Chapter 2.1 Basic Concepts and Terminology
readme.html2-0_ChapterSetup.R for this
tutorial because we start with importing the raw data stored in the .dta
format (Stata)LoadInstallPackages.R# assuming you are working within .Rproj environment
library(here)
# install (if necessary) and load other required packages
source(here("source", "LoadInstallPackages.R"))In chapter 2.1, we introduce different notations of sequence data using example data on family biographies from age 18 to 40. The data come from a sub-sample of the German Family Panel - pairfam. For further information on the study and on how to access the full scientific use file see here.
We generated the example dataset in Stata. Next to the sequence variables it comprises a few additional variables which will be used to analyze the sequences in later chapters.
We import the data to R using the read_dta function from
the {haven} package and inspect the names
of the imported variables.
# import data
family <- read_dta(here("data", "Stata", "PartnerBirthbio.dta"))# view variable names
names(family) [1] "id" "weight40" "sex"
[4] "doby_gen" "dob" "ethni"
[7] "migstatus" "yeduc" "sat1i4"
[10] "sat5" "sat6" "highschool"
[13] "church" "biosib" "stepsib"
[16] "east" "famstructure18" "state1"
[19] "state2" "state3" "state4"
[22] "state5" "state6" "state7"
[25] "state8" "state9" "state10"
[28] "state11" "state12" "state13"
[31] "state14" "state15" "state16"
[34] "state17" "state18" "state19"
[37] "state20" "state21" "state22"
[40] "state23" "state24" "state25"
[43] "state26" "state27" "state28"
[46] "state29" "state30" "state31"
[49] "state32" "state33" "state34"
[52] "state35" "state36" "state37"
[55] "state38" "state39" "state40"
[58] "state41" "state42" "state43"
[61] "state44" "state45" "state46"
[64] "state47" "state48" "state49"
[67] "state50" "state51" "state52"
[70] "state53" "state54" "state55"
[73] "state56" "state57" "state58"
[76] "state59" "state60" "state61"
[79] "state62" "state63" "state64"
[82] "state65" "state66" "state67"
[85] "state68" "state69" "state70"
[88] "state71" "state72" "state73"
[91] "state74" "state75" "state76"
[94] "state77" "state78" "state79"
[97] "state80" "state81" "state82"
[100] "state83" "state84" "state85"
[103] "state86" "state87" "state88"
[106] "state89" "state90" "state91"
[109] "state92" "state93" "state94"
[112] "state95" "state96" "state97"
[115] "state98" "state99" "state100"
[118] "state101" "state102" "state103"
[121] "state104" "state105" "state106"
[124] "state107" "state108" "state109"
[127] "state110" "state111" "state112"
[130] "state113" "state114" "state115"
[133] "state116" "state117" "state118"
[136] "state119" "state120" "state121"
[139] "state122" "state123" "state124"
[142] "state125" "state126" "state127"
[145] "state128" "state129" "state130"
[148] "state131" "state132" "state133"
[151] "state134" "state135" "state136"
[154] "state137" "state138" "state139"
[157] "state140" "state141" "state142"
[160] "state143" "state144" "state145"
[163] "state146" "state147" "state148"
[166] "state149" "state150" "state151"
[169] "state152" "state153" "state154"
[172] "state155" "state156" "state157"
[175] "state158" "state159" "state160"
[178] "state161" "state162" "state163"
[181] "state164" "state165" "state166"
[184] "state167" "state168" "state169"
[187] "state170" "state171" "state172"
[190] "state173" "state174" "state175"
[193] "state176" "state177" "state178"
[196] "state179" "state180" "state181"
[199] "state182" "state183" "state184"
[202] "state185" "state186" "state187"
[205] "state188" "state189" "state190"
[208] "state191" "state192" "state193"
[211] "state194" "state195" "state196"
[214] "state197" "state198" "state199"
[217] "state200" "state201" "state202"
[220] "state203" "state204" "state205"
[223] "state206" "state207" "state208"
[226] "state209" "state210" "state211"
[229] "state212" "state213" "state214"
[232] "state215" "state216" "state217"
[235] "state218" "state219" "state220"
[238] "state221" "state222" "state223"
[241] "state224" "state225" "state226"
[244] "state227" "state228" "state229"
[247] "state230" "state231" "state232"
[250] "state233" "state234" "state235"
[253] "state236" "state237" "state238"
[256] "state239" "state240" "state241"
[259] "state242" "state243" "state244"
[262] "state245" "state246" "state247"
[265] "state248" "state249" "state250"
[268] "state251" "state252" "state253"
[271] "state254" "state255" "state256"
[274] "state257" "state258" "state259"
[277] "state260" "state261" "state262"
[280] "state263" "state264"
The sequence variables begin with the prefix state. The
data comprise 264 sequence variables per person (wide data format).
These variables include monthly information on family biographies
covering a period of 22 years. Haven imports them as numeric variables
with labels attached to them (class = "haven_labelled").
