Summary
Good hypotheses identify observable implications of the theory – things we would observe if the theory were correct – and make predictions about relationships between measurable indicators of the theory’s concepts. Measurement thus plays a critical role in the transition from claims to tests. Six types of hypotheses are common in political science. Probabilistic hypotheses include directional, relative, no-effect, and conditional types; these hypotheses make claims that they expect to be true, on average, across many cases. Deterministic hypotheses, on the other hand, make claims that should always hold; these include claims of necessity and/or sufficiency. Preregistration attempts to reduce the incentives to adjust hypotheses to match findings.
Articles
Web Extra: Hypotheses of No Relationship
Web Extra: Hypotheses of Necessity and Sufficiency
Web Extra: Probabilistic Theorizing, Falsifiers, and Counterexamples
Web Extra: Preregistration Resources and Registered Reports
Vocab Flashcards
[qdeck random=”true”]
[q] Characteristic of an indicator: the indicator captures the concept of interest and nothing else
[a] validity
[q] Degree of precision used in the operationalization of a variable; most common in political science are interval-ratio, ordinal, and nominal
[a] level of measurement
[q] Level of measurement: unrankable but discrete categories, with no implied direction or magnitude; lowest precision of measurement
[a] nominal
[q] Level of measurement: continuous or discrete quantities with consistent units attached such as years or votes; most precise level used in political science
[a] interval-ratio
[q] Level of measurement: rankable categories, where the intervals between categories may or may not be equal or precisely definable; intermediate level of measurement
[a] ordinal
[q] Claim that the effect of one IV is dependent (conditional) on the effect of another IV, sometimes called an interaction hypothesis
[a] conditional hypothesis
[q] Single or rare cases that do not fit the hypothesis; possibly defined as outliers in some contexts
[a] counter-examples
[q] Hypotheses that explain adverse findings
[a] counter-explanations
[q] The outcome variable in a hypothesis
[a] dependent variable (DV)
[q] Class of hypotheses arguing that a particular relationship should hold across all cases; includes primarily hypotheses of necessity, sufficiency, and necessity and sufficiency
[a] deterministic hypothesis
[q] Describes an indicator or variable that takes on only two possible values; usually framed as a “yes/no” item; sometimes called “dummy” variables
[a] dichotomous variable
[q] A positive association between two variables – they both increase or decrease together
[a] direct relationship
[q] Hypothesis type that predicts increases or decreases in a DV as a function of increases in one or more IVs
[a] directional hypothesis
[q] Specific pieces of evidence that would falsify a theory; the research would expect to find these if the theory were incorrect [a]
[a] falsifiers
[q] Hypothesizing after results known – ethically questionable practice in deductive empirical research
[A] HARKing
[q] A statement of the relationship that the researcher expects to find between her dependent variable and independent variable(s); usually phrased in terms of indicators
[h] hypothesis
[q] The causal or explanatory variable in a hypothesis
[a] independent variable (IV)
[q] Shorthand form denoting independent & dependent variables, direction of change for each, and a causal direction arrow
[a] hypothesis notation
[q] Observable characteristic; measurable version of a concept
[a] indicator
[q] A negative association between two variables—one increases as the other decreases
[a] inverse relationship
[q] Set of cells in a square table or matrix running from the top left corner to the bottom right corner; typically corresponds to cases where X = Y
[a] main diagonal
[q] Asserts that some cause X is required for the outcome Y to occur; implies that Y cannot occur in the absence of X
[a] necessary condition
[q] Claim that one or more IVs has no (usually statistically) discernible effect on another; implies that the coefficient is not statistically significant
[a] hypothesis of no relationship
[q] Empirical patterns that should emerge if a theory is correct
[a] observable implications
[q] publication format providing ungated access to research reports in peer-reviewed publications
[a] open access
[q] Procedure by which scholars evaluate each other’s research for rigor and completeness prior to publishing; acts as a gatekeeping device for professional publications; typically double-blind
[a] peer review process
[q] Process of publicly filing hypotheses, data collection, & data analysis plan before analysis to prevent HARKing
[a] preregistration
[q] Class of hypotheses arguing that a relationship holds across a pool of cases even though individual cases may not support the relationship; four main types are directional, relative, no relationship, and conditional (interactive).
[a] probabilistic hypotheses
[q] Hypothesis type comparing the magnitude of effect of two or more independent variables
[a] relative hypothesis
[q] Asserts that some cause X always leads to the occurrence of Y; the absence of X may or may not result in Y
[a] sufficient condition
[/qdeck]
Review Quiz
[qwiz random=”true” random_mc=”true”]
[q] Variables measured at the ____ level have units attached.
[c]IGJpbmFyeQ==[Qq]
[c]IG9yZGluYWw=[Qq]
[c]IG5vbWluYWw=[Qq]
[c]IGludGVydm FsLXJhdGlv[Qq]
[q] A ____ hypothesis compares two relationships; a _____ hypothesis expects null results.
[c]IHJlbGF0aXZlL25vLX JlbGF0aW9uc2hpcA==[Qq]
[c]IGNvbmRpdGlvbmFsL3JlbGF0aXZl[Qq]
[c]IHJlbGF0aXZlL2RpcmVjdGlvbmFs[Qq]
[c]IGNvbXBhcmF0aXZlL25vLXJlbGF0aW9uc2hpcA==[Qq]
[q] All you need for hypothesis notation is a dependent variable and an independent variable.
[c]IFRSVUU=[Qq]
[c]IEZB TFNF[Qq]
[q]The process of going from theory to hypotheses requires identifying ____.
[c]IG9ic2VydmFibGUg aW1wbGljYXRpb25z[Qq]
[c]IG11bHRpcGxlIGltcHV0ZWQgY29uY2VwdHVhbGl6YXRpb25z[Qq]
[c]IEhBUktpbmc=[Qq]
[c]IGEgdmFsaWQgcmVzZWFyY2ggZGVzaWdu[Qq]
[q]A _____ will capture the concept you want and only that thing.
[c]IHJlbGlhYmxlIG9wZXJhdGlvbmFsaXphdGlvbg==[Qq]
[c]IHZhbGlkIG9wZXJhdG lvbmFsaXphdGlvbg==[Qq]
[c]IHZhbGlkIGNvbmNlcHR1YWxpemF0aW9u[Qq]
[c]IHJlbGlhYmxlIGNvbmNlcHR1YWxpemF0aW9u[Qq]
[/qwiz]