QMCC
How can we study for exams:
• Lectures
• Required material for tutorial
• Additional reading (Creswell, Sue & Ritter, mediation hand-out)
• Pallent book: more like guideline, not important for the exam
Week 1 Lecture
RQ, Hypotheses, variables
• Theory: an interrelated set of variables formed into hypothesis that specify the RS
among variables, with the purpose of explaining natural phenomenon
• Theoretical rationale: provides an explanation or prediction about why and how
variable X would influence variable Y
**Quantitative RQs: you have to identify a RS
• Variable: a characteristics or attribute that varies among the people that are being
studied e.g. how many hours they are exposed to media
• Independent variable (IV): those that probably influence or affect outcomes
(treatment, manipulated, antecedent, predictor) e.g.media violence
• Dependent variable (DV): those that are the presumed result of the influence of the
IV (criterion, outcome, effect) e.g. well-being
Hypothesis
• Hypotheses
o tested with statistics
o based on theory
o can be answered by saying true/false
o vs. opinion
• Two types of hypotheses:
o Null hypothesis H0
▪ No difference/ change
, ▪ Never stated, always implied
▪ E.g. Media violence does not influence well-being XX media violence
decrease well-being; human behavior cannot be put in numbers
o Alternative hypothesis H1
▪ Statement of prediction
▪ Actual research hypothesis
▪ E.g. Media violence increase well-being; politicians are arrogant; men
talk way less than women
o The goal of hypothesis testing -> reject one hypothesis and accept the other
• Two types of H1:
o Directional hypothesis
▪ Difference or effect in particular direction
▪ E.g. media violence increases mood
o Non-directional hypothesis
▪ Difference or effect but not in particular direction
▪ Avoid when possible
▪ E.g. media violence influences mood
Variables that influence the rs of IV and DV
• Spurious rs: a rs in which IV and DV seem related, but in fact not (rationally thinking)
• Confounding variables: variables that are not measured but might influence or
explain the observed rs
o E.g. direct rs between chimneys and pregnant women-> More chimneys, the
more pregnant women -> confounding variable: number of citizens which
help explain the rs -> more citizens, the more houses(chimneys), more
pregnant women within a community
o E.g. IV money spent on ice cream, DV people die on drowning, confounding
variable: hot weather
o **Spurious rs (IV and DV are completely unrelated) and confounding rs (IV
and DV are related through a third variable that links them) is not the same
• Control variables: no assumptions about the impact of CV on rs between IV and DV
but just that researchers put them into measure because they think the variables
may potentially influence the DV/ in case the variables cause effects. (usually
demographics such as age).
• Mediator (Mediating/ Intervening variable): stand betweenn the IV and DV and
“mediate” the effects of IV on the DV; tell you how an IV affect the DV
o E.g. Exposure to media violence (IV) > Media entertainment (MV) > Well-
being (DV) -> exposure to media violence can increase well-being if you
are entertained by the movie
o Age can NEVER be a mediator because they cannot be influenced by IVs
• Moderator (Moderating variables): (e.g. gender) affect the rs between the IV and DV,
such that the effect present for one group (e.g. male) but not another (e.g. female);
tell you for whom an IV affect DV
o Moderator variable can be categorical or continuous variable
,Tutorial 1
1. Determine the IV and DV
H1: Girls will show a higher use for social media than boys while boys will play video games
more often
• IV: Gender (**rmb its not girl/boy, they are attributes of gender)
2. Improve the hypotheses
H1: The frequency of being frightened by fantasy characters and events will not decrease
with age
• Will not decrease -> increase (** keep the words simple, avoid ambiguity)
H2: The tendency of being scared by realistic characters and events will increase with age
H3: Girls will show a higher use for social media than boys while boys will play video games
more often
• Separate into two hypotheses: Girls will have higher use of social media; Girls will
have lower video games playing (*keep H1 simple so only 1 IV and DV)
• Or separate the DV into 2: so H1A. How gender affect social media use H1B. How
gender affect video games playing
3. Create a non-directional and directional hypothesis based on the uses and gratification
theory
Q: Name your IV and DV
Do you expect this relation to be the same for all people? Or only for a specific group (do
you have a moderator)? Why?
