PSYC 3020 Final Exam | Questions with Verified Answers
7 views 0 purchase
Course
PSYC 3020
Institution
PSYC 3020
PSYC 3020 Final Exam | Questions with Verified Answers A categorical variable can always be measured using a nominal scale (T/F) True In soccer, the team with the highest number of goals is categorized as the winner. The other team is categorized as the loser. What type of scale is this? Ordinal ...
A categorical variable can always be measured using a nominal scale (T/F)
True
In soccer, the team with the highest number of goals is categorized as the winner. The
other team is categorized as the loser. What type of scale is this?
Ordinal
Consider political parties from left to right (One nation, Nationals, LNP, Labour, Greens.
What type of scale is this?
Ordinal
Olympics (Gold, Silver, Bronze). What type of scale is this?
Ordinal
"As in things placed in an order; distance between ranks not meaningful however"
Ordinal
In an art competition, there is one winner decided by the judges, one second place
decided by the judges, and a separate "people's choice" winner, decided on by the
public. The rest of the entries are designated "losers".
Nominal, because of the people’s choice category (it cannot be ranked). If you remove
people’s choice, it is ordinal
Describe an Interval Scale
Interval because things is now meaningful, but arbitrary zero
Temperature, as measured in Degrees Celsius, is a ratio measurement (T/F)
False! It is an Interval scale
What scale is TIME measured on?
Interval, not ratio
Ratio Scale
As in the ratio between things is meaningful - the zero point means an absence of the
quantity
What scale is Money on?
Ratio scale
What scale is Timing in seconds on?
Ratio scale
,If we can state that a score on a measure is twice that of another score on the same
measure, then these scores must have been gauged on an interval scale? (T/F)
False, ratio scale would be needed
What are the usual Scales in Psychology?
Usually actually ordinal, but we like to think of them as Interval so we can use
parametric tests
Measurements using the ratio scale always require the use of non- parametric statistics
(T/F)
False. (but not always, if the data is not normally distributed)
Measurements using the nominal and ordinal scale require the use of non-paramedics
statistics
False
We generally treat psychological scales as if they're ratio, even though they're
technically interval scales.
False. Interval, when actually ordinal
Why would we treat ordinal scales as interval scales?
We can do more sensitive statistical tests on them (i.e. parametric tests)
Parametric tests can be done on what scales?
Interval and Ratio
Non-parametric tests are done on what scales?
Ordinal and Nominal
Is a typical intelligent test an ordinal scale, not interval?
True
We tend to trend psychological scales as if they're ratio, even though they're technically
interval scales (T/F)
False. They're technically ordinal and we treat them as interval
We tend to treat psychological scores as being interval scales so we can do non-
parametric tests on them (T/F)
False. We treat them as interval scales so we can do parametric tests
Another name for the normal curve?
Laplace-Gauss, or Gaussian nature
If we can assume scores from a test yield a normal distribution then we only need the
mean and SD of a suitable reference sample to figure out how someone's raw score
compares with that reference sample (T/F)
,True
Why is the normal curve useful in psychology?
In practice, the scores on many psychological tests tend to approximate a normal
distribution and we can do more sensitive statical tests on our data
What tends to happen to the distribution of scores if we measure a wider range of things
using a larger sample?
The distribution tends to become more normal
If something is normally distributed we know 3 things, what are they
1. The Mean, Median and Mode equal each other, and 50% of people are above and
below the mean
2. 68% are +/- SD from the mean
3. 95% are +/-SD from the mean
If you have an IQ less than 70 then you have
A cognitive impairment, relative to the rest of the population
Why might we like the distribution of a measure to be normal?
So we can use parametric (more powerful) tests and it makes scales more comparable
What are the different strategies we can use to make a skewd distribution normal? (3
answers)
1. Do a non-linear transformation (e.g. log or square root). Doesn't change rank order
but stretches the scale out.
2. Redesign your measure if possible (e.g. change wording of questionnaire items)
3. Use non-parametric statistics (i.e. do not normalize the data)
Describe what a non-linear transformation is and explain when we might use it
You do logs/square roots of your scores and it changes the shape of your distribution
What are standard scores and why do we use them?
1. Raw scores are converted usually via linear transformation (which doesn't change the
shape of the distribution). Usually anchor the mean (0) and SD (1)
2. We use standard scores so we don't indicate our raw scale and helps up to compare
across scales
A 7yr old boy completes a test of reading comprehension and his raw score is
converted into a z score of +1.68 compared with other children is own age (where a
higher score = better comprehension). This means he is performing within the middle
68% of children his age, assuming a normal distribution (T/F)
False, because it is higher than 1+ (outside 68% -1 : 1+)
Z score formula
(x-mean) / standard deviation
, I have a scale with a mean of 100 and a SD of 10. Someone gets a raw score of 105 on
this scale. Their z score is therefore 0.5 (T/F)
True
A ten year old boy completes a test of reading comprehension and his raw score is
converted into a z-score of +0.15 compared with other children his own age (where a
higher score = better comprehension). This means he is performing within the middle
two thirds of the children his age, assuming a normal distribution (T/F)
True
Percentile Rank
The percentage of scores below a specific score in a distribution of scores
If someone gets a raw score of 50 and this equates to a percentile rank of 60, what
percent of the norm group scored 50 or less?
60% of the norm group scored 50 or less
Converting a z score into a percentile rank is an example of non-linear transformation
(T/F)
True
If someone has a positive z score of some measure, then we can convert this into a
percentile rank by referring to the column marked 'Smaller Portion' (T/F)
False. Use 'Larger Portion' for positive z scores
What is correlation?
Relationship between two variables from +1 to -1
The correlation coefficient is a measure of effect size (T/F)
True
The correlation coefficient tells us whether a relationship is statistically significant or not
(T/F)
False. It just tells us the strength and direction of the relationship
The correlation coefficient is a description statistics (T/F)
True
Describe a study that could be used to determine whether a test of plumbing ability was
actually measuring plumbing ability (i.e. if it was valid)?
Recruit lots of electricians of different abilities. Get them all to do the test. Get an expert
electrician to evaluate each participant doing the job and rate it on job performance. See
if there is a positive correlation between the test score and the job performance scores.
What term would we use to describe the relationship between a participant's test score
and their actual job performance ratings?
The benefits of buying summaries with Stuvia:
Guaranteed quality through customer reviews
Stuvia customers have reviewed more than 700,000 summaries. This how you know that you are buying the best documents.
Quick and easy check-out
You can quickly pay through credit card or Stuvia-credit for the summaries. There is no membership needed.
Focus on what matters
Your fellow students write the study notes themselves, which is why the documents are always reliable and up-to-date. This ensures you quickly get to the core!
Frequently asked questions
What do I get when I buy this document?
You get a PDF, available immediately after your purchase. The purchased document is accessible anytime, anywhere and indefinitely through your profile.
Satisfaction guarantee: how does it work?
Our satisfaction guarantee ensures that you always find a study document that suits you well. You fill out a form, and our customer service team takes care of the rest.
Who am I buying these notes from?
Stuvia is a marketplace, so you are not buying this document from us, but from seller NurseHenny. Stuvia facilitates payment to the seller.
Will I be stuck with a subscription?
No, you only buy these notes for $22.49. You're not tied to anything after your purchase.
