You are on page 1of 7

Polytechnic University of the Philippines

Engineering Data Analysis

Parametric Tests
One Sample t-test
Used to compare the mean of one sample to a know
One Sample t-test standard (theoretical or hypothetical) mean.
Parametric Tests
Null Hypothesis (Ho) Alternative Hypothesis (Ha)
One Sample t-test
µ = µ0 µ ≠ µ0
Dependent Sample t - test

Independent Sample t - test µ ≤ µ0 µ > µ0


One-way Analysis of µ ≥ µ0 µ < µ0
Variance

Pearson Product Moment Alternative


Correlation Command
Hypothesis (Ha)
Assumptions
µ ≠ µ0 t.test(x, mu = 0, alternative = “two.sided”, conf.level = 0.95)
Samples must be
independent t.test(x, mu = 0, alternative = “greater”, conf.level = 0.95)
µ > µ0
Approximately Normal t.test(x, mu = 0, alternative = “less”, conf.level = 0.95)
µ < µ0
x is a numeric vector of data values

Parametric Statistics
Engineering Data Analysis
One Sample t-test Example
Parametric Tests A psychologist makes use of a test instrument for measuring depression. The
One Sample t-test instrument is known to have a mean score of 70 for normal individuals. Twenty
individuals who have been described as severely depressed by a therapist takes the
Dependent Sample t - test
tests. A psychologist is interested to know if the average test score made by severely
Independent Sample t - test depressed individuals is greater than 70. The data are reflected on the table below.
One-way Analysis of No Score No Score
Variance 1 75 11 75
Pearson Product Moment 2 77 12 74
Correlation 3 73 13 63
Assumptions
4 80 14 76
Samples must be
5 65 15 67
independent
6 74 16 70
Approximately Normal
7 75 17 69
8 69 18 76
9 71 19 65
Parametric Statistics 10 72 20 68
Engineering Data Analysis
One Sample t-test Check Assumptions: Normality Check
Parametric Tests
Step 1:
One Sample t-test
Ho: The data is normally distributed
Dependent Sample t - test
Ha: The data is not normally distributed
Independent Sample t - test
Step 2
One-way Analysis of
Variance set α = 0.05
Pearson Product Moment
Correlation Step 3
Assumptions Use R to apply Shapiro Wilk test
Samples must be #Load the required data set in R
independent
shapiro.test(scores$Score)
Approximately Normal

Parametric Statistics
Engineering Data Analysis
One Sample t-test Check Assumptions: Normality Check
Parametric Tests
Step 4
One Sample t-test

Dependent Sample t - test

Independent Sample t - test

One-way Analysis of
Variance Step 5
Pearson Product Moment Since the p-value is greater than α = 0.05, then we fail to reject
Correlation
the null hypothesis
Assumptions
Samples must be Step 6
independent
Since the p-value is greater than α = 0.05, then we fail to reject
Approximately Normal
the null hypothesis. Therefore, the sample data is normally
distributed.

Parametric Statistics
Engineering Data Analysis
One Sample t-test Application
Parametric Tests
Step 1:
One Sample t-test
Ho: µ ≤ 70
Dependent Sample t - test
Ha: µ > 70
Independent Sample t - test
Step 2
One-way Analysis of
Variance set α = 0.05
Pearson Product Moment
Correlation Step 3
Assumptions Since we are comparing the mean of one sample to a known
Samples must be standard mean, we will use the one sample t - test
independent

Approximately Normal
Step 4
t.test(scores$Score, mu = 70, alternative = "greater", conf.level = 0.95)

Parametric Statistics
Engineering Data Analysis
One Sample t-test Check Assumptions: Normality Check
Parametric Tests
Step 4
One Sample t-test

Dependent Sample t - test

Independent Sample t - test

One-way Analysis of
Variance

Pearson Product Moment Step 5


Correlation
Assumptions
Since the p-value is greater than α = 0.05, then we fail to reject
Samples must be
the null hypothesis
independent
Step 6
Approximately Normal
There is no sufficient evidence to conclude that the average score
made by severely depressed individual is greater than 70
Parametric Statistics
Engineering Data Analysis

You might also like