INDEPENDENT T-
TEST
INTRODUCTION
• The independent t-test compares the means between two unrelated
groups
• Example : To test whether Job Satisfaction differed based on Gender
• Dependent variable: Job Satisfaction
• Independent variable: Gender, which has two groups: "male" and "female").
INTRODUCTION
• Assumptions
• Dependent variable should be measured on a continuous scale
• Independent variable should consist of two categorical, independent
groups.
• Independence of observations
• No outlier (unusual data point)
• Dependent variable should be approximately normally distributed for
each group of the independent variable
• Homogeneity of variances (variances approximately equal across
groups)
SAMPLES
• Sample data file:
• C:\Program Files (x86)\SPSSInc\…\Samples\English\[Link]
• To test whether Job Satisfaction, Household income… differed based on Gender
• Dependent variable: Job Satisfaction
• Independent variable: Gender, which has two groups: "male" and "female").
• Hypothesis:
• H0: µ1 - µ2 = 0 ("there no difference between means of two population")
H1: µ1 - µ2 ≠ 0 ("the difference between the two population means is not 0")
• The differences between 2 means
• Levene’s Test
• t statistic
LEVENE’S TEST FOR EQUALITY OF
VARIANCES
• To test Homogeneity of variances (variances approximately equal across
groups)
• F is the test statistic of Levene's test. Sig. is the p-value corresponding to this
test statistic.
• Levene's test should be Insignificant
• If result of Levene's test is significant -> variances approximately NOT equal
across groups => See the result of t-statistic in the row Equal variances not
assumed
T-TEST FOR EQUALITY OF MEANS
• t: computed test statistic. t > 1.96 -> significant
• df is the degrees of freedom
• Sig (2-tailed) is the p-value corresponding to the given test statistic and
degrees of freedom
• Mean Difference is the difference between the sample means; it also
corresponds to the numerator of the test statistic
• Std. Error Difference is the standard error; it also corresponds to the
denominator of the test statistic
• Example of conclusion: There was no difference in mean Household Income
between male and female (t6398 = 0.702, p =.483)
ONE-WAY ANOVA
ONE-WAY ANALYSIS OF VARIANCE
INTRODUCTION
• One-Way ANOVA is commonly used to test the differences among the means of two or more
groups, interventions or change scores
• Both the One-Way ANOVA and the Independent t Test can compare the means for two groups.
However, only the One-Way ANOVA can compare the means across three or more groups.
• Assumptions
• Dependent variable should be measured on a continuous scale
• Independent variable should consist of two or more categorical, independent groups.
• Independence of observations
• No outlier (unusual data point)
• Dependent variable should be approximately normally distributed for each group of the
independent variable
• Homogeneity of variances (variances approximately equal across groups)
SAMPLES
• Sample data file:
• C:\Program Files (x86)\SPSSInc\…\Samples\English\[Link]
• To test whether Household income… differed based on
• Dependent variable: Household income…
• Independent variable: Years with current employer , which has 3 groups: “Less
than 5“, “5-15” and “more than 15").
• Hypothesis:
• H0: µ1 = µ2 = µ3 = ... = µk ("all k population population means are equal")
H1: At least one µi different ("at least one of the k population means is not equal to
the others")
• The differences among the means
• Levene’s Test
• F statistic
LEVENE’S TEST FOR EQUALITY OF
VARIANCES
• To test Homogeneity of variances (variances approximately equal across
groups)
• Levene Statistic: Sig. is the p-value corresponding to this test statistic.
• Levene's test should be Insignificant
• If result of Levene's test is significant -> variances approximately NOT equal
across groups. The result maybe due to the large number of samples that
could make any small difference be significant => Have to argue the result.
ANOVA TABLE
• F statistic. df is the degrees of freedom
• Sig is the p-value corresponding to the given test statistic and Between group
degrees of freedom
• Anova table show the difference between group means, but we do not know
which of the specific groups differed
• Multiple Comparisons table shows which groups differed from each other
• Post-hoc Test:
compare 2
means
EXAMPLE OF REPORTING THE OUTPUT
• There was a statistically significant difference between groups as determined
by one-way ANOVA (F(2,6397) = 1054.203, p < .001).
• Based on purpose of study, we focus on the comparison of specific groups. i.e
A Tukey post-hoc test revealed that Household income in thousand is lower in
group “Less than 5 years” (M=35.58 ± 24.26 ) compared to group “5-15”
(M=54.38 ± 41.06, p<0.001) and “more than 15” (M=130.35 ± 116.13,
p<0.001)
TWO-WAY ANOVA
AND
UNIVARIATE MODEL
EXAMPLE
Dependent variable: Household income in thousand (continuous variable)
Independent variables: Gender, Years with current employer
Gender
Male Female
Years with Less than 5
current
employer 5-15 years
More than 15
CHI-SQUARE TEST
INTRODUCTION
• The chi-square test for independence (Pearson's chi-square test, the chi-
square test of association) is used to discover if there is a relationship between
two categorical variables.
• Assumptions
• Two variables should be measured at an ordinal or nominal level
• Two variable should consist of two or more categorical, independent groups
• Sample data file:
• C:\Program Files (x86)\SPSSInc\…\Samples\English\[Link]
• Is there a relationship between Year with current employer and Income
category in thousand?
• Year with current employer: 3 categories (less than 5, 5-15, more than 15)
• Income category in thousand: 4 categories (<25, 25-49, 50-74, >75)
• χ(6) = 0.2506, p <0.001 => There is a
statistically significant association between
between Year with current employer and
Income category in thousand
PEARSON
CORRELATION
INTRODUCTION
• The bivariate Pearson Correlation produces a sample correlation coefficient, r,
which measures the strength and direction of linear relationships between
pairs of continuous variables.
• Assumption:
• Two variables should be measured at the interval or ratio level (continuous
variables)
• No significant outliers
• Approximately normally distributed
• Sample data file:
• C:\Program Files (x86)\SPSSInc\…\Samples\English\[Link]
• Pearson correlation indicates
• Whether a statistically significant linear relationship exists between two
continuous variables
• The strength of a linear relationship (i.e., how close the relationship is to being a
perfectly straight line)
• The direction of a linear relationship (increasing or decreasing)
• Significant? Weight and height have a statistically significant linear relationship
(p < .001).
• The direction of the relationship is positive (or negative correlated)?
• The magnitude, or strength, of the association is strong (.5 < | r |) , moderate
(.3 < | r | < .5), or weak (.3 > | r |) ?
LINEAR REGRESION
INTRODUCTION
• Linear regression is the next step up after correlation.
• It is used when we want to predict the value of a variable based on the value
of another variable.
• The variable we want to predict is called the dependent variable
• The variable we are using to predict the other variable's value is called the
independent variable
• Sample data file:
• C:\Program Files (x86)\SPSSInc\…\Samples\English\[Link]
• The R value represents the simple
correlation
• The R2 value (the "R Square"
column) indicates how much of the
total variation in the dependent
variable
• ANOVA table, which reports how
well the regression equation fits the
data (i.e., predicts the dependent
variable)
• Intercept
• Beta, Standardized Beta
• t-test of beta and Sig.
• The regression equation