Psych 350 Test 2
when you round to 0
0,1,2,3,9
When do you round to 5
4,5,6
Tell when to use each type of ANOVA, the possible research hypotheses for this statistical model, and when ANOVA can be used to test each type of Research Hypothesis (attributive, associative and causal).
ANOVA is used to compare mean DV scores from the different IV conditions BG ANOVA is used to compare mean DV scores for between groups designs, WG ANOVA is used to compare mean DV scores for within-groups designs The possible RH:s for ANOVA are G1 > G2, G1 = G2 and G1 < G2. ANOVA can never be used to test an attributive research hypothesis, because attributive hypotheses are univariate and ANOVA is a bivariate statistical test. ANOVA can be used to test an associative hypothesis whenever the data are appropriate for a ANOVA analysis. ANOVA can be used to test a causal hypothesis when the data are appropriate for an ANOVA analysis and the data come from a true experiment with no confounds
Compare and contrasts the "interesting pairs" of the four bivariate data analysis models we are working with
All bivariate tests ask if the relationship between the variables in the sample is strong enough to conclude there is a relationship between the variables in the population. Pearson's correlation and Pearson's Chi-square are both used to test for bivariate association, correlation for two quantitative variables and chi-square for two qualitative variables BG ANOVA and WG ANOVA are both used to test for mean differences, BG ANOVA is used for between groups designs and WG ANOVA for within-groups designs BG ANOVA and Pearson's Chi-square are both used for between groups designs, ANOVA for quantitative DVs and chi-square for qualitative DVs Pearson's correlation and WG ANOVA are both used with two quantitative variables, Pearson's to test for an association between the variables and WG ANOVA to test for a mean difference between the variables
Tell when to use Pearson's Chi-square, the possible research hypotheses for this statistical model, and when Chi-square can be used to test each type of Research Hypothesis (attributive, associative and causal).
Chi-square is used to test for a pattern of relationship between two qualitative variables The possible RH:s for Chi-square are a specific pattern of relationship between the qualitative variables and no pattern of relationship between the two qualitative variables Chi-square can never be used to test an attributive research hypothesis, because attributive hypotheses are univariate and Chi-square is a bivariate statistical test. Chi-square can be used to test an associative hypothesis whenever the data are appropriate for a Chi-square analysis. Chi-square can be used to test a causal hypothesis when the data are appropriate for an Chi-square analysis and the data come from a true experiment with no confounds
Tell when to use a Pearson's correlation, the possible research hypotheses for this statistical model, and when correlation can be used to test each type of Research Hypothesis (attributive, associative and causal)
Correlation is used to test for a linear relationship between two quantitative variables. The possible RH:s for Correlation are +r, r=0 and -r. Correlation can never be used to test an attributive research hypothesis, because attributive hypotheses are univariate and correlation is a bivariate statistical test. Correlation can be used to test an associative hypothesis whenever the data are appropriate for a correlation analysis. Correlation can be used to test a causal hypothesis when the data are appropriate for an correlation analysis and the data come from a true experiment with no confounds
Describe effect size estimates, tell how they are related to significance tests, and the information they provide that is not provided by significance tests.
Correlation, chi-square, and ANOVA all use "r" as the effect size estimate. Effect size estimates are an estimate of the size or strength of the bivariate relationship between the two variables. The larger the effect size the more likely we are to reject the H0:. Effect size estimates provide a one-number quantitative summary of the strength of the relationship between two variables that was found in a particular study, allowing us to more easily compare different studies of those variables.
Respond to and describe the statement, "Rejecting the null hypothesis guarantees support for the research hypothesis."
Deciding to retain/reject H0: and to support/not support RH: are two separate decisions. The RH: might be the H0 If the RH: is also the H0:, retaining H0: guarantees support for the RH:
Type I
False alarm
Retain the null what is there for the rest
I is not possible, II possible, III not possible
A Type __ error or a ___ is a statistical decision error made when you mistakenly decide the variables are related in the target population, when you mistakenly conclude the variables aren't related in the target population the type of statistical error is called a Type ___ error or a ___, when you correctly conclude the variables are related in the target population but get the direction or pattern of that relationship wrong the type of statistical error is called a Type __ error or a ___.
I, false alarm, II, miss, III, misspecification
If the H0: is true in the population a p less than .05 will lead you to make a Type __ error or a ___, and a p> .05 will lead you to make a ___
I, false alarm, correct retention.
When you mistakenly conclude the variables aren't related in the target population the type of statistical error is called a Type ___ error or a ___, when you correctly conclude the variables are related in the target population but get the direction or pattern of that relationship wrong the type of statistical error is called a Type ___ error or a ___, a Type __ error or a ___ is a statistical decision error made when you mistakenly decide the variables are related in the target population.
