Week one Flashcards
NOMINAL stats do not assign a quantity.
TRUE
ORDINAL stats rank data, but not in quantifiable amount. Rank ordering.
TRUE
INTERVAL scale assigns a number and tells us how different each number is. The number means something specific. The distance between points is quantifiable. Zero does not exist.
TRUE
RATIO scale of measurement has a true zero. Allows ratio comparisons. e.g. someone who has 5 friends is half as popular as someone who has 10 friends.
TRUE
What are some ways a distribution of data?
Central tendency and variability are ways of describing distributions of data.
What is unique about a perfectly normal distribution?
the mean, median, and mode are all the same.
what does the standard deviation represent?
the average-ish of how far data is from the mean of a distribution. i.e. a large SD says that the data is quite spread out, as on average, each data point is quite far from the mean. The opposite is true for the a small SD.
what is a Z-score?
z-scores transform all data into a measurement that tells us how many sd’s that point is away from the mean.
Z = (X-mean)/sd
If the Z-score is postive, the data point is above the mean. If the Z-score is negative the data point is below the mean.
For a Z-score distribution, what is the mean and sd?
0 and 1
Inferential stats aims to use samples to say something about a population.
The mean of the sampling distribution of means, will be the same as the population mean.
TRUE
When the sample size increases, the sampling distribution of the mean becomes narrower. i.e. as sample gets bigger, error gets smaller.
What is central limit theorem?
What are type I and type II errors?
Errors that are inherent in NHST.
Type I - the probability of rejecting the null hyp. when it was in fact true. The probability of this is the alpha level. e.g. if it is .05 then 5 out of 100 times I will be incorrect. In contrast, 95% of the time we correctly reject the null hypothesis.
Type II - the probability of not rejecting the null hyp. when there was in fact an effect. This probability has a value of beta.
What is power in NHST?
1 - beta.
Is it true that the type I probability is the same as alpha?
Yes.
What is power in NHST?
Power refers to the probability that we correctly reject the null hypothesis.
Is it true that the bigger the effect size, the bigger the power?
Yes and vice versa.
Bigger sample sizes lead to higher power.
