Summa Week 1 Flashcards
Why are stats courses required?
conduct resaerch for theses and dissertations and design experiments
what is required to design experiments?
ask empirical questions (what do we want to know) and statistical considerations (how can we analyze the data)
Why so many stats courses?
A lot of material, and step-by-step is an effective learning strategy
How to approach course
read material before and after class attend classes take notes bring materials ask questsions engage work through problems participate in study groups get a tutor if necessary work hard
Objective of advanced design?
to design research, analyze data using SPSS, reach appropriate conclusions, report results following APA format, evaluate research of others
Examples of inferential statistics
null hypothesis significance testing general linear model correlation and regression analysis of variance effect sizes and confidence intervals nonparametric statistics
SPSS Stats course now?
25, although we have 24
What is myDesktop?
a Virtual Desktop Infrastructure (VDI)
What is a VDI?
technology providing remote access to software used for specific courses (Virtual Desktop Infrastructure)
Who published DESIGN OF EXPERIMENTS, a book that articulated the features of experimental research design?
Ronald Fisher (1890 - 1962)
What did Ronald Fisher incorporate in his statistical practice?
he incorporated ONE kind of statistical practice into Psychology in the 1940s and 1950s, i.e. null hypothesis significance testing
Who thought there were TWO kinds of statistical practice in psychology?
Jerzy Neyman (1894-1981) and Egon Pearson (1895-1980)
Who wrote What’s wrong with Psychology, anyway?
David Lykken, 1991
Should the Table and number be italicized in APA?
No
Should the title of a table be italicized in APA?
Yes
If placing tables in Appendices, how should they be labelled?
Table A1, Table A2…
How should you refer to tables?
By their number, not “as shown by the table above”
Where does the caption go when presenting a table?
directly ABOVE the table, and close enough to be associated with it
In table captions, should important words be capitalized?
Yes
Should captions be italicized in tables?
Yes
Are subscripts and Greek symbols italicized in table headings?
No
Are vertical lines used in headings?
NEVER
Can abbreviations for statistical indices (e.g., M for mean) be used in table headings?
Yes
How many horizontal lines are in a table?
three - above the heading, below the heading, and at the bottom of the table
How many decimals do p-values have?
3
How many decimals do participant numbers have?
0 (they are individuals, not .3 of a person)
How many decimals do statistical data have (apart from p-values)?
2
When do you use bold or italics in a table?
Never
Where are notes placed for a table?
Immediately underneath
How are probability levels of significance designated with in tables?
asterisks (*)
What is a golden rule about table descriptions in APA?
do not reiterate all the information in the body of the table
How do you label a table with a caption?
in italics* “Figure X.”
**Note: figures are NOT italicized when in text
Do you capitalize the first letter of each important word in the caption?
HELL NAW!
True or false: captions are italicized for figures in APA.
FALSE
Do captions end with a period for tables in APA?
Yes.
Where can captions for tables be placed in APA?
Above, below, or to the side of the figure, albeit close-by
How large must the elements of figures be in APA style?
Large enough and sharp enough to be legible
What kind of typeface do I use for APA style?
A simple, nonserif typeface with enough space between letters to avoid crowding.
Can I ever have different-sized letters in figures be in APA style?
No!
How large should the font size be for figures be in APA style??
Larger than 8, smaller than 14; ideally 12
What should be in the descriptions for papers in APA style?
A summary of the information WITHOUT reiterating all of the information in the figure
What does SPSS stand for?
Statistical Package for the Social Sciences
What does the logo icon look like for SPSS?
A summary sign followed by a greek a, and a division sign, all in white letters in a blue circle
What types of files are typically saved into SPSS as datatables?
.sav
What are the two viewtabs in SPSS?
Dataview and variable view
What are the rows and columns in SPSS referred to?
cases and variables
What does each column represent?
a variable
What are the typical variable types in SPSS?
numeric or string
What type of variable needs you to specify the number of decimal places in variable view?
numeric
How many characters long can a variable name be?
256, but must start with a letter
What does each row represent?
a case
What typically are the participants in a SPSS table?
cases
If you have 100 participants in a study, how many cases do you have?
100 cases, or rows of information generated, regardless of number of trials
What is a cell in SPSS?
an intersection between cases and variables. Each response to a survey question should be entered in a cell for each participant according to the defining variable data types
What are the typical data types in SPSS?
strong, date, numeric, etc.
