BUAL 2650 Exam STUDY GUIDE
the researcher has little or no control over the
observational studies
variables under study and merely observes their
values
the researcher attempts to control the levels of one
designed experiment
or more variables to determine their effect on a
variable of interest
, response variable is the variable of interest to be measured in the experiment
(dependent variable) (typically quantitative)
factors (independent are those variables whose effect on the response is of
variables) interest to the experimenter
quantitative factors are measured on a numerical scale
qualitative factors are not measured (naturally) on a numerical scale
factor levels are the values of the factor used in the experiment
treatments are the factor-level combinations used in an experiment
experimental unit is the object on which the response and factors are observed
or measured
is a design in which the experimental units are
completely randomized randomly assigned to the (k) treatment or in which
design
independent random samples of experimental units
are selected for each treatment
- tests the equality of two or more (k) population means
ANOVA F-test (single
factor): - used to analyze completely randomized experimental
designs
- variation due to treatment
total variation includes: (2
types) - variation due to random sampling
- sum of squares among
- sum of squares between
variation due to treatment
- sum of squares treatment
includes:
- among groups variation
- sum of squares within
- sum of squares error
variation due to random
- sum of squares residual
sampling includes:
- within groups variation
- within each sample group, the individual scores
vary about their sample mean (group variation)
within - groups variation - it is a direct reflection of the inherent variation
among individuals given the same treatment
- does not reflect differences caused by different treatments
- means of the sample groups vary among themselves
between - groups variation
- reflection of inherent variation plus differential treatment
effect
the assumption of the variance within each of the populations is equal
homogeneity of variance
SStotal = SSbetween + SSerror
MSB/MSE
Test statistic (F) = - MSB is mean of square for between groups (treatment)
- MSE is mean of square for error
- v1 betwen = k - 1 (numerator df)
degrees of freedom = - v2 error = n - k (denominator df)
(ANOVA single factor) - k = number of groups
- n = total sample size
between (treatment): mean MSB = SSB/k-1
the researcher has little or no control over the
observational studies
variables under study and merely observes their
values
the researcher attempts to control the levels of one
designed experiment
or more variables to determine their effect on a
variable of interest
, response variable is the variable of interest to be measured in the experiment
(dependent variable) (typically quantitative)
factors (independent are those variables whose effect on the response is of
variables) interest to the experimenter
quantitative factors are measured on a numerical scale
qualitative factors are not measured (naturally) on a numerical scale
factor levels are the values of the factor used in the experiment
treatments are the factor-level combinations used in an experiment
experimental unit is the object on which the response and factors are observed
or measured
is a design in which the experimental units are
completely randomized randomly assigned to the (k) treatment or in which
design
independent random samples of experimental units
are selected for each treatment
- tests the equality of two or more (k) population means
ANOVA F-test (single
factor): - used to analyze completely randomized experimental
designs
- variation due to treatment
total variation includes: (2
types) - variation due to random sampling
- sum of squares among
- sum of squares between
variation due to treatment
- sum of squares treatment
includes:
- among groups variation
- sum of squares within
- sum of squares error
variation due to random
- sum of squares residual
sampling includes:
- within groups variation
- within each sample group, the individual scores
vary about their sample mean (group variation)
within - groups variation - it is a direct reflection of the inherent variation
among individuals given the same treatment
- does not reflect differences caused by different treatments
- means of the sample groups vary among themselves
between - groups variation
- reflection of inherent variation plus differential treatment
effect
the assumption of the variance within each of the populations is equal
homogeneity of variance
SStotal = SSbetween + SSerror
MSB/MSE
Test statistic (F) = - MSB is mean of square for between groups (treatment)
- MSE is mean of square for error
- v1 betwen = k - 1 (numerator df)
degrees of freedom = - v2 error = n - k (denominator df)
(ANOVA single factor) - k = number of groups
- n = total sample size
between (treatment): mean MSB = SSB/k-1
