Measurements
Measurements again
Theories and Facts
Errors
Tests
100
Mathematical likelihood of event: the likelihood that an event will occur, expressed as the ratio of the number of favorable outcomes in the set of outcomes divided by the total number of possible outcomes. Always take a value between 0 and 1
What is Probabilities
100
Numbers that have all the characteristics of interval numbers but also have an absolute 0 point. The highest level of measurement. Example, income
What are Ratio Measures?
100
Hypothesis of "No difference". Typically corresponds to a general or default position. For example, it might be that there is no relationship between two measured phenomena or that a potential treatment has no effect. Analogous to the mathematics strategy of proof by contradiction. The goal of any scientific experiment is to disprove one of the hypotheses, usually this one.
What is Null Hypothesis?
100
An error that is caused by the improper functioning of the instrument.These type of errors can be avoided by using an instrument that works properly. Systematic error. Sampling bias. Non-random processes in selection Attrition, non-volunteers, different parts of the population are available for sampling at different times, etc. Known and controllable (instrument errors, personal errors) A. Personal B. Assignable blunder C. Systematic
What is Determinate error?
100
A range in which true value will be found 95% of the time. Probability value usually represented as a percentage. Used to indicate the reliability of an estimate.
What is Confidence Interval?
200
Variable with unpredictable values: a variable that can have any of a range of values that occur randomly but can be described probabilistically. Numeric outcome of a random experiment.
What is Random Variable?
200
Numbers used to name attributes of a variable. Not an actual value or position. Examples, female or male; yes or no; Democrat, Republican, or independent. Lowest level of measurement.
What are Nominal Measures?
200
This hypothesis is a new or revised belief about a current situation based on the fact that the current belief is mistaken. Often, it is difficult, if not impossible to prove a hypothesis is correct, so instead scientists try to disprove all the other theories. At the end of an experiment, one of the hypotheses is said to be rejected or not rejected. By disproving, or rejecting the other hypotheses, they will eventually be left with one that has not been disproven. This hypothesis states the opposite conclusion compared to the null hypothesis.
What is Alternate hypothesis?
200
Rejecting the Null hypothesis when it is true. Also known as alpha error. In other words, the researcher claims a difference between groups when, if the entire population were measured, there would be no difference. Reducing the level of significance (p<.05) will reduce the chances of making this type of error. p = 0.05 indicates that 5 times out of 100 the null hypothesis can be rejected when it is accurate. It is often considered more serious to make this type of error because the researcher is claiming a significant relationship or outcome when there is none.
What is Type I error?
200
Two-dimensional frequency distribution primarily used with categorical (Nominal or ordinal) data. A chi-squared test could be used to test group differences.
What is Contingency table?
300
Association between variables: a process for determining the statistical relationship between a random variable and one or more independent variables that is used to predict the value of the random variable. Variable intensity of symptoms to that an ineffective treatment seems to be effective. Statistical phenomenon in which extreme scores tend to regress or cluster around the mean on repeated testing occasion.
What is Regression?
300
The extent to which you can rely on the results obtained from an instrument. If you were to measure the same variable in the same person in the same situation over and over again, your results would be the same. Degree of consistency which an instrument measures an attribute. Example...blood pressure cuff or weight scale must be consistent to assess an accurate value that approximates a "true" physiological value for an individual. A measure of the random error of the measurement process itself.
What is Reliability?
300
Using the Science of Influence to Improve the Art of Persuasion a. Authority-people tend to obey people in authority, even if they are asked to perform objectionable acts b. Social proof-people do things they see other people doing c. Liking-people are easily persuaded by people they like d. Reciprocity-people tend to return a favor e. Commitment and consistency- If people commit, orally or in writing, to an idea or goal, they are more likely to honor that commitment f. Scarcity-Perceived scarcity will generate demand. For example, saying offers are available for a "limited time only" encourages sales
What is Cialdini's theory, "Different weapons of influence"
300
Failing to reject the Null Hypothesis when it is false. Also known as Beta error. Occurs if the null hypothesis is mistakenly accepted when it should not be. The researcher fails to ascertain group differences when they have occured. Conclude that the intervention did not have a positive outcome on the dependent variable when it actually did. Based in large part on the power of the statistic to detect group differences. As you reduce risk of Type I error you increases chance of this error.
What is Type II error?
300
The test used to determine if there is any relationship at all. It doesn't tell you where the differences are.
What is Chi squared test?
400
Given the following numbers.....1,1,1,1,2,2,3,4,5,8,9; the answer is 1
What is the mode?
400
Addresses the critical issue of the relationswhip between a concept and its measurement. Asks whether what is being measured is a reflection of the underlying concept. A measure of systematic error, or "nonrandom error" (a systematic bias or an error that consistently occurs). Inversely related to the amount of systematic error present in an instrument.
What is Validity?
400
The degree to which the independent variable brings about change in the dependent variable
What is Internal Validity?
400
Measure of Variability. Indicator of the average deviation of scores around the mean.
What is Standard Deviation?
400
The most basic statistical procedure. Used to compare two sample means on one variable. If the researcher finds a significant difference between the two sample means, the null hypothesis will fail to be accepted. Indicates the probability that the null hypothesis is correct. Can only be used when the means of two groups are compared.
What is t test?
500
Numbers that share the characteristics of ordinal and nominal measures but also have the characteristic of equal spacing between categories. It indicates how much categories differ. Continuous variables in which the ) point is arbitrary. The absence of a trye 0 point deos not allow statements to be made concerning ratios.
What are Interval Measures?
500
1. Conceptualization (identify concept, define concept) 2. Operationalization (Determine level of measurement, Select scaling technique. 3. Reliability and Validity
What is Measurement process?
500
Statistical test used to determine if there are significant differences between two or more means. Serves the same purpose as the t-test. Also referred to as the F-test, can manage two or more groups. Raw data are put into a formula to obtain a calculated value. The calculated value is compared against the critical value, and the null hypothesis is not accepted if the calculated value is larger than the tabled critical value or accepted if the calculated value is less than the critical value. Yields an F value with degrees of freedom.
What is "One-way" Analysis of Variance (ANOVA)?
500
Errors are random errors that randomly fluctuate and cannot be eliminated. Those which are beyond the analyst's control and are unknown errors e.g room temperature etc. Sampling error Random processes can generate non-representative samples (especially when sample size is small)
What is Indeterminate error?
500
A measure of the asymmetry of the probability distribution of a real-valued random variable. The value can be positive or negative, or even undefined. Qualitatively, a negative skew indicates that the tail on the left side of the probability density function is longer than the right side and the bulk of the values (possibly including the median) lie to the right of the mean. A positive skew indicates that the tail on the right side is longer than the left side and the bulk of the values lie to the left of the mean. A zero value indicates that the values are relatively evenly distributed on both sides of the mean, typically (but not necessarily) implying a symmetric distribution.
What is Skewness?
M
e
n
u