With the follwing commands we can take a look at the labels.
str(family$state1) dbl+lbl [1:1866] 5, 1, 5, 1, 3, 3, 1, 3, 1, 1, 1, 1, 1, 3, 1, 1,...
@ format.stata: chr "%22.0g"
@ labels : Named num [1:9] 1 2 3 4 5 6 7 8 9
..- attr(*, "names")= chr [1:9] "Single, no child" "Single, child(ren)" "LAT, no child" "LAT, child(ren)" ...attributes(family$state1)$labels Single, no child Single, child(ren) LAT, no child
1 2 3
LAT, child(ren) Cohabiting, no child Cohabiting, child(ren)
4 5 6
Married, no child Married, 1 child Married, 2+ children
7 8 9 The first examples in the book are based on sequences with a reduced
alphabet only distinguishing partnership states. The following code
generates a data set (seqvars.partner) containing the
recoded sequence variables using {dplyr}.
# extracting and recoding the sequence variables (which all start with state)
# recode to reduced state space capturing partnership status only
seqvars.partner <- family %>%
select(starts_with("state")) %>%
mutate_all(~(case_when(
. < 3 ~ 1, # Single
. %in% c(3,4) ~ 2, # LAT
. %in% c(5,6) ~ 3, # Cohabiting
. > 6 ~ 4,))) # MarriedThen we define two vectors storing the long and short labels for the
states in the newly defined alphabet. Once that is done, we can define
the data as a state sequence object. Most {TraMineR} functions for analyzing
sequences require the data to have this format.
shortlab.partner <- c("S", "LAT", "COH", "MAR")
longlab.partner <- c("Single", "LAT", "Cohabiting", "Married")
# create state sequence object
partner.month.seq <- seqdef(seqvars.partner,
labels = longlab.partner,
states = shortlab.partner,
weights = family$weight40)Note that the seqdef function can include many more
optional arguments. Some of these arguments - most importantly
cpal - affect the appearance of state sequence plots
rendered with seqplot or seqplot.rf. We cover
the definition of color palettes on two separate pages (definition of color palettes; definition of grayscale
palettes)
In chapter 2.1, we introduce different notations for printing sequences. The following commands print the sequences in STS, DSS, and SPS format.
print(partner.month.seq[8, ], format = "STS") Sequence
8 LAT-LAT-LAT-LAT-LAT-LAT-LAT-LAT-LAT-LAT-LAT-LAT-LAT-S-S-S-S-S-S-LAT-LAT-LAT-LAT-LAT-LAT-LAT-LAT-LAT-LAT-LAT-LAT-LAT-LAT-LAT-LAT-LAT-LAT-LAT-LAT-LAT-LAT-LAT-LAT-LAT-LAT-LAT-LAT-LAT-LAT-LAT-LAT-LAT-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-LAT-LAT-LAT-LAT-LAT-LAT-LAT-LAT-LAT-LAT-LAT-LAT-LAT-LAT-LAT-LAT-LAT-LAT-LAT-LAT-LAT-LAT-LAT-LAT-LAT-LAT-LAT-LAT-LAT-LAT-LAT-LAT-LAT-LAT-LAT-LAT-LAT-LAT-LAT-LAT-LAT-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-LAT-LAT-LAT-LAT-LAT-LAT-LAT-LAT-LAT-LAT-COH-COH-COH-COH-COH-COH-COH-COH-COH-COH-COH-COH-COH-COH-MAR-MAR-MAR-MAR-MAR-MAR-MAR-MAR-MAR-MAR-MAR-MAR-MAR-MAR-MAR-MAR-MAR-MAR-MAR-MAR-MAR-MAR-MAR-MAR-MAR-MAR-MAR-MAR-MAR-MAR-MAR-MAR-MAR-MAR-MAR-MAR-MAR-MAR-MAR-MAR-MAR-MAR-MAR-MAR-MAR-MAR-MAR-MAR-MAR-MAR-MAR-MAR-MAR-MAR-MAR-MAR-MAR-MAR-MAR-MAR-MAR-MAR-MAR-MAR-MAR-MAR-MAR-MAR-MAR-MAR-MAR-MAR-MAR-MAR-MAR-MAR-MAR-MAR-MAR-MAR-MAR-MAR-MAR-MAR-MAR-MAR-MAR-MARseqdss(partner.month.seq[8, ]) Sequence
8 LAT-S-LAT-S-LAT-S-LAT-COH-MARprint(partner.month.seq[8, ], format = "SPS") Sequence
8 (LAT,13)-(S,6)-(LAT,33)-(S,24)-(LAT,41)-(S,35)-(LAT,10)-(COH,14)-(MAR,88)If you see mistakes or want to suggest changes, please create an issue on the source repository.
Text and figures are licensed under Creative Commons Attribution CC BY-NC 4.0. Source code is available at https://github.com/sa-book/sa-book.github.io, unless otherwise noted. The figures that have been reused from other sources don't fall under this license and can be recognized by a note in their caption: "Figure from ...".