Statistical Tests: T-Tests

T Test

-is a stat test evaluating the means of 2 groups

Can be used to evaluate:

-whether 2 groups differ from each other (an independent two-sample t test)

-whether there is a significant difference in paired measurements (a paired, or dependent sample t-test)

-whether a single group differs from a known value (one-sample t-test)

independent sample T-Test

-When these two groups are independent (or unrelated to one another), we can use a procedure known as the unpaired

-used for differences in 2 groups means or compares means for 2 independent groups of cases

-used to test comparative research questions

independent samples t-test

We may ask whether the blood pressure of a group taking a new treatment is different than the blood pressure of a group taking placebo.

What type of T-test would you use in this scenario?

two-tailed hypothesis test

•Involves the comparison of difference between two population means

•The most frequently used method to determine if population means are unequal

EX: "There is a difference between the mean blood pressure of a group taking a new treatment than the mean blood pressure of a group taking placebo"

one-tailed hypothesis test

•Involves the comparison of difference between two population means

•The most frequently used method to determine if one population means is larger than the other population means

EX: "The mean body weight of a group taking a placebo is less than the mean body weight of a group taking new weight-loss medication "

normality

The variable on which the two groups are being compared is normally distributed in each population

variance

The variances of the variable in the two populations are equal (called homogeneity of variance)

independence

The observations within each group and between each group are independent, meaning that knowing the value of any one observation tells us nothing about the value of another observation

-most imp. for independent sample t-test

-normality

-variance

-independence

What are the assumptions you make when doing an independent sample T-test?

Paired Observations (Pre/Post design)

Comparing means on a variable measured at one time (pretest) and again another time later (posttest) on the same subjects.

Paired T-tests

when we compare 2 means

One sample T-test

•Used to determine whether an unknown population mean is different from a specific value.

•Use the test for continuous data.

-Your data should be a random sample from a normal population.

unrelated

The independent t-test is used to compare two sample means from ____________ groups. This means that there are different people providing scores for each group.

to determine if samples differ from each other

What is the purpose of a independent T-test?

paired t-test

You want to check whether a new drug increases memory performance. You test the memory performance of 40 people before and after they take the medicine.

What type of t-test should you use?

one-sample t-test

is a statistical hypothesis test used to determine whether an unknown population mean is different from a specific value