h2(#description). Description This template will run an F-test to check if two continuous variables have the same means. h3(#introduction). Introduction F test compares the means of two continuous variables. In other words it shows if their means were statistically different. We should be careful, while using the F test, because of the strict normality assumption, where strict means approximately normal ditribution is not enough to satisfy that. h3(#normality-assumption-check-internet-usage-for-educational-purposes-hours-per-day). Normality assumption check (_Internet usage for educational purposes (hours per day)_) The "_Shapiro-Wilk test_":http://en.wikipedia.org/wiki/Shapiro%E2%80%93Wilk_test, the "_Lilliefors test_":http://en.wikipedia.org/wiki/Lilliefors_test and the "_Anderson-Darling test_":http://en.wikipedia.org/wiki/Anderson_Darling_test help us to decide if the above-mentioned assumption can be accepted of the _Internet usage for educational purposes (hours per day)_.
Method Statistic p-value
Lilliefors (Kolmogorov-Smirnov) normality test 0.2223 2.243e-92
Anderson-Darling normality test 42.04 3.31e-90
Shapiro-Wilk normality test 0.7985 6.366e-28
So, the conclusions we can draw with the help of test statistics: * based on _Lilliefors test_, distribution of _Internet usage for educational purposes (hours per day)_ is not normal * _Anderson-Darling test_ confirms violation of normality assumption * according to _Shapiro-Wilk test_, the distribution of _Internet usage for educational purposes (hours per day)_ is not normal As you can see, the applied tests confirm departures from normality. h3(#normality-assumption-check-age). Normality assumption check (_Age_) The "_Shapiro-Wilk test_":http://en.wikipedia.org/wiki/Shapiro%E2%80%93Wilk_test, the "_Lilliefors test_":http://en.wikipedia.org/wiki/Lilliefors_test and the "_Anderson-Darling test_":http://en.wikipedia.org/wiki/Anderson_Darling_test help us to decide if the above-mentioned assumption can be accepted of the _Internet usage for educational purposes (hours per day)_.
Method Statistic p-value
Lilliefors (Kolmogorov-Smirnov) normality test 0.17 6.193e-54
Anderson-Darling normality test 32.16 1.26e-71
Shapiro-Wilk normality test 0.8216 9.445e-27
So, the conclusions we can draw with the help of test statistics: * based on _Lilliefors test_, distribution of _Age_ is not normal * _Anderson-Darling test_ confirms violation of normality assumption * according to _Shapiro-Wilk test_, the distribution of _Age_ is not normal As you can see, the applied tests confirm departures from normality. _In this case it is advisable to run a more robust test, then the F-test._ h2(#description-1). Description This template will run an F-test to check if two continuous variables have the same means. h3(#introduction-1). Introduction F test compares the means of two continuous variables. In other words it shows if their means were statistically different. We should be careful, while using the F test, because of the strict normality assumption, where strict means approximately normal ditribution is not enough to satisfy that. h3(#the-f-test). The F-test Here is the the result of the _F test_ to compare the means of _Internet usage for educational purposes (hours per day)_ and _Age_.
Method Statistic p-value
F test to compare two variances 0.08618 3.772e-180
We can see from the table (in the p-value coloumn) that there is a significant difference between the means of _Internet usage for educational purposes (hours per day)_ and _Age_. h2(#description-2). Description This template will run an F-test to check if two continuous variables have the same means. h3(#introduction-2). Introduction F test compares the means of two continuous variables. In other words it shows if their means were statistically different. We should be careful, while using the F test, because of the strict normality assumption, where strict means approximately normal ditribution is not enough to satisfy that. h3(#the-f-test-1). The F-test Here is the the result of the _F test_ to compare the means of _cyl_ and _drat_.
Method Statistic p-value
F test to compare two variances 11.16 1.461e-09
We can see from the table (in the p-value coloumn) that there is a significant difference between the means of _cyl_ and _drat_.
This report was generated with "R":http://www.r-project.org/ (3.0.1) and "rapport":http://rapport-package.info/ (0.51) in _0.814_ sec on x86_64-unknown-linux-gnu platform. !images/logo.png!