• Age, Gender: moderator
• IV: Self-posting on social media DV: satisfaction on self-presentation
• Non-directional: The frequency of self-posting on social media affects the
satisfaction on self-presentation
• Directional: the frequency of self-posting on social media increases the satisfaction
on self-presentation.
,Week 2 Lecture
Scale and Quality of scale
• Data are only as good as the instrument that you use to collect them.
• “good science” also included careful operation ( i.e. defining, selecting and refining
of measurements)
Introducing scale
• The variables (i.e. characteristics or attributes that varies among the people that are
being studied) in your research q and hypotheses may be abstract concepts (e.g.
press freedom, materialism, life satisfaction, friendship quality, addiction…)
• Abstract concepts can’t be measured with one question (XX e.g. what is your level of
materialism? How high is your friendship quality?)
• Some characteristics can, for instance gender, sex, education level, ethnicity,
nationality, age etc. (What is your age? What gender do you identify with?)
• To measure abstract concepts => a set of qs/ a scale!!
Scale
• Contain multiple items, being questions or statements, which participants have to
react to
• For each item of a scale, an identical number of answer options should be provided
e.g. 1=no, no at all, 2= no, not really, 3= yes, a little…
• Scale score calculation:
• The scores on separate items (i.e. questions/statements) can be summed or
averaged (depend on how the final variable will be used)
o Sum scores are used when the scale is meant to categorize the
participants: e.g. intelligence, autism, addiction, total number of hours
spent with media.
o Average scale scores are used when to interpret the scale score with the
original answer option e.g. answer 3= yes, a little -> interpretation: the
child would be a little materialistic.
• Some scales combine positive and negative items -> negative items need to be
recoded
o E.g. negative statements (When i look at the world, i don’t see much to be
grateful for)-> a high score (7= strongly agree) indicate ungratefulness
o So need to be recoded in order to measure gratefulness -> reverse the score
so a score of 7 will be converted to 1
o After recoding the negative items, the high score indicates gratefulness
A good operationalization
• Reliable measure ( the measure always measure the same )
• Valid measure (measure what you wanted)
• Objective measure (the measure measured the same when you conduct the study or
when your neighbor does)
• Internal consistency + content validity of the scale can be verified
, When Introduce new scale, following information is needed
• No of items (statement/ questions)
• Content of the items
• No of ans options
• Content of ans options
• Whether some items need to be reversed scored
• The reliability of the scale
• The validity of the scale
Realibity of scale
• Two frequently used indicator:
1. Internal Consistency
o The degree to which the items that make up the scale are all
measuring the same underlying attribute.
o Cronbach’s alpha: statistical measure of internal consistency – show
average correlation among all of the items that make up the scale
▪ Range from 0-1
▪ >0.70= accepted
▪ >0.80= preferable
2. Test-retest reliability (temporal stability)
o Accessed by administering it to the same people at multiple
occasions, and calculating the correlation between the two scores
obtained (logic: same test with same people should have similar
result, the abstract concept should generally states the same)
o Small correlation (r =0.10 to 0.29): low
o Medium correlation (r= 0.30 to 0.49): moderate
o Large correlation (r=0.50 to 0.99): high
o Zero/ negative correlation= poor
Validity of scale
• Refer to the degree to which it measures what it is supposed to measure
1. Content validity= refers to the extent to which the items of the scale are
representative of the entire domain the scale intends to measure.
o In plain language, do the questions capture the concept well?
o Really look into how the items are traced, just evaluate it logically
o Some scales consist of subscales, in such case the items should
capture the designated sub concept!
