STATS 4TH QUARTER REVIEWER The rejection region (also called a critical region) is a part of
hypothesis testing. The rejection region is a probability area
UNDERSTANDING HYPOTHESES TESTING that indicates if a hypothesis is probably true.
Type I error The alpha α can be graphed as a rejection region in
When the null hypothesis is true and you reject it, you make a probability distributions depending on the direction/tail.
type I error.
Then 1 - α is called as "acceptance region" in some
Type II error
When the null hypothesis is false and you fail to reject it, you references.
make a type II error. The critical values separate the rejection regions from the
acceptance regions.
𝑥̅ − 𝜇
𝑧= 𝜎
√𝑛
Parameter
A parameter is a useful component of statistical analysis. It
refers to the characteristics that are used to define a given
population. It is used to describe a specific characteristic of
the entire population.
The one-sample z-test is a statistical test for the mean of a
population and applicable to interval and ratio scale. It is used
when n≥ 30, or when the population is normally distributed,
and population standard deviation is known.
standard error of the mean means the standard deviation of
the sampling distribution of the means.
Assumptions in One Sample z-test:
• Subjects are randomly selected.
• Population distribution is normal. Test Statistic for Hypotheses tests for One Population
• The population mean should be known. Our test statistic should be a measure of how far the sample
• Cases of the samples should be independent. proportion p-hat is from the null value p0 relative to the
• Sample size should be greater than or equal to 30. variation of p-hat (as measured by the standard error of p-
hat).
The one sample t-test is a statistical procedure that is used to
know the mean difference between the sample and the z-Test for Proportion
known value of the population mean based from an interval To compare sample proportion and population proportion,
or ratio scale. use the z-test for one-sample proportion. The test statistic for
this is
Assumptions in One Sample t-test:
• The population must be approximately normally 𝑃̂ − 𝑃𝑜
𝑧=
distributed. 𝑝𝑜 𝑞𝑜
• Samples are drawn from the population should be √
𝑛
random.
• Cases of the samples should be independent. Where:
𝑥
• Sample size should be less than 30. 𝑝̂ = = 𝑠𝑎𝑚𝑝𝑙𝑒 𝑝𝑟𝑜𝑝𝑜𝑟𝑡𝑖𝑜𝑛
𝑛
• The population mean should be known. 𝑝𝑜 = 𝑝𝑜𝑝𝑢𝑙𝑎𝑡𝑖𝑜𝑛 𝑝𝑟𝑜𝑝𝑜𝑟𝑡𝑖𝑜𝑛
𝑞𝑜 = 1 − 𝑝𝑜
𝑛 = 𝑠𝑖𝑧𝑒 𝑜𝑓 𝑡ℎ𝑒 𝑠𝑎𝑚𝑝𝑙𝑒
Understanding Correlation Analysis
Qualitative data – non-numerical data. Qualitative data are
characteristics that cannot be counted or measured.
Examples: eye color, texture, gender
Quantitative data – numerical data. Quantitative data can be
obtained by counting or measuring.
Examples: amount of time spent online, number of pens,
height
Univariate data – quantitative data with only one variable. A
study uses univariate data if it does not compare between
Moderate Weak
two sets of data.
Examples: age, lot size, grade level
Bivariate data – quantitative data with two variables. A study
uses bivariate data if it compares two sets of data, usually
independent and dependent variables. Bivariate data can be
represented visually using a scatter plot.
Form – the scatter plot's shape. No Correlation
Correlation – the statistical relationship between bivariate
data. It pertains to the degree to which two variables are
linearly related.
Correlation Analysis – the statistical method used to evaluate
the degree of relationship between bivariate data.
Linear Non – Linear The Pearson Product-Moment Correlation
Direction – the scatter plot's trend. The direction can be One that is commonly used in linear correlation is Pearson
visualized when a trend line is graphed in the scatter plot. A Product-Moment coefficient of correlation, symbolized by r,
trend line is the closest line to the points plotted in a scatter named in honor of the statistician who did a lot of research
plot. on this area, Karl Pearson.
𝑛(∑𝑥𝑦)−(∑𝑥)(∑𝑦)
𝑟=
√[𝑛∑𝑥 2 −(∑𝑥)2 ][𝑛∑𝑦−(∑𝑦)2 ]
Positive (Direct)
𝑥, 𝑦, 𝑥 2 , 𝑦 2 , 𝑥𝑦
Negative (Indirect/Inverse)
No Correlation (No direction)
Variation – the strength of the relationship between the two
variables graphed in a scatter plot. The variation is visualized
by how close the points are to the trend line in the scatter
plot.
Perfect Strong
