class 14

Question 1

inferential statistics

Answer 1

-allow researchers to draw inferences about a population using the data from a given sample

Question 2

what inferential statistics used to do

Answer 2

-test hypotheses, relationships, differences
-address questions, objective
-predict

Question 2

alpha “a” - inferential statistics

Answer 2

-researchers control the risk for type 1 “false positive” errors by selecting a level of significance aka alpha level
-the smaller the # the less chance of a type 1 error (but increased risk of a type 2 error “false negative”)
-minimally accepted is 0.05

Question 3

hypothesis testing - inferential statistics

Answer 3

-researchers use statistical procedures to test whether null hypotheses should be accepted or rejected
-did it occur by chance or is the patterns in responses

Question 4

alpha must be ___ the p value to be considered significant

Answer 4

greater then or equal

Question 5

p-value statistical significance - inferential statistics

Answer 5

the probability that the obtained results are due to chance alone
-all or nothing
ex: a=0.05, p=0.3 (not significant) p=0.03(significant)

Question 6

the p value represents the ____

Answer 6

confidence level

Question 7

confidence intervals (CI’s) - inferential statistics

Answer 7

similar to alpha levels-researchers may choose to set a confidence level
-the range of values that is likely to contain the “true” value
-point estimate: the statistical estimate that will be reported (e.g. mean, odds ratio, r value)
-most frequent are CI 95% and CI 99%
-if the cI contains the null value, the result is not significant!!!

Question 8

lower bound CI:

Answer 8

the lowest estimated population value

Question 9

upper bound CI:

Answer 9

the highest estimated population value

Question 10

parametric vs nonparametric

Answer 10

statistical tests for which the data must meet certain assumptions for the test to work like normal distribution, interval/ratio level of measurement
-if assumptions are not met, must use non-parametric alternative

Question 11

what is a t-test

Answer 11

requires at least interval level measurement (needs continuous data)
tests for significant differences in TWO group means
-most commonly used test of differences
-parametric

Question 12

what is a t-score

Answer 12

ratio of the difference between two groups and the difference within the groups
-large= big difference between groups small=only little difference
-each t-score has a p-value to go with it

Question 13

what is an independent t-test

Answer 13

compares the means of two INDEPENDENT groups in order to determine whether there is statistical evidence that the associated population means are significantly different
-aka groups dont impact eachother

Question 14

what is a paired t-test

Answer 14

compares the difference between two variables for the SAME subject
often the two variables are seperated by time (e.g. pre-post test)
ex: if you get 80% in your pre-test you will normally get 80+ on your post test

Question 15

what is analysis of variance
(ANOVA) test

Answer 15

tests for differences between means of 3+ groups
variations between groups is compared with variation within groups (f ratio)

Question 16

one-way ANOVA

Answer 16

compares between-group differences for 3+ groups

Question 17

repeated measures ANOVA (RM-ANOVA)

Answer 17

compares means at different points in time of 3+ groups

Question 18

what is a post-hoc analysis

Answer 18

further testing conducted after primary testing (elaborates upon initial results)
determining which groups are significantly different from each other
e.g. bonferroni’s procedure

Question 19

what is chi-squared test (x^2)

Answer 19

use with nominal data or data that is not normally distributed
-tests for differences between two or more groups
-nonparametric
-dependent variable has to be a # ex: a mean

Question 20

regression analysis - multivariate tests

Answer 20

to predict the value of one variable based on the value of another variable
-simple or multiple regression
R^2 amount of variance in the data that is explained by the equation
-accounts for confounding

Question 21

simple regression analysis

Answer 21

-is NOT a test of difference
used for predicting
ex: predict the possibility of passing the NCLEX-RN based on the GPA from nursing school

Question 22

multiple regression analysis

Answer 22

-predicts what combination of elements are causing the outcome
ex:predict the length of a stay in NICU based on gestational age, birth weight, number of complications, and sucking strength

Question 23

what is analysis of covariance (ANCOVA)

Answer 23

-extension of ANOVA that explores differences between groups while statistically controlling for additional variables (covariates)
-helps remove confounding variables that may skew study to find the true relationship between variables

Question 24

process for quantitative data analysis

Answer 24

-prep the data for analysis
-describe sample (mean age, income, education, etc)
-testing the reliability of the instruments for the present sample
-exploratory analysis of the data
-confirmatory analysis guided by objectives or hypothesis
-post-hoc analysis if necessary

Question 25

factors that must be considered for judging statistical suitability

Answer 25

-study purpose
-hypotheses, questions, or objectives
-design
-level of measurement

Question 26

what is judging statistical suitability?

Answer 26

judging whether the correct statistical test was performed and the results interpreted correctly