Summary
This chapter explored three basic tools that we use to analyze data. Chi-squared (χ2) tests examine whether the distribution of cases in a cross-tabulation appears to be independent. If one variable’s value affects the likelihood of observing a certain value on the other variable, above what we’d expect by chance, we will find a significant χ2 value and conclude that the variables do show an association. This test requires two nominal or ordinal variables. A difference of means test compares the means of two groups, or a mean of one group against a fixed outside value. It asks whether the gap is significantly larger than 0; significant t-tests show a difference between the groups (or that the value is not 0, in the case of a one-sample test). The DV must always be interval-ratio, and the IV must take the form of two groups. Regression allows you to mix independent variables from different levels of analysis so long as the outcome is interval-ratio. A regression coefficient tells us the sign, size, and sureness of the relationship between that IV and the DV, holding all other variables in the model constant.
Articles
Web Extra: How to Calculate Chi Square
Web Extra: How to Calculate a t-test
Web Extra: Assumptions of Regression
Vocab Flashcards
[qdeck random=”true”]
[q] Mathematical altering of the scale of a variable to create a more linear relationship
[a] transformation
[q] Goodness of fit measure for bivariate OLS regression; interprets as percentage of DV variation explained by variations in IV
[a] R2
[q] In the statistical sense, an indication that the observed relationship is not 0
[a] significance
[q] another name for a t-test
[a] difference in means test
[q] Process of combining or collapsing value categories in a distribution; loses information but may increase analytical traction
[a] pooling
[q] The leftover, unsystematic parts of an observed value; calculated as observed value minus expected value in regression
[a] residual
[q] Descriptor for a table with equal numbers of rows and columns
[a] square
[q] Test statistic for difference of means; compares means of one group to an external referent (one-sample), or two groups/values to each other (two-sample independent or paired, respectively)
[a] t-test
[/qdeck]
Review Quiz
[qwiz random=”true” random_mc=”true”]
[q] The chi-squared test requires an independent variable that is ____ and a dependent variable that is ____.
[c]IGNhdGVnb3JpY2FsIOKA piBjYXRlZ29yaWNhbA==[Qq]
[c]IGNhdGVnb3JpY2FsIOKApiBjb250aW51b3Vz[Qq]
[c]IGNvbnRpbnVvdXMg4oCmIGNhdGVnb3JpY2Fs[Qq]
[c]IGNvbnRpbnVvdXMg4oCmIGNvbnRpbnVvdXM=[Qq]
[q] The t-test requires an independent variable that is ____ and a dependent variable that is ____.
[c]IGNhdGVnb3JpY2FsIOKApiBjYXRlZ29yaWNhbA==[Qq]
[c]IGNhdGVnb3JpY2FsIO KApiBjb250aW51b3Vz[Qq]
[c]IGNvbnRpbnVvdXMg4oCmIGNhdGVnb3JpY2Fs[Qq]
[c]IGNvbnRpbnVvdXMg4oCmIGNvbnRpbnVvdXM=[Qq]
[q] For regression, all variables must be continuous.
[c]IEZB TFNF[Qq]
[c]IFRSVUU=[Qq]
[q random_mc=”false”] The key quantity of interest in regression output is the ____.
[c]IGh5cGVycGFyYW1ldGVy[Qq]
[c]IGNvbnN0YW50[Qq]
[c]IGdvb2RuZXNzIG9mIGZpdCBzdGF0aXN0aWM=[Qq]
[c]IGNyaXRpY2FsIHZhbHVl[Qq]
[c]IGxvZyBsaWtlbGlob29k[Qq]
[c]IG5vbmUgb2YgdGhlIGFib3ZlIOKAky BpdOKAmXMgc29tZXRoaW5nIGVsc2U=[Qq]
[q] Tables for statistical output should NOT ___.
[c]IGNvbnRhaW4gdGFibGUgbm90ZXMgaW5kaWNhdGluZyB3aGF0IHRoZSB0YWJsZSBzaG93cw==[Qq]
[c]IGJlIHBhc3RlZCBpbiBmcm9tIHlvdX Igc3RhdGlzdGljYWwgc29mdHdhcmU=[Qq]
[c]IGRlZmluZSB5b3VyIGFzdGVyaXNrIHNjaGVtZSwgaWYgdXNlZA==[Qq]
[c]IGluZGljYXRlIHRoYXQgY29lZmZpY2llbnRzIGZvciB2YXJpYWJsZXMgb21pdHRlZCBmcm9tIGEgbW9kZWwgYXJlIDA=[Qq]
[q] We can include variables besides our variable of interest in a multiple regression. These additional ____ variables capture the additional effect of factors we know matter in explaining the outcome.