What are the typical measurement scales in SPSS?
nominal, ordinal, or scale
If you have a variable called a name, what type of variable should you use?
a string type
If you have a variabled called a number, what type of variable should you use?
a numeric type, typically with 2 decimal places
What does scale signify in SPSS?
ratio (true zero) or interval data (no true zero)
What does the ruler symbol signify in SPSS?
a scale (continuous) variable
What does the bar chart symbol signify in SPSS?
an ordinal variable
What does the three coloured circles symbol in SPSS signify?
a nominal variable
What is an output file typically saved as in SPSS?
.spv
What does a data file save as in SPSS?
.sav
How do you create a graph in SPSS?
With a completed table, select Analyze, then Graphs, then Linear Dialogs, and then the appropriate graph-type
What are the two branches of statistics?
descriptive summaries and descriptions of a group of numbers,
and
inferential - infers information about a population by using information gathered by a SAMPLE
What is a population in inferential statistics?
the complete set of data elements , regardless of size or finiteness
What is a sample in inferential statistics?
a portion of a population selected for further analysis
What is a parameter in inferential statistics?
a characteristic of the whole population (typically descriptive statistic)
What is a statistic?
a characteristic of a sample, PRESUMABLY descriptive
What is randomness in inferential statistics?
that which a sample not only allows us to estimate certain characteristics of the population, but also attest the accuracy of our estimates. If not accurate, then not meaningful
What implies external validity?
Random selection
Would you define random selection and external validity as relevant to sociology or psychology?
it is more suitable to sociology because it does not require true randomness, since individuals are inherently who they are regardless and their assignment to certain types or groups, etc. CANNOT be randomly assigned
Would you define random assignment and internal validity as relevant to sociology or psychology?
Psychology
What is the experimental method?
has a high level of control to isolate the independent variables to assume a cause and effect relationship; random assignment renders groups equivalent, comparison/control of at least two groups observed
What is the quasi-experimental method?
a method using a non-manipulated IV which lacks random assignmnt to groups and/or lack of control (comparison) group i.e. gender
What is the correlational method?
variables are measured as they naturally occur - they lack random assignment and control to determine cause-effect, more specific to anthropology
What the scales of measurement according to S. Stevens (1946, Harvard psychologist)?
the degree to which measured variables conform to the abstract number system; includes: Identity, Order, Equal distance, and Absolute zero (i.e. complete absence of the variable)
What is the nominal scale?
a categorical measurement
What is the ordinal scale?
the sequence of categories measured e.g. rank
What is the interval scale?
a numerical measurement that does not have a true zero point i.e. temperature
What is the ratio scale?
a numerical measurement ordering with a true zero point i.e. weight
What do scales of measurement determine?
the type of statistical analyses possible
What are measurements of central tendency?
MMM: mean, median, and mode
What is the formula for mean?
X = sum of datapoints divided by number of variables
What is the formula for median?
number of variables +1 divided by the datapoint in question
What is the formula for mode?
no formula. line the datapoints from smallest to largest, and note the most frequent datapoint listed, otherwise average if there are more than one
If a bell curve is normal, are the mean, median and mode assumed to be the same?
No. the mode may be elsewhere, but the mean and median are likely to be the same
If a positively skewed graph of data, what is the assumed order of
From smallest to largest: mode, median, and mean
If there is an assumed normal curve but there is a dip in the middle of it, where are the locations of the central tendency?
assumably the mean and median would be in the middle, and the modes would be at the boobs
if data is as often across the board, then where are the central tendencies?
the mean and median would be in the middle, and there would be NO mode
What are elements of descriptive statistics?
variation, including range, variance, and standard deviation
What are the types of range in descriptive statistics?
interquartile range (inner 25%), incorporating Q1 (separated bottom 1/4 from top 3/4), Q2 which is the same as the MEDIAN, Q3 (separates bottom 3/4 from top 1/4), and IQR (Q3-q1)
What is the formula for variance?
s(squared)x = sum of (x - mean)squared divided by number of datapoints minus 1
What is the formula for standard deviation?
sx = square root of (sum of (X minus mean) squared, divided by N-1)
What is the most common graphic tool for descriptive statistics?
a mean plot, histogram, boxplot
What does the histogram show?
- centre of data
- spread of data
- skewness of data
- presence of outliers
- presence of multiple modes in the data
What is a boxplot describing?
the centre and dispersion of datasets and locates outliers
detects and illustrates location and variation changes between different groups of data
assumes that the data are UNIMODAL. thus, they never claim that a distribution is normal!
