Lecture 8 - Null hypothesis significance testing (A way to test the reliability of results) Flashcards
What is the coefficient of determination and how is it calculated?
The coefficient of determination (r^2) is the proportion of variance in the dependent variable (Y) that is predictable from the independent variable (X). It is calculated by squaring the correlation coefficient r. For example, if r = 0.62, the r^2 = 0.38
Explain how the coefficient of determination is used to understand shared variance.
the coefficient of determination indicates the percentage of variance in one variable that can be explained by the variance in another variable. For instance, if r^2 = 0.30, the 30% of the variance in the dependent variable can be explained by the independent variable
what is the sampling distribution of the mean, and what are its properties?
the sampling distribution of the mean is the distribution of sample means over repeated sampling from the same population. Its properties include:
- the mean of the sampling distribution (standard error, σM) depends on the population standard deviation (σ) and the sample size (N) and is calculated as:
calculate the standard error for a population with σ=10 and a sample size of N = 25
see photo
Given a population mean (μ) of 70 and a standard deviation (σ) of 20, what is the probability of obtaining a sample mean of 80 or higher from a sample of 25 people?
- calculate the standard error: see photo
- convert the sample mean to a z-score: see photo
- Use a z-table to find the probability:
The area above a z-score of 2.5 is 0.62%. Thus, the probability of obtaining a sample mean of 80 or higher is 0.62%
within what limits would the central 95% of sample means fall for the same distribution and sample size?
- the central 95% of a normal distribution corresponds to z-scores of -1.96 and +1.96
- convert these z-scores to raw scores:
- lower limit = 70 - (1.96 x 4) = 62.16
- upper limit = 70 + (1.96 x 4) = 77.84
Therefore, 95% of sample means would fall between 62.16 and 77.84
What is the null hypothesis significance testing (NHST)?
NHST is a statistical method used to determine if there is enough evidence to reject a null hypothesis, which assumes that any observed difference is due to sampling error. The alternative hypothesis assumes that the observed difference is real.
Explain the four possible decision outcomes in NHST
The four possible decision outcomes in NHST are:
- True Positive (Correct Rejection): The null hypothesis is false, and we correctly reject it/
- False Positive (Type I Error): The null hypothesis is true, but we incorrectly reject it
- True Negative (correct retention): The null hypothesis is true, and we correctly retain it
- False Negative (Type II Error): The null hypothesis is false, but we incorrectly retain it.
What is the conventional threshold for statistical significance in NHST, and what does it mean?
The conventional threshold for statistical significance in NHST is 5% (p < 0.05). It means that is the probability of obtaining the observed result under the null hypothesis is less than 5%, we reject the null hypothesis and consider the result statistically significant
Given a population IQ mean (μ) of 100 and standard deviation (σ) of 15, and a sample mean (M) of 110 from 4 students, assess the probability of obtaining this sample mean under the null hypothesis
- Calculate the standard error: see photo
- Convert the sample mean to a z-score: see photo
- Use a z-table to find the probability:
the probability of a z-score of 1.33 or more is approximately 9%. Therefore, the probability of obtaining a sample mean of 110 or higher due to sampling error is 9%, which is not statistically significant (p >0.05)