Ch 15 - Inferential Statistics (Christensen et al., 2007) Flashcards
Alpha level
.
Alternative hypothesis
.
Analysis of covariance
.
ANCOVA
.
Chi-square test for contingency tables
.
Clinical significance
.
Confidence interval
a range of numbers inferred from the sample that has a certain probability or chance of including the true population value; increased confidence (e.g., moving from 95% to 99% confident) comes with a cost. The 99% interval will have to be wider (i.e., less precise) than a 95% interval on a set of data. That’s why 95% confidence intervals are popular in research; it offers a reasonable compromise
- The larger the sample size, the more precise (i.e., the narrower) your confidence interval. So if you need a precise (i.e., narrow) confidence interval, then make sure that you include many participants in your research study
Critical region
.
Degrees of freedom
.
Directional alternative hypothesis
.
Effect size indicators
.
Independent samples t test
.
Interval estimation (aka, confidence interval - CI)
- andy said it’s “when you save money”
- sample statistics (such as the mean) jump around from sample to sample and that the value of the sample statistic rarely is exactly the same as the value of the population parameter. Because of this probabilistic nature of sample statistics, researchers usually prefer to use interval estimation; the researcher puts a confidence interval around the point estimates. e.g., if the mean income in a sample is $49,000, the researcher might use a statistical program (such as SPSS or SAS) to obtain an interval estimate (also called a confidence interval) around the sample mean of $49,000. Perhaps the “95% confidence interval” is “$44,000 to $54,000.”
Level of significance
.
Logic of hypothesis testing
.
Nondirectional alternative hypothesis
.
Null hypothesis
.
One-way analysis of variance
.
One-way repeated measures analysis of variance
.
Parameter
.
Partial eta squared
.
Point estimation
use one number in your sample to estimate the one number (point) of interest in the population. In point estimation, researchers use the value of a sample statistic as the estimate of the value of a population parameter.
Population
full group to which one wants to generalize
Post hoc tests
.
Practical significance
.
Probability value
.
p value
.
Sample
set of cases chosen from population
Sampling distribution
theoretical probability distribution of the values of a sample statistic that would result from all possible samples of a particular size drawn from a population
Sampling distribution of the mean
.
Semi-partial correlation squared
.
Standard error
he term that is used to refer to the standard deviation of a sampling distribution; i.e. the SAMPLE
Statistic
The word “statistics” is used in several different senses. In the broadest sense, “statistics” refers to a range of techniques and procedures for analyzing data, interpreting data, displaying data, and making decisions based on data. This is what courses in “statistics” generally cover.
In a second usage, a “statistic” is defined as a numerical quantity (such as themean) calculated in a sample. Such statistics are used to estimate parameters.
The term “statistics” sometimes refers to calculated quantities regardless of whether or not they are from a sample. For example, one might ask about a baseball player’s statistics and be referring to his or her batting average, runs batted in, number of home runs, etc. Or, “government statistics” can refer to any numerical indexes calculated by a governmental agency.
although the different meanings of “statistics” has the potential for confusion, a careful consideration of the context in which the word is used should make its intended meaning clear.
Statistical power
.
Statistically significant
.
t test for correlation coefficient
.
t test for regression coefficients
.
Test statistic
a sample statistic (e.g., difference between means, correlation coefficient, regression coefficient) that has been converted into a statistic that follows a known sampling distribution that is convenient to work with for obtaining probability values and testing hypotheses. e.g., the z distribution, t distributions, F distributions, and chi-square (i.e., X2) distributions.
Two-way analysis of variance
.
Type I error
.
Type II error
.
Inferential Statistics
the use of SAMPLE data to make generalizations about populations w/ goal of understanding pop parameters; random sampling utilized
Statistic
calculating a numerical index on SAMPLE data (i.e., correlational coefficient or mean)
Population Parameter
calculating a numerical index or CHARACTERISTIC on POPULATION data (i.e., correlational coefficient or mean)
Descriptive Statistics
used to describe and summarize the NUMERICAL characteristics of a set of data
Hypothesis Testing
goal is to test HYPOTHESES about population parameters
Estimation
goal is to estimate the VALUE of population parameters; “Based on my random sample, what is my estimate of the population parameter?”
Symbols