2. Criterion validity = concerns the relationship between scale scores and some
specified, measurable criterion
o This is usually assessed through a scale’s correlation to other scales
intended to measure the same or a similar concept e.g. new
materialism scale is measured against other known materialism
scales.
o Small correlations (r = 0.10 to 0.29) indicate low validity
o Medium correlations (r = 0.30 to 0.49) indicate moderate validity
o Large correlations (r = 0.50 to 1.00) indicate high validity
How can we study for exams:
• Lectures
• Required material for tutorial
• Additional reading (Creswell, Sue & Ritter, mediation hand-out)
• Pallent book: more like guideline, not important for the exam
Week 1 Lecture
RQ, Hypotheses, variables
• Theory: an interrelated set of variables formed into hypothesis that specify the RS
among variables, with the purpose of explaining natural phenomenon
• Theoretical rationale: provides an explanation or prediction about why and how
variable X would influence variable Y
**Quantitative RQs: you have to identify a RS
• Variable: a characteristics or attribute that varies among the people that are being
studied e.g. how many hours they are exposed to media
• Independent variable (IV): those that probably influence or affect outcomes
(treatment, manipulated, antecedent, predictor) e.g.media violence
• Dependent variable (DV): those that are the presumed result of the influence of the
IV (criterion, outcome, effect) e.g. well-being
Hypothesis
• Hypotheses
o tested with statistics
o based on theory
o can be answered by saying true/false
o vs. opinion
• Two types of hypotheses:
o Null hypothesis H0
▪ No difference/ change
, ▪ Never stated, always implied
▪ E.g. Media violence does not influence well-being XX media violence
decrease well-being; human behavior cannot be put in numbers
o Alternative hypothesis H1
▪ Statement of prediction
▪ Actual research hypothesis
▪ E.g. Media violence increase well-being; politicians are arrogant; men
talk way less than women
o The goal of hypothesis testing -> reject one hypothesis and accept the other
• Two types of H1:
o Directional hypothesis
▪ Difference or effect in particular direction
▪ E.g. media violence increases mood
o Non-directional hypothesis
▪ Difference or effect but not in particular direction
▪ Avoid when possible
▪ E.g. media violence influences mood
Variables that influence the rs of IV and DV
• Spurious rs: a rs in which IV and DV seem related, but in fact not (rationally thinking)
• Confounding variables: variables that are not measured but might influence or
explain the observed rs
o E.g. direct rs between chimneys and pregnant women-> More chimneys, the
more pregnant women -> confounding variable: number of citizens which
help explain the rs -> more citizens, the more houses(chimneys), more
pregnant women within a community
o E.g. IV money spent on ice cream, DV people die on drowning, confounding
variable: hot weather
o **Spurious rs (IV and DV are completely unrelated) and confounding rs (IV
and DV are related through a third variable that links them) is not the same
• Control variables: no assumptions about the impact of CV on rs between IV and DV
but just that researchers put them into measure because they think the variables
may potentially influence the DV/ in case the variables cause effects. (usually
demographics such as age).
• Mediator (Mediating/ Intervening variable): stand betweenn the IV and DV and
“mediate” the effects of IV on the DV; tell you how an IV affect the DV
o E.g. Exposure to media violence (IV) > Media entertainment (MV) > Well-
being (DV) -> exposure to media violence can increase well-being if you
are entertained by the movie
o Age can NEVER be a mediator because they cannot be influenced by IVs
• Moderator (Moderating variables): (e.g. gender) affect the rs between the IV and DV,
such that the effect present for one group (e.g. male) but not another (e.g. female);
tell you for whom an IV affect DV
o Moderator variable can be categorical or continuous variable
,Tutorial 1
1. Determine the IV and DV
H1: Girls will show a higher use for social media than boys while boys will play video games
more often
• IV: Gender (**rmb its not girl/boy, they are attributes of gender)
2. Improve the hypotheses
H1: The frequency of being frightened by fantasy characters and events will not decrease
with age
• Will not decrease -> increase (** keep the words simple, avoid ambiguity)
H2: The tendency of being scared by realistic characters and events will increase with age
H3: Girls will show a higher use for social media than boys while boys will play video games
more often
• Separate into two hypotheses: Girls will have higher use of social media; Girls will
have lower video games playing (*keep H1 simple so only 1 IV and DV)
• Or separate the DV into 2: so H1A. How gender affect social media use H1B. How
gender affect video games playing
3. Create a non-directional and directional hypothesis based on the uses and gratification
theory
Q: Name your IV and DV
Do you expect this relation to be the same for all people? Or only for a specific group (do
you have a moderator)? Why?
