Hypothesis Testing

If alpha is 0.05 and obtained probability level is 0.01, you could be making a _________.

Type I error or a correct decision

Which is true of one-tailed tests?

Smaller CV

If H0 is in reality false and it is legitimate to use a directional H1, which of the following will yield a more powerful test?

one-tailed alternative hypothesis

If alpha equals 0.05 and the probability level of your experiment is 0.04, you would _________.

reject the null hypothesis

What happens to alpha as effect size increases (all else held constant)?

remains constant

The nondirectional alternative hypothesis asserts that _________.

the independent variable has an effect

When the results are statistically significant, this means _________.

the obtained probability is equal to or less than alpha and we can reject H0

It is impossible to ever prove that H0 is true because _________.

the power to detect very weak but real effects of the independent variable is always low

In an experiment with a repeated measures design _________.

the same subjects receive both treatments

If we set alpha at 0.05 instead of 0.01 _________.

we have a greater risk of a Type I error and we have a lesser risk of a Type II error

The advantage of a powerful experiment is that _________.

you are more likely to detect the real effects of the independent variable, if there are any.

T or F If your results are statistically significant, you should accept the null hypothesis.

False

T or F Letting an innocent man go free is equivalent to a type 1 error.

False

T or F Power is the ability to detect an effect if no effect exists.

False

T or F Retaining H0 and accepting H0 mean the same thing.

False

T or F Test statistics are usually located in a table rather than computed.

False

T or F The statement "Drug X has no effect on Y and any observed effect is due to chance alone" is an example of a nondirectional alternative hypothesis.

False

T or F Together, power and type 1 error rates must equal 1.0.

False

T or F Your test statistic (TS) should be smaller than the critical value (CV) in order to reject the null.

False

T or F It is appropriate to determine if H1 is directional or nondirectional after the data is analyzed.

False

T or F Type I errors are always worse to make than Type II errors.

False

To calculate the probability of drawing three sevens in a row from a deck of cards involves the use of the multiplication rule and equals 4/52 + 3/51 + 2/50.

False

If the probability of drawing a member of a population is not equal for all members, then the sample is said to be _________.

biased

If p(A or B) = p(A) + p(B) then A and B must be _________.

mutually exclusive

Truth demands that scientists set _________.

not necessarily a = 0.01 or 0.05, but use their best judgment

S(z - µz) equals _________.

0

The mean of the z distribution equals _________.

0

A royal flush in poker is when you end up with the ace, king, queen, jack, and 10 of the same suit. It's the most rare event in poker. If you are playing with a well- shuffled, legitimate deck of 52 cards, what is the probability that if you are dealt 5 cards, you will have a royal flush? Assume randomness.

0.0000015

The probability of drawing an ace, a king and a queen of any suit in that order is _________. Sampling is without replacement from a deck of 52 ordinary playing cards.

0.00048

If you have 15 red socks (individual, not pairs), 24 green socks, 17 blue socks, and 100 black socks, what is the probability you will reach in the drawer and randomly select a pair of green socks? (Assume sampling without replacement.)

0.0228

The probability of rolling "boxcars" (two sixes) with one roll of a pair of fair dice is _________.

0.028

Suppose you are going to randomly order individuals A, B, C, D, E and F. The probability the order will begin A B _ _ _ _ is _________.

0.033

The probability of correctly calling 4 tosses of an unbiased coin in a row equals _________.

0.0625

Assume you are rolling two fair dice once. The probability of obtaining a sum of 2 or 12 equals _________.

0.0833

The probability of randomly selecting a face card (K, Q, or J) or a spade in one draw equals _________.

0.4231

The proportion of scores that lie between 460 and 600 is _________.

0.5365

Assume you are rolling two fair die (a pair of dice) once. The probability of obtaining at least one 3 or one 4 equals _________.

0.5556

If µ = 35.2 and s = 10, then p(X) for X £ 39 equals _________. Assume random sampling.

0.6480

The probability of rolling an even number or a one on a throw of a single die equals _________.

0.6667

What is the probability the first beverage you get is a beer?

0.9250

If H0 is true and the probability of making a Type I error is 0.05, then the probability of making a correct decision is _________.

0.95

In the standard normal curve, 13.59% of the scores will always be contained between the mean (µ) and +1s.

False

T or F A Cohen's d of .5 is considered a large effect size.

False

T or F A correlation of .3 is considered a large effect size.

False

T or F As alpha increases, power decreases.

False

T or F Beta is both your statistical significance level and your type 1 error rate.

False

T or F Convicting an innocent man is the equivalent of making a type 2 error.

False

T or F Convicting an innocent man is the equivalent power.

False

T or F Failing to find an effect that does exist is called a type 1 error.

False

T or F If H0 is true and you retain H0 in your experiment you have made a Type II error.

False

T or F If a result is statistically significant, it must be an important result.

False

T or F If alpha increases, power decreases and type 1 error rates increase.

False

You can only compute power when ________.

H1 is given

All standard scores are z scores.

True

T or F Alpha is both your statistical significance level and your type 1 error rate.

True

T or F Beta is the probability of retaining H0 when H0 is false.

True

T or F H0 and H1 must be mutually exclusive and exhaustive.

True

T or F If H0 is false, and we retain it, we have made a Type II error.

True

T or F If we reject H0 one can say the experimental results are significant.

True

T or F Power is the ability to detect an effect if one exists.

True

T or F Regardless of whether H1 is directional or nondirectional, when evaluating H0 we always assume chance is responsible for the differences in results between conditions.

True

T or F The value used for alpha depends on the consequences of making a Type I and Type II error.

True

T or F You can't make both a type 1 and a type 2 error at the same time.

True

T or F If the probability of the results obtained equals 0.05 and a = 0.05, you should reject H0.

True

T or F It is technically correct to conclude by "accepting" rather than "failing to reject" H0.

True

If you reject the null hypothesis, you may be making _________.

a Type I error and a correct decision

A testing service has 1000 raw scores. It wants to transform the distribution so that the mean = 10 and the standard deviation = 1. To do so, _________.

a and d

If you reject H0 when H0 is false, you have made a _________.

correct decision

What happens to power as alpha decreases (all else held constant)?

goes down

A distribution of raw scores is positively skewed. You want to transform it so that it is normally distributed. Your friend, who fancies herself a statistics whiz, advises you to transform the raw scores to z scores; that the z scores will be normally distributed. You should _________.

ignore the advice because z distributions have the same shape as the raw scores.

The alpha level _________.

is determined by the consequences of making a Type I and Type II error