II, miss, III, misspecification, I, false alarm
Type II
Miss
Type III
Missrepresentation
Describe the process of NHST, tell the (five) possible outcomes and tell the likely reasons for each.
NHST stands for Null Hypothesis Significance Testing The NHST process is obtain a sample from the population you want to study, collect the data, run the appropriate statistical analysis, obtain a summary statistic and the p-value estimating the probability of your finding (or one larger) if the H0: were true, and decide whether to retain (p>.05) or reject (p < .05) the H0: Correctly rejecting the H0: and correctly retaining the H0: happen when there is good sampling, good variable measurement, no confounds changing your results and "chance is on your side" Type I and Type III statistical decisions errors happen when there is bad sampling, bad variable measurement, confounds changing your results, and/or "chance is against you" Type II statistical decisions errors happen when there is bad sampling, bad variable measurement, confounds changing your results, a too-small sample size and/or "chance is against you"
Should I be concerned about power? retain and r<0.1
No this combo of p-value
Types if you reject
Possible, not possbile, possible
What is meant by "statistical power" and what is the advantage if our research has lots of it? Describe how power analyses are conducted and how they can inform our statistical decisions.
Statistical power, also called sensitivity, is the ability to reject the null hypothesis when there really is a relationship between the variables in the population. The advantage of having lots of statistical power is that we make fewer Type II errors (misses). There are two types of statistical power analyses. An a priori power analysis is conducted before the study is run, to estimate the sample size needed to find a significant effect. A post hoc power analysis is conducted after the study is run, the analyses completed, and you have retained the H0:, to estimate the probability of Type II error.
When comparing groups using a quantitative DV, ___ is used when the same participants are in both IV conditions, ___ is used when different participants are in the two IV conditions
WG ANOVA, between groups ANOVA
When comparing the DV means of different IV conditions, ___ is used when the same participants are in both IV conditions, ___ is used when different participants are in the two IV conditions.
WG ANOVA, between groups ANOVA
When you have repeated measures data, ___ tests hypotheses about change ___ tests hypotheses about linear relationships.
WG ANOVA, correlation
When you have repeated measures data, ___ tests hypotheses about differences, ___ tests hypotheses about prediction.
WG ANOVA, correlation
A/an ___ power analysis is performed before the study is conducted, a/an ___ power analysis is performed after a study is conducted.
a priori, post hoc
A/an _____ power analysis is performed to determine the sample size that should be used for the study, a/an ___ power analysis is performed when you retain the H0: to help estimate the probability of a Type II error.
a priori, post hoc
___ Chi-square data patterns are usually weaker effects than ___ Chi-square data patterns
asymmetrical, symmetrical
___ Chi-square data patterns often have a difference between the rows of only one column, ___ Chi-square data patterns have the larger frequencies on one diagonal and the smaller frequencies on the other diagonal.
asymmetrical, symmetrical
When comparing groups using a quantitative DV, ___ is used when different participants are in the two IV conditions ___ is used when the same participants are in both IV conditions.
between groups ANOVA, WG ANOVA
When comparing the DV means of different IV conditions ___ is used when different participants are in the two IV conditions ___ is used when the same participants are in both IV conditions.
between groups ANOVA, WG ANOVA
When making between groups comparisons, ___ is to ask if the participants in the differnt IV conditions have differnt response averages, ___ is used to ask if the participants in the different IV conditions have different response likelihoods.
between groups ANOVA, chi-square
When making between groups comparisons, ___ is used when the DV is quantitative and ___ is used with the DV is qualitative.
between groups ANOVA, chi-square
___ groups comparisons involve different participants in each IV condition, while ___ groups comparisons include the same participants in all IV conditions.
between, within
Correlation, Chi-square and ANOVA are ___ statistics. The mean, standard deviation and skewness are ___ statistics.
bivariate, univariate
___ statistics summarize the relationship between two variables, ___ statistics involve summaries of a single variable.
bivariate, univariate
The mean describes the ___ of the distribution, the standard deviation its ___ and the skewness its ___
center, variability, shape
When making between groups comparisons, ___ is used to ask if the participants in the different IV conditions have different response likelihoods, ___ is to ask if the participants in the differnt IV conditions have differnt response averages.
chi-square, between groups ANOVA
When making tests of bivariate association, ___ is used to ask questions about patterns of bivariate relationship and ___ is used to ask questions about bivariate linear relationshps.
chi-square, correlation
If the H0: is false in the population a p less than .05, this will lead you to make a ___ , and a p greater than .05 will lead you to make a Type __ error (which is also called a ___).
correct rejection, II, miss
When you have repeated measures data, ___ tests hypotheses about linear relationships and ___ tests hypotheses about change.