[c]IGNvbn Ryb2w=[Qq]
[c]IGludGVyLWNvbmpvaW50IHNwbGl0dGluZw==[Qq]
[c]IHRyYW5za2VkYXN0aWM=[Qq]
[c]IHRyYWluaW5nIGRhdGE=[Qq]
[c]IG5vcm1hbGl6aW5n[Qq]
[q] Which statement below is TRUE?
[c]IENvcnJlbGF0aW9uIHRlbGxzIHVzIGhvdyBzdGVlcCB0aGUgaW1hZ2luYXJ5IGxpbmUgZml0dGVkIGJldHdlZW4gdHdvIHZhcmlhYmxlcyBpcy4=[Qq]
[c]IE91ciB0b29sIGZvciBhbmFseXppbmcgbW9yZSB0aGFuIG9uZSByaWdodC1oYW5kLXNpZGUgdmFyaWFibGUgYXQgYSB0aW1lIGlzIGNhbGxlZCBjb3JyZWxhdGVkIGxlYXN0IHNxdWFyZXMu[Qq]
[c]IERlLW1lYW5pbmcgYSB2YXJpYWJsZSBtYWtlcyBpdCBub3JtYWxseSBkaXN0cmlidXRlZC4=[Qq]
[c]IFRoZSBmb3JtdWxhIGZvciBhIHJlZ3Jlc3Npb24gY29lZmZpY2llbnQgaXMgc2ltaWxhci B0byBvdGhlciBmb3JtdWxhcyBmb3Igc2xvcGUsIHRoYXQgaXMsIHJpc2Utb3Zlci1ydW4u[Qq]
[q] Which of the following statements about control variables is FALSE?
[c]IEFsbCBjb2VmZmljaWVudHMgYW5kIHN0YW5kYXJkIGVycm9ycyBhcmUgYWZmZWN0ZWQgYnkgdGhlIGluY2x1c2lvbiBvZiBhZGRpdGlvbmFsIHJpZ2h0LWhhbmQgc2lkZSAoY29udHJvbCBhbmQgaW5kZXBlbmRlbnQpIHZhcmlhYmxlcy4=[Qq]
[c]IENvZWZmaWNpZW50cyBvbiBjb250cm9sIHZhcmlhYmxlcyBhcmUgbm90IG9mdGVuIGRpc2N1c3NlZCBpbiB0aGUgcGFwZXIgaXRzZWxmLg==[Qq]
[c]IENvbnRyb2wgdmFyaWFibGVzIGFuZCB0aGVpciBjb2VmZmljaWVudHMgc2hv dWxkIG5ldmVyIGJlIHJlcG9ydGVkIGluIHRoZSByZXN1bHRzIHRhYmxlLg==[Qq]
[c]IFN0YXRpc3RpY2FsIHNvZnR3YXJlIGNhbm5vdCBkaWZmZXJlbnRpYXRlIGJldHdlZW4gY29udHJvbCB2YXJpYWJsZXMgYW5kIGluZGVwZW5kZW50IHZhcmlhYmxlcy4=[Qq]
[q random_mc=”false”] You estimate a multiple regression. Which of the following is a CORRECT interpretation of the results? (Hint: You don’t need to see the model or table to answer this!)
[c]IFRoZSB2YXJpYWJsZSA=V29yayBmcm9tIEhvbWUgaXMgc2lnbmlmaWNhbnQgYXQgMC4xLCB3aGljaCBtZWFucyBpdCBpcyBhbiBpbXBvcnRhbnQgcHJlZGljdG9yIG9mIA==Sm9iIFNhdGlzZmFjdGlvbi4=[Qq]
[c]IEVhY2ggYWRkaXRpb25hbCBraWxvbWV0ZXIgb2YgcmFpbHJvYWQgd2l0aGluIDEwa20gb2YgdGhlIGJvcmRlciBwcmVkaW N0cyBhbiBpbmNyZWFzZSBvZiAwLjE0JSBpbiB0cmFkZSBiZXR3ZWVuIHRoZSBzdGF0ZXMsIGFsbCBlbHNlIGVxdWFsLg==[Qq]
[c]IFRoZSBjb2VmZmljaWVudCBvbiB0aGUgY29udHJvbCB2YXJpYWJsZSBmb3IgRURVX0NBVF8xNyBpcyBpbnNpZ25pZmljYW50LCBhbmQgaXQgaXMgZHJvcHBlZCBmcm9tIHRoZSBzZWNvbmQgbW9kZWwu[Qq]
[c]IEFsbCBvZiB0aGUgYWJvdmUgYXJlIGNvcnJlY3Qu[Qq]
[/qwiz]