In order to analyse our data, it is important to determine the appropriate statistical test that is being used. The type of statistical test chosen depends on:
1. Type of research question
"Is a person's BMI related to his height?"
As seen from above, our research topic falls under as a correlation question.
2. Type of measurement of variables
With regards to our independent (height) and dependent (BMI) variables, both variables are scale type of measurements.
Therefore, having considering these in mind first, we have decided to use the Pearson’s r test.
Pearson's r is a symmetric measure of association for interval level variables. Pearson's correlation coefficient ranges from -1.0 (perfect negative relationship) to +1.0 (perfect positive relationship).
When using Pearson's r, it is important to take note of four assumptions:
Assumption 1: All observations must be independent of each other
Assumption 2: The dependent variable should be normally distributed at each value of the independent variable
Assumption 3: The dependent variable should have the same variability at each value of the independent variable
Assumption 4: The relationship between the dependent and independent variables should be linear
As these assumptions are fulfilled in our data, we are able to use Pearson’s r as our statistical test.
Data Analysis 1:
Research hypothesis H1: There is a relationship between a person’s BMI and his height.
Null hypothesis H0: There is no relationship between a person’s BMI and his height.
So firstly, we have generated a scatter plot in the diagram shown above. The scatter plot appears to follow a general positive linear trend, although it shows the relationship is very weak. However, there is no violation of the linearity assumption.
Following that, we can compute Pearson's r.
From the table above,
Pearson's r value is 0.199 → This shows that there is a positive but very weak relationship between BMI and height.
However, the p value shows 0.218 (> 0.05). When p > 0.05, we accept the null hypothesis (H0).
In conclusion, there is no relationship between a person’s BMI and his/her height.
Data Analysis 2:
From our literature review, we found out that there is a difference in the relationship between height and weight for males and females. Therefore, we would like to find out if gender do make a difference in the BMI-height relationship.
(For females)
Research question: Is a female's BMI related to her height?
Research hypothesis H1: There is a relationship between a female’s BMI and her height.
Null hypothesis H0: There is no relationship between a female’s BMI and her height.
From the table above,
Pearson's r value is 0.046 → This shows that there is a positive but very weak relationship between BMI and height for females.
The p value is 0.848 (> 0.05). When p > 0.05, we accept the null hypothesis (H0).
Therefore, there is no relationship between females's BMI and his height.
(For males)
Research question: Is a male's BMI related to his height?
Research hypothesis H1: There is a relationship between a male’s BMI and his height.
Null hypothesis H0: There is no relationship between a male’s BMI and his height.
From the table above,
Pearson's r value is -2.24 → This shows that there is a negative relationship between BMI and height for males.
The p value is 0.343 (> 0.05). When p > 0.05, we accept the null hypothesis (H0).
Therefore, there is no relationship between males's BMI and his height.
Data Analysis 3:
With the results we found as mentioned previously, our group wanted to explore a little further if a person's BMI is related to his weight instead.
Research question: Is a person's BMI related to his weight?
Research hypothesis H1: There is a relationship between a person’s BMI and his weight.
Null hypothesis H0: There is no relationship between a person’s BMI and his weight.
A scatter plot was generated and it appears to follow a positive linear trend with a strong relationship.
Next, the pearson's r value was computed.
From the table above,
Pearson's r value is 0.866 → This shows that there is a strong positive relationship between BMI and weight for both males and females
The p value is 0.000 (< 0.05). When p < 0.05, we reject the null hypothesis (H0). Therefore, there is relationship between a person’s BMI and his/her weight.
No comments:
Post a Comment