correlation, WG ANOVA
When making tests of bivariate association, and __ is used when the variables are quantitative ___ is used when the variables are qualitative
correlation, chi-square
Using a larger sample size does not increase the chances of finding a _____ effect, but does increase the chances of finding a _____ effect .
large, significant
The ___ and the ___ can only be used with quantitative variables, while the ___ can be used with both quantitative and qualitative variables.
mean, median, mode
The ___ is the balancing point of the distribution, the ___ has 50% of the scores above and below it, and the ___ is the most common score.
mean, median, mode
The ___ is the most common value, the ___ is the average value and the ___ is the middlemost value
mode, mean, median
Should I be concerned about power? reject
no significant effect indicates sufficient power
A correlation should not be used if the variables have a ___ bivarite relationship because performing a correlation presumes there is a ___ bivariate relationship between the two variables.
nonlinear, linear
A scatterplot can be used to decide if two quantitative variables have a ___ bivariate relationship that can't be represented by a correlation or if the two quantitative variables have a ___ bivariate relationship.
nonlinear, linear
A/an ___ power analysis is performed after a study is conducted, a/an ___ power analysis is performed before the study is conducted.
post hoc, a priori
A/an _____ power analysis is performed when you retain the H0: to help estimate the probability of a Type II error, a/an _____ power analysis is performed to determine the sample size that should be used for the study.
post hoc, a priori
Having sufficient ___ decreases the probability of making a Type ___ error.
power, II
When is it BG ANOVA
qual and quant with diff people
When is it Chi Square
qual for both and BG
___ variables are those for which different values indicate different amounts and ___ variables are those for which different values indicate different kinds.
quantitative, qualitative
___ is used to measure a linear relationship, while ___ is used to compare different means.
r, anova
___ occur when we don't find the data pattern we "hoped for",a ___ occurs when we don't find the data pattern we "should have".
results contrary to the research hypothesis, Type III error
___ occur(s) when the significant pattern of results is different from the pattern we expected, a ___ occurs when the significant pattern found in the sample data is different from the pattern in the population.
results contrary to the research hypothesis, Type III error
___ is/are identified by comparing the significant pattern found in the sample data with the pattern that was expected based upon theory, a ___ is/are identified (in theory) by comparing the significant pattern found in the sample data with the pattern in the population.
results contrary to the research hypothesis, type III error
A ___ is used to display relationships between 2 quantitative variables, a ___ used to display relationships between 2 qualitative variables.
scatterplot, contingency table
A ___ should be examined before a correlation is calculated, a ___ should be examined to describe the pattern revealed by a significant Chi-square.
scatterplot, contingency table
The skewness describes the ___ of the distribution, the mean its ___ and the standard deviation, its ___
shape, center, variability
The ___ of r tells the direction of the linear relationship while the ___ of r tells the strength of the linear relationship.
sign, size
The ____ of r is not related to whether or not the correlation is significant,while the ___ is.
sign, size
Using a larger sample size increases the chances of finding a ___ effect but does not increase the chances of finding a ___ effect.
significant, large
The ___ of r is the "effect size" and the ___ of r is the "effect direction".
size, sign
The ___ measures the extent of asymmetry of the distribution, the ___ measures the spread of scores around the mean.
skewness, standard deviation
The ___ estimates the variability of scores around the population mean, the ____ estimates the variability of repeated estimates of population mean around the population mean.
standard deviation, standard error of the mean
The ___ estimates the variability of scores around the population mean, the___ estimates the variability of repeated estimates of population mean around the population mean.
standard deviation, standard error of the mean
The ___ together with sample size is used to calculate the ___, which estimates accuracy with which sample means represent the population mean is estimated by the.
standard deviation, standard error of the mean
Accuracy with which sample means represent the population mean is estimated by the ___, which is calculated from the ___ and the sample size.
standard error of the mean, standard deviation
Accuracy with which sample means represent the population mean is estimated by the ____, which is calculated from the ___ and the sample size
standard error of the mean, standard deviation
The ___ estimates the variability of repeated estimates of population mean around the population mean, the ___ estimates the variability of scores around the population mean.
standard error of the mean, standard deviation
___ Chi-square data patterns have row differences in opposite directions in the two columns, ___ Chi-square data patterns often have a difference between the rows of only one column.
symmetrical, asymmetrical
___ statistics involve summaries of a single variable, ___ statistics summarize the relationship between two variables.
univariate, bivariate
___ are measures/behaviors for which the set of participants have at least two different values, while ___ are measures/behaviors for which all participants have the same value
variables, constants
___ groups ANOVA is used for a longitudinal or repeated-measures design, while ___ groups ANOVA is used for a cross-sectional design.
within, between
___ groups comparisons include the same participants in all IV conditions, while ___ groups comparisons involve different participants in each IV condition.
within, between
Should I be concerned about power? retain and r>0.1
yes this combination of p value and effect size indicates