• Age, Gender: moderator
• IV: Self-posting on social media DV: satisfaction on self-presentation
• Non-directional: The frequency of self-posting on social media affects the
satisfaction on self-presentation
• Directional: the frequency of self-posting on social media increases the satisfaction
on self-presentation.
,Week 2 Lecture
Scale and Quality of scale
• Data are only as good as the instrument that you use to collect them.
• “good science” also included careful operation ( i.e. defining, selecting and refining
of measurements)
Introducing scale
• The variables (i.e. characteristics or attributes that varies among the people that are
being studied) in your research q and hypotheses may be abstract concepts (e.g.
press freedom, materialism, life satisfaction, friendship quality, addiction…)
• Abstract concepts can’t be measured with one question (XX e.g. what is your level of
materialism? How high is your friendship quality?)
• Some characteristics can, for instance gender, sex, education level, ethnicity,
nationality, age etc. (What is your age? What gender do you identify with?)
• To measure abstract concepts => a set of qs/ a scale!!
Scale
• Contain multiple items, being questions or statements, which participants have to
react to
• For each item of a scale, an identical number of answer options should be provided
e.g. 1=no, no at all, 2= no, not really, 3= yes, a little…
• Scale score calculation:
• The scores on separate items (i.e. questions/statements) can be summed or
averaged (depend on how the final variable will be used)
o Sum scores are used when the scale is meant to categorize the
participants: e.g. intelligence, autism, addiction, total number of hours
spent with media.
o Average scale scores are used when to interpret the scale score with the
original answer option e.g. answer 3= yes, a little -> interpretation: the
child would be a little materialistic.
• Some scales combine positive and negative items -> negative items need to be
recoded
o E.g. negative statements (When i look at the world, i don’t see much to be
grateful for)-> a high score (7= strongly agree) indicate ungratefulness
o So need to be recoded in order to measure gratefulness -> reverse the score
so a score of 7 will be converted to 1
o After recoding the negative items, the high score indicates gratefulness
A good operationalization
• Reliable measure ( the measure always measure the same )
• Valid measure (measure what you wanted)
• Objective measure (the measure measured the same when you conduct the study or
when your neighbor does)
• Internal consistency + content validity of the scale can be verified
, When Introduce new scale, following information is needed
• No of items (statement/ questions)
• Content of the items
• No of ans options
• Content of ans options
• Whether some items need to be reversed scored
• The reliability of the scale
• The validity of the scale
Realibity of scale
• Two frequently used indicator:
1. Internal Consistency
o The degree to which the items that make up the scale are all
measuring the same underlying attribute.
o Cronbach’s alpha: statistical measure of internal consistency – show
average correlation among all of the items that make up the scale
▪ Range from 0-1
▪ >0.70= accepted
▪ >0.80= preferable
2. Test-retest reliability (temporal stability)
o Accessed by administering it to the same people at multiple
occasions, and calculating the correlation between the two scores
obtained (logic: same test with same people should have similar
result, the abstract concept should generally states the same)
o Small correlation (r =0.10 to 0.29): low
o Medium correlation (r= 0.30 to 0.49): moderate
o Large correlation (r=0.50 to 0.99): high
o Zero/ negative correlation= poor
Validity of scale
• Refer to the degree to which it measures what it is supposed to measure
1. Content validity= refers to the extent to which the items of the scale are
representative of the entire domain the scale intends to measure.
o In plain language, do the questions capture the concept well?
o Really look into how the items are traced, just evaluate it logically
o Some scales consist of subscales, in such case the items should
capture the designated sub concept!
2. Criterion validity = concerns the relationship between scale scores and some
specified, measurable criterion
o This is usually assessed through a scale’s correlation to other scales
intended to measure the same or a similar concept e.g. new
materialism scale is measured against other known materialism
scales.
o Small correlations (r = 0.10 to 0.29) indicate low validity
o Medium correlations (r = 0.30 to 0.49) indicate moderate validity
o Large correlations (r = 0.50 to 1.00) indicate high validity