Can a boxplot describe normality?
no, it just assumes it
What would you use to describe normality using a graphic plot?
a mean plot or a histogram
How many IQR are from Q3 to the upper inner fence?
1.5 IQR
How many IQR are from Q1 to the lower inner fence?
1.5 IQR
What does a + signify in a boxplot?
the mean
What is Q2 in a boxplot?
the median
What are the upper and lower bars in a boxplot for?
the upper and lower adjacents
What are the 1.5 IQRs from the upper and lower adjacents/bars signify?
upper inner fence and lower inner fence, respectively
What are the methods for dealing with outliers?
correct them go back to raw data estimation remove them keep them transform them (logtransformation)
What are types of descriptions for distributions?
normality
symmetry/skewness
kurtosis/heavy or light-tailed
modality/uni-, bi-, or multi-modal
What is the difference between qualitative and quantitative variables noting the relationship of nominal, ordinal, interval, and ratio data to these terms?
I don’t know…gotta check!
Explain the difference in proper use between a bar graph and a histogram
histograms measure frequencies of stats in sampling distributions, whereas boxplots represent actual statistics
A(n) _______________ scale is a scale in which objects or
individuals are broken into categories that have no
numerical properties.
nominal
A(n) _______________ scale is a scale in which the units of
measurement between the numbers on the scale are all
equal in size.
ordinal?
Measures of ______________ are numbers intended to
characterize an entire distribution.
statistics
The _______________ is the middle score in a distribution
after the scores have been arranged from highest to lowest
or lowest to highest
median
When mean and median are the same, the distribution has
to be _______________.
normal?
Measures of _______________ are numbers that indicate
how dispersed scores are around the mean of the
distribution.
standard deviation
When we divide the squared deviation scores by N ‐ 1
rather than by N, we are using the _______________ of the
population standard deviation.
degrees of freedom
s represents the _______________ standard deviation and σ
represents the _______________ standard deviation.
sample; population
A distribution in which the peak is to the left of the center
point and the tail extends toward the right is a
______________ skewed distribution.
positively
On average, _______________ statistic has the same value
as the population parameter.
sample?
Letter grade on a test is to the _______________ scale of
measurement and height is to the _______________ scale of
measurement.
a. ordinal; ratio
b. ordinal; nominal
c. nominal; interval
d. interval; ratio
ordinal; ratio
Weight is to the _______________ scale of measurement
and political affiliation is to the _______________ scale of
measurement.
a. ratio; ordinal
b. ratio; nominal
c. interval; nominal
d. ordinal; ratio
ratio; nominal
Qualitative variable is to quantitative variable as ____ is to
_____.
a. categorical variable; numerical variable
b. numerical variable; categorical variable
c. bar graph; histogram
d. categorical variable and bar graph; numerical variable
and histogram
a?
Inferential statistics allow us to infer something about the
_______________ based on the _______________.
a. sample; population
b. population; sample
c. sample; sample
d. population; population
population; sample
Which of the following is not true?
a. All scores in the distribution are used in the calculation of
the range.
b. The average deviation is a more sophisticated measure of
variation than the range; however, it may not weight
extreme scores adequately.
c. The standard deviation is the most sophisticated measure
of variation because all scores in the distribution are used
and because it weights extreme scores adequately.
d. None of the other alternatives is false.
d?
If the shape of a frequency distribution is lopsided, with a
long tail projecting longer to the left than to the right, how
would the distribution be skewed?
a. Normally
b. Negatively
c. Positively
d. Average
negatively
Calculate the mean, median, and mode for the following
distribution: 1, 1, 2, 2, 4, 5, 8, 9, 10, 11, 11, 11
mean = 6.25, median = 6.5, mode = 11
Calculate the range and standard deviation for the following distribution
range = 2 to 8?
standard deviation = square root of (sum of (datapoint - mean)squared /N-1)
What is the symbol for standard deviation of the sample means (statistic)?
the o-symbol; I guess this is because it’s a made up number, therefore it is a made up symbol
What is the symbol for standard deviation of the population means (parameter)?
the s-symbol; because it is a known number, therefore it is a known letter
To create an APA table in SPSS, what area do I work in?
Table Look, organizing the cell formats into Times New Roman and 12 point black font, with left alignment except for the Column Labels which are centred, and the data lines which are tiered
What border lines are specified in SPSS to make an APA-style table?
- Top Inner Frame (thin single lines)
- Bottom inner frame
- Data area top - tables from data
- Horizontal category border (columns)
THE REST ARE WITHOUT A LINE
