Intro to Hypothesis Testing Flashcards
What’s the difference between inferential and descriptive statistics?
Inferential: Uses a sample of data collected to make predictions/generalizations about a larger population
Descriptive: Summarizes & describes characteristics of a dataset for populations or samples
What are the two primary techniques used for inferential statistics?
Hypothesis testing, regression analysis
What are the three primary techniques used for descriptive statistics?
Central Tendency, distribution, variability
T/F: Hypothesis testing is a descriptive statistic
False; it is an inferential one
What is meant by the phrase, “Failure to reject Ho”?
That the results of your hypothesis are not statistically significant
Failure to reject a null hypothesis in simpler terms is described as what?
That (the researcher/analyst) didn’t find strong enough evidence to say something is different or has changed. This doesn’t mean that the null hypothesis is definitely true, just that they couldn’t prove it wrong that one time.
What is the estimated standard error used for?
It is used as an estimate of the real standard error when the value of a population standard deviation (σ) is unknown
“Reject the null hypothesis” means what?
There is strong evidence against the Ho (null hypothesis)
“Failure to reject the null hypothesis” means what?
There is not enough evidence that something is different from the “average” or norm
When and why is a t-statistic used instead of a z-score for hypothesis testing?
- When the population standard deviation (σ) is unknown
FORMULA
Sample variance
s²= SS/df
FORMULA
Estimated standard error
SM= √s²/n
What is a confidence interval?
A range of values centered around a sample statistic
When we find a significant effect through hypothesis testing, it means that the sample mean is what?
Very unlikely given that the null hypothesis is true
What does Cohen’s d measure?
Effect size (A measure of the magnitude of a treatment effect in a way that is “independent” of sample size)
T/F: A confidence interval tells us the range of sample means that we can reasonably expect to see in the manipulated population and the range of sample means we can confidently expect to see if we were to repeat the experiment over again
True
T/F: Z-scores use population variance to compute standard error
True
T/F: T-statistics use sample variance as a best estimate
True
What is hypothesis testing?
The statistical method using sample data to formally evaluate a hypothesis about a population of interest
T/F: In statistics, we go into all statistical tests assuming that the null hypothesis is true
True
